Medication compliance verification method, device and equipment based on bioelectric characteristics

Abstract

The present application relates to the technical field of data processing, and discloses a medication compliance verification method and device based on bioelectric characteristics, equipment and medium, comprising: acquiring the current remote photoplethysmogram of a user and current acoustic respiratory rhythm information; determining the current heart rate and current heart rate variability according to the current remote photoplethysmogram; determining the current joint physiological fingerprint according to the current heart rate, the current heart rate variability and the current acoustic respiratory rhythm information; determining the current physiological fingerprint correlation coefficient according to the current joint physiological fingerprint and the corresponding reference joint physiological fingerprint; determining the continuous compliance index of the user according to the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient; and if the continuous compliance index is less than or does not exceed the preset index threshold, risk warning is performed. The present application can be applied to the question and answer scene of medical health, and can effectively verify the medication compliance of the user.

Description

Technical Field

[0001] This invention relates to the fields of telemedicine and data processing technology, and in particular to a method, apparatus, equipment and medium for verifying medication adherence based on bioelectrical characteristics. Background Technology

[0002] Telemedicine utilizes communication technology to allow doctors and patients to consult each other without meeting in person. It encompasses diagnosis, consultation, and nursing care, aiming to improve diagnostic and medical standards, reduce medical expenses, and meet the healthcare needs of the general public. However, in telemedicine services, doctors rely on patients' self-reports to adjust medication regimens. Statistics show that approximately 30% to 50% of patients with chronic diseases (such as hypertension and diabetes) have poor medication adherence, often lying to doctors about taking their medication on time, leading doctors to make adjustments based on incorrect information and thus delaying treatment. Existing methods cannot effectively verify user medication adherence. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and medium for verifying medication adherence based on bioelectrical characteristics, in order to solve the technical problem of the inability to effectively verify users' medication adherence.

[0004] Firstly, a method for verifying medication adherence based on bioelectrical characteristics is provided, including: Obtain the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; Determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram; The current combined physiological fingerprint is determined based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; The correlation coefficient of the current physiological fingerprint is determined based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. Based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, the user's continuous compliance index is determined; If the continuous compliance index is less than or does not exceed a preset index threshold, a risk warning will be issued.

[0005] Secondly, a medication adherence verification device based on bioelectrical characteristics is provided, comprising: The information acquisition module is used to acquire the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; The heart rate information determination module is used to determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram. The physiological fingerprint determination module is used to determine the current combined physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information. The fingerprint correlation coefficient determination module is used to determine the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. The compliance index acquisition module is used to determine the user's continuous compliance index based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient. The risk alarm module is used to issue a risk alarm if the continuous compliance index is less than or does not exceed a preset index threshold.

[0006] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for verifying medication adherence based on bioelectrical characteristics.

[0007] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described method for verifying medication adherence based on bioelectrical characteristics.

[0008] In the aforementioned scheme implemented by the bioelectrical characteristic-based medication adherence verification method, device, equipment, and storage medium, the server can obtain the user's current remote photoplethysmography (TPM) and current acoustic respiratory rhythm information from the client; determine the current heart rate and current heart rate variability based on the current TPM; determine the current combined physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; determine the correlation coefficient of the current physiological fingerprint based on the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint; and determine the user's consecutive... The continuous adherence index is used to determine the user's medication adherence. If the continuous adherence index is less than or does not exceed a preset threshold, a risk warning is issued. In this invention, during remote medical services, the current combined physiological fingerprint can be determined based on the user's current heart rate, current heart rate variability, and current acoustic respiratory rhythm information. The correlation coefficient of the current combined physiological fingerprint is determined based on the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint. The user's continuous adherence index is determined based on the correlation coefficient of the current physiological fingerprint and the correlation coefficient of historical physiological fingerprints. A risk warning is issued when the continuous adherence index is less than or does not exceed a preset threshold, effectively verifying the user's medication adherence. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of an application environment for a medication adherence verification method based on bioelectrical characteristics, according to an embodiment of the present invention.

[0011] Figure 2 This is a flowchart illustrating a method for verifying medication adherence based on bioelectrical characteristics in one embodiment of the present invention.

[0012] Figure 3 This is a schematic diagram of a medication compliance verification device based on bioelectrical characteristics in one embodiment of the present invention.

[0013] Figure 4 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

[0014] Figure 5 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] The medication adherence verification method based on bioelectrical characteristics provided in this invention can be applied to, for example... Figure 1In this application environment, the server can obtain the user's current remote photoplethysmography (RPG) and current acoustic respiratory rhythm information from the client; determine the current heart rate and current heart rate variability based on the current RPG; determine the current joint physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; determine the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint; determine the user's continuous compliance index based on the correlation coefficient of the current physiological fingerprint and the historical physiological fingerprint; if the continuous compliance index is less than or not exceeding... If a preset index threshold is exceeded, a risk alarm is issued, and the risk alarm information can be fed back to the client. In this invention, during remote medical services, the current combined physiological fingerprint can be determined based on the user's current heart rate, current heart rate variability, and current acoustic respiratory rhythm information; the correlation coefficient of the current combined physiological fingerprint is determined based on the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint; the user's continuous compliance index is determined based on the correlation coefficient of the current physiological fingerprint and the correlation coefficient of historical physiological fingerprints; and a risk alarm is issued when the continuous compliance index is less than or does not exceed the preset index threshold, which can effectively verify the user's medication compliance. The client can include, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented using a separate server or a server cluster consisting of multiple servers. The invention will be described in detail below through specific embodiments.

[0017] Please see Figure 2 As shown, Figure 2 A flowchart illustrating a medication adherence verification method based on bioelectrical characteristics provided in an embodiment of the present invention includes the following steps: S10: Obtain the user's current remote photoplethysmogram and current acoustic respiratory rhythm information.

[0018] The medication adherence verification method based on bioelectrical characteristics provided by this invention can be applied to telemedicine services, typically implemented through a server that can receive user information in real time. For example, remote photoplethysmography and acoustic respiratory rhythm information can effectively verify user medication adherence. Specifically, the acoustic respiratory rhythm information can be quantitative information related to respiratory frequency and rhythm extracted by collecting and analyzing sound signals generated during breathing; specifically, the acoustic respiratory rhythm information can include respiratory frequency and / or respiratory depth.

[0019] The aforementioned remote photoplethysmography (rPPG) can include waveform signals showing the periodic changes in blood volume in facial skin and capillaries as the heart beats. Specifically, a camera can capture subtle color changes on the skin surface. When the heart beats, the blood flow in facial capillaries changes periodically. Because blood absorbs specific wavelengths (especially green light), the intensity of reflected light fluctuates constantly. The green channel signal of the region of interest (ROI) on the face is extracted from the video frame, and after denoising using independent component analysis (ICA), the pulse waveform is reconstructed to obtain a remote photoplethysmography (rPPG). The medication mentioned above can be a dopamine agonist or a common antihypertensive drug (such as amlodipine). The aforementioned acquisition of the user's current remote photoplethysmography can be monitored within a specific time window after the user (patient) takes the medication, using the user's mobile phone's front-facing camera or other cameras.

[0020] In this embodiment, ordinary devices such as mobile phone cameras can be upgraded to drug effect detectors, which can reduce the monitoring cost for patients.

[0021] S20, determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram.

[0022] After obtaining the current remote photoplethysmogram (RPG), the current heart rate and its variability can be determined based on it. For example, if the sampling rate is 30fps (i.e., the camera takes 30 photos per second), the brightness changes of 30 consecutive frames form a pulse waveform with peaks one after another. If the detected frame interval sequence between peaks is {24, 25, 24, 26} frames, that is, there are 24 frames between the first and second heartbeats, 25 frames between the second and third heartbeats, and so on. 24 frames means that the time interval between two heartbeats is 24 ÷ 30 = 0.8 seconds (i.e., 800ms). The instantaneous heart rate calculation process is as follows: if there are 24 frames between two heartbeats, it means that there are 30 frames / second × 60 seconds = 1800 frames per minute, and 1800 frames ÷ 24 frames = 75 bpm. 75 bpm reflects the current beating speed, i.e., the current heart rate.

[0023] Heart rate variability (HRV) reflects the irregularity of heartbeat intervals and can be measured by calculating the standard deviation of the time interval between heartbeat peaks (SDNN). In a healthy person, the heartbeat interval should fluctuate slightly, such as {800ms, 833ms, 800ms}, while medications (such as sedatives) usually reduce the value of heart rate variability.

[0024] S30, determine the current combined physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information.

[0025] In step S30, the current combined physiological fingerprint is determined based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information, including: A vector is formed using the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information, and the vector is used as the current joint physiological fingerprint, wherein the acoustic respiratory rhythm information includes respiratory rate.

[0026] Specifically, a vector is formed using the current heart rate X, the current heart rate variability Y, and the current respiratory rate Z. , with vector As a current combined physiological fingerprint, for example, if the current heart rate X is 75 (bpm), the current heart rate variability Y is 56 (ms), and the respiratory rate Z is 16 (breaths / min), then the current combined physiological fingerprint is: .

[0027] In this embodiment, a vector is formed using the current heart rate, current heart rate variability, and current acoustic respiratory rhythm information. This vector serves as the current joint physiological fingerprint, which can be used to determine the user's joint physiological fingerprint in real time. This allows for the rapid determination of the subsequent continuous compliance index, enabling a risk warning to be issued and improving the efficiency of medication compliance verification.

[0028] S40, determine the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint.

[0029] It should be noted that the baseline joint physiological fingerprint can be obtained from the physiological fingerprint database, which may include joint physiological fingerprints from multiple preset time points in history; the aforementioned baseline joint physiological fingerprint may refer to the joint physiological fingerprint from the physiological fingerprint database at the preset time point corresponding to the current joint physiological fingerprint.

[0030] In step S40, the correlation coefficient of the current physiological fingerprint is determined based on the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint, including: The correlation coefficient of the current physiological fingerprint is determined based on the Euclidean distance or Piasson correlation coefficient between the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint.

[0031] In a specific implementation process, the correlation coefficient of the current physiological fingerprint is determined by Euclidean distance. For example, if the current combined physiological fingerprint... The corresponding baseline combined with physiological fingerprint Therefore, the Euclidean distance between the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint can be calculated to be approximately 3.74. It should be noted that the smaller the Euclidean distance, the higher the matching degree between the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint.

[0032] In another specific implementation, the correlation coefficient of the current physiological fingerprint is determined based on the Piasson correlation coefficient between the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint. The Piasson correlation coefficient can be expressed as: in, For current joint physiological fingerprinting Combined with corresponding baseline physiological fingerprints Piasson correlation coefficient, For current joint physiological fingerprinting Combined with corresponding baseline physiological fingerprints covariance, and represents the population standard deviation of the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint, respectively. For the Piasson correlation coefficient, The value ranges from -1 to 1. A value greater than 0.85 indicates a high correlation between the fluctuation pattern of current physiological characteristics and the pattern of drug metabolism.

[0033] It should be noted that the physiological fingerprint database may include joint physiological fingerprints at multiple preset time points; the corresponding benchmark joint physiological fingerprint mentioned above can refer to the joint physiological fingerprint in the physiological fingerprint database at the preset time point corresponding to the current joint physiological fingerprint. For example, if the preset time point corresponding to the current joint physiological fingerprint is 3 PM on the first day after taking the medication, then the corresponding benchmark joint physiological fingerprint can refer to the joint physiological fingerprint in the physiological fingerprint database at 3 PM on the first day after taking the medication.

[0034] In this embodiment, the correlation coefficient of the current physiological fingerprint is determined by the Euclidean distance or Piasson correlation coefficient between the current combined physiological fingerprint and the corresponding benchmark combined physiological fingerprint. This can quickly and accurately determine the correlation coefficient of the user's current physiological fingerprint and improve the efficiency of medication adherence verification.

[0035] In one embodiment, before determining the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint in step S40, the method further includes: S31, collect heart rate, heart rate variability and acoustic respiratory rhythm information of subjects after taking medication at multiple preset time points; S32, determine the combined physiological fingerprint of the multiple preset time points based on the heart rate, heart rate variability and acoustic respiratory rhythm information of the subject after taking the drug; S33, construct a physiological fingerprint database based on the combined physiological fingerprints at the multiple preset time points, and determine the corresponding benchmark combined physiological fingerprint from the physiological fingerprint database.

[0036] In one specific implementation process, after taking a medication (such as a dopamine agonist or a common antihypertensive drug), heart rate, heart rate variability, and acoustic respiratory rhythm information are collected from the subject at multiple preset time points, such as 3 PM on the first day, 3 PM on the third day, and 3 PM on the fifth day, to obtain a combined physiological fingerprint at multiple preset time points. , , A physiological fingerprint database can be constructed using the combined physiological fingerprints at multiple preset time points. The physiological fingerprint database includes the combined physiological fingerprints at multiple preset time points. The subjects mentioned above can be multiple individuals, and the combined physiological fingerprints at the preset time points can be the average of the combined physiological fingerprints of multiple subjects at the preset time points.

[0037] In this embodiment, heart rate, heart rate variability, and acoustic respiratory rhythm information of the subject after taking the medication are collected at multiple preset time points to determine the joint physiological fingerprint at multiple preset time points. A physiological fingerprint database is constructed based on the joint physiological fingerprint at multiple preset time points, which facilitates the subsequent determination of the corresponding benchmark joint physiological fingerprint from the physiological fingerprint database. This helps to improve the efficiency of determining the correlation coefficient of the user's current physiological fingerprint and can also improve the efficiency of medication adherence verification.

[0038] S50, determine the user's continuous compliance index based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient.

[0039] It should be noted that the above continuous compliance index characterizes the correlation between current physiological characteristics (physiological fingerprint) and drug metabolism. The continuous compliance index can take values ​​between 0 and 1. The larger the value, the greater the correlation between current physiological characteristics and drug metabolism.

[0040] In one embodiment, step S50, determining the user's continuous compliance index based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, includes: S51, obtain the correlation coefficients of multiple historical physiological fingerprints within a first preset time period; S52, Based on the multiple historical physiological fingerprint correlation coefficients, determine the largest physiological fingerprint correlation coefficient; S53, perform a weighted average of the current physiological fingerprint correlation coefficient and the largest physiological fingerprint correlation coefficient to obtain the user's continuous compliance index.

[0041] It should be noted that the continuous adherence index is not a single-dimensional judgment, but a weighted model of physiological fingerprint correlation coefficient and historical medication patterns. For example, if the current physiological fingerprint correlation coefficient R_today = 0.9, multiple historical physiological fingerprint correlation coefficients within a first preset time period are obtained. If the user's maximum physiological fingerprint correlation coefficient R_history at a preset time point (3 pm) in the past 7 days is 0.95, then the user's continuous adherence index CII = w1×R_today + w2×R_history, where w1 is the first weight coefficient and w2 is the second weight coefficient. The sum of the first and second weight coefficients equals 1. For example, if w1 is 0.6 and w2 is 0.4, then the user's continuous adherence index CII is 0.92.

[0042] In one embodiment, step S51 involves obtaining multiple historical physiological fingerprint correlation coefficients within a first preset time period, including: S511, within the first preset time period, the user's heart rate, heart rate variability and acoustic respiratory rhythm information after taking the medication are collected once at a second preset time interval to obtain multiple historical joint physiological fingerprints within the first preset time period.

[0043] S512, based on the Euclidean distance or Piasson correlation coefficient between the historical joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint, determine the correlation coefficients of multiple historical physiological fingerprints within the first preset time period.

[0044] It should be noted that the correlation coefficients of multiple historical physiological fingerprints within the first preset time period can be the correlation coefficients of multiple historical physiological fingerprints within the first preset time period after the current user takes the medication. Within the first preset time period, the user's heart rate, heart rate variability, and acoustic respiratory rhythm information after taking the medication are collected every second preset time interval. Following the method for determining the current joint physiological fingerprint, multiple historical joint physiological fingerprints within the first preset time period can be obtained, and thus the correlation coefficients of multiple historical physiological fingerprints within the first preset time period can be determined.

[0045] S60, if the continuous compliance index is less than or does not exceed a preset index threshold, a risk warning is issued.

[0046] In this embodiment, medication adherence can be verified based on an objective continuous adherence index. An alarm is triggered when the continuous adherence index is less than a preset index threshold, which can significantly improve the safety of chronic disease management.

[0047] It should be noted that the preset index threshold can be set according to actual conditions. For example, 0.8. If the continuous compliance index is less than 0.8, a risk warning can be issued, triggering reminders or doctor intervention suggestions. If the compliance index obtained for the current user is higher than the preset index threshold multiple times consecutively, it is judged as high compliance.

[0048] In one embodiment, the above-mentioned method for verifying medication adherence based on bioelectrical characteristics further includes: S71, acquires the user's facial temperature changes and facial feature points; S72, track and identify micro-expression changes based on the facial feature points; S73, cross-validate the facial temperature change with the micro-expression change. If the verification fails, issue a risk warning.

[0049] Specifically, changes in facial temperature (micro-temperature) can be captured using an infrared camera and cross-validated with emotional fluctuations (micro-expression changes). Real physiological drug responses are often accompanied by regulation of the autonomic nervous system; for example, some vasodilators can cause a slight increase in facial temperature. This necessitates verifying whether facial temperature and emotional fluctuations exhibit physiologically consistent in-phase fluctuations under the same stimulus.

[0050] In one specific implementation, facial feature points can be acquired using the front-facing camera of a mobile phone (exemplarily including an infrared camera and a dot projector) to track and identify subtle micro-expression changes (such as muscle contraction frequency). For example, motion vectors of 68 facial feature points can be acquired to calculate micro-expression contrast entropy, thereby obtaining subtle micro-expression changes. As an example, if a facial temperature rise of a preset temperature (e.g., 0.2 degrees Celsius) is detected, accompanied by natural micro-expression relaxation, it is determined to be a genuine drug metabolism response; if there is only a temperature increase but no corresponding emotional physiological signal, or if emotional indicators show extreme anxiety (possibly due to lying), the verification fails, and a risk warning can be issued.

[0051] If a pulsed increase in heart rate (HRV) caused by drug metabolism is detected, according to the logic of human pathophysiology, an increase in heart rate is usually accompanied by sympathetic nerve excitation, which will lead to an acceleration of local microcirculation in the face (a 0.1-0.2 degree Celsius increase in the temperature of the tip of the nose and the forehead) and a synchronous slight increase in respiratory rate. The delay time between the peak of heart rate and the peak of temperature rise can be calculated. The facial temperature can be cross-validated based on whether the respiratory rate increases synchronously and the delay time. If the validation fails, a risk alarm can be issued.

[0052] Since many medications have mild sedative or stimulating effects on the respiratory system, altering its acoustic characteristics, acoustic respiratory rhythm information can be incorporated into medication adherence verification. This information can include respiratory frequency and respiratory depth. Specifically, for the respiratory frequency, an ambient audio sequence can be acquired using a microphone at close range. A high-pass filter removes background noise, retaining the respiratory sound waves in the 20Hz-500Hz frequency range. By analyzing the periodic fluctuations of the audio envelope, the alternation frequency of inhalation and exhalation is identified, thus obtaining the respiratory frequency. Respiratory depth can be determined by extracting the peak amplitude of the acoustic energy. During deep breathing, the turbulent acoustic energy (energy spectral density) generated by airflow through the respiratory tract is significantly higher than during shallow breathing.

[0053] In the above scheme, during the remote medical service process, the current combined physiological fingerprint can be determined based on the user's current heart rate, current heart rate variability, and current acoustic respiratory rhythm information; the correlation coefficient of the current combined physiological fingerprint can be determined based on the current combined physiological fingerprint and the corresponding baseline combined physiological fingerprint; the user's continuous compliance index can be determined based on the correlation coefficient of the current physiological fingerprint and the correlation coefficient of the historical physiological fingerprint; and a risk alarm can be issued when the continuous compliance index is less than a preset index threshold, which can effectively verify the user's medication compliance and realize the monitoring of the user's medication use.

[0054] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0055] In one embodiment, a medication adherence verification device based on bioelectrical characteristics is provided, which corresponds one-to-one with the medication adherence verification method based on bioelectrical characteristics described in the above embodiments. For example... Figure 3 As shown, the medication adherence verification device based on bioelectrical characteristics includes an information acquisition module 31, a heart rate information determination module 32, a physiological fingerprint determination module 33, a fingerprint correlation coefficient determination module 34, an adherence index acquisition module 35, and a risk alarm module 36. Detailed descriptions of each functional module are as follows: Information acquisition module 31 is used to acquire the user's current remote photoplethysmogram and current acoustic breathing rhythm information; Heart rate information determination module 32 is used to determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram; The physiological fingerprint determination module 33 is used to determine the current combined physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information. The fingerprint correlation coefficient determination module 34 is used to determine the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. The compliance index acquisition module 35 is used to determine the user's continuous compliance index based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient. The risk alarm module 36 is used to issue a risk alarm if the continuous compliance index is less than or does not exceed a preset index threshold.

[0056] In one embodiment, the physiological fingerprint determination module 33 is further configured to: A vector is formed using the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information, and the vector is used as the current joint physiological fingerprint, wherein the acoustic respiratory rhythm information includes respiratory rate.

[0057] In one embodiment, the fingerprint correlation coefficient determination module 34 is further configured to: The correlation coefficient of the current physiological fingerprint is determined based on the Euclidean distance or Piasson correlation coefficient between the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint.

[0058] In one embodiment, the physiological fingerprint determination module 33 is further configured to: Before determining the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint, Heart rate, heart rate variability, and acoustic respiratory rhythm information were collected from subjects at multiple preset time points after medication administration. The combined physiological fingerprint of the multiple preset time points is determined based on the heart rate, heart rate variability and acoustic respiratory rhythm information of the subject after taking the medication; A physiological fingerprint database is constructed based on the combined physiological fingerprints at the multiple preset time points, and the corresponding benchmark combined physiological fingerprint is determined from the physiological fingerprint database.

[0059] In one embodiment, the compliance index acquisition module 35 is further configured to: Obtain the correlation coefficients of multiple historical physiological fingerprints within a first preset time period; Based on the correlation coefficients of the multiple historical physiological fingerprints, the largest physiological fingerprint correlation coefficient is determined; The user's continuous compliance index is obtained by taking a weighted average of the current physiological fingerprint correlation coefficient and the largest physiological fingerprint correlation coefficient.

[0060] In one embodiment, the compliance index acquisition module 35 is further configured to: Within the first preset time period, the heart rate, heart rate variability and acoustic respiratory rhythm information of the user after taking the medication are collected once at a second preset time interval to obtain multiple historical joint physiological fingerprints within the first preset time period. Based on the Euclidean distance or Piasson correlation coefficient between the historical joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint, multiple historical physiological fingerprint correlation coefficients within a first preset time period are determined.

[0061] In one embodiment, the medication adherence verification device based on bioelectrical characteristics further includes a cross-validation module, which is used for: Acquire user facial temperature changes and facial feature points; Micro-expression changes are tracked and identified based on the facial feature points; The facial temperature changes are cross-validated with the micro-expression changes. If the verification fails, a risk warning is issued.

[0062] This invention provides a medication adherence verification device based on bioelectrical characteristics. It can determine the current combined physiological fingerprint based on the user's current heart rate, current heart rate variability, and current acoustic respiratory rhythm information; determine the correlation coefficient of the current combined physiological fingerprint with the corresponding baseline combined physiological fingerprint; determine the user's continuous adherence index based on the correlation coefficient of the current physiological fingerprint and the correlation coefficient of historical physiological fingerprints; and issue a risk alarm when the continuous adherence index is less than a preset threshold, thus effectively verifying the user's medication adherence.

[0063] Specific limitations regarding the bioelectrical characteristic-based medication adherence verification device can be found in the limitations of the intelligent question-and-answer method described above, and will not be repeated here. Each module in the aforementioned bioelectrical characteristic-based medication adherence verification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0064] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a bioelectrical characteristic-based medication adherence verification method on the server side.

[0065] In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When executed by the processor, the computer program implements the client-side functions or steps of a medication adherence verification method based on bioelectrical characteristics.

[0066] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Obtain the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; Determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram; The current combined physiological fingerprint is determined based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; The correlation coefficient of the current physiological fingerprint is determined based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. Based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, the user's continuous compliance index is determined; If the continuous compliance index is less than or does not exceed a preset index threshold, a risk warning will be issued.

[0067] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Obtain the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; Determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram; The current combined physiological fingerprint is determined based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; The correlation coefficient of the current physiological fingerprint is determined based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. Based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, the user's continuous compliance index is determined; If the continuous compliance index is less than or does not exceed a preset index threshold, a risk warning will be issued.

[0068] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0069] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0071] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for verifying medication adherence based on bioelectrical characteristics, characterized in that, include: Obtain the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; Determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram; The current combined physiological fingerprint is determined based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information; The correlation coefficient of the current physiological fingerprint is determined based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. Based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, the user's continuous compliance index is determined; If the continuous compliance index is less than or does not exceed a preset index threshold, a risk warning will be issued.

2. The method for verifying medication adherence based on bioelectrical characteristics according to claim 1, characterized in that, Based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information, a current combined physiological fingerprint is determined, including: A vector is formed using the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information, and the vector is used as the current joint physiological fingerprint, wherein the acoustic respiratory rhythm information includes respiratory rate.

3. The method for verifying medication adherence based on bioelectrical characteristics according to claim 1, characterized in that, Based on the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint, determine the correlation coefficient of the current physiological fingerprint, including: The correlation coefficient of the current physiological fingerprint is determined based on the Euclidean distance or Piasson correlation coefficient between the current joint physiological fingerprint and the corresponding baseline joint physiological fingerprint.

4. The method for verifying medication adherence based on bioelectrical characteristics according to claim 1, characterized in that, Before determining the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint, the method further includes: Heart rate, heart rate variability, and acoustic respiratory rhythm information were collected from subjects at multiple preset time points after medication administration. The combined physiological fingerprint of the multiple preset time points is determined based on the heart rate, heart rate variability and acoustic respiratory rhythm information of the subject after taking the medication; A physiological fingerprint database is constructed based on the combined physiological fingerprints at the multiple preset time points, and the corresponding benchmark combined physiological fingerprint is determined from the physiological fingerprint database.

5. The method for verifying medication adherence based on bioelectrical characteristics according to claim 1, characterized in that, Based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient, the user's continuous compliance index is determined, including: Obtain the correlation coefficients of multiple historical physiological fingerprints within a first preset time period; Based on the correlation coefficients of the multiple historical physiological fingerprints, the largest physiological fingerprint correlation coefficient is determined; The user's continuous compliance index is obtained by taking a weighted average of the current physiological fingerprint correlation coefficient and the largest physiological fingerprint correlation coefficient.

6. The method for verifying medication adherence based on bioelectrical characteristics according to claim 5, characterized in that, Obtain correlation coefficients of multiple historical physiological fingerprints within a first preset time period, including: Within the first preset time period, the heart rate, heart rate variability and acoustic respiratory rhythm information of the user after taking the medication are collected once at a second preset time interval to obtain multiple historical joint physiological fingerprints within the first preset time period. Based on the Euclidean distance or Piasson correlation coefficient between the historical joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint, multiple historical physiological fingerprint correlation coefficients within a first preset time period are determined.

7. The method for verifying medication adherence based on bioelectrical characteristics according to claim 1, characterized in that, The medication adherence verification method based on bioelectrical characteristics further includes: Acquire user facial temperature changes and facial feature points; Micro-expression changes are tracked and identified based on the facial feature points; The facial temperature changes are cross-validated with the micro-expression changes. If the verification fails, a risk warning is issued.

8. A medication adherence verification device based on bioelectrical characteristics, characterized in that, include: The information acquisition module is used to acquire the user's current remote photoplethysmogram and current acoustic respiratory rhythm information; The heart rate information determination module is used to determine the current heart rate and current heart rate variability based on the current remote photoplethysmogram. The physiological fingerprint determination module is used to determine the current combined physiological fingerprint based on the current heart rate, the current heart rate variability, and the current acoustic respiratory rhythm information. The fingerprint correlation coefficient determination module is used to determine the correlation coefficient of the current physiological fingerprint based on the current joint physiological fingerprint and the corresponding benchmark joint physiological fingerprint. The compliance index acquisition module is used to determine the user's continuous compliance index based on the current physiological fingerprint correlation coefficient and the historical physiological fingerprint correlation coefficient. The risk alarm module is used to issue a risk alarm if the continuous compliance index is less than or does not exceed a preset index threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the medication adherence verification method based on bioelectrical characteristics as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the medication adherence verification method based on bioelectrical characteristics as described in any one of claims 1 to 7.

Images