Device control method and apparatus, electronic device, and computer-readable storage medium

Abstract

This application discloses a device control method, apparatus, electronic device, and computer-readable storage medium, relating to the field of computer technology. The method includes: receiving raw electroencephalogram (EEG) signals of a target user collected by a signal detection device, and acquiring the raw operating state of an Internet of Things (IoT) device; performing frequency domain conversion processing on the raw EEG signals, and determining the target user's eye state information in the frequency domain based on the converted signal data; adjusting the operating state of the IoT device based on the eye state information, the raw operating state, and a preset state adjustment relationship, thereby achieving rapid and stable adjustment of the IoT device's operating state based on the user's actual eye state, with high applicability.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to device control methods, apparatus, electronic devices, and computer-readable storage media. Background Technology

[0002] With the development of the Internet of Things (IoT) technology, more and more fields are using it to control application devices. For example, in the field of device control, the operating status of the controlled device can be controlled through the user's brainwave signals.

[0003] In related technologies, different algorithms such as Multivariate Empirical Mode Decomposition (MEMD), Logistic Regression (LR), Artificial Neural Network (ANN), or Support Vector Machine (SVM) are often used to extract the main features from the user's EEG signals, and the working state of the controlled device is controlled based on the extracted features. However, each algorithm is often complex because it requires a large number of training sequences before use, and the time required to extract EEG signal features based on the algorithm is long, resulting in low control efficiency, failure to meet actual needs, and poor user experience. Summary of the Invention

[0004] This application provides a device control method to solve the problem of low operating efficiency when controlling IoT devices based on EEG signals in related technologies.

[0005] Accordingly, embodiments of this application also provide a device control apparatus, an electronic device, and a computer-readable storage medium to ensure the implementation and application of the above methods.

[0006] On one hand, embodiments of this application provide a device control method, the method comprising:

[0007] It receives raw EEG signals from the target user collected by the signal detection device, and obtains the raw working status of the Internet of Things device;

[0008] The original EEG signals were subjected to frequency domain transformation, and the target user's eye state information in the frequency domain was determined based on the transformed signal data.

[0009] Based on the eye status information, the original working state, and the preset state adjustment relationship, the working state of the IoT device is adjusted.

[0010] On the other hand, embodiments of this application provide a device control apparatus, which includes:

[0011] The signal acquisition module is used to receive the raw EEG signals of the target user collected by the signal detection device, and to acquire the raw working status of the Internet of Things device.

[0012] The eye state information determination module is used to perform frequency domain conversion processing on the above-mentioned raw EEG signals, and determine the eye state information of the target user in the frequency domain based on the converted signal data.

[0013] The working status adjustment module is used to adjust the working status of IoT devices based on the eye status information, the original working status, and the preset status adjustment relationship.

[0014] Optionally, when adjusting the working state of an IoT device based on eye status information, the original working state, and a preset state adjustment relationship, the aforementioned working state adjustment module can be specifically used for:

[0015] Based on the target user's EEG signal in the second time period, the target user's first state information in the frequency domain is determined; wherein, the original EEG signal includes the target user's EEG signal in the first time period; the second time period is the time period before the first time period, and there is a first overlapping time window between the second time period and the first time period.

[0016] Based on the target user's EEG signal in the third time period, the target user's second state information in the frequency domain is determined; the third time period is the time period after the first time period, and there is a second overlapping time window between the third time period and the first time period;

[0017] Based on eye state information, first state information, and second state information, when it is determined that the target user's eye state has changed, the original working state of the IoT device is adjusted to the target working state based on the state adjustment relationship.

[0018] Optionally, the aforementioned eye state information determination module can also be used for:

[0019] If the target eye state is different from the first state information, but the target eye state is the same as the second state information, it is determined that the target user's eye state has changed.

[0020] If the target eye state differs from the first state information and also differs from the second state information, it is determined that the target user's eye state has not changed.

[0021] Optionally, when the aforementioned eye state information determination module performs frequency domain conversion processing on the original EEG signal and determines the target user's eye state information in the frequency domain based on the converted signal data, it can be specifically used for:

[0022] The original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal.

[0023] A sliding transform is applied to the denoised EEG signal to obtain the frequency domain EEG signal corresponding to the original EEG signal;

[0024] Eye state information is obtained based on frequency domain EEG signals.

[0025] Optionally, when obtaining eye state information based on frequency domain EEG signals, the aforementioned eye state information determination module can be specifically used for:

[0026] Based on the first frequency domain EEG signal and the second frequency domain EEG signal, the target frequency domain parameter value is determined; wherein, the target eye state is either the first type of eye state or the second type of eye state; the first frequency domain EEG signal is the frequency domain EEG signal corresponding to the first type of eye; the second frequency domain EEG signal is the frequency domain EEG signal corresponding to the second type of eye state;

[0027] Eye state information is determined based on target frequency domain parameter values ​​and reference frequency domain parameter values; wherein, the reference frequency domain parameter values ​​are determined based on the sample frequency domain parameter values ​​of the sample users and the eye state information of the sample users.

[0028] Optionally, before determining the eye state information based on the target frequency domain parameter value and the reference frequency domain parameter value, the aforementioned eye state information determination module may also be used for:

[0029] Obtain the first sample frequency domain parameter value of the sample user under the first type of eye state, and obtain the second sample frequency domain parameter value of the sample user under the second type of state information;

[0030] Determine the maximum value among the frequency domain parameter values ​​of each first sample, and the minimum value among the frequency domain reference values ​​of each second sample;

[0031] The reference frequency domain parameter values ​​are determined based on the maximum and minimum values.

[0032] Optionally, when determining eye state information based on target frequency domain parameter values ​​and reference frequency domain parameter values, the aforementioned eye state information determination module can be specifically used for:

[0033] If the target frequency domain parameter value is less than or equal to the reference frequency domain parameter value, the target eye state is determined to be the first type of eye state;

[0034] If the target frequency domain parameter value is greater than the reference frequency domain parameter value, the target eye state is determined to be the second type of eye state.

[0035] Optionally, when receiving the raw EEG signals of the target user collected by the signal detection device, the above-mentioned signal acquisition module is specifically used for:

[0036] The raw electroencephalogram (EEG) signals collected by the detection electrodes of the receiving signal detection device;

[0037] The detection electrode is located in the right occipital region of the target user.

[0038] On the other hand, embodiments of this application provide an electronic device, including a processor and a memory, which are interconnected;

[0039] The aforementioned memory is used to store computer programs;

[0040] The processor described above is configured to execute the device control method provided in the embodiments of this application when the computer program described above is invoked.

[0041] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the device control method provided in embodiments of this application.

[0042] In this embodiment, by performing frequency domain conversion processing on the raw EEG signals of the target user collected by the signal detection device, and determining the target user's eye state information in the frequency domain based on the converted signal data, compared to directly determining eye state information based on the raw EEG signals in the time domain, it is possible to obtain eye state information of the target user that matches the actual eye state more quickly and stably. Furthermore, by acquiring the original operating state of the IoT device, and using this eye state information as a control command to adjust the operating state of the IoT device, the operating state of the IoT device is adjusted based on this eye state information, the original operating state, and a preset state adjustment relationship. This allows for rapid and stable adjustment of the IoT device's operating state based on the user's actual eye state, improving adjustment efficiency. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart illustrating the device control method provided in an embodiment of this application is shown.

[0045] Figure 2 A schematic diagram of an information collection device provided in an embodiment of this application is shown;

[0046] Figure 3 A schematic diagram of a bandpass filter provided in an embodiment of this application is shown;

[0047] Figure 4 This paper illustrates a system architecture diagram of a device control method provided in an embodiment of this application.

[0048] Figure 5 This paper shows a schematic diagram of the structure of a device control apparatus provided in an embodiment of this application;

[0049] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] In real life, in order to further free up users' hands and improve user experience, automated control of physical devices can be implemented. This is especially useful for stroke patients and patients with traumatic brain injury who stay at home for a long time. Although their brain activity is normal, they may be unable to control home appliances due to physical disabilities.

[0052] In view of this, embodiments of this application provide a device control method that employs BCI (Brain Computer Interface, a system that can bypass traditional communication channels and provide direct communication and control between the human brain and physical devices) technology. This method controls the operation of physical devices by converting different brain patterns into control commands in real time. Specifically, brainwave sensors can be used to sense brain signals and other data, which are then converted into data packets and transmitted to the relay circuit of the physical device. The relay circuit then generates control commands based on the received data packets, and controls the physical device using these generated control commands.

[0053] The control method for this device will be described below with reference to specific embodiments:

[0054] like Figure 1 As shown in the figure, this application provides a device control method, which includes:

[0055] Step S110: Receive the raw EEG signal of the target user collected by the signal detection device, and obtain the raw working status of the Internet of Things device.

[0056] The signal detection device can be any EEG signal detection device, and this application embodiment does not limit it. For example, the raw EEG signal can be collected by wearing an EEG detection cap and using the EEG electrodes corresponding to the EEG detection cap.

[0057] Raw brainwave signals can be categorized as brain waves. By analyzing the relationship between brain waves and brain states, brain waves are classified into alpha waves, beta waves, theta waves, and delta waves, among others. Different brain waves correspond to different brain states.

[0058] Specifically, alpha waves are associated with the most relaxed and stable brain state, with a frequency range of 8 Hz to 13 Hz; beta waves are associated with a highly aroused brain state, with a frequency range of 13 Hz to 22 Hz; theta waves are associated with the brain state in the early stages of sleep (i.e., the transition period between full wakefulness and full sleep when one begins to feel drowsy), with a frequency range of 4 Hz to 8 Hz; and delta waves are associated with the brain state during deep sleep, with a frequency range of 0.5 Hz to 4 Hz.

[0059] Internet of Things (IoT) devices can be any device that can be controlled using IoT technology, such as smart home devices, smart terminals, and smart speakers. Smart home devices can include, but are not limited to, refrigerators, televisions, air conditioners, kitchen burners, light bulbs, and heating systems.

[0060] Taking a kitchen burner as an example of an IoT device, the working status of a kitchen burner can include on, off, high flame, low flame, medium flame, etc.

[0061] Among them, Internet of Things (IoT) technology connects any object to the network through information sensing devices according to agreed protocols. The objects exchange and communicate information through information transmission media to achieve functions such as intelligent identification, positioning, tracking, and monitoring.

[0062] Step S120: Perform frequency domain conversion processing on the above-mentioned raw EEG signal, and determine the target user's eye state information in the frequency domain based on the converted signal data.

[0063] In this implementation, in order to more accurately determine the target user's eye state information in the frequency domain, the original EEG signal can be amplified before frequency domain conversion, and then the amplified EEG signal can be further processed to capture the subtle EEG signals in the original EEG signal, so as to more accurately determine the user's eye state information.

[0064] Since the raw EEG signals collected are usually continuous signals in the time domain and are dynamic, they may be affected by time and become unstable during data analysis. By performing frequency domain transformation on the raw EEG signals, we can obtain transformed signal data in the frequency domain, which allows for subsequent signal processing operations in the frequency domain. This process is unaffected by time, more stable, and concise, laying the foundation for obtaining stable eye state information of the target user in the frequency domain.

[0065] It is understandable that, in the specific implementation process, compared with other user characteristics, such as the user's facial micro-expressions, the user's eye state information is easier to collect. In the embodiments of this application, the target user's eye state information in the frequency domain can be determined based on the converted signal data.

[0066] Eye status information can include open eyes (oE), closed eyes (cE), and blinking. Blinking can also be determined based on blink frequency.

[0067] In actual processing, the converted signal data can be obtained directly by performing frequency domain conversion on the original EEG signal.

[0068] Of course, in order to further improve the accuracy of data analysis and improve the efficiency of data processing, it is also possible to filter out the EEG signals related to eye state information in the original EEG signals in advance based on the correspondence between different waves in the EEG signals and brain states, and then perform frequency domain conversion processing on the filtered EEG signals to obtain the converted signal data.

[0069] In related technologies, delta waves and theta waves in electroencephalogram (EEG) signals are typically used to determine whether a user's eyes are closed or open. However, based on the relationships between alpha waves, beta waves, theta waves, and delta waves and brain states described earlier, delta waves and theta waves are more associated with sleep states, while alpha waves and beta waves are related to the user's awake state. Controlling the operating state of IoT devices through delta waves and theta waves may pose safety risks.

[0070] In view of this, in the embodiments of this application, when controlling the working state of IoT devices, alpha waves and beta waves can be used as EEG signals related to eye state information in the original EEG signals. The user's eye state information can be determined by alpha waves and beta waves in the EEG signals, so as to more safely control the working state of IoT devices when the brain is in a conscious state and improve the safety of the control process.

[0071] Specifically, based on the frequency range corresponding to alpha and beta waves, EEG signals related to alpha and beta waves in the original EEG signal can be filtered out, and frequency domain transformation processing can be performed on the filtered EEG signals to obtain transformed signal data.

[0072] In the specific implementation process, multiple sample users' EEG signals and actual eye state information can be collected in advance. Based on the converted signal data corresponding to the EEG signals of each sample user and the corresponding eye state information, the correspondence between the converted signal data and the corresponding eye state information can be determined. After obtaining the converted signal data, the target user's eye state information in the frequency domain can be determined based on the correspondence and the converted signal data.

[0073] Step S130: Adjust the working state of the IoT device based on the eye status information, the original working state, and the preset state adjustment relationship.

[0074] The preset state adjustment relationship can include the correspondence between eye state information and the working state of IoT devices.

[0075] Taking a kitchen burner as an example of an IoT device, the preset state adjustment relationship can include adjusting the working state of the IoT device to the off state when the eye status information switches from the open state to the closed state, and adjusting the working state of the IoT device to the on state when the eye status information switches from the closed state to the open state.

[0076] In this embodiment, by performing frequency domain conversion processing on the raw EEG signals of the target user collected by the signal detection device, and determining the target user's eye state information in the frequency domain based on the converted signal data, compared to directly determining eye state information based on the raw EEG signals in the time domain, it is possible to obtain eye state information of the target user that matches the actual eye state more quickly and stably. Furthermore, by acquiring the original operating state of the IoT device, and using this eye state information as a control command to adjust the operating state of the IoT device, the operating state of the IoT device is adjusted based on this eye state information, the original operating state, and a preset state adjustment relationship. This allows for rapid and stable adjustment of the IoT device's operating state based on the user's actual eye state, improving adjustment efficiency.

[0077] In related technologies, at least 14 electrodes and large EEG devices are typically required to collect EEG signals. This method of acquiring EEG signals is complex and cannot meet the needs of prolonged use in daily life. Therefore, embodiments of this application also provide the following optional implementation methods:

[0078] The aforementioned EEG signal detection device includes detection electrodes, and the raw EEG signals of the target user acquired by the aforementioned receiving signal detection device may include:

[0079] The raw electroencephalogram (EEG) signals collected by the detection electrodes of the receiving signal detection device;

[0080] The aforementioned detection electrode is located in the right occipital region of the target user.

[0081] In this implementation, based on the above description of EEG signals related to the user's eye state, the EEG signals of multiple sample users (i.e., subjects) can be detected. Studies have shown that when subjects have their eyes closed, the alpha rhythm in the occipital region of the brain is dominant; when visual stimulation occurs, the alpha rhythm in the occipital region of the brain decreases. Therefore, in this implementation, by placing the detection electrodes in the right occipital region of the target user, EEG signals related to the user's eye state can be collected through the detection electrodes, simplifying the acquisition process and avoiding the problem of complex acquisition processes caused by using multiple electrodes, which could not meet the user's needs.

[0082] It should be understood that, in the specific process of acquiring EEG signals, the signal detection equipment may also include ground electrodes and reference electrodes.

[0083] exist Figure 2 In the illustrated scenario, the detection electrode, ground electrode, and reference electrode in the signal detection device can be placed according to the 10-20 international electrode placement system. Specifically, conductive gel can be used to fix each electrode to the target user's scalp. The detection electrode can be placed at the O2 position (i.e., the right occipital region), and the reference electrode and ground electrode can be placed in hairless locations that facilitate placement, such as the FP2 position (i.e., the right frontal region) and the A1 position (the left ear region), respectively. This improves EEG signal quality while further shortening the acquisition time, enhancing the ease of use of the signal detection device and the user's wearing comfort.

[0084] Optionally, the above-mentioned frequency domain transformation processing of the original EEG signal, and the determination of the target user's eye state information in the frequency domain based on the transformed signal data, may include:

[0085] The original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal.

[0086] A sliding transform is applied to the denoised EEG signal to obtain the frequency domain EEG signal corresponding to the original EEG signal;

[0087] Eye state information is obtained based on frequency domain EEG signals.

[0088] Denoising EEG signals refer to EEG signals related to eye state information in the original EEG signals, namely alpha and beta waves in the original EEG signals, which are signals in the original EEG signals in the range of 8Hz to 22Hz (i.e., the frequency range corresponding to alpha waves is 8Hz to 13Hz, and the frequency range corresponding to beta waves is the sum of 13Hz to 22Hz).

[0089] Considering that in practical applications it may be impossible to accurately acquire signals in the 8Hz to 22Hz range, this implementation method can... Figure 3 The bandpass filter shown is used to filter and denoise the raw EEG signal, obtaining denoised EEG signals between 4.7Hz and 29.2Hz. Compared to obtaining denoised EEG signals between 3Hz and 45Hz using traditional BCI equipment, this method can more accurately obtain EEG signals related to eye state information from the raw EEG signal.

[0090] in, Figure 3 The bandpass filter shown specifically comprises four parts: (i) a 50Hz notch filter (implemented through a 47kΩ 1kΩ resistor R11, a 1kΩ resistor R12, a 47kΩ resistor R13, a 47kΩ resistor R14, a 68nΩ capacitor C11, a 68nΩ capacitor C12, and an amplifier U1), which can avoid interference from electrical equipment near the signal detection device's wiring; (ii) a second-order low-pass filter (implemented through a 300kΩ resistor R21, a 300kΩ resistor R22, a 10nΩ capacitor C14, and an amplifier U1), which can avoid interference from electrical equipment near the signal detection device's wiring; and (ii) a second-order low-pass filter (implemented through a 300kΩ resistor R21, a 300kΩ resistor R22, a 10nΩ capacitor C14, and an amplifier U1). (iii) A second-order high-pass filter (implemented by a 100k resistor R31, a 51k resistor R32, a 470n capacitor C31, a 470n capacitor C32, and an amplifier U3); (iv) A gain-adjustable final bandpass filter (implemented by a 200k resistor R41, a 100k resistor R42, a variable resistor R43, a 470n capacitor C41, a 22n capacitor C42, and an amplifier U4).

[0091] The method of acquiring the frequency domain EEG signal corresponding to the EEG signal can be called power spectral density analysis (PSDA). Here, PSD (power spectral density) is the distribution of the frequency signal in the frequency domain.

[0092] In this embodiment of the application, the frequency domain EEG signal can be from n rInitially, the frequency domain EEG signals corresponding to the EEG signals obtained by sliding N time windows are considered. The EEG signal corresponding to each time window can be represented as x(n), which is the EEG signal of the zero-mean signal x at discrete time n.

[0093] The EEG signals obtained in each time window are obtained using the following formula (1), i.e., {x(n r ), x(n) r +1), ..., x(n) r By performing a sliding transform (ST) on {+N-1}, the frequency domain EEG signal can be obtained.

[0094]

[0095] Where Φ is usually a complex function, w k This indicates the frequency corresponding to the denoised EEG signal.

[0096] Where Φ is Φ1, Φ(w) in formula (1) k +n) can be expressed as the Discrete Fourier Transform (DFT), as shown in formula (2) below:

[0097] Φ1(w k ,n)=e jw k n =cOs(w k n)+j sin(w k n) Formula (2)

[0098] In this implementation, the original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal. Then, a sliding transform is performed on the denoised EEG signal to obtain the frequency domain EEG signal corresponding to the original EEG signal. Based on the frequency domain EEG signal, eye state information is obtained. This allows for a faster and more stable determination of the target user's eye state information in the frequency domain that matches the target user's actual eye state.

[0099] As mentioned earlier, alpha waves are associated with the most relaxed and stable brain state, while beta waves are associated with a highly aroused brain state. Therefore, beta waves indicate a higher level of alertness compared to alpha waves.

[0100] Considering that a user's level of alertness is higher when their eyes are open than when they are awake, in this embodiment of the application, taking eye state information including both open and closed states as an example, the following methods can be used: First, frequency-domain transformation is performed on the alpha wave-related signals in the original EEG signal to obtain first-transformed signal data; based on this first-transformed signal data, information related to the closed-eye state is obtained. Second, frequency-domain transformation is performed on the beta wave-related signals in the original EEG signal to obtain second-transformed signal data; based on this second-transformed signal data, information related to the open-eye state is obtained. Finally, based on the information related to the closed-eye state and the information related to the open-eye state, the target user's eye state information in the frequency domain is determined.

[0101] Specifically, the following optional implementation methods can be used to determine eye state information:

[0102] The above-mentioned information on eye state obtained based on frequency domain EEG signals may include:

[0103] Based on the first frequency domain EEG signal and the second frequency domain EEG signal, the target frequency domain parameter value is determined; wherein, the eye state information is either a first type of eye state or a second type of eye state; the first frequency domain EEG signal is the signal in the above frequency domain EEG signal corresponding to the first type of eye state; the second frequency domain EEG signal is the signal in the above frequency domain EEG signal corresponding to the second type of eye state;

[0104] Eye state information is determined based on the target frequency domain parameter value and the reference frequency domain parameter value; wherein, the reference frequency domain parameter value is determined based on the sample frequency domain parameter value of the sample user and the eye state information of the sample user.

[0105] The first type of state can be a closed-eye state, and the second type of state can be an open-eye state. Of course, the first type of state can also be an open-eye state, and the second type of state can also be a closed-eye state. This application does not limit this, and the first type of state and the second type of state can be determined according to actual needs, as long as they correspond to each other.

[0106] In this embodiment, the first type of state is the closed-eye state, and the second type of state is the open-eye state, as an example for explanation. The first frequency domain EEG signal is the first converted signal data, and the second frequency domain EEG signal is the second converted signal data.

[0107] In this implementation, the above formula (1) or formula (2) can be used to perform frequency domain conversion processing on the signal corresponding to the first type of eye state in the EEG signal to obtain the first frequency domain EEG signal; and the signal corresponding to the second type of eye state in the EEG signal can be performed to perform frequency domain conversion processing to obtain the second frequency domain EEG signal.

[0108] The target frequency domain parameter value can be the ratio between the first frequency domain EEG signal and the second frequency domain EEG signal.

[0109] For example, taking the first type of state as the closed-eye state and the second type of state as the open-eye state as an example, by performing frequency domain transformation on the signal in the EEG signal corresponding to the closed-eye state (α wave), we can obtain the first frequency domain EEG signal, that is, the power α corresponding to the α wave. By performing frequency domain transformation on the signal in the EEG signal corresponding to the open-eye state (β wave), we can obtain the second frequency domain EEG signal, that is, the power β corresponding to the β wave, and determine the target frequency domain parameter value as R = β / α, which can be referred to as the R ratio below.

[0110] In this implementation, multiple sample users' EEG signals and eye state information corresponding to each EEG signal can be collected in advance. After determining the sample frequency domain parameter value of each EEG signal, the sample frequency domain parameter value is matched with the corresponding eye state information to determine the reference frequency domain parameter value. Based on the relationship between the target frequency domain parameter value and the reference frequency domain parameter value, the eye state information is determined.

[0111] In this embodiment, a reference frequency domain parameter value is determined in advance based on the sample frequency domain parameter value of the sample user and the eye state information of the sample user. After determining the target frequency domain parameter value based on the frequency domain EEG signal corresponding to different types of eye states, the eye state information is determined based on the target frequency domain parameter value and the reference frequency domain parameter value. This allows for a more accurate determination of which type of eye state the eye state information corresponds to.

[0112] Optionally, before determining the eye state information based on the target frequency domain parameter values ​​and the reference frequency domain parameter values, the above method may further include:

[0113] Obtain the first sample frequency domain parameter value of the sample user under the first type of eye state, and obtain the second sample frequency domain parameter value of the sample user under the second type of eye state;

[0114] Determine the maximum value among the frequency domain parameter values ​​of each first sample, and the minimum value among the frequency domain parameter values ​​of each second sample;

[0115] The reference frequency domain parameter values ​​are determined based on the maximum and minimum values.

[0116] In the actual implementation process, the average of the maximum and minimum values ​​can be determined as the reference frequency domain parameter value.

[0117] Taking the first type of state as the closed-eye state and the second type of state as the open-eye state as an example, the R ratio RcE of the cE user state and the R ratio RoE of the oE user state can be determined respectively.

[0118] Specifically, the reference frequency domain parameter value T can be determined using the following formula (3):

[0119] T=[max(RcE)+min(RoE)] / 2 Formula (3)

[0120] Alternatively, the reference frequency domain parameter values ​​can be determined based on the minimum value among the first sample frequency domain parameter values ​​and the maximum value among the second sample frequency domain parameter values. However, the correspondence between the target frequency domain parameter values ​​and the reference frequency domain parameter values ​​needs to be updated based on the method used to determine these reference frequency domain parameter values.

[0121] In this embodiment, a reference frequency domain parameter value can be determined based on the first sample frequency domain parameter value of the sample user under the first type of eye state and the second sample frequency domain parameter value under the second type of eye state, laying the groundwork for subsequent determination of the user's eye state information.

[0122] In the specific implementation process, the EEG signals corresponding to the sample users can be obtained based on the following methods:

[0123] The first signal acquisition task involved collecting EEG signals from the sample user for 60 seconds in the oE (out-of-eye) state, while the second task involved collecting EEG signals from the sample user for 60 seconds in the cE (closed-eye) state. There was at least a 3-second interval between each task to ensure that the sample user's brain and eyes could get sufficient rest before completing the new task, thus avoiding errors caused by visual fatigue or other factors.

[0124] After repeatedly collecting each signal acquisition task 5 times, the EEG signals corresponding to the 10 signal acquisition tasks (i.e., 10 minutes) for each sample user can be obtained. Specifically, the EEG signals corresponding to the 5 signal acquisition tasks for oE eye state and the EEG signals corresponding to the 5 signal acquisition tasks for cE eye state for each sample user can be obtained.

[0125] Based on the EEG signals corresponding to each signal acquisition task of each sample user, the first sample frequency domain parameter value of the sample user in the first eye state and the second sample frequency domain parameter value of the sample user in the second eye state are analyzed. The maximum value of each first sample frequency domain parameter value and the minimum value of each second sample frequency domain parameter value of each sample user are determined to determine the reference frequency domain parameter value.

[0126] Optionally, the above-mentioned determination of eye state information based on target frequency domain parameter values ​​and reference frequency domain parameter values ​​may include:

[0127] If the target frequency domain parameter value is less than or equal to the reference frequency domain parameter value, the eye state information is determined to be the first type of eye state;

[0128] If the target frequency domain parameter value is greater than the reference frequency domain parameter value, the eye state information is determined to be the second type of eye state.

[0129] This method enables the detection of the specific eye state of a target user using a threshold-based (reference frequency domain parameter value) classifier.

[0130] Taking the first type of state as closed eyes and the second type of state as open eyes as an example, assuming the reference frequency domain parameter value is T, it can be set that if R is lower than the reference frequency domain parameter value, the eye state information is determined to be closed eyes; if R is higher than the reference frequency domain parameter value, the eye state information is determined to be open eyes. The specific expression is shown in formula (4):

[0131]

[0132] By using the relationship between the target frequency domain parameter values ​​and the reference frequency domain parameter values, the specific eye state of the target user can be determined. This avoids situations where, due to artifacts in the electroencephalogram or abnormal EEG signals, a unified standard cannot be used to determine the specific eye state of the target user, leading to classification errors and subsequent control errors of IoT devices.

[0133] Figure 4 The illustration shows an application scenario of the device control method provided in this application embodiment. In this application scenario, the device control system is a device control system integrating BCI devices in an Internet of Things (IoT) environment. This system can detect whether the target user's eyes are closed (cE) or open (oE) and control smart home devices based on this eye state.

[0134] like Figure 4 As shown, the control system of the device includes a signal detection device (i.e., an input electrode sensor, an EEG head-mounted device), a microprocessor (implemented through a signal processing unit (sampling EEG signals + converter), a classifier, and an MQTT communication client), an MQTT protocol transmission module, and a smart home device (i.e., an Internet of Things device).

[0135] In this implementation, EEG signals are acquired through input electrode sensors, and the acquired signals are amplified and then sent to a microprocessor.

[0136] The microprocessor uses a bandpass filter-based EEG signal sampling module to acquire EEG signals between 4.7Hz and 29.2Hz. A converter in the microprocessor converts the output signal from the sampling EEG signal module into a frequency-domain EEG signal. A classifier determines target frequency-domain parameter values ​​based on the frequency-domain EEG signal, and based on the relationship between these target and reference frequency-domain parameter values, determines the user's eye state information. An MQTT client generates an MQTT control packet (CP) based on the eye state information, and the MQTT protocol transmission module transmits this MQTT control packet to smart home devices, enabling the smart home devices to adjust their operating status based on this eye state information.

[0137] MQTT (Message Queuing Telemetry Transport) is a simple and lightweight messaging protocol designed for low-bandwidth networks, used for publish / subscribe. The protocol allows a maximum data packet size of 256MB.

[0138] An MQTT control packet consists of a maximum of three parts: (1) a fixed header, which is always present in all CPs; (2) an optional variable header; and (3) an optional payload. The header indicates the type of CP, and the payload is related to the actual information transmitted. In this embodiment, the payload is related to the aforementioned eye state information; that is, the microprocessor-processed eye state information can be transmitted through the payload portion of the CP. The MQTT control packet is one byte in size and is used to indicate the user's eye state.

[0139] Smart home devices can receive MQTT control packets from an MQTT client and react accordingly based on the user's eye state indicated by the MQTT control packet.

[0140] To enable more precise control of IoT devices, the embodiments of this application also provide the following optional implementation methods:

[0141] The above-mentioned adjustment of the working state of IoT devices based on the eye state information, the original working state, and the preset state adjustment relationship can include:

[0142] Based on the target user's EEG signal in the second time period, the target user's first state information in the frequency domain is determined; wherein, the original EEG signal includes the target user's EEG signal in the first time period; the second time period is the time period before the first time period, and there is a first overlap time period between the second time period and the first time period;

[0143] Based on the target user's EEG signal in the third time period, the target user's second state information in the frequency domain is determined; the third time period is the time period after the first time period, and there is a second overlapping time period between the third time period and the first time period;

[0144] Based on eye state information, first state information, and second state information, when it is determined that the target user's eye state has changed, the original working state of the IoT device is adjusted to the target working state based on the state adjustment relationship.

[0145] In this implementation, the method of determining eye state information based on the original EEG signal can be referred to above to determine the first state information and the second state information, which will not be elaborated here.

[0146] In this implementation, the specific time lengths corresponding to the first time period, the second time period, the third time period, the first overlapping time period, and the second overlapping time period can be determined based on the actual situation, and this application embodiment does not impose any restrictions here.

[0147] By setting overlapping time windows within adjacent time periods, and determining whether the target user's eye state has changed based on the eye state corresponding to each adjacent time period, and adjusting the original working state of the IoT device to the target working state based on the state adjustment relationship when the target user's eye state changes, the accuracy of controlling the working state of IoT devices can be improved.

[0148] Taking a kitchen burner as an example of a smart home device, if the kitchen burner determines that the user has been in a closed-eye state for a long time based on MQTT control data packets, it can determine that the user may have fallen asleep, and then the kitchen burner can be turned off to avoid any risks.

[0149] Alternatively, the change in the target user's eye state can be determined using the following methods:

[0150] If the target eye state is different from the first state information, but the target eye state is the same as the second state information, it is determined that the target user's eye state has changed;

[0151] If the target eye state differs from the first state information and also differs from the second state information, it is determined that the target user's eye state has not changed.

[0152] By determining whether the target user's eye state has changed in the first time period if the current time period (i.e., the first time period) differs from the previous time period (i.e., the target eye state differs from the first state information), and if the current time period is the same as the subsequent time period (i.e., the third time period) (i.e., the target eye state is the same as the second state information), then it can be determined that the target user's eye state has not changed in the first time period. Conversely, if the current time period differs from the previous time period, and if the current time period differs from the subsequent time period (i.e., the target eye state differs from the second state information), then it can be determined that the target user's eye state has not changed in the first time period. This method can accurately determine whether the user's eye state has changed, avoiding problems such as adjustment errors in the adjustment process of the IoT device's working state due to eye fatigue, detection process errors, etc.

[0153] The following analysis, using specific data, examines the accuracy rates for determining different eye states using methods based on related technologies (as shown in Table 1) and methods provided in this application's embodiments (as shown in Table 2). The data in Tables 1 and 2 are average values ​​of actual sampled data (i.e., average accuracy rate of cE in the closed state / average accuracy rate of oE in the open state). Furthermore, the accuracy rates for both methods in related technologies and methods provided in this application's embodiments are determined by whether or not cross-time periods are set between adjacent time periods.

[0154] Table 1:

[0155]

[0156] Table 2:

[0157]

[0158] In Tables 1 and 2, the duration of each time segment is D seconds, and the overlap time segment between adjacent time segments (i.e., the time gap) is d seconds. Furthermore, during the experiment, the larger the duration D of each time segment, the larger the sample size N, and the greater the computational cost. Simultaneously, since each time segment needs to acquire EEG signals from non-overlapping periods with adjacent time segments, the duration D of each time segment also increases with the increase of the overlap time gap d. Moreover, due to the overlapping time between other time segments within each time segment, the waiting time (i.e., decision delay) for determining the user's eye state in each time segment is Dd.

[0159] As can be seen from Tables 1 and 2, regardless of whether the method is based on related technologies or the method provided in the embodiments of this application, the average accuracy of acquiring EEG signals using an overlapping time window is significantly higher than the average accuracy of acquiring EEG signals using a non-overlapping window. Clearly, acquiring EEG signals using an overlapping time window significantly improves the accuracy of the eye state detection system.

[0160] Especially for short decision delay times, the average accuracy of the overlapping window cE / oE ratio in Table 1 can be calculated. The average accuracy of the method provided in this application using the overlapping time window to collect EEG signals is 95.30%, while the average accuracy of the method based on the overlapping time window to collect EEG signals in related technologies is 92.74%. Therefore, it can be seen that the method provided in this application is generally better than the methods in related technologies in determining the user's eye state, especially in the open-eye state (oE). Although the method based on related technologies shows higher accuracy in determining the user's eye state in the closed-eye state (cE) compared to the method provided in this application, these differences are far smaller than the effect achieved by the method provided in this application in the open-eye state (oE).

[0161] Therefore, the method provided in this application embodiment can more accurately determine the eye state of different users, thereby improving the robustness of controlling the working state of IoT devices. Furthermore, this method is relatively simple, reducing system training time and lowering the optimization objective of reducing the delay between acquired and decision signals.

[0162] Based on the same principle as the device control method provided in the embodiments of this application, the embodiments of this application also provide a device control apparatus. For example... Figure 5 As shown, the device 50 includes:

[0163] The signal acquisition module 51 is used to receive the original EEG signal of the target user collected by the signal detection device, and to acquire the original working status of the Internet of Things device.

[0164] The eye state information determination module 52 is used to perform frequency domain conversion processing on the above-mentioned original EEG signal and determine the eye state information of the target user in the frequency domain based on the converted signal data.

[0165] The working status adjustment module 53 is used to adjust the working status of the Internet of Things device based on the eye status information, the original working status, and the preset status adjustment relationship.

[0166] Optionally, when adjusting the working state of the IoT device based on eye status information, the original working state, and a preset state adjustment relationship, the aforementioned working state adjustment module 53 can be specifically used for:

[0167] Based on the target user's EEG signal in the second time period, the target user's first state information in the frequency domain is determined; wherein, the original EEG signal includes the target user's EEG signal in the first time period; the second time period is the time period before the first time period, and there is a first overlapping time window between the second time period and the first time period.

[0168] Based on the target user's EEG signal in the third time period, the target user's second state information in the frequency domain is determined; the third time period is the time period after the first time period, and there is a second overlapping time window between the third time period and the first time period;

[0169] Based on eye state information, first state information, and second state information, when it is determined that the target user's eye state has changed, the original working state of the IoT device is adjusted to the target working state based on the state adjustment relationship.

[0170] Optionally, the eye state information determination module 52 described above can also be used for:

[0171] If the target eye state is different from the first state information, but the target eye state is the same as the second state information, it is determined that the target user's eye state has changed.

[0172] If the target eye state differs from the first state information and also differs from the second state information, it is determined that the target user's eye state has not changed.

[0173] Optionally, when the aforementioned eye state information determination module 52 performs frequency domain conversion processing on the original EEG signal and determines the target user's eye state information in the frequency domain based on the converted signal data, it can be specifically used for:

[0174] The original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal.

[0175] A sliding transform is applied to the denoised EEG signal to obtain the frequency domain EEG signal corresponding to the original EEG signal;

[0176] Eye state information is obtained based on frequency domain EEG signals.

[0177] Optionally, when the eye state information determination module 52 obtains eye state information based on frequency domain EEG signals, it can be specifically used for:

[0178] Based on the first frequency domain EEG signal and the second frequency domain EEG signal, the target frequency domain parameter value is determined; wherein, the target eye state is either the first type of eye state or the second type of eye state; the first frequency domain EEG signal is the frequency domain EEG signal corresponding to the first type of eye; the second frequency domain EEG signal is the frequency domain EEG signal corresponding to the second type of eye state;

[0179] Eye state information is determined based on target frequency domain parameter values ​​and reference frequency domain parameter values; wherein, the reference frequency domain parameter values ​​are determined based on the sample frequency domain parameter values ​​of the sample users and the eye state information of the sample users.

[0180] Optionally, before determining the eye state information based on the target frequency domain parameter value and the reference frequency domain parameter value, the aforementioned eye state information determination module 52 may also be used for:

[0181] Obtain the first sample frequency domain parameter value of the sample user under the first type of eye state, and obtain the second sample frequency domain parameter value of the sample user under the second type of state information;

[0182] Determine the maximum value among the frequency domain parameter values ​​of each first sample, and the minimum value among the frequency domain reference values ​​of each second sample;

[0183] The reference frequency domain parameter values ​​are determined based on the maximum and minimum values.

[0184] Optionally, when determining eye state information based on target frequency domain parameter values ​​and reference frequency domain parameter values, the aforementioned eye state information determination module 52 can be specifically used for:

[0185] If the target frequency domain parameter value is less than or equal to the reference frequency domain parameter value, the target eye state is determined to be the first type of eye state;

[0186] If the target frequency domain parameter value is greater than the reference frequency domain parameter value, the target eye state is determined to be the second type of eye state.

[0187] Optionally, when receiving the raw EEG signal of the target user collected by the signal detection device, the signal acquisition module 51 is specifically used for:

[0188] The raw electroencephalogram (EEG) signals collected by the detection electrodes of the receiving signal detection device;

[0189] The detection electrode is located in the right occipital region of the target user.

[0190] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0191] Based on the same principles as the device control method and apparatus provided in the embodiments of this application, the embodiments of this application also provide an electronic device (such as a server). The electronic device may include a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the device control method provided in any optional embodiment of this application.

[0192] It receives raw EEG signals from the target user collected by the signal detection device, and obtains the raw working status of the Internet of Things device;

[0193] The original EEG signals were subjected to frequency domain transformation, and the target user's eye state information in the frequency domain was determined based on the transformed signal data.

[0194] Based on the eye status information, the original working state, and the preset state adjustment relationship, the working state of the IoT device is adjusted.

[0195] In this embodiment, by performing frequency domain conversion processing on the raw EEG signals of the target user collected by the signal detection device, and determining the target user's eye state information in the frequency domain based on the converted signal data, compared to directly determining eye state information based on the raw EEG signals in the time domain, it is possible to obtain eye state information of the target user that matches the actual eye state more quickly and stably. Furthermore, by acquiring the original operating state of the IoT device, and using this eye state information as a control command to adjust the operating state of the IoT device, the operating state of the IoT device is adjusted based on this eye state information, the original operating state, and a preset state adjustment relationship. This allows for rapid and stable adjustment of the IoT device's operating state based on the user's actual eye state, improving adjustment efficiency.

[0196] See Figure 6 , Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Figure 6As shown, the electronic device 600 in this embodiment may include: a processor 601, a network interface 604, and a memory 605. Furthermore, the electronic device 600 may also include: an object interface 603, and at least one communication bus 602. The communication bus 602 is used to implement communication between these components. The object interface 603 may include a display screen and a keyboard; optionally, the object interface 603 may also include a standard wired interface or a wireless interface. The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 605 may be a high-speed RAM or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory 605 may also be at least one storage device located remotely from the aforementioned processor 601. Figure 6 As shown, the memory 605, which is a computer-readable storage medium, may include an operating system, a network communication module, an object interface module, and a device control application.

[0197] exist Figure 6 In the illustrated electronic device 600, the network interface 604 provides network communication functionality; the object interface 603 is primarily used to provide an input interface for objects; and the processor 601 can be used to call the device control application stored in the memory 605 to achieve:

[0198] In some feasible implementations, the processor 601 described above is used for:

[0199] It should be understood that in some feasible implementations, the processor 601 described above may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0200] In specific implementation, the aforementioned electronic device 600 can perform the above-described actions through its built-in functional modules. Figure 1 The implementation methods provided for each step are detailed in the above-mentioned implementation methods, and will not be repeated here.

[0201] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement... Figure 1 The methods provided in each step are detailed in the implementation methods provided in the above steps, and will not be repeated here.

[0202] The aforementioned computer-readable storage medium can be an internal storage unit of the device control apparatus or electronic device provided in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device. The aforementioned computer-readable storage medium can also include magnetic disks, optical disks, read-only memory (ROM), or random access memory (RAM), etc. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0203] This application provides a computer program product, which includes a computer program that is executed by a processor. Figure 1 The methods provided for each step in the process.

[0204] The terms "first," "second," etc., in the claims, description, and drawings of this application are used to distinguish different objects, rather than to describe a specific order.

[0205] Furthermore, those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. The terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or electronic device.

[0206] The reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The inclusion of this phrase in various locations throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and / or" as used in this specification and the appended claims means, and includes, any combination of one or more of the associated listed items and all possible combinations.

[0207] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Those skilled in the art can implement the described functions using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

[0208] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A device control method, characterized in that, The method includes: It receives raw EEG signals from the target user collected by the signal detection device, and obtains the raw working status of the Internet of Things device; The original EEG signal is subjected to frequency domain conversion processing, and the eye state information of the target user in the frequency domain is determined based on the converted signal data. Based on the eye state information, the original working state, and the preset state adjustment relationship, the working state of the IoT device is adjusted; The step of performing frequency domain transformation on the original EEG signal and determining the target user's eye state information in the frequency domain based on the transformed signal data includes: The original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal. The denoised EEG signal is subjected to a sliding transform to obtain the frequency domain EEG signal corresponding to the original EEG signal; The eye state information is obtained based on the frequency domain EEG signal; The process of obtaining the eye state information based on the frequency domain EEG signal includes: Based on the first frequency domain EEG signal and the second frequency domain EEG signal, a target frequency domain parameter value is determined; wherein, the target frequency domain parameter value is the ratio between the first frequency domain EEG signal and the second frequency domain EEG signal; the target eye state is a first type of eye state or a second type of eye state; the first frequency domain EEG signal is the signal of the frequency domain EEG signal corresponding to the first type of eye; the second frequency domain EEG signal is the signal of the frequency domain EEG signal corresponding to the second type of eye state; The eye state information is determined based on the target frequency domain parameter value and the reference frequency domain parameter value; wherein, the reference frequency domain parameter value is determined based on the sample frequency domain parameter value of the sample user and the eye state information of the sample user.

2. The method according to claim 1, characterized in that, The adjustment of the working state of the IoT device based on the eye state information, the original working state, and a preset state adjustment relationship includes: Based on the target user's EEG signal in the second time period, the first state information of the target user in the frequency domain is determined; wherein, the original EEG signal includes the target user's EEG signal in the first time period; the second time period is the time period before the first time period, and there is a first overlapping time window between the second time period and the first time period; Based on the target user's EEG signal in the third time period, the target user's second state information in the frequency domain is determined; the third time period is the time period after the first time period, and there is a second overlapping time window between the third time period and the first time period; Based on the eye state information, the first state information, and the second state information, when it is determined that the target user's eye state has changed, the original working state of the IoT device is adjusted to the target working state based on the state adjustment relationship.

3. The method according to claim 2, characterized in that, The method further includes: If the target eye state is different from the first state information, and the target eye state is the same as the second state information, it is determined that the target user's eye state has changed; If the target eye state is different from the first state information and the target eye state is different from the second state information, it is determined that the target user's eye state has not changed.

4. The method according to claim 1, characterized in that, Before determining the eye state information based on the target frequency domain parameter value and the reference frequency domain parameter value, the method further includes: Obtain the first sample frequency domain parameter value of the sample user under the first type of eye state, and obtain the second sample frequency domain parameter value of the sample user under the second type of state information; Determine the maximum value among the frequency domain parameter values ​​of each of the first samples, and the minimum value among the frequency domain reference values ​​of each of the second samples; The reference frequency domain parameter value is determined based on the maximum value and the minimum value.

5. The method according to claim 4, characterized in that, Determining the eye state information based on the target frequency domain parameter value and the reference frequency domain parameter value includes: If the target frequency domain parameter value is less than or equal to the reference frequency domain parameter value, the target eye state is determined to be the first type of eye state; If the target frequency domain parameter value is greater than the reference frequency domain parameter value, the target eye state is determined to be the second type of eye state.

6. The method according to claim 1, characterized in that, The raw electroencephalogram (EEG) signals of the target user collected by the receiving signal detection device include: Receive the raw electroencephalogram (EEG) signals collected by the detection electrodes of the signal detection device; The detection electrode is located in the right occipital region of the target user.

7. A device control apparatus, characterized in that, The device includes: The signal acquisition module is used to receive the raw EEG signals of the target user collected by the signal detection device, and to acquire the raw working status of the Internet of Things device. An eye state information determination module is used to perform frequency domain conversion processing on the original electroencephalogram (EEG) signal and determine the eye state information of the target user in the frequency domain based on the converted signal data. The working state adjustment module is used to adjust the working state of the Internet of Things device based on the eye state information, the original working state, and the preset state adjustment relationship; The eye state information determination module, when performing frequency domain conversion processing on the original EEG signal and determining the target user's eye state information in the frequency domain based on the converted signal data, is specifically used for: The original EEG signal is filtered and denoised using a bandpass filter to obtain a denoised EEG signal. A sliding transform is applied to the denoised EEG signal to obtain the frequency domain EEG signal corresponding to the original EEG signal; Eye state information is obtained based on frequency domain EEG signals; When the eye state information determination module obtains eye state information based on frequency domain EEG signals, it is specifically used for: Based on the first frequency domain EEG signal and the second frequency domain EEG signal, a target frequency domain parameter value is determined; wherein, the target frequency domain parameter value is the ratio between the first frequency domain EEG signal and the second frequency domain EEG signal; the target eye state is either a first type of eye state or a second type of eye state; the first frequency domain EEG signal is the frequency domain EEG signal corresponding to the first type of eye state; the second frequency domain EEG signal is the frequency domain EEG signal corresponding to the second type of eye state. Eye state information is determined based on target frequency domain parameter values ​​and reference frequency domain parameter values; wherein, the reference frequency domain parameter values ​​are determined based on the sample frequency domain parameter values ​​of the sample users and the eye state information of the sample users.

8. An electronic device, characterized in that, It includes a processor and a memory, which are interconnected; The memory is used to store computer programs; The processor is configured to perform the method according to any one of claims 1 to 6 when the computer program is invoked.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images