Emotion recognition massage system and method based on electroencephalogram signals and storage medium

Abstract

The invention relates to the technical field of massage chairs, and discloses an emotion recognition massage system and method based on electroencephalogram signals and a storage medium, the system comprises an electroencephalogram signal acquisition module, an electroencephalogram signal processing module, an emotion recognition module, a control module and a massage chair, the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals of a user in real time; the electroencephalogram signal processing module is used for preprocessing the electroencephalogram signal to obtain a processing result; the emotion recognition module is used for recognizing the emotional state of the user according to the processing result, and the control module is used for converting the emotional state into a corresponding control instruction and controlling a motor and an audio playing module of the massage chair according to the control instruction to provide massage service and music service for the user. According to the method, the electroencephalogram signals are collected and preprocessed, the emotional state of the user is obtained only through the preprocessed electroencephalogram signals, the complexity of user operation is reduced, and personalized massage services can be provided for the user according to different emotional states.

Description

Technical Field

[0001] The present invention relates to the technical field of massage chairs, and in particular to an emotion recognition massage system, method and storage medium based on electroencephalogram signals. Background Art

[0002] Emotions play a pivotal role in human life. They play a core role in rational decision-making, deep perception, complex interpersonal interactions, and the development of human intelligence. Emotions are not only a basic component of human beings, but also a driving force for our actions, adding profound meaning and rich colors to various life experiences. Current emotion recognition computing technology has successfully associated emotional changes with EEG signals, so emotional changes can be identified and classified from EEG signals under appropriate stimulation. Massage chairs, as a home health product that combines technology with humanized design, have developed rapidly in the market in recent years. From a global perspective, the sales of the massage chair market continue to grow, and it is expected to maintain a steady growth trend in the next few years. Especially in the Chinese market, the massage chair industry is in a rapid development stage, the market size continues to expand, and it is expected to become one of the main growth points of the global massage chair market in the future. In the current era, massage chairs can be combined with intelligent control systems to support functions such as switching of multiple massage modes, adjustment of massage intensity, and setting of massage time. They are easy to operate and users can easily control them through touch screens, remote controls, etc.

[0003] The prior art discloses a massage chair, including a seat provided with a massage mechanism; the massage mechanism includes a plurality of massage units with adjustable positions, and the massage chair also includes a handheld control terminal for adjusting the massage mechanism, a wireless communication module for communicating with an external smart device, a power mechanism for providing power to the massage chair, and a control module for controlling the operating state of the massage chair. In the embodiment of the present invention, by providing an adjustable massage unit on the seat and manually adjusting the position of the massage unit through the handheld control terminal, the massage chair can be suitable for users of different physiques, thereby improving the practicality of the massage chair; at the same time, by connecting and communicating with an external smart device through the wireless communication module, the parameters of the massage chair can be set and adjusted through the external smart device, and the control module can identify and match the external smart device, which is convenient for next use, effectively improving the user experience. In the prior art, manual operation is required for setting the massage mode, and the process is cumbersome, and personalized services cannot be provided to users. Summary of the invention

[0004] The primary purpose of the present invention is to overcome the problems existing in the prior art and provide an emotion recognition massage system based on EEG signals. The present invention can effectively reduce the complexity of user operations and can provide users with personalized massage services.

[0005] As another object of the present invention, a method suitable for the system based on the aforementioned object is also provided.

[0006] As another object of the present invention, a non-volatile storage medium suitable for storing a computer program implemented according to the method described is provided.

[0007] In order to achieve the above-mentioned primary purpose, the present invention provides an emotion recognition massage system based on EEG signals, comprising: an EEG signal acquisition module, an EEG signal processing module, an emotion recognition module, a control module and a massage chair, wherein the EEG signal acquisition module is used to acquire the user's EEG signals in real time, and transmit the EEG signals to the EEG signal processing module; the EEG signal processing module is used to pre-process the EEG signals, and transmit the processing results to the emotion recognition module; the emotion recognition module is used to identify the user's emotional state according to the processing results, and the control module is used to convert the emotional state into corresponding control instructions, and control the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

[0008] Furthermore, the preprocessing includes denoising the EEG signal to obtain a denoised EEG signal; segmenting the denoised EEG signal using fast Fourier transform; obtaining a plurality of continuous frequency band signals; and calculating the energy characteristics of each frequency band signal, wherein the energy characteristics are input to the emotion recognition module, and the energy characteristics include relative energy and / or logarithmic relative energy.

[0009] Furthermore, multi-layer wavelet transform is used to perform denoising on the EEG signal, specifically: (1) Perform multi-layer wavelet decomposition on the EEG signal to obtain approximate coefficients and detail coefficients of each layer; (2) Decompose the approximate coefficient and detail coefficient of each layer to obtain the decomposed approximate coefficient and detail coefficient of each layer; (3) Perform denoising on the detail coefficients after decomposition of each layer to obtain the processed detail coefficients; (4) Based on the detail coefficients after each layer of processing and the approximate coefficients after each layer of decomposition, wavelet reconstruction is performed to obtain the denoised EEG signal.

[0010] Furthermore, the decomposition of each layer of detail coefficients is subjected to denoising to obtain the processed detail coefficients, specifically:

[0011] in is the threshold value, is the detail coefficient after decomposition.

[0012] Furthermore, the wavelet reconstruction is performed based on the processed detail coefficients of each layer and the approximate coefficients of each layer to obtain the denoised EEG signal. The calculation method of the wavelet reconstruction is as follows:

[0013] in, is the approximate coefficient after decomposition at each layer, is the scale function, is the wavelet function.

[0014] Furthermore, the relative energy is calculated as follows:

[0015] in, is the energy of the frequency band signal, is the energy of the EEG signal, and calculates the energy of the frequency band signal The way is as follows:

[0016] Calculating the energy of EEG signals The way is as follows:

[0017] The logarithmic relative energy is calculated as follows:

[0018] in, is the starting index of the frequency band signal, is the end index of the frequency segment, is the total length of the EEG signal, EEG The discrete Fourier transform of .

[0019] Furthermore, the emotion recognition module is used to identify the user's emotional state based on the processing result, specifically: the processing result is input into the emotion recognition model in the emotion recognition module, and the user's emotional state index is output; and the user's emotional state is identified based on the emotional state index.

[0020] Furthermore, the emotional state indicator includes at least one of activation, pleasure and dominance.

[0021] In order to achieve another object of the present invention, the present invention also provides an emotion recognition massage method based on EEG signals, comprising: The EEG signal acquisition module collects the user's EEG signals in real time; The EEG signal processing module pre-processes the EEG signal to obtain a processing result; The emotion recognition module obtains the user's emotional state based on the processing result; The control module converts the emotional state into corresponding control instructions, and controls the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

[0022] In order to achieve another purpose of the present invention, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer-stored program is executed by a processor, the emotion recognition massage method based on EEG signals is implemented.

[0023] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects the user's EEG signals in real time through an EEG signal acquisition module, and then the EEG signal processing module preprocesses the EEG signals. Next, the emotion recognition model determines the user's emotional state according to the preprocessing result, and the control module converts the emotional state into corresponding control instructions, and controls the motor and audio playback module of the massage chair according to the control instructions, providing massage services and music services for the user, avoiding the complexity of manual operation, and being able to provide personalized massage services for the user's different emotions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a block diagram of an emotion recognition massage system based on EEG signals according to Embodiment 1 of the present invention; Figure 2 This is a flow chart of an emotion recognition massage method based on EEG signals according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0025] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0026] In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0027] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] Furthermore, in the description of the present invention, unless otherwise specified, “plurality” means two or more.

[0029] Example 1 like Figure 1 As shown, an emotion recognition massage system based on EEG signals according to a preferred embodiment of the present invention includes: An EEG signal acquisition module, an EEG signal processing module, an emotion recognition module, a control module and a massage chair, wherein the EEG signal acquisition module is used to acquire the user's EEG signals in real time and transmit the EEG signals to the EEG signal processing module; the EEG signal processing module is used to pre-process the EEG signals and transmit the processing results to the emotion recognition module; the emotion recognition module is used to identify the user's emotional state according to the processing results, and the control module is used to convert the emotional state into corresponding control instructions, and control the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

[0030] In a feasible embodiment, the massage chair automatically fits the user according to the user's height and body shape to ensure that the electrodes for collecting EEG signals are in good contact, and starts collecting the user's EEG signals after confirming good contact.

[0031] Further, the preprocessing includes: 1. De-noising the EEG signal to obtain a denoised EEG signal. In this embodiment, multi-layer wavelet transform is used to de-noise the EEG signal, including: (1) Perform multi-layer wavelet decomposition on the EEG signal to obtain the approximate coefficients and detail coefficients of each layer, as follows:

[0032] in, is the approximation coefficient of each layer, is the detail coefficient of each layer; (2) Decompose the approximate coefficient and detail coefficient of each layer to obtain the decomposed approximate coefficient and detail coefficient of each layer, as follows:

[0033]

[0034] in, is the scale function, is the wavelet function.

[0035] (3) Perform denoising on the detail coefficients after decomposition of each layer to obtain the processed detail coefficients, as follows:

[0036] in is the threshold value, is the detail coefficient after decomposition.

[0037] (4) Based on the detail coefficients after each layer of processing and the approximate coefficients after each layer of decomposition, wavelet reconstruction is performed to obtain the denoised EEG signal, as follows:

[0038] in, is the approximate coefficient after decomposition at each layer, is the scale function, is the wavelet function.

[0039] 2. Use fast Fourier transform to segment the denoised EEG signal; obtain multiple continuous frequency band signals, which are respectively , , , , Five frequency bands.

[0040] 3. Calculate the energy feature of each frequency band signal. The energy feature is the input of the emotion recognition module. The energy feature includes relative energy and / or logarithmic relative energy. In this embodiment, the frequency domain relative energy is defined as the signal in [ ]The ratio of the energy in the frequency band to the total energy in the entire frequency domain. The specific calculation method is as follows:

[0041] in, is the energy of the frequency band signal, is the energy of the EEG signal, and calculates the energy of the frequency band signal The way is as follows:

[0042] Calculating the energy of EEG signals The way is as follows:

[0043] The logarithmic relative energy is calculated as follows:

[0044] in, is the starting index of the frequency band signal, is the end index of the frequency segment, is the total length of the EEG signal, EEG The logarithmic relative energy is the logarithm of the relative energy, which can provide a better numerical dynamic range and is more intuitive when processing certain signal features.

[0045] Further, the emotion recognition module is used to identify the user's emotional state according to the processing results, specifically: the processing results are input into the emotion recognition model in the emotion recognition module, and the user's emotional state index is output, and the emotional state index includes at least one of activation, pleasure and dominance. ; Identify the user's emotional state according to the emotional state index, and the emotional state includes excitement and tension, confidence and control, sadness and depression, and calmness and relaxation. It should be noted that the emotion recognition model is obtained in the following way: using the DEAP database as a data source, the database is a rich resource covering EEG signals, multiple physiological signals and corresponding emotional labels, which is very suitable for research in the field of emotion analysis and recognition. The EEG signals in the DEAP data set are used as training data, and these signals have been labeled with activation, pleasure and dominance. In the module, the EEG signals in the DEAP database are first subjected to multi-layer wavelet transform denoising, and then divided into different frequency bands, and the energy characteristics of each frequency band are extracted. The specific calculation method is the same as before, and will not be repeated here. Use these features and the corresponding activation, pleasure and dominance labels to train a machine learning model so that it can learn the mapping relationship from EEG signals to emotional labels, thereby obtaining an emotion recognition model.

[0046] After acquiring the user's emotional state, the control module converts the emotional state into a corresponding control instruction, and controls the motor and audio playback module of the massage chair according to the control instruction to provide massage services and music services to the user. In this embodiment, different emotional states correspond to different massage methods and different music, as shown in the following table: .

[0047] Example 2 like Figure 2 As shown, an emotion recognition massage method based on EEG signals according to an embodiment of the present invention comprises: The EEG signal acquisition module collects the user's EEG signals in real time; The EEG signal processing module pre-processes the EEG signal to obtain a processing result; The emotion recognition module obtains the user's emotional state based on the processing result; The control module converts the emotional state into corresponding control instructions, and controls the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

[0048] It can be understood that the method proposed in this embodiment corresponds to the system of the above embodiment, and the options in the above embodiment 1 are also applicable to this embodiment, so they will not be described repeatedly here.

[0049] Example 3 An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer-stored program is executed by a processor, the emotion recognition massage method based on electroencephalogram signals is implemented.

[0050] In summary, the embodiments of the present invention provide an emotion recognition massage system, method and system based on EEG signals, which collects the user's EEG signals in real time through an EEG signal acquisition module, and then the EEG signal processing module preprocesses the EEG signals. Then, the emotion recognition model determines the user's emotional state according to the preprocessing results, and the control module converts the emotional state into corresponding control instructions, and controls the motor and audio playback module of the massage chair according to the control instructions, providing massage services and music services for the user, avoiding the complexity of manual operation, and being able to provide personalized massage services for the user's different emotions.

[0051] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. An emotion recognition massage system based on EEG signals, characterized in that: The system includes: an EEG signal acquisition module, an EEG signal processing module, an emotion recognition module, a control module and a massage chair. The EEG signal acquisition module is used to acquire the user's EEG signals in real time and transmit the EEG signals to the EEG signal processing module; the EEG signal processing module is used to pre-process the EEG signals and transmit the processing results to the emotion recognition module; the emotion recognition module is used to identify the user's emotional state according to the processing results, and the control module is used to convert the emotional state into corresponding control instructions, and control the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

2. The emotion recognition massage system based on EEG signals according to claim 1, characterized in that: The preprocessing includes denoising the EEG signal to obtain a denoised EEG signal; segmenting the denoised EEG signal using a fast Fourier transform; and obtaining a plurality of continuous frequency band signals; The energy feature of each frequency band signal is calculated, and the energy feature is the input of the emotion recognition module. The energy feature includes relative energy and / or logarithmic relative energy.

3. The emotion recognition massage system based on EEG signals according to claim 2, characterized in that: The EEG signal is denoised using multi-layer wavelet transform, specifically: (1) Perform multi-layer wavelet decomposition on the EEG signal to obtain approximate coefficients and detail coefficients of each layer; (2) Decompose the approximate coefficient and detail coefficient of each layer to obtain the decomposed approximate coefficient and detail coefficient of each layer; (3) Perform denoising on the detail coefficients after decomposition of each layer to obtain the processed detail coefficients; (4) Based on the detail coefficients after each layer of processing and the approximate coefficients after each layer of decomposition, wavelet reconstruction is performed to obtain the denoised EEG signal.

4. The emotion recognition massage system based on EEG signals according to claim 3, characterized in that: The denoising process is performed on the detail coefficients after decomposition of each layer to obtain the processed detail coefficients, specifically: in is the threshold value, is the detail coefficient after decomposition.

5. The emotion recognition massage system based on EEG signals according to claim 3 is characterized in that The wavelet reconstruction is performed based on the detail coefficients after processing each layer and the approximate coefficients after decomposition of each layer to obtain the denoised EEG signal. The calculation method of the wavelet reconstruction is as follows: in, is the approximate coefficient after decomposition at each layer, is the scale function, is the wavelet function.

6. The emotion recognition massage system based on EEG signals according to claim 2, characterized in that: The relative energy is calculated as follows: in, is the energy of the frequency band signal, is the energy of the EEG signal, and calculates the energy of the frequency band signal The way is as follows: Calculating the energy of EEG signals The way is as follows: The logarithmic relative energy is calculated as follows: in, is the starting index of the frequency band signal, is the end index of the frequency segment, is the total length of the EEG signal, EEG The discrete Fourier transform of .

7. The emotion recognition massage system based on EEG signals according to claim 1, characterized in that The emotion recognition module is used to identify the user's emotional state according to the processing result, specifically: the processing result is input into the emotion recognition model in the emotion recognition module, and the user's emotional state index is output; and the user's emotional state is identified according to the emotional state index.

8. The emotion recognition massage system based on EEG signals according to claim 7, characterized in that In the embodiment, the emotional state indicator includes at least one of activation, pleasure and dominance.

9. An emotion recognition massage method based on EEG signals, the method being based on any one of claims 1 to 8 An emotion recognition massage system based on EEG signals comprises: The EEG signal acquisition module collects the user's EEG signals in real time; The EEG signal processing module pre-processes the EEG signal to obtain a processing result; The emotion recognition module obtains the user's emotional state based on the processing result; The control module converts the emotional state into corresponding control instructions, and controls the motor and audio playback module of the massage chair according to the control instructions to provide massage services and music services to the user.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer stored program is executed by the processor, the emotion recognition massage method based on EEG signals as described in claim 9 is implemented.

Images