Brain-computer interface system, electroencephalogram data trigger event marking method and device

Abstract

This application discloses a brain-computer interface system, a method and apparatus for marking EEG data trigger events. The brain-computer interface system includes a stimulus generator and a controller, a trigger, and an EEG acquisition device. The controller sends a first label value, a second label value, and a third label value to the trigger. The trigger sends the first label value, the second label value, and the third label value to the EEG acquisition device. The EEG acquisition device acquires EEG data, inserts the first label value, the second label value, and the third label value into the EEG data, and sends the EEG data to the controller. The controller decodes the EEG data to obtain decoded stimulus information, obtains standard stimulus information based on one or more of the first label value, the second label value, and the third label value, and compares the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct. This application divides the EEG data segments in more detail, effectively increasing the system's redundancy and stability, and improving the performance of the decoding algorithm.

Description

Technical Field

[0001] This application belongs to the field of brain-computer interface technology, specifically relating to a brain-computer interface system, a method and apparatus for marking EEG data trigger events. Background Technology

[0002] Because of the chaotic nature of EEG data, analysis and processing of EEG data requires decoding and analyzing specific time periods. A common method is to label the EEG data to mark specific time periods, for example, using different labels at the beginning and during stimulation. During decoding, the host computer algorithm can extract and analyze specific segments of the EEG data that resonate based on these labels.

[0003] Existing tagging methods have the following problems:

[0004] 1. The label must be strictly aligned with the stimulus initiation event, and the label cannot be lost or flipped, otherwise it will cause decoding confusion and lead to decoding errors;

[0005] 2. The algorithm cannot clearly label the stimulation frequency and phase information contained in the EEG signal segments. In the brain-computer interface research phase, when decoding segmented EEG data, the algorithm needs to understand the frequency and phase information encoded in that segment. For example, if the stimulation frequency is f1 and the encoded phase angle is ω1, this segment of EEG is labeled (f1, ω1). If, due to the introduction of ocular noise, electromyographic noise, or power line interference noise, the algorithm ultimately decodes this segment of EEG as (f2, ω2), the algorithm cannot detect the error under the existing labeling method and cannot correct or calibrate it, thus leading to incorrect decoding decisions.

[0006] 3. The trigger events in the labels are singular, generally only able to sense changes in light intensity to trigger events to label EEG data, which limits the application scenarios and does not meet the requirements of brain-computer interface systems such as ERP, motor imagery, auditory evoked, and emotion evoked. Summary of the Invention

[0007] The purpose of this application is to provide a method and device for marking EEG data trigger events and a brain-computer interface system to solve the technical problems of existing marking methods, which require labels to be strictly aligned with the stimulus initiation event and that labels cannot be lost or flipped, otherwise it will cause decoding confusion and errors, and will not be able to indicate the stimulus frequency and phase information contained in the EEG signal segment, and the trigger event is singular.

[0008] To achieve the above objectives, one technical solution adopted in this application is:

[0009] A brain-computer interface system is provided, including a stimulation generator and a controller, trigger and EEG acquisition device for signal connection;

[0010] The stimulus generator is used to generate stimulus information;

[0011] The controller is configured to send a first tag value to the trigger when the stimulus information begins, send a second tag value to the trigger when the stimulus information ends, and send a third tag value to the trigger at a preset time after the stimulus information ends. One or more of the first tag value, the second tag value, and the third tag value include a stimulus information identifier.

[0012] The trigger is used to send the first label value, the second label value, and the third label value to the EEG acquisition device;

[0013] The EEG collector is used to collect the user's EEG data, insert the first tag value into the beginning of the user's resonant EEG data in response to the stimulus information, insert the second tag value into the end of the resonant EEG data, insert the third tag value into the EEG data, and send the EEG data to the controller in real time.

[0014] The controller is also configured to decode the EEG data to obtain decoded stimulus information, obtain standard stimulus information based on one or more of the first label value, the second label value, and the third label value, and compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

[0015] In one or more embodiments, one or more of the first label value, the second label value, and the third label value are determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

[0016] In one or more embodiments, the controller and the trigger are connected to the trigger via a serial port, parallel port, or USB-to-serial port; the trigger is connected to the EEG acquisition device via the ISM band; and the EEG acquisition device is connected to the controller via the Wi-Fi wireless band.

[0017] To achieve the above objectives, another technical solution adopted in this application is:

[0018] A method for tagging trigger events in EEG data is provided, including:

[0019] At the start of the stimulus information, a first tag value is sent to a trigger, so that the trigger sends the first tag value to the EEG collector and drives the EEG collector to insert the first tag value into the beginning of the resonant EEG data, which is the EEG data of the user in response to the stimulus information collected by the EEG collector;

[0020] At the end of the stimulation information, a second label value is sent to the trigger, so that the trigger sends the second label value to the EEG collector and drives the EEG collector to insert the second label value into the end of the resonant EEG data;

[0021] At a preset time after the stimulus information ends, a third tag value is sent to the trigger, so that the trigger sends the third tag value to the EEG collector and drives the EEG collector to insert the third tag value into the EEG data of the user collected by the EEG collector;

[0022] Receive the EEG data sent by the EEG acquisition device, and decode the EEG data to obtain decoded stimulus information;

[0023] Standard stimulus information is obtained based on one or more of the first label value, the second label value, and the third label value; wherein one or more of the first label value, the second label value, and the third label value includes a stimulus information identifier;

[0024] The standard stimulus information is compared with the decoded stimulus information to determine whether the decoding is correct.

[0025] In one or more embodiments, one or more of the first label value, the second label value, and the third label value are determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

[0026] To achieve the above objectives, another technical solution adopted in this application is:

[0027] A device for marking EEG data trigger events is provided, comprising:

[0028] The first tag sending module is used to send a first tag value to a trigger when the stimulus information begins, so that the trigger sends the first tag value to the EEG collector and drives the EEG collector to insert the first tag value into the beginning of the resonant EEG data, wherein the resonant EEG data is the EEG data of the user in response to the stimulus information collected by the EEG collector.

[0029] The second tag sending module is used to send a second tag value to the trigger when the stimulus information ends, so that the trigger sends the second tag value to the EEG collector and drives the EEG collector to insert the second tag value into the end of the resonant EEG data.

[0030] The third tag sending module is used to send a third tag value to the trigger at a preset time after the end of the stimulus information, so that the trigger sends the third tag value to the EEG collector and drives the EEG collector to insert the third tag value into the EEG data of the user collected by the EEG collector.

[0031] The decoding module is used to receive the EEG data sent by the EEG acquisition device and decode the EEG data to obtain decoded stimulus information.

[0032] The acquisition module is configured to acquire standard stimulus information based on one or more of the first label value, the second label value, and the third label value, wherein one or more of the first label value, the second label value, and the third label value includes a stimulus information identifier;

[0033] The comparison module is used to compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

[0034] To achieve the above objectives, another technical solution adopted in this application is:

[0035] An electronic device is provided, comprising:

[0036] At least one processor; and

[0037] A memory that stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the EEG data trigger event labeling method as described in any of the above embodiments.

[0038] To achieve the above objectives, another technical solution adopted in this application is:

[0039] A machine-readable storage medium is provided that stores executable instructions, which, when executed, cause the machine to perform the EEG data trigger event labeling method as described in any of the above embodiments.

[0040] The advantages of this application, which differ from existing technologies, are:

[0041] The controller of this application can send a first label value, a second label value, and a third label value to a trigger at preset times when the stimulus information begins, ends, and ends. The trigger then sends these three labels to the EEG collector, which inserts them into the EEG data to mark the start, end, and decoding ends, respectively. During decoding, the controller can extract the user's resonant EEG data in response to the stimulus information from the EEG data using the first and / or second label values. This helps extract valuable EEG data requiring decoding analysis from the otherwise chaotic EEG data. Furthermore, the controller does not need to perform decoding algorithm processing on the EEG data during the decoding phase between the second and third label values, or on the EEG data between the third label value and the first label value of the next stimulus segment, thereby improving the controller's decoding performance.

[0042] The first, second, and third label values ​​in this application are specific values ​​corresponding to the stimulus start, stimulus end, and decoding end states, respectively. When the controller receives the first, second, or third label value, it can determine that the current state is the stimulus start, stimulus end, or decoding end state. Even if one or two of the three label values ​​are lost during transmission, the controller can still distinguish the EEG data segment corresponding to the specific stimulus information based on the remaining label values ​​and the label values ​​of the next stimulus stage. This allows for a more detailed division of the EEG data segments, effectively increasing the redundancy and stability of the system and improving the performance of the decoding algorithm.

[0043] One or more of the first label value, second label value, and third label value in this application include stimulus information identifiers. The controller can obtain standard stimulus information based on one or more of the first label value, second label value, and third label value. Therefore, the controller can determine whether the decoding is correct by comparing the standard stimulus information and the decoded stimulus information obtained by decoding when the decoding is completed, and provide real-time feedback when misinterpretation occurs, which helps the operator update the decoding algorithm parameters. Attached Figure Description

[0044] Figure 1 This is a diagram of EEG data;

[0045] Figure 2 This is a structural block diagram of one embodiment of the brain-computer interface system of this application;

[0046] Figure 3 This is a flowchart illustrating one implementation of the EEG data trigger event labeling method of this application;

[0047] Figure 4 This is a schematic diagram of one embodiment of the EEG data tag of this application;

[0048] Figure 5 This is a schematic diagram of one embodiment of the EEG data trigger event labeling device of this application;

[0049] Figure 6 This is a schematic diagram of one embodiment of the electronic device of this application. Detailed Implementation

[0050] The present application will now be described in detail with reference to the embodiments shown in the accompanying drawings. However, these embodiments do not limit the present application, and any structural, methodological, or functional modifications made by those skilled in the art based on these embodiments are included within the protection scope of the present application.

[0051] SSVEP stands for Steady-State Visual Evoked Potential. Its main principle is as follows: The human brain contains various neural networks, each with its own inherent resonant frequency. Under normal conditions, these neural networks are asynchronous, chaotic, and irregular; the resulting brainwave signals are called spontaneous EEG. When a stable frequency of external visual stimulation is applied to the eyes, neural networks that resonate with the stimulation frequency or harmonic frequency will resonate, causing a significant change in the brain's electrical activity at the stimulation frequency or harmonic frequency, thus generating an SSVEP signal. By detecting the SSVEP signal, it can be acquired and decoded, and then converted into control commands.

[0052] Because of the chaotic nature of EEG data, its analysis and processing require decoding and analysis over a specific time period. For example... Figure 1 As shown, Figure 1This is a schematic diagram of EEG data. In the time domain, EEG data from different channels are labeled with M1 and M2 tags respectively. When applying fixed-frequency stimulation in the SSVEP brain-computer interface system, the EEG data needs to be tagged. The upper-level computer algorithm, based on the tagged data, can determine that the EEG data corresponds to the start of stimulation. At this time, the EEG data in the brain resonates, and there are strong power spectrum changes at the stimulation frequency and harmonic frequencies. In the diagram, the M1 and M2 tags correspond to the start and in progress of stimulation, respectively. At the start of stimulation, a trigger event is triggered. In the SSVEP system, the start of screen flashing is usually used as the trigger event. At this time, the EEG data is tagged with the trigger event label M1 to inform the decoding algorithm that the EEG data starting at this moment is the start of stimulation. During the EEG data acquisition and decoding period, usually about a few seconds, the EEG data is tagged with M2 to inform the decoding algorithm that the EEG data is still in the previous stimulation target stage and the current stimulation has not yet ended. Once the decoding is complete, the next stimulus will begin, triggering a new stimulus event, which will be labeled with M1. During the stimulation and decoding process, the EEG will be labeled with M2, and so on in a cyclical manner.

[0053] In the aforementioned trigger event labeling system, binary 1s and 0s are typically used to indicate whether a fixed-frequency stimulus has started and whether the fixed-frequency stimulus is still in progress. Typically, 1 (i.e., the M1 label) indicates the stimulus has started, and 0 (i.e., the M2 label) indicates the stimulus is in progress, meaning the algorithm is decoding.

[0054] Currently, the SSVEP brain-computer interface system typically uses only M1 (binary code 1) and M2 (binary code 0) tags to indicate whether a fixed stimulation frequency has started and whether stimulation is in progress. The advantage of this labeling method is its relative simplicity, but its significant drawback is the requirement that each label cannot be lost or flipped. In other words, the M1 label must be strictly aligned with the stimulation start event; otherwise, decoding errors will occur. For example, if the label is not strictly aligned during application or is lost during transmission (data loss during wireless transmission is normal), the algorithm's decoding end will mistakenly identify the EEG data with the lost label as belonging to the previous stimulation start, causing a decoding error. Alternatively, if the M2 label and M1 label are flipped (0 to 1 or 1 to 0), the algorithm will also incorrectly label the EEG data as belonging to the previous stimulation frequency or incorrectly label it as belonging to the start of a new stimulation frequency.

[0055] Even assuming no loss or accidental flipping of the M1 / M2 tags, this tagging method still has shortcomings: it cannot indicate the stimulation frequency and phase information contained in the EEG signal segment. Typically, in the SSVEP brain-computer interface system, when visual stimuli are generated on the screen, the stimulation-related frequency and phase information are encoded into the EEG signal. During the brain-computer interface research phase, when the algorithm decodes segmented EEG data, it needs to understand the encoded frequency and phase information of that segment. That is, assuming the stimulation frequency is f1 and the encoded phase angle is ω1, this segment of EEG is labeled (f1, ω1). If, due to the introduction of oculomotor noise, electromyographic noise, or power line interference noise, the algorithm ultimately decodes this segment of EEG as (f2, ω2), the algorithm cannot detect the error and cannot correct it, resulting in a decoding error. Therefore, researchers need to obtain the encoded (f, ω) information in the EEG data based on the tag information in the segmented EEG data decoding algorithm. Clearly, the M1 / M2 binary labels cannot achieve this function.

[0056] Furthermore, the SSVEP brain-computer interface system primarily operates on visual stimulation, and the labeling of events triggered by the optical sensor aligns with the requirements of visual stimulation. However, these optical sensor triggers can only trigger binary events, and adding labels can only assign binary values ​​(0 / 1), which doesn't fully meet the requirements for expanding label values. In other brain-computer interface systems, optical sensor triggers have limitations. For example, in systems like ERP, motor imagery, auditory evoked responses, and emotion evoked responses, the optical sensor triggers are rather limited and may not even meet the requirements for labeling trigger events.

[0057] To address the aforementioned issues, the applicant has developed a brain-computer interface system. Please refer to [link / reference]. Figure 2 , Figure 2 This is a structural block diagram of one embodiment of the brain-computer interface system of this application.

[0058] The brain-computer interface system includes a stimulus generator and a controller, trigger, and EEG acquisition device for signal connection.

[0059] The stimulus generator is used to generate stimulus information. This stimulus information can be visual; it can also be other types of evoked stimuli, such as auditory or olfactory stimuli; or it can be a combination of multiple evoked stimuli, such as the emotion-evoking experiments in emotion-based brain-computer interfaces, where emotional induction is achieved by playing sad or comedic films, combined with visual and auditory stimuli. The stimulus generator can be an output device such as a display screen that can be received by the user, all of which can achieve the effects of this embodiment.

[0060] The controller may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile electronic devices, smartphones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable electronic devices, consumer electronic devices, etc.

[0061] The trigger is used to generate and transfer tag values ​​between the controller and the EEG acquisition device.

[0062] The EEG acquisition device may include an MCU module, an ADC module, an EEG data transmission module, a tag transmission module, and an EEG cap module. The EEG cap module can be equipped with electrodes for acquiring EEG data, and may also include one REF reference electrode and one RLD right leg drive electrode. The EEG cap module can be connected to the ADC module via a cable. The ADC module can be composed of a high-precision, low-noise ADC sampling chip, responsible for acquiring EEG data.

[0063] The MCU module controls the ADC module to collect EEG data, and controls the transmission module to receive tag data, insert the tag data into the EEG data, and finally transmit the EEG data to the controller through the EEG data transmission module.

[0064] Specifically, the controller is used to send a first label value to the trigger when the stimulus information begins and a second label value to the trigger when the stimulus information ends.

[0065] The trigger is used to send the first and second label values ​​to the EEG acquisition device.

[0066] The EEG collector is used to collect the user's EEG data, insert a first tag value into the beginning of the user's resonant EEG data in response to stimulus information, insert a second tag value into the end of the resonant EEG data, and send the EEG data to the controller in real time.

[0067] The controller is also used to decode EEG data to obtain decoded stimulus information.

[0068] Understandably, the EEG acquisition device continuously collects the user's EEG data and sends the EEG data to the controller in real time. During the EEG data collection process, the EEG acquisition device can insert the received first tag value and second tag value into the EEG data to calibrate the start and end of the resonant EEG data.

[0069] The controller can cache and reprocess the received tagged EEG data. Since the EEG data is marked with a first tag value and a second tag value to indicate the start and end of the stimulus, the controller can extract the user's resonant EEG data in response to the stimulus information based on the first and second tag values ​​after receiving the EEG data. This helps to extract valuable EEG data that needs to be decoded and analyzed from the messy EEG data, effectively improving decoding efficiency.

[0070] To further increase the system's redundancy and stability, improve the performance of the decoding algorithm, and further divide the EEG data segments into more detailed segments, the controller is also used to send a third tag value to the trigger at a preset time after the stimulus information ends.

[0071] The trigger is also used to send the third label value to the EEG collector; the EEG collector is also used to insert the third label value into the EEG data.

[0072] The third label value can mark the end of decoding. The controller can skip the decoding algorithm processing for the EEG data in the decoding stage between the second and third label values, as well as the EEG data between the third label value and the first label value of the next stimulus, thereby improving the controller's decoding performance.

[0073] In one implementation, the first, second, and third label values ​​can be specific values ​​corresponding to the stimulus start, stimulus end, and decoding end states, respectively. It is understood that when the controller receives the first, second, or third label value, it can determine whether the current state is stimulus start, stimulus end, or decoding end. Therefore, even if one or two of the three label values ​​are lost during transmission, the controller can still distinguish the specific EEG data segment corresponding to the stimulus information based on the remaining label values ​​and the label values ​​for the next stimulus phase.

[0074] In order to achieve the mapping between label values ​​and stimulus information, in one embodiment, one or more of the first label value, the second label value and the third label value include a stimulus information identifier, that is, at least one of the three label values ​​may include the frequency and phase of the stimulus information.

[0075] The controller is also used to obtain standard stimulus information based on one or more of the first label value, the second label value, and the third label value, and to compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

[0076] Specifically, one or more of the first label value, the second label value, and the third label value are determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

[0077] In one implementation, in order to transmit the first tag value, the second tag value, and the third tag value, the controller can connect to the trigger via an interface such as a serial port, a parallel port, or a USB-to-serial port, thereby enabling the transmission of extended first tag values, second tag values, and third tag values.

[0078] In other implementations, the controller and trigger can also use other interface methods to transmit data, as long as the stable transmission of tag values ​​can be guaranteed.

[0079] Furthermore, to avoid mutual interference in signal transmission between the EEG acquisition device and the trigger and controller, in one embodiment, the trigger can be connected to the EEG acquisition device via the ISM band, and the EEG acquisition device can be connected to the controller via the Wi-Fi wireless band, thus avoiding mutual interference.

[0080] In other embodiments, the trigger, EEG acquisition device and controller can also be connected by other methods, such as cable connection or wireless connection in other frequency bands, all of which can achieve the effect of this embodiment.

[0081] This application also provides a method for tagging EEG data trigger events. This method extends the labeling, solves the problem of decoding confusion caused by label loss and misflipping. At the same time, it adds the encoding information of stimulation frequency and phase to the label information, and establishes a mapping relationship of "label value - stimulation information". This allows the algorithm decoding program to understand the frequency and phase information encoded in the EEG segment after obtaining the label value, which helps to tag different types of trigger events in various brain-computer interface systems.

[0082] Specifically, please refer to Figure 3 , Figure 3 This is a flowchart illustrating one implementation of the EEG data trigger event labeling method of this application, wherein the execution subject of the method is a controller.

[0083] The method includes:

[0084] S100. At the start of the stimulus information, a first label value is sent to the trigger so that the trigger sends the first label value to the EEG collector and drives the EEG collector to insert the first label value into the beginning of the resonant EEG data.

[0085] Among them, resonant EEG data refers to the EEG data collected by the EEG acquisition device in response to the user's stimulus information.

[0086] Specifically, the stimulus information can be visual; it can also be other types of evoking stimuli, such as auditory or olfactory stimuli; or it can be a combination of multiple evoking stimuli, such as the emotion-evoking experimental stimuli of emotion-related brain-computer interfaces, which induce emotions by playing some sad or comedic movies, and combine visual and auditory stimuli, all of which can achieve the effect of this implementation method.

[0087] The controller can send a first label value to the trigger when the stimulus information begins. The trigger is used to receive the first label value sent by the controller and transmit the first label value to the EEG collector.

[0088] The EEG acquisition device can collect the user's EEG data in real time. When the EEG acquisition device receives the first tag value, the user's EEG data resonates. Therefore, the EEG acquisition device can insert the first tag value into the beginning of the resonant EEG data in real time, so that the first tag value can mark the start of the stimulus.

[0089] Understandably, in order to ensure the real-time nature of the trigger event triggering mark, the first tag value should be sent at least one frame before the stimulus information begins, i.e., 16.67ms. This ensures that the first tag value is transmitted to the EEG collector when the stimulus information begins, so that the EEG collector can insert the first tag value at the beginning of the resonant EEG data to mark the start of the stimulus.

[0090] S200. At the end of the stimulus information, a second label value is sent to the trigger so that the trigger sends the second label value to the EEG collector and drives the EEG collector to insert the second label value into the end of the resonant EEG data.

[0091] When the stimulus information ends, the controller can also send a second label value to the trigger. After the trigger sends the second label value to the EEG collector, the EEG collector can insert the second label value into the end of the resonant EEG data, so that the second label value can mark the end of the stimulus.

[0092] Understandably, in order to ensure that the EEG acquisition device can insert the second tag value into the end of the resonant EEG data in real time, the controller should send the second tag value before the end of the stimulus information. The time can be one frame before the end of the stimulus information, i.e., 16.67ms.

[0093] To further increase the system's redundancy and stability, improve the performance of the decoding algorithm, and further refine the segmentation of EEG data, the following steps are also included after the above steps:

[0094] S300. At a preset time after the stimulus information ends, a third tag value is sent to the trigger so that the trigger sends the third tag value to the EEG collector and drives the EEG collector to insert the third tag value into the EEG data of the user collected by the EEG collector.

[0095] The preset time can be determined based on the controller's decoding capability. Generally, the controller's decoding time has a limited range, and it should at least ensure that the controller can complete the decoding of the resonant EEG data within the preset time.

[0096] The EEG acquisition device inserts the third tag value into the EEG data to mark the end of the decoding of the previous segment of resonant EEG data.

[0097] S400: Receives EEG data sent by the EEG acquisition device, and decodes the EEG data to obtain decoded stimulus information.

[0098] Specifically, the EEG acquisition device can send the collected EEG data of the user to the controller in real time. The controller can decode the EEG data through a decoding algorithm to obtain the decoded stimulus information.

[0099] Please see Figure 4 , Figure 4 This is a schematic diagram of one embodiment of the EEG data tag of this application. Since the EEG data is marked with a first tag value and a second tag value to indicate the start and end of the stimulus, the controller can extract the resonant EEG data of the user in response to the stimulus information from the EEG data, which helps to extract valuable EEG data that needs to be decoded and analyzed from the messy EEG data.

[0100] The third label value can mark the end of decoding. The controller can skip the decoding algorithm processing for the EEG data in the decoding stage between the second and third label values, as well as the EEG data between the third label value and the first label value of the next stimulus, thereby improving the controller's decoding performance.

[0101] In one implementation, the first, second, and third label values ​​can be specific values ​​corresponding to the stimulus start, stimulus end, and decoding end states, respectively. That is, when the controller receives the first, second, or third label value, it can determine that the current state is stimulus start, stimulus end, or decoding end. Therefore, even if one or two of the three label values ​​are lost during transmission, the controller can still distinguish the specific EEG data segment corresponding to the stimulus information based on the remaining label values ​​and the label values ​​for the next stimulus phase.

[0102] Understandably, the above-mentioned labeling method divides EEG data segments in more detail compared to binary labels, effectively increasing the system's redundancy and stability, and improving the performance of the decoding algorithm.

[0103] To enable the controller to directly acquire stimulus information based on label values, thereby allowing the controller to provide real-time feedback when decoding errors occur and facilitating the correction of decoding algorithm parameters, in one embodiment, one or more of the first, second, and third label values ​​include stimulus information identifiers; that is, at least one of the three label values ​​may include the frequency and phase of the stimulus information. The above steps may also include the following prior to the above steps:

[0104] S500: Based on one or more of the first label value, the second label value, and the third label value, standard stimulus information is obtained.

[0105] When the controller receives EEG data, it can obtain the frequency and phase of the stimulus information, i.e., the standard stimulus information, based on the first label value, second label value, or third label value of the stimulus information identifier in the EEG data.

[0106] S600: Compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

[0107] By comparing the standard stimulus information with the decoded stimulus information obtained by the controller, it is possible to determine whether the decoding was correct. When the controller detects a decoding error, it can provide real-time feedback, facilitating the correction of the decoding algorithm parameters.

[0108] In one implementation, one or more of the first label value, the second label value, and the third label value can be determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

[0109] The following example, using a brain-controlled typing scenario, illustrates the mapping relationship between label values ​​and stimulus information in this application.

[0110] In one implementation, the first label value, the second label value, and the third label value can all include the frequency and phase of the stimulus information. For brain-controlled typing scenarios, different English letters, numbers, or punctuation marks can be encoded differently using (f,ω), and different stimulus characters can correspond to different stimulus frequencies f and stimulus phases ω.

[0111] Each stimulus character can correspond to a specific first label value, a specific second label value, and a specific third label value. Since there are many ASCII characters and ASCII extended characters, totaling 128, most of which are infrequently used invisible characters, control characters, or Greek letters, in one implementation, 40 commonly used visible characters can be selected for label encoding to establish a mapping relationship between stimulus information and label values, resulting in the following stimulus encoding mapping table.

[0112]

[0113]

[0114] As shown in the table above, each stimulus character in the stimulus coding mapping table corresponds to a stimulus frequency and a stimulus phase. Each stimulus frequency is spaced 0.2 Hz apart, i.e., starting from 8 Hz and increasing by 0.2 Hz each time, up to 15.8 Hz. For the phase, each stimulus target uses a cyclic encoding from 0 to 2π, with each increment being 0.5π. Each stimulus target is assigned a different first label value, second label value, and third label value, thus establishing the stimulus coding mapping relationship.

[0115] When the controller receives the tag value 79, it can know from the stimulus encoding mapping table that the stimulus character currently received by the user is 'e', ​​and this tag corresponds to the stimulus start state. Correspondingly, when the controller receives the tag value 144, it can know that the tag corresponds to the stimulus end state of the stimulus character 'e', ​​and can extract the user's resonant EEG data for the stimulus character 'e' based on the tag values ​​79 and 144.

[0116] The controller decodes the resonant EEG data to obtain decoded stimulus information. By comparing the decoded stimulus information with the known stimulus character 'e', ​​it can determine whether the decoding is correct.

[0117] It is understood that the above implementation only shows a specific encoding scenario. In other implementations, the label value can be adjusted arbitrarily, as long as different stimulus characters correspond to different label values ​​to achieve the mapping relationship.

[0118] Furthermore, the above implementation only shows a scheme where all three label values ​​are mapped to the stimulus character. In other implementations, only one or two label values ​​can be mapped to the stimulus character, and the other label values ​​can be mapped only to the stimulus start, stimulus end, or decoding end states, which can also achieve the effect of this implementation.

[0119] This application also provides a trigger event labeling device for EEG data; please refer to [link to relevant documentation]. Figure 5 , Figure 5 This is a schematic diagram of one embodiment of the EEG data trigger event labeling device of this application.

[0120] The device includes a first tag sending module 21, a second tag sending module 22, a third tag sending module 23, a decoding module 24, an acquisition module 25, and a comparison module 26.

[0121] The first tag sending module 21 is used to send a first tag value to a trigger at the beginning of the stimulus information, so that the trigger sends the first tag value to the EEG collector and drives the EEG collector to insert the first tag value into the beginning of the resonant EEG data, which is the EEG data of the user in response to the stimulus information collected by the EEG collector; the second tag sending module 22 is used to send a second tag value to a trigger at the end of the stimulus information, so that the trigger sends the second tag value to the EEG collector and drives the EEG collector to insert the second tag value into the end of the resonant EEG data; the third tag sending module 23 is used to send a first tag value to a trigger at the end of the stimulus information, so that the trigger sends the second tag value to the EEG collector and drives the EEG collector to insert the second tag value into the end of the resonant EEG data; the third tag sending module 23 is used to send a first tag value to a trigger at the beginning of the stimulus information, so that the trigger sends the second tag value to the EEG collector and drives the EEG collector to insert the second tag value into the end of the resonant EEG data; the third tag sending module 23 is used to send a first tag value to a trigger at the beginning of the stimulus information, so that the trigger sends the first ... trigger and drives the EEG collector to insert the second tag value into the end of the resonant EEG data; the third tag sending module 23 is used to send a first tag value to a trigger at the beginning of the stimulus information, so that the trigger sends the first tag value to the trigger and drives the EEG collector to insert the second tag value into the end of the resonant EEG data; the third tag sending module 23 is used to send a first tag value to a trigger at the beginning of the stimulus information, so that the trigger sends the first tag value to the At a preset time after the stimulus information ends, a third label value is sent to the trigger, so that the trigger sends the third label value to the EEG collector and drives the EEG collector to insert the third label value into the EEG data of the user collected by the EEG collector; the decoding module 24 is used to receive the EEG data sent by the EEG collector and decode the EEG data to obtain the decoded stimulus information; the obtaining module 25 is used to obtain the standard stimulus information based on one or more of the first label value, the second label value and the third label value; the comparison module 26 is used to compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

[0122] This application also provides an electronic device, please refer to... Figure 6 , Figure 6 This is a schematic diagram of one embodiment of the electronic device of this application.

[0123] Electronic device 30 may include at least one processor 31, memory 32 (e.g., non-volatile memory), RAM 33, and communication interface 34, and the at least one processor 31, memory 32, RAM 33, and communication interface 34 are connected together via bus 35. At least one processor 31 executes at least one computer-readable instruction stored or encoded in memory 32.

[0124] It should be understood that the computer-executable instructions stored in memory 32, when executed, cause at least one processor 31 to perform the above-described combinations in the various embodiments of this specification. Figures 1-4 The description includes various operations and functions.

[0125] In the embodiments of this specification, electronic device 30 may include, but is not limited to: personal computer, server computer, workstation, desktop computer, laptop computer, notebook computer, mobile electronic device, smartphone, tablet computer, cellular phone, personal digital assistant (PDA), handheld device, messaging device, wearable electronic device, consumer electronic device, etc.

[0126] According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., the elements implemented in software as described above), which, when executed by a machine, cause the machine to perform the above-described combinations of the various embodiments of this specification. Figures 1-4 The various operations and functions described. Specifically, a system or apparatus equipped with a readable storage medium storing software program code that implements the functions of any of the embodiments described above, and enabling the computer or processor of the system or apparatus to read and execute the instructions stored in the readable storage medium.

[0127] In this case, the program code read from the readable medium itself can perform the functions of any of the above embodiments, and therefore the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of this specification.

[0128] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0129] Those skilled in the art will understand that the various embodiments disclosed above can be modified and varied without departing from the spirit of the invention. Therefore, the scope of protection of this specification should be defined by the appended claims.

[0130] It should be noted that not all steps and units in the above process and system structure diagrams are mandatory; some steps or units can be omitted according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above embodiments can be a physical structure or a logical structure. That is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or they may be jointly implemented by certain components in multiple independent devices.

[0131] In the above embodiments, the hardware units or modules can be implemented mechanically or electrically. For example, a hardware unit, module, or processor may include permanent dedicated circuitry or logic (such as a dedicated processor, FPGA, or ASIC) to perform the corresponding operation. The hardware unit or processor may also include programmable logic or circuitry (such as a general-purpose processor or other programmable processor), which can be temporarily configured by software to perform the corresponding operation. The specific implementation method (mechanical, dedicated permanent circuitry, or temporarily configured circuitry) can be determined based on cost and time considerations.

[0132] The specific embodiments described above with reference to the accompanying drawings are exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of the claims. The term "exemplary" as used throughout this specification means "serving as an example, instance, or illustration" and does not imply that it is "preferred" or "advantageous" compared to other embodiments. Specific details are included to provide an understanding of the described techniques. However, these techniques can be practiced without these specific details. In some instances, well-known structures and apparatuses are shown in block diagram form to avoid obscuring the concepts of the described embodiments.

[0133] The foregoing description of this disclosure is provided to enable any person skilled in the art to implement or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles applicable herein can be applied to other variations without departing from the scope of this disclosure. Therefore, this disclosure is not limited to the examples and designs described herein, but is consistent with the widest scope of the principles and novel features disclosed herein.

Claims

1. A brain-computer interface system, characterized in that, This includes a stimulation generator and a controller for signal connection, triggers, and an EEG acquisition device; The stimulus generator is used to generate stimulus information; The controller is configured to send a first tag value to the trigger when the stimulus information begins, send a second tag value to the trigger when the stimulus information ends, and send a third tag value to the trigger at a preset time after the stimulus information ends. One or more of the first tag value, the second tag value, and the third tag value include a stimulus information identifier. The trigger is used to send the first label value, the second label value, and the third label value to the EEG acquisition device; The EEG collector is used to collect the user's EEG data, insert the first tag value into the beginning of the user's resonant EEG data in response to the stimulus information, insert the second tag value into the end of the resonant EEG data, insert the third tag value into the EEG data, and send the EEG data to the controller in real time. The controller is also configured to decode the EEG data to obtain decoded stimulus information, obtain standard stimulus information based on one or more of the first label value, the second label value, and the third label value, and compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

2. The brain-computer interface system according to claim 1, characterized in that, One or more of the first label value, the second label value, and the third label value are determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

3. The brain-computer interface system according to claim 1 or 2, characterized in that, The controller and the trigger are connected to the trigger via a serial port, parallel port, or USB-to-serial port; the trigger is connected to the EEG acquisition device via the ISM band; the EEG acquisition device is connected to the controller via the Wi-Fi wireless band.

4. A method for marking trigger events in electroencephalogram (EEG) data, characterized in that, include: At the start of the stimulus information, a first tag value is sent to a trigger, so that the trigger sends the first tag value to the EEG collector and drives the EEG collector to insert the first tag value into the beginning of the resonant EEG data, which is the EEG data of the user in response to the stimulus information collected by the EEG collector; At the end of the stimulation information, a second label value is sent to the trigger, so that the trigger sends the second label value to the EEG collector and drives the EEG collector to insert the second label value into the end of the resonant EEG data; At a preset time after the stimulus information ends, a third tag value is sent to the trigger, so that the trigger sends the third tag value to the EEG collector and drives the EEG collector to insert the third tag value into the EEG data of the user collected by the EEG collector; Receive the EEG data sent by the EEG acquisition device, and decode the EEG data to obtain decoded stimulus information; Standard stimulus information is obtained based on one or more of the first label value, the second label value, and the third label value; wherein one or more of the first label value, the second label value, and the third label value includes a stimulus information identifier; The standard stimulus information is compared with the decoded stimulus information to determine whether the decoding is correct.

5. The EEG data trigger event labeling method according to claim 4, characterized in that, One or more of the first label value, the second label value, and the third label value are determined by a stimulus encoding mapping table, which includes the first label value and / or the second label value and / or the third label value corresponding to each stimulus information.

6. A brainwave data trigger event labeling device, characterized in that, include: The first tag sending module is used to send a first tag value to a trigger when the stimulus information begins, so that the trigger sends the first tag value to the EEG collector and drives the EEG collector to insert the first tag value into the beginning of the resonant EEG data, wherein the resonant EEG data is the EEG data of the user in response to the stimulus information collected by the EEG collector. The second tag sending module is used to send a second tag value to the trigger when the stimulus information ends, so that the trigger sends the second tag value to the EEG collector and drives the EEG collector to insert the second tag value into the end of the resonant EEG data. The third tag sending module is used to send a third tag value to the trigger at a preset time after the end of the stimulus information, so that the trigger sends the third tag value to the EEG collector and drives the EEG collector to insert the third tag value into the EEG data of the user collected by the EEG collector. The decoding module is used to receive the EEG data sent by the EEG acquisition device and decode the EEG data to obtain decoded stimulus information. The acquisition module is configured to acquire standard stimulus information based on one or more of the first label value, the second label value, and the third label value, wherein one or more of the first label value, the second label value, and the third label value includes a stimulus information identifier; The comparison module is used to compare the standard stimulus information with the decoded stimulus information to determine whether the decoding is correct.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory that stores instructions that, when executed by the at least one processor, cause the at least one processor to perform the EEG data trigger event labeling method as described in claim 4 or 5.

8. A machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the EEG data trigger event labeling method as described in claim 4 or 5.

Images