An intelligent massage evaluation method and device fusing noise reduction and electronic equipment

Abstract

The application provides a fusion noise reduction intelligent massage evaluation method and device and electronic equipment, and relates to the technical field of biological signal detection. In the application, in response to a first massage operation of a massage device on a target object, an original surface electromyogram of the target object and a pressure signal of the massage device acting on the target object are acquired in real time; the pressure signal is subjected to signal decoupling processing through a first signal filter to obtain a first signal component related to a motion artifact generated by the operation of the massage device; noise components caused by the motion artifact in the original surface electromyogram are eliminated based on the first signal component to obtain a pure surface electromyogram; and a first relaxation index for evaluating the massage effect is determined based on a first median frequency determined based on a power spectral density of the pure surface electromyogram and a second median frequency of a resting surface electromyogram of the target object in a resting state. In this way, the massage effect of the massage device can be accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of biosignal detection technology, and in particular to an intelligent massage evaluation method, device and electronic device that integrates noise reduction. Background Technology

[0002] When a massage device is applied to muscles, the pressure and massage cause changes in local blood flow, leading to the accumulation of lactic acid produced by anaerobic metabolism and a decrease in the pH value of the extracellular fluid. This decrease in pH value inhibits the activity of the sodium-potassium pump on the muscle fiber membrane, which slows down the motor nerve conduction velocity (MNCV) of the muscle fibers.

[0003] In the frequency domain, the power spectral density (PSD) of surface electromyography (sEMG) signals is "compressed" towards lower frequencies, specifically a decrease in the median frequency (MF) and mean power frequency (MPF). Therefore, sEMG signals are an ideal bioelectrical indicator for evaluating the effectiveness of massage, allowing for the analysis of how massage relaxes muscle fatigue.

[0004] However, during actual massage, the noise generated by the mechanical vibration of the massage device produces significant motion artifacts (MA) on the surface electromyography (SEMG) signal. These artifacts highly overlap with the main energy frequency band of the SEMG signal, severely affecting its signal quality. This makes it impossible to accurately evaluate the massage effect of the massage device directly based on the acquired SEMG signal. Therefore, how to accurately evaluate the massage effect of a massage device is a problem that urgently needs to be solved. Summary of the Invention

[0005] This application provides a method, device, and electronic device for evaluating massage performance using noise reduction, which can accurately evaluate the massage effect of a massage device based on the collected surface electromyography signals.

[0006] In a first aspect, embodiments of this application provide an intelligent massage evaluation method incorporating noise reduction, the method comprising: In response to the first massage operation of the massage device on the target object, the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device applied to the target object are acquired in real time; wherein, the original surface EMG signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; The pressure signal is decoupled by a first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the massage device. The noise component caused by motion artifacts in the original surface electromyography signal is eliminated based on the first signal component to obtain a pure surface electromyography signal. Based on the first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal, and the second median frequency of the resting surface electromyography signal of the target object in the resting state, a first relaxation index of the target object is determined; the first relaxation index is used to characterize the massage effect of the massage device massaging the target object according to the first massage operation at the current moment.

[0007] In one optional embodiment, eliminating the noise component caused by motion artifacts in the original surface electromyography (EMG) signal based on a first signal component to obtain a pure EMG signal includes: Acquire historical signal components that are adjacent to the current time and whose number matches that of the adaptive filter; wherein each historical signal component is related to the motion artifact generated by the massage device at the corresponding historical time. Based on the noise conversion coefficient vector of the adaptive filter, noise conversion coefficient matching is performed on the first signal component and each historical signal component to obtain the first signal component and each historical signal component after noise conversion coefficient matching; wherein, the first noise conversion coefficient in the noise conversion coefficient vector is set for the first signal component, and the Nth noise conversion coefficient in the noise conversion coefficient vector is set for the historical signal component of the N-1th historical time adjacent to the current time, where N is an integer greater than 0 and less than or equal to the filter order; The first signal component after noise conversion coefficient matching and each historical signal component are input into the adaptive filter so that the first signal component after noise conversion coefficient matching and each historical signal component are fitted with the noise conversion coefficient vector to obtain the noise component. The difference between the original surface electromyography (EMG) signal and the noise component is used as the pure EMG signal.

[0008] In an optional embodiment, after using the difference signal between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the method further includes: Based on the preset step length factor, the first signal component, and the pure surface electromyography signal, the first product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the preset first parameter and the sum of squares, the first summation result is obtained; where the first parameter is a positive number; Based on the ratio between the first product result and the first summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0009] In an optional embodiment, the method further includes: The pressure signal is decoupled by a second signal filter to obtain a second signal component. The passband frequency of the second signal filter is lower than that of the first signal filter. The second signal component is used to indicate the effective massage pressure applied to the target object by the massage device at the current moment. After using the difference between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the following steps are also included: Based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient at the current moment, the noise conversion coefficient of the next moment adjacent to the current moment is determined; wherein, the first parameter is a positive number.

[0010] In one optional embodiment, the noise conversion coefficient of the next time step adjacent to the current time step is determined based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, a preset pressure sensitivity compensation factor, a preset first parameter, a pure surface electromyography signal, and the noise conversion coefficient at the current time step, including: Based on the adjustable step size factor, the first signal component, and the pure surface electromyography signal, the second product result is obtained; Based on the pressure sensitivity compensation factor and the second signal component, the third product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the sum of squares, the first parameter, and the third product result, the second summation result is obtained; Based on the ratio between the second product result and the second summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0011] In one optional embodiment, determining a first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state includes: Multiple historical surface electromyography (EMG) signals, after noise cancellation, adjacent to the pure surface EMG signal are acquired through a set sliding window. Based on the pure surface EMG signal and the multiple historical surface EMG signals, a discrete-time signal is obtained. The first median frequency is determined based on the power spectral density of the discrete-time signal, and the first relaxation index is determined based on the first median frequency and the second median frequency.

[0012] In one alternative embodiment, determining a first relaxation index based on a first median frequency and a second median frequency includes: Calculate the median frequency shift between the first and second median frequencies, and use this median frequency shift as the first relaxation index; or... Calculate the median frequency shift between the first and second median frequencies and the time interval between the pure surface electromyography (EMG) signal and the resting surface EMG signal; use the ratio of the median frequency shift to the time interval as the first relaxation index; or, Calculate the median frequency shift between the first median frequency and the second median frequency, and use the ratio of the median frequency shift to the second median frequency as the first relaxation index.

[0013] In an optional embodiment, after determining the first relaxation index based on the first median frequency and the second median frequency, the method further includes: If the first relaxation index is greater than or equal to the relaxation index threshold, a first control signal is sent to the massage device; the first control signal is used to instruct the massage device to stop massaging the target object. If the first relaxation index is less than the relaxation index threshold and the massage duration reaches the duration threshold, then a first control signal is sent to the massage device.

[0014] In an optional embodiment, the method further includes: If the first relaxation index is less than the relaxation index threshold and the massage duration does not reach the duration threshold, then obtain the second relaxation index of the target object after the set massage duration. When the second relaxation index is still less than the relaxation index threshold, a second control signal is sent to the massage device; the second control signal is used to instruct the massage device to massage the target object according to the second massage operation, and the massage intensity corresponding to the second massage operation is greater than the massage intensity corresponding to the first massage operation.

[0015] Secondly, embodiments of this application also provide an intelligent massage evaluation device with noise reduction integration, the device comprising: The signal acquisition module is used to acquire the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device applied to the target object in real time in response to the first massage operation of the massage device on the target object; wherein, the original surface EMG signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; The signal decoupling module is used to decouple the pressure signal through the first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the operation of the massage device. The noise cancellation module is used to eliminate the noise component caused by motion artifacts in the original surface electromyography signal based on the first signal component, so as to obtain a pure surface electromyography signal. The massage evaluation module is used to determine a first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state. The first relaxation index is used to characterize the massage effect of the massage device massaging the target object according to the first massage operation at the current moment.

[0016] In an optional embodiment, when eliminating the noise component caused by motion artifacts in the original surface electromyography (EMG) signal based on the first signal component to obtain a pure EMG signal, the noise elimination module is specifically used for: Acquire historical signal components that are adjacent to the current time and whose number matches the adaptive filter order; wherein, each historical signal component is related to the motion artifact generated by the massage device at the corresponding historical time. Based on the noise conversion coefficient vector of the adaptive filter, noise conversion coefficient matching is performed on the first signal component and each historical signal component to obtain the first signal component and each historical signal component after noise conversion coefficient matching; wherein, the first noise conversion coefficient in the noise conversion coefficient vector is set for the first signal component, and the Nth noise conversion coefficient in the noise conversion coefficient vector is set for the historical signal component of the N-1th historical time adjacent to the current time, where N is an integer greater than 0 and less than or equal to the filter order; The first signal component after noise conversion coefficient matching and each historical signal component are input into the adaptive filter so that the first signal component after noise conversion coefficient matching and each historical signal component are fitted with the noise conversion coefficient vector to obtain the noise component. The difference between the original surface electromyography (EMG) signal and the noise component is used as the pure EMG signal.

[0017] In an optional embodiment, after using the difference signal between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the noise cancellation module is further configured to: Based on the preset step length factor, the first signal component, and the pure surface electromyography signal, the first product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the preset first parameter and the sum of squares, the first summation result is obtained; where the first parameter is a positive number; Based on the ratio between the first product result and the first summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0018] In an optional embodiment, the signal decoupling module is further configured to: The pressure signal is decoupled by a second signal filter to obtain a second signal component. The passband frequency of the second signal filter is lower than that of the first signal filter. The second signal component is used to indicate the effective massage pressure applied to the target object by the massage device at the current moment. After using the difference between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the noise cancellation module is also used for: Based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient at the current moment, the noise conversion coefficient of the next moment adjacent to the current moment is determined; wherein, the first parameter is a positive number.

[0019] In an optional embodiment, when determining the noise conversion coefficient of the next time step adjacent to the current time step based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient of the current time step, the noise cancellation module is specifically used for: Based on the adjustable step size factor, the first signal component, and the pure surface electromyography signal, the second product result is obtained; Based on the pressure sensitivity compensation factor and the second signal component, the third product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the sum of squares, the first parameter, and the result of the second product, the second summation result is obtained; Based on the ratio between the second product result and the second summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0020] In an optional embodiment, when determining the first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state, the massage evaluation module is specifically used for: Multiple historical surface electromyography (EMG) signals, after noise cancellation, adjacent to the pure surface EMG signal are acquired through a set sliding window. Based on the pure surface EMG signal and the multiple historical surface EMG signals, a discrete-time signal is obtained. The first median frequency is determined based on the power spectral density of the discrete-time signal, and the first relaxation index is determined based on the first median frequency and the second median frequency.

[0021] In one optional embodiment, when determining the first relaxation index based on a first median frequency and a second median frequency, the massage evaluation module is specifically used to: Calculate the median frequency shift between the first and second median frequencies, and use this median frequency shift as the first relaxation index; or... Calculate the median frequency shift between the first and second median frequencies and the time interval between the pure surface electromyography (EMG) signal and the resting surface EMG signal; use the ratio of the median frequency shift to the time interval as the first relaxation index; or, Calculate the median frequency shift between the first median frequency and the second median frequency, and use the ratio of the median frequency shift to the second median frequency as the first relaxation index.

[0022] In an optional embodiment, after determining the first relaxation index based on a first median frequency and a second median frequency, the device further includes a massage control module, which is specifically used for: If the first relaxation index is greater than or equal to the relaxation index threshold, a first control signal is sent to the massage device; the first control signal is used to instruct the massage device to stop massaging the target object. If the first relaxation index is less than the relaxation index threshold and the massage duration reaches the duration threshold, then a first control signal is sent to the massage device.

[0023] In an optional embodiment, the massage control module is further configured to: If the first relaxation index is less than the relaxation index threshold and the massage duration does not reach the duration threshold, then obtain the second relaxation index of the target object after the set massage duration. When the second relaxation index is still less than the relaxation index threshold, a second control signal is sent to the massage device; the second control signal is used to instruct the massage device to massage the target object according to the second massage operation, and the massage intensity corresponding to the second massage operation is greater than the massage intensity corresponding to the first massage operation.

[0024] Thirdly, embodiments of this application provide an electronic device, including: processor; Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the intelligent massage evaluation method with fused noise reduction as described in the first aspect.

[0025] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the intelligent massage evaluation method with fusion noise reduction as described in the first aspect.

[0026] Fifthly, this application provides a computer program product that, when invoked by a computer, causes the computer to execute the steps of the intelligent massage evaluation method with fusion noise reduction as described in the first aspect.

[0027] The beneficial effects of this application are as follows: In the intelligent massage evaluation method with fusion noise reduction provided in this application embodiment, in response to the first massage operation of the massage device on the target object, the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device acting on the target object are acquired in real time; wherein, the original EMG signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; then, the pressure signal is decoupled by a first signal filter to obtain a first signal component; the first signal component is related to the motion artifact generated by the operation of the massage device; further, the noise component caused by the motion artifact in the original EMG signal is eliminated based on the first signal component to obtain a pure EMG signal; finally, a first relaxation index of the target object is determined based on the first median frequency determined by the power spectral density corresponding to the pure EMG signal and the second median frequency of the resting EMG signal of the target object in the resting state; the first relaxation index is used to characterize the massage effect of the massage device performing the first massage operation on the target object at the current moment. In this way, by using the first signal component related to the generation of motion artifacts obtained from the decoupled pressure signal as noise generated by the mechanical vibration of the massage device, the noise component caused by motion artifacts in the original surface electromyography (EMG) signal can be eliminated, thus obtaining a pure EMG signal (i.e., a high-quality EMG signal). Furthermore, since the median frequency can effectively reflect the fatigue level of the target object, the first relaxation index, determined based on the first median frequency of the pure EMG signal and the second median frequency of the target object's resting EMG signal, can objectively and quantitatively evaluate the massage effect of the massage device performing the first massage operation on the target object at the current moment. Therefore, by employing the aforementioned intelligent massage evaluation method with fusion and noise reduction, the massage effect of the massage device can be accurately evaluated based on the collected EMG signals.

[0028] Furthermore, other features and advantages of this application will be set forth in the following description and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described herein are used to provide a further understanding of this application, constitute a part of this application, and do not constitute an improper limitation of this application. In the accompanying drawings: Figure 1 This is a schematic diagram of an optional application scenario provided for an embodiment of this application.

[0030] Figure 2 This is a schematic diagram illustrating the implementation process of an intelligent massage evaluation method with noise reduction fusion, provided in an embodiment of this application.

[0031] Figure 3 This is a schematic diagram illustrating the implementation process of a method for extracting pure surface electromyography signals, provided in an embodiment of this application.

[0032] Figure 4 This is a logic diagram of a massage device control provided in an embodiment of this application.

[0033] Figure 5 This is a schematic diagram of the structure of an intelligent massage evaluation device with noise reduction fusion provided in an embodiment of this application.

[0034] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0035] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0036] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0037] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this application are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0038] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0039] The names of the messages or information exchanged between multiple devices in the embodiments of this application are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0040] The design concept of the embodiments of this application is briefly introduced below: Surface electromyography (EMG) signals are the temporal and spatial superposition of numerous motor unit action potentials (MUAPs). When the central nervous system issues a command, nerve impulses are conducted along axons to the neuromuscular junction, causing changes in the muscle fiber membrane potential. Surface EMG signals are weak, non-stationary, random signals, typically with amplitudes between 10µV and 5mV, and energy concentrated in the frequency range of 20Hz–500Hz. When a massage device (or massager) acts on muscles, the massage and compression cause changes in local blood flow, leading to the accumulation of lactic acid produced by anaerobic metabolism and a decrease in the extracellular fluid pH. This decrease in pH inhibits the activity of the sodium-potassium pump on the muscle fiber membrane, resulting in a slowdown in the motor nerve conduction velocity of the muscle fibers.

[0041] In the frequency domain, this manifests as a "compression" of the power spectral density of surface electromyography (EMG) signals towards lower frequencies, specifically a decrease in the median and average power frequencies. However, during actual massage, especially dynamic massage, the low-frequency noise (typically between 20Hz and 500Hz) generated by the mechanical vibration of the massage equipment produces significant motion artifacts. These artifacts highly overlap with the main energy frequency band of the EMG signals, severely impacting the signal quality of the EMG signals acquired in real-time. It should be noted that the energy of these low-frequency noises is typically more than 100 times greater than that of bioelectrical signals (e.g., EMG signals). Conventional fixed-parameter filters (e.g., infinite impulse response (IIR) or finite impulse response (FIR) filters), lacking the ability to sense environmental changes, cannot handle these nonlinear artifacts caused by mechanical pressure.

[0042] Therefore, how to dynamically remove interference from the mechanical movement of the massage device (or massage head) based on the collected pressure signal, and thus accurately evaluate the massage effect of the massage device, is a problem that urgently needs to be solved. To solve or improve the aforementioned problem, this application proposes a fusion-noise-reducing intelligent massage evaluation method, specifically including: in response to a first massage operation of the massage device on a target object, acquiring in real time the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device acting on the target object; wherein, the original EMG signal includes at least a noise component introduced by motion artifacts generated by the operation of the massage device; then, decoupling the pressure signal through a first signal filter to obtain a first signal component; the first signal component is correlated with the motion artifacts generated by the operation of the massage device; further, based on the first signal component, eliminating the noise component caused by motion artifacts in the original EMG signal to obtain a pure EMG signal; finally, based on a first median frequency determined by the power spectral density corresponding to the pure EMG signal, and a second median frequency of the resting EMG signal of the target object in a resting state, determining a first relaxation index of the target object; the first relaxation index is used to characterize the massage effect of the massage device performing the first massage operation on the target object at the current moment.

[0043] In this way, the first signal component related to the generation of motion artifacts, obtained by decoupling from the pressure signal, can eliminate the noise component caused by motion artifacts in the original surface electromyography (EMG) signal, thereby obtaining a pure EMG signal (i.e., a high-quality EMG signal). Furthermore, since the median frequency can effectively reflect the fatigue level of the target object, the first relaxation index, determined based on the first median frequency of the pure EMG signal and the second median frequency of the target object's resting EMG signal in the resting state, can objectively evaluate the massage effect of the massage device performing the first massage operation on the target object at the current moment. Therefore, by employing the above-described intelligent massage evaluation method with fusion and noise reduction, the massage effect of the massage device can be accurately evaluated based on the acquired EMG signal.

[0044] In particular, the preferred embodiments of this application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments of this application and the features in the embodiments can be combined with each other without conflict.

[0045] See Figure 1 The diagram illustrates an optional application scenario provided by an embodiment of this application. This application scenario may include a massage device 101 and a server 102. The massage device 101 and the server 102 can interact via a communication network, wherein the communication network can employ wireless communication or wired communication methods.

[0046] For example, the massage device 101 can access the network via cellular mobile communication technology and communicate with the server 102. The cellular mobile communication technology may include 5th generation mobile networks (5G) technology or next-generation mobile communication technology.

[0047] Optionally, the massage device 101 can access the network and communicate with the server 102 via short-range wireless communication. This short-range wireless communication method may include wireless fidelity (Wi-Fi) technology.

[0048] This application embodiment does not limit the number of communication devices involved in the above application scenarios. For example, the above application scenarios may include more massage devices, or other devices. Figure 1 As shown, only the massage device 101 and the server 102 are described as examples. The following is a brief introduction to the above-mentioned communication devices and their respective functions.

[0049] The massage device 101 can be a neck massager worn on the neck of a target (or user), a facial massager worn on the head or other parts of the target's body, an eye massager, or a massage chair, handheld massager, etc. This application embodiment does not specifically limit its application. After being activated, the massage device 101 can perform massage operations according to the selected massage operation (or massage method). Depending on the values ​​of one or more operating parameters used when performing the massage operation, such as the massage mode, massage level, and heating temperature, the massage device 101 can be in different operating states.

[0050] Different massage devices 101 can provide a variety of massage modes. For example, a neck massager may include massage modes such as soothing mode, vitality mode, and smart mode, while a facial massager may include massage modes such as cleansing mode, essence infusion mode, and lifting mode. Furthermore, the massage device 101 can also provide different massage levels. For instance, the massage device 101 can provide massage levels from 1 to 5, with higher levels providing a more intense sensation for the user.

[0051] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0052] It is worth noting that, in this embodiment, the server 102 can, in response to the first massage operation of the massage device on the target object, acquire in real time the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device acting on the target object; then, the pressure signal is decoupled by a first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the operation of the massage device; further, based on the first signal component, the noise component caused by motion artifacts in the original surface EMG signal is eliminated to obtain a pure surface EMG signal; finally, based on the first median frequency determined by the power spectral density corresponding to the pure surface EMG signal and the second median frequency of the resting surface EMG signal of the target object in the resting state, a first relaxation index is determined. The first relaxation index is used to characterize the massage effect of the massage device performing the first massage operation on the target object at the current moment.

[0053] The following describes the intelligent massage evaluation method with fusion noise reduction provided by the exemplary embodiments of this application, in conjunction with the above application scenarios and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way in this respect.

[0054] See Figure 2 The diagram shown illustrates the implementation flow of an intelligent massage evaluation method with noise reduction fusion provided in this application embodiment. Taking a server as an example, the specific implementation flow of this method is as follows: S201: In response to the first massage operation of the massage device on the target object, the original surface electromyographic signal of the target object and the pressure signal of the massage device acting on the target object are acquired in real time.

[0055] The first massage operation can be a massage operation performed by the massage device on the target object according to a first massage intensity (e.g., a first massage force and a first massage frequency). The original surface electromyography (EMG) signal can include at least the noise component introduced by motion artifacts generated by the operation of the massage device. The original EMG signal is a composite signal containing the pure EMG signal and the noise component caused by motion artifacts.

[0056] In other words, the raw surface electromyography (EMG) signals acquired are usually mixed with noise. The high-frequency components in the pressure signal are usually related to motion artifacts (or mechanical artifacts) generated by the massage device at the current moment, while the low-frequency components in the pressure signal are used to characterize the macroscopic compression intensity, that is, the effective massage pressure applied by the massage device to the target object at the current moment.

[0057] Optionally, the raw surface electromyography (EMG) signal can be acquired using an EMG signal sensor (e.g., one or more pairs of EMG electrodes) mounted on the massage device, while the pressure signal can be acquired using a pressure sensor (e.g., a flexible pressure sensor) mounted on the massage device. The EMG signal sensor and pressure sensor can acquire signals in real time or periodically; this embodiment does not specifically limit this. Furthermore, the raw EMG signal can be represented as: The pressure signal can be represented as: .

[0058] It should be understood that both the surface electromyography (SEMG) sensor and the pressure sensor are integrated into the skin contact surface between the massage device and the target object. Taking a massage device of the massage head type as an example, since the massage head achieves muscle relaxation through contact and kneading with the muscles, a flexible pressure sensor and one or more pairs of surface electromyography electrodes are typically placed on the skin contact surface of the massage head (e.g., the top of the massage ball of the massage device) to detect the force of the massage head acting on the target object and the electromyography signal of the target object. Exemplarily, the flexible pressure sensor and the surface electromyography electrodes are connected to the built-in signal preprocessing circuit of the massage head via a slip ring or flexible lead through the central axis of the massage head.

[0059] S202: The pressure signal is decoupled by the first signal filter to obtain the first signal component.

[0060] The first signal component is related to the motion artifacts generated by the massage device. For example, the pass frequency range of the first signal filter is typically 20Hz to 500Hz, used to extract the noise component caused by motion artifacts in the pressure signal; that is, the first signal filter can be a bandpass filter with a pass frequency range of 20Hz to 500Hz. The first signal component can also be called a high-frequency signal component, and can be represented as: .

[0061] S203: Based on the first signal component, eliminate the noise component caused by motion artifacts in the original surface electromyography signal to obtain a pure surface electromyography signal.

[0062] In one alternative implementation, during step S203, after receiving the first signal component, the server can execute the reference. Figure 3 The implementation process for extracting pure surface electromyographic signals is shown below, with the specific steps as follows: S301: Obtain historical signal components that are adjacent to the current time and whose number matches the filter order of the adaptive filter.

[0063] Each historical signal component is associated with the motion artifact generated by the massage device at the corresponding historical moment; that is, each historical signal component can be considered as the first signal component in the pressure signal at the corresponding historical moment. It should be understood that the historical signal components of the aforementioned quantity-matched adaptive filter are also the historical signal components of one or more historical moments adjacent (or immediately adjacent, neighboring) to the current moment. The adaptive filter is used for signal conversion between pressure and noise.

[0064] For example, taking four historical moments adjacent to the current moment as an example, the historical signal components of the aforementioned four historical moments can be represented as follows: , , .in, This represents the historical signal component at the first historical moment preceding the current moment. This represents the historical signal component at the second historical moment before the current moment. This represents the historical signal component at the third historical moment preceding the current moment. This represents the historical signal component at the fourth historical moment prior to the current moment.

[0065] Furthermore, the statement that the number of historical signal components is adjacent to the current time and matches the filter order of the adaptive filter can be understood as the total number of signal components, including the first signal component and historical signal components, being the same as the filter order of the adaptive filter. Taking an adaptive filter with a filter order of L as an example, after obtaining the first signal component, the server can acquire the historical signal components of the L-1 historical times adjacent to the current time.

[0066] S302: Based on the noise conversion coefficient vector of the adaptive filter, noise conversion coefficient matching is performed on the first signal component and each historical signal component to obtain the first signal component and each historical signal component after noise conversion coefficient matching.

[0067] The first noise conversion coefficient in the noise conversion coefficient vector is set for the first signal component, and the Nth noise conversion coefficient in the noise conversion coefficient vector is set for the historical signal component of the (N-1)th historical time adjacent to the current time. N is an integer greater than 0 and less than or equal to the filter order (i.e., L).

[0068] For example, using the noise transformation coefficient vector = [ , ,..., For example, The noise conversion coefficient is set for the first signal component. The noise conversion coefficient is set for the historical signal component of the first historical moment adjacent to the current moment, and so on. This application embodiment will not describe them one by one.

[0069] S303: Input the first signal component after noise conversion coefficient matching and each historical signal component into the adaptive filter so that the first signal component after noise conversion coefficient matching and each historical signal component are fitted with the noise conversion coefficient vector to obtain the noise component.

[0070] In this way, after the server matches the noise conversion coefficient of the first signal component and the noise conversion coefficients corresponding to each historical signal component from the noise conversion coefficient vector, it can obtain the noise component based on the first signal component and its corresponding noise conversion coefficient, as well as each historical signal component and its corresponding noise conversion coefficient. That is, the noise component is obtained by inputting the first signal component with matched noise conversion coefficients and each historical signal component into the adaptive filter. It should be understood that the aforementioned noise component is also the output signal of the adaptive filter.

[0071] Optionally, the calculation formula for the noise components described above can be expressed as follows:

[0072] in, Represents noise components. Represents the first signal component or the first signal component adjacent to the first signal component. k -1 historical signal component of a historical moment The noise conversion coefficient representing the first signal component or the second signal component. k The noise conversion coefficient of the historical signal component at -1 historical moment. L This indicates the filter order of the adaptive filter.

[0073] S304: Use the difference between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal.

[0074] Optionally, the calculation method for the pure surface electromyography signal described above is specifically expressed as follows:

[0075] in, This represents the pure surface electromyography (EMG) signal, i.e., the difference signal between the original EMG signal and the noise component. Represents the original surface electromyographic signal. This represents the noise component caused by motion artifacts.

[0076] Since the noise conversion coefficient vector includes various noise conversion coefficients that are adaptive weights of the adaptive filter, the noise conversion coefficient vector is updated after each determination of the noise-removed surface electromyography (SEMG) signal (e.g., a pure SEMG signal). Therefore, in one optional implementation, after obtaining the pure SEMG signal, the server can also obtain a first product result based on a preset step size factor, a first signal component, and the pure SEMG signal, and calculate the sum of squares of the first signal component and each historical signal component; then, using a preset first parameter and the aforementioned sum of squares, a first summation result is obtained; finally, based on the ratio between the first product result and the first summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time step adjacent to the current time step is determined. In this way, the noise conversion coefficient vector can be updated according to the aforementioned noise conversion coefficient at the next time step.

[0077] The preset step size factor is used to control the convergence speed, and its value is usually between 0 and 2. The preset first parameter is a positive number and usually a minimum value to prevent the first summation result from being 0.

[0078] For example, the formula for calculating the noise conversion coefficient at the next moment can be specifically expressed as follows:

[0079] in, This represents the noise conversion factor at the next time step. This represents the noise conversion factor at the current moment. This represents the preset step size factor, such as, The value of is 1. This indicates pure surface electromyography (EMG) signals. Indicates the first signal component. L This indicates the filter order of the adaptive filter. Represents the first signal component or the first signal component adjacent to the first signal component. k -1 historical signal component of a historical moment This indicates that the first parameter is a very small positive number to prevent the denominator from being zero. Furthermore, This represents the result of the first product. This represents the sum of squares of the first signal component and all historical signal components. ) represents the first summation result.

[0080] It should be noted that, in order to ensure the universality and computational stability of the adaptive filter algorithm (e.g., normalized least mean squares (NLMS)), the initial noise conversion coefficients are configured to be zero, so that the adaptive filter is in an unbiased monitoring state at the initial moment, and then enters the steady state of operation by relying on the self-convergence characteristics of the algorithm.

[0081] To improve the adaptability of the step size factor, low-frequency components in the pressure signal can be introduced when updating the noise conversion coefficient vector (i.e., calculating the noise conversion coefficient at the next time step).

[0082] Therefore, the server can also decouple the pressure signal using a second signal filter to obtain a second signal component. The passband frequency of the second signal filter is lower than that of the first signal filter, and the second signal component can be used to indicate the effective massage pressure applied to the target object by the massage device at the current moment.

[0083] For example, the pass frequency range of the second signal filter is typically 0Hz to 5Hz. The second signal filter can also be called a low-pass filter, and the second signal component can also be called a low-frequency signal component, which can be represented as: .

[0084] Furthermore, after obtaining the pure surface electromyography (EMG) signal, the server can determine the noise conversion coefficient for the next adjacent moment based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, a preset pressure sensitivity compensation factor, a preset first parameter, the pure EMG signal, and the noise conversion coefficient at the current moment. The aforementioned preset pressure sensitivity compensation factor can be used to balance the influence of macroscopic pressure on the update frequency, and its value is typically between 0.1 and 10. The magnitude of the adjustable step size factor is negatively correlated with the magnitude of the second signal component; that is, the larger the second signal component, the smaller the adjustable step size factor.

[0085] In one optional implementation, when the server determines the noise conversion coefficient of the next time step adjacent to the current time step based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient of the current time step, it can obtain a second product result based on the adjustable step size factor, the first signal component and the pure surface electromyography signal, and obtain a third product result based on the preset pressure sensitivity compensation factor and the second signal component, and calculate the sum of squares of the first signal component and each historical signal component; then, based on the aforementioned sum of squares, the preset first parameter and the third product result, a second summation result is obtained; finally, based on the ratio between the second product result and the second summation result, and the noise conversion coefficient of the current time step, the noise conversion coefficient of the next time step adjacent to the current time step is determined.

[0086] Optionally, the formula for calculating the noise conversion coefficient at the next time step is expressed as follows:

[0087] in, This represents the noise conversion factor at the next time step. This represents the noise conversion factor at the current moment. Indicates the adjustable step size factor. This indicates pure surface electromyography (EMG) signals. Indicates the first signal component. L This indicates the filter order of the adaptive filter. Represents the first signal component or the first signal component adjacent to the first signal component. k -1 historical signal component of a historical moment This represents the preset pressure sensitivity compensation factor. Indicates the second signal component. This indicates that the first parameter is a very small positive number to prevent the denominator from being zero. Furthermore, This represents the result of the second product. This represents the sum of squares of the first signal component and all historical signal components. Indicates the result of the third product, ( () indicates the second summation result.

[0088] Based on the above approach, if the effective massage pressure increases, the low-frequency component in the pressure signal (i.e., the amplitude of the second signal component) will increase, and the denominator will become larger. At this time, the update step size (i.e., the adjustable step size factor) will automatically decrease. This is because an increase in effective massage pressure leads to drastic nonlinear changes in the contact characteristics between the massage device and the skin, causing significant fluctuations in the second signal component. Decreasing the step size prevents the adaptive filter from overshooting or diverging due to sudden large vibrations, maintaining the algorithm's stability under higher effective massage pressure. Furthermore, if the effective massage pressure decreases, the low-frequency component in the pressure signal (i.e., the amplitude of the second signal component) will decrease, and the denominator will become smaller. At this time, the update step size will automatically increase. Increasing the step size improves the algorithm's tracking sensitivity, enabling the adaptive filter to quickly capture subtle mechanical fluctuations.

[0089] S204: Determine the first relaxation index of the target object based on the first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and the second median frequency of the resting surface electromyography signal of the target object in the resting state.

[0090] The first relaxation index can be used to characterize the effect of the massage device on the target object at the current moment according to the first massage operation. In this way, by using the median frequency change that can characterize the abstract fatigue feeling of the target object, the muscle fatigue characteristics of the target object can be extracted, and the massage effect of the massage device can be evaluated more objectively and accurately.

[0091] It should be noted that the second median frequency of the resting surface electromyography signal of the target subject in the resting state was calculated when the target subject was wearing the massage device and the massage device was in "resting calibration" mode. At this time, the massage device was in a non-operating state, maintaining only a weak contact force.

[0092] In one alternative implementation, when executing step S204, after the server obtains the clean surface electromyography (EMG) signal at the current moment, it can acquire multiple historical EMG signals adjacent to the clean EMG signal after noise cancellation through a set sliding window, and obtain a discrete-time signal based on the clean EMG signal and the multiple historical EMG signals.

[0093] Taking the above-mentioned sliding window of 5 seconds as an example, the above-mentioned discrete time signal includes the pure surface electromyography (EMG) signal and multiple historical EMG signals that have undergone noise cancellation processing within the past 5 seconds adjacent to the pure EMG signal.

[0094] Next, after obtaining the discrete-time signal, the server can perform frequency domain transformation on the discrete-time signal, thereby determining the first median frequency based on the power spectral density of the discrete-time signal.

[0095] Specifically, assuming Given the power spectral density of a discrete-time signal, the first median frequency is... The following conditions must be met:

[0096] Finally, after determining the first median frequency, the server can determine the first relaxation index based on the first median frequency and the second median frequency of the resting surface electromyography signal of the target object in the resting state using any of the following three methods: Method 1: Calculate the median frequency shift between the first median frequency and the second median frequency, and use the median frequency shift as the first relaxation index.

[0097] Optionally, the second median frequency is expressed as Then the median frequency shift Δ The calculation method is specifically expressed as follows: △ = -

[0098] At this point, the first relaxation index = △ .

[0099] Method 2: Calculate the median frequency shift between the first and second median frequencies and the time interval between the pure surface electromyography (EMG) signal and the resting EMG signal. Use the ratio of the median frequency shift to the time interval as the first relaxation index. Optionally, the first relaxation index... The calculation method is specifically expressed as follows:

[0100] Understandably, the first relaxation index A negative value with a large absolute value indicates that the target subject is fatigued or experiencing increased tension quickly, while the first relaxation index... If the value gradually approaches 0, it indicates that the target object is relaxed and tending to stabilize.

[0101] Method 3: Calculate the median frequency shift between the first and second median frequencies, and use the ratio of this median frequency shift to the second median frequency as the first relaxation index. In this case, the first relaxation index... The calculation method is expressed as follows:

[0102] This improves upon the current problem that the evaluation of massage effects has long been stuck in the vague stage of subjective perception. Based on the principle of spectral shift, the abstract feeling of fatigue is transformed into a digital indicator of median frequency shift, which can quantify the recovery slope of muscles from "stiffness" to "relaxation" in real time, and can provide scientific and intuitive feedback on the effect.

[0103] In one alternative implementation, see [link to relevant documentation]. Figure 4 As shown, after determining a first relaxation index based on a first median frequency and a second median frequency, if the first relaxation index is greater than or equal to a relaxation index threshold, the server can send a first control signal to the massage device. This first control signal is used to instruct the massage device to stop massaging the target object.

[0104] With the aforementioned relaxation index threshold Taking 90% as an example, if the target's first relaxation index... The target's relaxation level at the current moment is 92%, which is the first relaxation level. Greater than the relaxation index threshold This indicates that the target object's muscles have relaxed by more than 90% compared to before the massage. At this point, the server can send a first control signal to the massage device to stop the massage device from performing the first massage operation on the target object.

[0105] Optionally, after receiving the first control signal, the massage device can automatically stop kneading, switch to a gentle heat therapy mode, and announce in voice: "Your muscles have reached the ideal state of relaxation, and this massage task is complete."

[0106] Furthermore, if the first relaxation index is less than the relaxation index threshold, and the massage duration reaches the duration threshold, the server can send a first control signal to the massage device. This prevents the first massage operation from failing to achieve the desired massage effect and allows for timely cessation of the current massage operation (i.e., the first massage operation), thereby reducing the power consumption of the massage device.

[0107] Still using the aforementioned relaxation index threshold Taking a 90% relaxation rate and a duration threshold T of 15 minutes as an example, if the target's first relaxation index is... The target's relaxation index at the current moment is 50%, and the massage duration of the massage device performing the first massage operation on the target is 15 minutes, which is the first relaxation index. Less than the relaxation index threshold If the massage duration performed by the massage device according to the first massage operation on the target object has reached the duration threshold T, it indicates that the first massage operation of the massage device cannot achieve the desired massage effect. At this time, the server can send a first control signal to the massage device to stop the massage device from performing the first massage operation on the target object.

[0108] Still Figure 4As shown, if the first relaxation index is less than the relaxation index threshold and the massage duration does not reach the duration threshold, the server can obtain the second relaxation index of the target object after the set massage duration, and send a second control signal to the massage device when the second relaxation index is still less than the relaxation index threshold.

[0109] The second control signal can be used to instruct the massage device to massage the target object according to a second massage operation, wherein the massage intensity corresponding to the second massage operation is greater than the massage intensity corresponding to the first massage operation. Optionally, the massage duration can be determined based on the current massage duration and a duration threshold.

[0110] Still using the aforementioned relaxation index threshold Taking a 90% relaxation rate and a duration threshold T of 15 minutes as an example, if the target's first relaxation index is... The target's relaxation index at the current moment is 60%, and the massage device performs the first massage operation on the target for 10 minutes. Furthermore, the target's second relaxation index after the set massage duration (e.g., 5 minutes) is... The figure is 80%, which is the second relaxation index. Still below the relaxation index threshold If the massage intensity is insufficient for the first massage operation of the massage device, then the massage intensity needs to be increased.

[0111] At this time, the server can send a second control signal to the massage device so that the massage device can massage the target object according to a second massage operation with a massage intensity greater than that of the first massage operation.

[0112] Based on the massage control method described above, the massage device starts the massage at the lowest setting after the massage begins, entering a cycle of "acquisition-noise reduction-analysis-adjustment". If the target object's relaxation index is detected to be rising, the massage device can provide a voice prompt: "Muscle relaxation detected, please maintain", or ask the user if they need to increase the intensity for further relaxation. If the difference between the second relaxation index and the first relaxation index after the set massage duration is less than the difference threshold or has not yet reached the relaxation index threshold, a voice prompt will be given: "It is recommended to increase the intensity for deeper relaxation".

[0113] In summary, in the intelligent massage evaluation method with fusion noise reduction provided in this application embodiment, the first signal component related to the generation of motion artifacts, obtained by decoupling from the pressure signal, is used as noise generated by the mechanical vibration of the massage device. This eliminates the noise component caused by motion artifacts in the original surface electromyography (EMG) signal, thereby obtaining a pure EMG signal. Furthermore, since the median frequency can better reflect the fatigue of the target object, the first relaxation index, determined based on the first median frequency of the pure EMG signal and the second median frequency of the resting EMG signal of the target object in the resting state, can objectively and quantitatively evaluate the massage effect of the massage device performing the first massage operation on the target object at the current moment. Therefore, by employing the aforementioned intelligent massage evaluation method with fusion noise reduction, the massage effect of the massage device can be accurately evaluated based on the collected EMG signal.

[0114] Furthermore, based on the same technical concept, embodiments of this application provide an intelligent massage evaluation device with integrated noise reduction, which is used to implement the above-described method flow of embodiments of this application. See also... Figure 5 As shown, the intelligent massage evaluation device 500 with noise reduction fusion includes: a signal acquisition module 501, a signal decoupling module 502, a noise cancellation module 503, a massage evaluation module 504, and a massage control module 505, wherein: The signal acquisition module 501 is used to acquire the original surface electromyography signal of the target object and the pressure signal of the massage device applied to the target object in real time in response to the first massage operation of the massage device on the target object; wherein, the original surface electromyography signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; The signal decoupling module 502 is used to perform signal decoupling processing on the pressure signal through the first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the operation of the massage device. The noise cancellation module 503 is used to eliminate the noise component caused by motion artifacts in the original surface electromyography signal based on the first signal component, so as to obtain a pure surface electromyography signal. The massage evaluation module 504 is used to determine a first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state; the first relaxation index is used to characterize the massage effect of the massage device massaging the target object according to the first massage operation at the current moment.

[0115] In an optional embodiment, when eliminating the noise component caused by motion artifacts in the original surface electromyography (EMG) signal based on the first signal component to obtain a pure EMG signal, the noise elimination module 503 is specifically used for: Acquire historical signal components that are adjacent to the current time and whose number matches the adaptive filter order; wherein, each historical signal component is related to the motion artifact generated by the massage device at the corresponding historical time. Based on the noise conversion coefficient vector of the adaptive filter, noise conversion coefficient matching is performed on the first signal component and each historical signal component to obtain the first signal component and each historical signal component after noise conversion coefficient matching; wherein, the first noise conversion coefficient in the noise conversion coefficient vector is set for the first signal component, and the Nth noise conversion coefficient in the noise conversion coefficient vector is set for the historical signal component of the N-1th historical time adjacent to the current time, where N is an integer greater than 0 and less than or equal to the filter order; The first signal component after noise conversion coefficient matching and each historical signal component are input into the adaptive filter so that the first signal component after noise conversion coefficient matching and each historical signal component are fitted with the noise conversion coefficient vector to obtain the noise component. The difference between the original surface electromyography (EMG) signal and the noise component is used as the pure EMG signal.

[0116] In an optional embodiment, after using the difference signal between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the noise cancellation module 503 is further configured to: Based on the preset step length factor, the first signal component, and the pure surface electromyography signal, the first product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the preset first parameter and the sum of squares, the first summation result is obtained; where the first parameter is a positive number; Based on the ratio between the first product result and the first summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0117] In an optional embodiment, the signal decoupling module 502 is further configured to: The pressure signal is decoupled by a second signal filter to obtain a second signal component. The passband frequency of the second signal filter is lower than that of the first signal filter. The second signal component is used to indicate the effective massage pressure applied to the target object by the massage device at the current moment. After using the difference signal between the original surface electromyography (EMG) signal and the noise component as the pure EMG signal, the noise cancellation module 503 is further used for: Based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient at the current moment, the noise conversion coefficient of the next moment adjacent to the current moment is determined; wherein, the first parameter is a positive number.

[0118] In an optional embodiment, when determining the noise conversion coefficient of the next time step adjacent to the current time step based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient of the current time step, the noise cancellation module 503 is specifically used for: Based on the adjustable step size factor, the first signal component, and the pure surface electromyography signal, the second product result is obtained; Based on the pressure sensitivity compensation factor and the second signal component, the second product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the sum of squares, the first parameter, and the result of the second product, the second summation result is obtained; Based on the ratio between the second product result and the second summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

[0119] In an optional embodiment, when determining the first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state, the massage evaluation module 504 is specifically used for: Multiple historical surface electromyography (EMG) signals, after noise cancellation, adjacent to the pure surface EMG signal are acquired through a set sliding window. Based on the pure surface EMG signal and the multiple historical surface EMG signals, a discrete-time signal is obtained. The first median frequency is determined based on the power spectral density of the discrete-time signal, and the first relaxation index is determined based on the first median frequency and the second median frequency.

[0120] In an optional embodiment, when determining the first relaxation index based on a first median frequency and a second median frequency, the massage evaluation module 504 is specifically used to: Calculate the median frequency shift between the first and second median frequencies, and use this median frequency shift as the first relaxation index; or... Calculate the median frequency shift between the first and second median frequencies and the time interval between the pure surface electromyography (EMG) signal and the resting surface EMG signal; use the ratio of the median frequency shift to the time interval as the first relaxation index; or, Calculate the median frequency shift between the first median frequency and the second median frequency, and use the ratio of the median frequency shift to the second median frequency as the first relaxation index.

[0121] In an optional embodiment, after determining the first relaxation index based on a first median frequency and a second median frequency, the massage control module 505 is specifically configured to: If the first relaxation index is greater than or equal to the relaxation index threshold, a first control signal is sent to the massage device; the first control signal is used to instruct the massage device to stop massaging the target object. If the first relaxation index is less than the relaxation index threshold and the massage duration reaches the duration threshold, then a first control signal is sent to the massage device.

[0122] In an optional embodiment, the massage control module 505 is further configured to: If the first relaxation index is less than the relaxation index threshold and the massage duration does not reach the duration threshold, then obtain the second relaxation index of the target object after the set massage duration. When the second relaxation index is still less than the relaxation index threshold, a second control signal is sent to the massage device; the second control signal is used to instruct the massage device to massage the target object according to the second massage operation, and the massage intensity corresponding to the second massage operation is greater than the massage intensity corresponding to the first massage operation.

[0123] Based on the description of the method and apparatus embodiments above, an exemplary embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform the method according to an embodiment of the present invention.

[0124] This application also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0125] This application also provides a computer program product, including a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0126] See Figure 6The diagram illustrates a structural block diagram of an electronic device 600 that can serve as a server or client in this application, serving as an example of hardware devices applicable to various aspects of this application. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0127] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0128] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 607 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 may include, but is not limited to, disks and optical discs. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and / or chipsets, such as Bluetooth devices, WiFi devices, worldwide interoperability for microwave access (WiMax) devices, cellular communication devices, and / or the like.

[0129] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the above-described fusion-denoising intelligent massage evaluation method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. In some embodiments, the computing unit 601 can be configured by any other suitable means (e.g., by means of firmware) to perform the above-described fusion-denoising intelligent massage evaluation method.

[0130] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM) or flash memory, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0132] As used in this application, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device, PLD) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0135] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0136] Furthermore, it should be understood that the above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of the invention. Therefore, any equivalent variations made in accordance with the claims of this invention are still within the scope of this application.

Claims

1. A smart massage evaluation method incorporating noise reduction, characterized in that, include: In response to the first massage operation of the massage device on the target object, the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device applied to the target object are acquired in real time; wherein, the original surface EMG signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; The pressure signal is decoupled by a first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the operation of the massage device. Based on the first signal component, the noise component caused by motion artifacts in the original surface electromyography signal is eliminated to obtain a pure surface electromyography signal; Based on the first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal, and the second median frequency of the resting surface electromyography signal of the target object in the resting state, a first relaxation index of the target object is determined; the first relaxation index is used to characterize the massage effect of the massage device massaging the target object according to the first massage operation at the current moment.

2. The method as described in claim 1, characterized in that, The step of eliminating noise components caused by motion artifacts in the original surface electromyography (EMG) signal based on the first signal component to obtain a pure EMG signal includes: Obtain historical signal components of the adaptive filter order that are adjacent to the current time and match the number of such components; wherein each historical signal component is related to the motion artifact generated by the massage device at the corresponding historical time. Based on the noise conversion coefficient vector of the adaptive filter, noise conversion coefficient matching is performed on the first signal component and each historical signal component to obtain the first signal component and each historical signal component after noise conversion coefficient matching; wherein, the first noise conversion coefficient in the noise conversion coefficient vector is set for the first signal component, and the Nth noise conversion coefficient in the noise conversion coefficient vector is set for the historical signal component of the N-1th historical time adjacent to the current time, where N is an integer greater than 0 and less than or equal to the filter order; The first signal component after noise conversion coefficient matching and each historical signal component are input into the adaptive filter so that the first signal component after noise conversion coefficient matching and each historical signal component are fitted with the noise conversion coefficient vector to obtain the noise component; The difference between the original surface electromyography (EMG) signal and the noise component is used as the pure EMG signal.

3. The method as described in claim 2, characterized in that, After using the difference signal between the original surface electromyography signal and the noise component as the pure surface electromyography signal, the method further includes: Based on the preset step size factor, the first signal component, and the pure surface electromyography signal, a first product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the preset first parameter and the sum of squares, a first summation result is obtained; wherein, the first parameter is a positive number; Based on the ratio between the first product result and the first summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

4. The method as described in claim 2, characterized in that, The method further includes: The pressure signal is decoupled by a second signal filter to obtain a second signal component; wherein the passband frequency of the second signal filter is less than the passband frequency of the first signal filter, and the second signal component is used to indicate the effective massage pressure applied by the massage device to the target object at the current moment; After using the difference signal between the original surface electromyography signal and the noise component as the pure surface electromyography signal, the method further includes: Based on the first signal component, the second signal component and its corresponding adjustable step size factor, each historical signal component, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient at the current moment, the noise conversion coefficient at the next moment adjacent to the current moment is determined; wherein, the first parameter is a positive number.

5. The method as described in claim 4, characterized in that, The step of determining the noise conversion coefficient of the next time step adjacent to the current time step based on the first signal component, the second signal component and its corresponding adjustable step size factor, the various historical signal components, the preset pressure sensitivity compensation factor, the preset first parameter, the pure surface electromyography signal, and the noise conversion coefficient of the current time step includes: Based on the adjustable step size factor, the first signal component, and the pure surface electromyography signal, the second product result is obtained; Based on the pressure sensitivity compensation factor and the second signal component, a third product result is obtained, and the sum of squares of the first signal component and each historical signal component is calculated. Based on the sum of squares, the first parameter, and the third product result, a second summation result is obtained; Based on the ratio between the second product result and the second summation result, and the noise conversion coefficient at the current time, the noise conversion coefficient at the next time adjacent to the current time is determined.

6. The method according to any one of claims 1-5, characterized in that, The determination of the first relaxation index of the target object based on the first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and the second median frequency of the resting surface electromyography signal of the target object in the resting state includes: Multiple historical surface electromyography (EMG) signals, after noise cancellation, adjacent to the pure surface EMG signal are acquired through a set sliding window, and a discrete-time signal is obtained based on the pure surface EMG signal and the multiple historical surface EMG signals. The first median frequency is determined based on the power spectral density of the discrete-time signal, and the first relaxation index is determined based on the first median frequency and the second median frequency.

7. The method as described in claim 6, characterized in that, Determining the first relaxation index based on the first median frequency and the second median frequency includes: Calculate the median frequency offset between the first median frequency and the second median frequency, and use the median frequency offset as the first relaxation index; or... Calculate the median frequency shift between the first median frequency and the second median frequency, and the time interval between the pure surface electromyography (EMG) signal and the resting EMG signal; use the ratio of the median frequency shift to the time interval as the first relaxation index; or, Calculate the median frequency offset between the first median frequency and the second median frequency, and use the ratio of the median frequency offset to the second median frequency as the first relaxation index.

8. The method as described in claim 6, characterized in that, After determining the first relaxation index based on the first median frequency and the second median frequency, the method further includes: If the first relaxation index is greater than or equal to the relaxation index threshold, a first control signal is sent to the massage device; the first control signal is used to instruct the massage device to stop massaging the target object. If the first relaxation index is less than the relaxation index threshold and the massage duration reaches the duration threshold, then the first control signal is sent to the massage device.

9. The method as described in claim 8, characterized in that, The method further includes: If the first relaxation index is less than the relaxation index threshold and the massage duration does not reach the duration threshold, then the second relaxation index of the target object after the set massage duration is obtained. When the second relaxation index is still less than the relaxation index threshold, a second control signal is sent to the massage device; the second control signal is used to instruct the massage device to massage the target object according to a second massage operation, wherein the massage intensity corresponding to the second massage operation is greater than the massage intensity corresponding to the first massage operation.

10. A smart massage evaluation device incorporating noise reduction, characterized in that, include: The signal acquisition module is used to acquire, in real time, the original surface electromyography (EMG) signal of the target object and the pressure signal of the massage device applied to the target object in response to the first massage operation of the massage device on the target object; wherein, the original surface EMG signal includes at least the noise component introduced by the motion artifact generated by the operation of the massage device; The signal decoupling module is used to perform signal decoupling processing on the pressure signal through a first signal filter to obtain a first signal component; the first signal component is related to the motion artifacts generated by the operation of the massage device. The noise cancellation module is used to eliminate the noise component caused by motion artifacts in the original surface electromyography signal based on the first signal component, so as to obtain a pure surface electromyography signal. The massage evaluation module is used to determine a first relaxation index of the target object based on a first median frequency determined by the power spectral density corresponding to the pure surface electromyography signal and a second median frequency of the resting surface electromyography signal of the target object in the resting state; the first relaxation index is used to characterize the massage effect of the massage device massaging the target object according to the first massage operation at the current moment.

11. An electronic device, characterized in that, include: processor; A memory storing a program; wherein the program includes instructions that, when executed by the processor, cause the processor to perform the method as described in any one of claims 1-9.

Images