Massage chair control method and system based on real-time electroencephalogram analysis

Abstract

The invention relates to the technical field of intelligent massage chairs, and discloses a massage chair control method and system based on real-time electroencephalogram analysis, and the method comprises the steps: collecting an electroencephalogram signal of a user; performing feature extraction on the electroencephalogram signals to obtain electroencephalogram features of the user; calculating a current user state according to the electroencephalogram characteristics of the user; and dynamically adjusting massage parameters of the massage chair according to the current user state until the user is in the target user state. According to the method, the electroencephalogram signals are collected in real time, the features are extracted, the parameters of the massage chair are intelligently adjusted to adapt to the user state, personalized massage is achieved, the comfort level and the effect are improved, the problem that a traditional massage chair cannot respond to the user requirement in real time is solved, excessive or insufficient massage is avoided, and the user can enjoy more accurate massage experience.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent massage chairs, and more specifically, to a massage chair control method and system based on real-time electroencephalogram analysis. Background Art

[0002] With the advancement of technology, the research and product innovation of massage chairs are constantly increasing. From the early 2D and 3D massage chairs to today's 4D massage chairs, the massage comfort has been significantly improved. The control method has also evolved from the initial button selection and voice control to the use of user big data analysis to recommend massage modes. However, despite the continuous advancement of technology, there is still room for improvement in the massage experience for specific users.

[0003] There are two main types of massage chairs on the market: one is a massage chair where the user can select the mode by themselves, switching the massage mode by buttons or voice; the other is a massage chair where the user can select the mode by recommendation, which recommends the massage mode by analyzing the user's historical usage data and physiological parameters. During the use of these massage chairs, the user may have poor massage effects due to improper self-selection, or the parameters cannot be adjusted according to real-time needs due to fixed programs. The recommendation mode based on historical data is also difficult to accurately meet the user's current massage needs. Therefore, the existing technology has the defect of being unable to dynamically adjust the massage parameters according to the individual needs of users in real time and intelligently. Summary of the invention

[0004] In order to overcome the defect of the prior art that the massage parameters cannot be dynamically adjusted in real time and intelligently according to the individual needs of users, the present invention proposes the following technical solutions:

[0005] In a first aspect, the present invention proposes a massage chair control method based on real-time EEG analysis, comprising:

[0006] Collect the user's EEG signals.

[0007] Feature extraction is performed on the EEG signal to obtain the user's EEG features.

[0008] Calculate the current user state based on the user's EEG characteristics.

[0009] According to the current user status, the massage parameters of the massage chair are dynamically adjusted until the user is in the target user state.

[0010] As a preferred technical solution, the method of calculating the current user state according to the user's EEG characteristics includes:

[0011] The characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics is calculated, and the current user state is obtained according to the characteristic distance.

[0012] As a preferred technical solution, before calculating the characteristic distance between the initial EEG characteristic and the preset ideal EEG characteristic, the method further includes:

[0013] The user state is divided into several large states, and the corresponding ideal EEG features are set for each large state.

[0014] As a preferred technical solution, the characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics is calculated, and the current user state is obtained according to the characteristic distance, including:

[0015] Calculate the characteristic distance between the user's EEG characteristics and the corresponding ideal EEG characteristics in each state.

[0016] The state corresponding to the smallest feature distance is taken as the user's current state.

[0017] As a preferred technical solution, the massage parameters of the massage chair are dynamically adjusted according to the current user status until the user reaches the ideal state, including:

[0018] Step a: According to the current user status, obtain the current EEG feature F0 and massage parameter V0.

[0019] Step b: Solve the first objective function according to the EEG feature F0 and the massage parameter V0 to obtain the feature transformation vector X1, whose expression is as follows:

[0020] min||F0X1-V0||2

[0021] Here, || ||2 represents the L2 norm.

[0022] Step c: After the massage time T, obtain the new EEG feature F1.

[0023] Step d: Solve the second objective function according to the feature transformation vector X1 and the EEG feature F1 to obtain a new massage parameter V1, whose expression is as follows:

[0024] min||F1X1-V1||2-||V0-V1||2

[0025] Step e: According to the massage parameter V1, solve the third objective function, and its expression is as follows:

[0026]

[0027] in, is the characteristic transformation vector of the ideal state.

[0028] Step f: Repeat steps a to e until the change in the massage parameter is less than a preset threshold, indicating that the user has reached an ideal state.

[0029] As a preferred technical solution, before extracting features from the EEG signal to obtain the EEG features of the user, the method further includes:

[0030] The EEG signal is preprocessed in sequence to remove noise and eye artifacts.

[0031] The empirical mode decomposition method is used to remove the first two eigenmode functions of the user's EEG features after preprocessing.

[0032] As a preferred technical solution, the EEG features include at least one of the mean value, variance, covariance, first-order difference, second-order difference, K-order origin moment and K-order central moment of EEG signals in different frequency bands.

[0033] As a preferred technical solution, the EEG signals in different frequency bands include at least one of EEG signals in delta wave, theta wave, alpha wave, beta wave and gamma wave frequency bands.

[0034] As a preferred technical solution, the massage parameters include at least one of voltage, frequency and the number of massage heads.

[0035] In a second aspect, the present invention further proposes a massage chair control system based on real-time EEG analysis, which is applied to the massage chair control method based on real-time EEG analysis as described in any solution of the first aspect, comprising:

[0036] The acquisition module is used to collect the user's EEG signals.

[0037] The extraction module is used to extract features from the EEG signal to obtain the user's EEG features.

[0038] The calculation module is used to calculate the current user state according to the user's EEG characteristics.

[0039] The adjustment module is used to dynamically adjust the massage parameters of the massage chair according to the current user state until the user is in the target user state.

[0040] The beneficial effects of the present invention include at least:

[0041] The present invention firstly collects the user's EEG signals in real time, providing basic data for subsequent intelligent control. Secondly, the collected EEG signals are feature extracted to obtain the user's EEG features, which can accurately identify the user's physiological state. Then, based on the extracted EEG features, the current user state can be accurately calculated, which solves the problem that traditional massage chairs cannot perceive user needs in real time. Finally, according to the calculated current user state, the system can dynamically adjust the massage parameters of the massage chair until the user reaches the target state. This process realizes true intelligent and personalized massage. The present invention overcomes the defect that traditional massage chairs cannot adjust the massage plan according to the user's real-time state, and avoids the inconvenience of users having to make frequent manual adjustments. By continuously monitoring and responding to changes in user status, it can meet user needs more accurately, effectively prevent the problem of over-massage or under-massage, and significantly improve the user's comfort and massage effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of the massage chair control method based on real-time EEG analysis provided in Example 1.

[0043] Figure 2 This is a schematic diagram of the principle of switching different user states provided in Example 2.

[0044] Figure 3 This is a schematic diagram of the flow of dynamically adjusting the massage parameters of the massage chair provided in Example 2.

[0045] Figure 4 This is an architectural diagram of the massage chair control system based on real-time EEG analysis provided in Example 3. DETAILED DESCRIPTION

[0046] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred technical solutions. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred technical solutions are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0047] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0048] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0049] Example 1

[0050] This embodiment proposes a massage chair control method based on real-time EEG analysis. Figure 1 As shown, Figure 1 The present invention provides a flow chart of a massage chair control method based on real-time EEG analysis, which includes the following steps:

[0051] S1: Collect the user's EEG signals.

[0052] In this embodiment, an EEG acquisition device with a frequency of 240 Hz is used to acquire the user's EEG signal to obtain the original EEG signal.

[0053] S2: Extract features from the EEG signal to obtain EEG features of the user.

[0054] S3: Calculate the current user state based on the user's EEG characteristics.

[0055] S4: Dynamically adjust the massage parameters of the massage chair according to the current user state until the user is in the target user state.

[0056] It can be understood that by collecting the user's EEG signals in real time, basic data is provided for subsequent intelligent control. Secondly, the collected EEG signals are feature extracted to obtain the user's EEG features, which can accurately identify the user's physiological state. Then, based on the extracted EEG features, the current user state can be accurately calculated, which solves the problem that traditional massage chairs cannot perceive user needs in real time. Finally, based on the calculated current user state, the system can dynamically adjust the massage parameters of the massage chair until the user reaches the target state. This process realizes true intelligent and personalized massage. The massage chair control method proposed in this embodiment overcomes the defect that traditional massage chairs cannot adjust the massage plan according to the user's real-time state, and avoids the inconvenience of users having to make frequent manual adjustments. By continuously monitoring and responding to changes in user status, user needs can be met more accurately, effectively preventing the problem of over-massage or under-massage, and significantly improving the user's comfort and massage effect.

[0057] Example 2

[0058] In this embodiment, before extracting features from the EEG signal to obtain the EEG features of the user, the method further includes:

[0059] The EEG signal is preprocessed in sequence to remove noise and eye artifacts.

[0060] The empirical mode decomposition method is used to remove the first two eigenmode functions of the user's EEG features after preprocessing.

[0061] It is understandable that there is usually a lot of noise in the original EEG signal, which needs to be processed before it can be used by subsequent algorithms, and it can also improve the accuracy of the entire processing process. Empirical mode decomposition can decompose complex signals into a finite number of intrinsic mode functions (IMF), and the decomposed IMF components contain the local characteristic signals of the original signal at different time scales. Generally speaking, the first few intrinsic mode functions contain the most high-frequency signal components, while most of the noise appears as high-frequency signals. Therefore, by removing the first two intrinsic mode functions and reconstructing the signal, the eye artifacts and Gaussian white noise mixed into the original signal during acquisition can be effectively removed. This processing method can greatly improve the signal quality and lay a good foundation for subsequent feature extraction and state calculation.

[0062] In this embodiment, the EEG signals in different frequency bands include EEG signals in delta wave, theta wave, alpha wave, beta wave and gamma wave frequency bands.

[0063] It is understandable that EEG signals are very suitable for capturing oscillatory brain activity or "brain waves" of multiple frequencies. These brain waves (generated by the synchronous activity of neuronal clusters, for example) have characteristic frequency ranges and spatial distributions, and they are often associated with different functional states of the brain. By analyzing these brain waves of different frequencies, the user's current state can be effectively inferred, thus providing an important basis for the intelligent control of massage chairs. The following are several main brain waves and their characteristics:

[0064] (1) Delta wave: The frequency range is 0.5-4 Hz and usually occurs during deep sleep. This waveform reflects that the brain is in a state of high relaxation and recovery.

[0065] (2) Theta waves: The frequency range is 4-8 Hz. They appear when you feel sleepy (or in the early stages of sleep). They also appear when your brain is idle or meditating. Theta waves are related to memory, emotional processing, and creativity.

[0066] (3) Alpha waves: The frequency range is 8-13 Hz. It is the most obvious wave among rhythmic brain waves. When an awake person is relaxed or has his eyes closed, alpha waves can be detected in the EEG detected in the occipital lobe area. Alpha waves are usually associated with mild relaxation and alertness.

[0067] (4) Beta waves: The frequency range is 13-30 Hz, which is a low-amplitude wave. When brain waves in this frequency range appear in the EEG, people tend to be in a state of concentration, active logical thinking, emotional fluctuations, alertness or anxiety. Beta waves are related to active thinking and concentration.

[0068] (5) Gamma waves: The frequency range is 30-50 Hz. When this frequency band appears, people are usually in a very excited or excited state, or have been strongly stimulated. Gamma waves are related to high cognitive processing, information integration and consciousness.

[0069] In this embodiment, the EEG features include the mean, variance, covariance, first-order difference, second-order difference, K-order origin moment and K-order central moment of EEG signals in different frequency bands. By extracting the above features, a feature vector is constructed. The calculation formula for each feature is as follows:

[0070] average value:

[0071] variance:

[0072] Covariance:

[0073] First-order difference:

[0074] Second order difference:

[0075] K-order origin moment:

[0076] K-order central moment:

[0077] The final number of features is sampling points*7*5.

[0078] In this embodiment, the current user state is calculated according to the EEG characteristics of the user, including:

[0079] The characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics is calculated, and the current user state is obtained according to the characteristic distance.

[0080] In this embodiment, before calculating the characteristic distance between the initial EEG characteristic and the preset ideal EEG characteristic, the method further includes:

[0081] The user state is divided into several large states, and the corresponding ideal EEG features are set for each large state.

[0082] As an exemplary illustration, Figure 2As shown in the figure, the principle diagram of switching different user states in this embodiment is as follows. In this embodiment, the user states are divided into sleep, normal, tired and sore states. The ideal parameters of the massage chair are obtained through experiments in each state. Ideal EEG characteristics

[0083] In this embodiment, the characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics is calculated, and the current user state is obtained according to the characteristic distance, including:

[0084] Calculate the characteristic distance between the user's EEG characteristics and the corresponding ideal EEG characteristics in each state.

[0085] The state corresponding to the smallest feature distance is taken as the user's current state.

[0086] In this embodiment, according to the current user state, the massage parameters of the massage chair are dynamically adjusted until the user reaches the ideal state, including:

[0087] Step a: According to the current user status, obtain the current EEG feature F0 and massage parameter V0.

[0088] Step b: Solve the first objective function according to the EEG feature F0 and the massage parameter V0 to obtain the feature transformation vector X1, whose expression is as follows:

[0089] min||F0X1-V0||2

[0090] Among them, ||||2 represents the L2 norm.

[0091] Step c: After the massage time T, obtain the new EEG feature F1.

[0092] Step d: Solve the second objective function according to the feature transformation vector X1 and the EEG feature F1 to obtain a new massage parameter V1, whose expression is as follows:

[0093] min||F1X1-V1||2-||V0-V1||2

[0094] Step e: According to the massage parameter V1, solve the third objective function, and its expression is as follows:

[0095]

[0096] in, is the characteristic transformation vector of the ideal state.

[0097] Step f: Repeat steps a to e until the change in the massage parameter is less than a preset threshold, indicating that the user has reached an ideal state.

[0098] In the specific implementation process, Figure 3 As shown, Figure 3 This is a flow chart of dynamically adjusting the massage parameters of the massage chair in this embodiment. When the user starts to use the massage chair, the user's current EEG feature F0 and massage parameter V0 are first collected. Then the EEG feature F0 and the ideal EEG feature V0 in each state are calculated. The system selects the ideal parameters of the massage chair for the next state of the large state. and ideal EEG characteristics As a basis for calculation:

[0099] That is, the characteristic transformation vector X1 is obtained by solving the objective function min||F0X1-V0||2. After a massage time T, the second EEG feature F1 is obtained, and the new massage chair parameter V1 is obtained by solving the objective function min||F1X1-V1||2-||V0-V1||2. Here, ||F1X1-V1||2 means that the massage parameters of this time are in line with the current state of EEG features, and ||V0-V1||2 means that the massage parameters should be as different as possible from the previous time to achieve the adjustment of the massage method. By solving the objective function Here, ||F1X2-V1||2 indicates that the feature transformation vector X2 is expected to be used, where X is consistent with the current EEG feature state, and It means that it is hoped that the next change direction will be closer to the next ideal state, that is, to achieve a transition from soreness to fatigue to normal to sleep. Then repeat the above process until the sleep state is reached or the massage parameters and feature transformation vector remain basically unchanged. In actual implementation, the massage chair parameters can be voltage, frequency, and the number of massage heads. The massage time can be detected once in a cycle of 5 seconds. In this process, today's deep learning methods are not used, and no complex operators are used. Most of the current chips that need to perform calculations can complete them in milliseconds, so the process can be implemented in real time.

[0100] Example 3

[0101] like Figure 4 As shown, this embodiment proposes a massage chair control system based on real-time EEG analysis, which is applied to the massage chair control method based on real-time EEG analysis as described in the above embodiment, including: an acquisition module 100, an extraction module 200, a calculation module 300 and an adjustment module.

[0102] Among them, the acquisition module 100 is used to collect the user's EEG signal. The extraction module 200 is used to extract the features of the EEG signal to obtain the user's EEG features. The calculation module 300 is used to calculate the current user state according to the user's EEG features. The adjustment module 400 is used to dynamically adjust the massage parameters of the massage chair according to the current user state until the user is in the target user state.

[0103] It should be noted that the aforementioned explanation of the embodiment of the massage chair control method based on real-time EEG analysis is also applicable to the massage chair control system based on real-time EEG analysis of this embodiment, and will not be repeated here.

[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0105] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0106] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0107] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0108] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0109] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A massage chair control method based on real-time EEG analysis, characterized in that: include: Collecting the user's EEG signals; Extracting features from the EEG signal to obtain EEG features of the user; Calculate the current user status based on the user's EEG characteristics; According to the current user status, the massage parameters of the massage chair are dynamically adjusted until the user is in the target user state.

2. The massage chair control method based on real-time EEG analysis according to claim 1, characterized in that: The step of calculating the current user state according to the user's EEG characteristics includes: The characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics is calculated, and the current user state is obtained according to the characteristic distance.

3. The massage chair control method based on real-time EEG analysis according to claim 2, characterized in that: Before calculating the characteristic distance between the initial EEG characteristic and the preset ideal EEG characteristic, the method further includes: The user state is divided into several large states, and the corresponding ideal EEG features are set for each large state.

4. The massage chair control method based on real-time EEG analysis according to claim 3, characterized in that: Calculating the characteristic distance between the user's EEG characteristics and the preset ideal EEG characteristics, and obtaining the current user state according to the characteristic distance, including: Calculate the characteristic distance between the user's EEG characteristics and the ideal EEG characteristics corresponding to each state; The state corresponding to the smallest feature distance is taken as the user's current state.

5. The massage chair control method based on real-time EEG analysis according to claim 4, characterized in that: According to the current user status, the massage parameters of the massage chair are dynamically adjusted until the user reaches the ideal state, including: Step a: According to the current user status, obtain the current EEG feature F0 and massage parameter V0; Step b: Solve the first objective function according to the EEG feature F0 and the massage parameter V0 to obtain the feature transformation vector X1, whose expression is as follows: min||F0X1-V0||2 Among them, || ||2 represents the L2 norm; Step c: After the massage time T, obtain a new EEG feature F1; Step d: Solve the second objective function according to the feature transformation vector X1 and the EEG feature F1 to obtain a new massage parameter V1, whose expression is as follows: min||F1X1-V1||2-||V0-V1||2 Step e: According to the massage parameter V1, solve the third objective function, and its expression is as follows: in, is the characteristic transformation vector of the ideal state; Step f: Repeat steps a to e until the change in the massage parameter is less than a preset threshold, indicating that the user has reached an ideal state.

6. The massage chair control method based on real-time EEG analysis according to claim 1, characterized in that: Before extracting features from the EEG signal to obtain the EEG features of the user, the method further includes: Preprocessing the EEG signal to remove noise and eye artifacts in sequence; The empirical mode decomposition method is used to remove the first two eigenmode functions of the user's EEG features after preprocessing.

7. The massage chair control method based on real-time EEG analysis according to claim 1, characterized in that: The EEG features include at least one of the mean value, variance, covariance, first-order difference, second-order difference, K-order origin moment and K-order central moment of EEG signals in different frequency bands.

8. The massage chair control method based on real-time EEG analysis according to claim 2, characterized in that: The electroencephalogram signals of different frequency bands include at least one of the electroencephalogram signals of delta wave, theta wave, alpha wave, beta wave and gamma wave frequency bands.

9. The massage chair control method based on real-time EEG analysis according to claim 1, characterized in that: The massage parameters include at least one of voltage, frequency and the number of massage heads.

10. A massage chair control system based on real-time EEG analysis, characterized in that: include: An acquisition module is used to collect the user's EEG signal; An extraction module, used to extract features from the EEG signal to obtain EEG features of the user; A calculation module, used to calculate the current user state according to the user's EEG characteristics; The adjustment module is used to dynamically adjust the massage parameters of the massage chair according to the current user state until the user is in the target user state.

Images