CN115344122B - Acoustic non-invasive brain-computer interface and control method - Google Patents

Abstract

The invention discloses a sound wave noninvasive brain-computer interface and a control method, wherein the brain-computer interface comprises the following components: the device comprises an ultrasonic cerebral blood flow imaging module, an analysis control module and execution equipment; the ultrasonic cerebral blood flow imaging module is used for acquiring initial cerebral blood flow imaging information of a target object in real time and sending the initial cerebral blood flow imaging information to the analysis control module; the analysis control module is connected with the ultrasonic cerebral blood flow imaging module and is used for acquiring initial cerebral blood flow imaging information, determining a control signal according to the initial cerebral blood flow imaging information and sending the control signal to the execution equipment; wherein the execution device comprises an action device and/or an ultrasonic stimulation device; the execution device is connected with the analysis control module and used for receiving the control signal and executing response action according to the control signal. By the technical scheme provided by the embodiment of the invention, the effects of improving the instantaneity and the accuracy of the brain-computer interface and improving the space-time resolution of recognizing the neural activity in the brain are realized.

Description

Acoustic non-invasive brain-computer interface and control method

Technical Field

The present invention relates to the technical field of brain-computer interface, and in particular to an acoustic wave non-invasive brain-computer interface and a control method thereof.

Background technique

Brain-computer interface (BCI) is an artificial intelligence technology that achieves information interaction and functional integration between the brain and the computer by establishing a direct connection pathway between the nerves inside the brain and external devices with high biocompatibility.

At present, high-resolution brain-computer interfaces use electrode arrays, open the dura mater through brain surgery, and implant electrodes directly into the brain, which poses a high risk. Non-implantable brain-computer interfaces can use electroencephalography, magnetoencephalography, functional near-infrared spectroscopy, and functional magnetic resonance imaging to collect brain electrical signals. However, the EEG signals have problems with low signal-to-noise ratio and spatiotemporal resolution, magnetoencephalography and functional magnetic resonance imaging have problems with large system size, high price, and complex operation, and functional near-infrared spectroscopy has signal delays, resulting in poor real-time performance.

Summary of the invention

The present invention provides an acoustic wave non-invasive brain-computer interface and a control method, so as to improve the real-time and accuracy of the brain-computer interface, reduce the risk of the brain-computer interface, improve the spatiotemporal resolution of stimulating neurons inside the brain, and improve the spatiotemporal resolution of identifying neural activities inside the brain.

According to one aspect of the present invention, there is provided an acoustic wave non-invasive brain-computer interface, the brain-computer interface comprising: an ultrasonic cerebral blood flow imaging module, an analysis control module and an execution device; wherein:

The ultrasonic cerebral blood flow imaging module is used to non-invasively acquire the initial cerebral blood flow imaging information of the target object in real time, and send the cerebral blood flow imaging information to the analysis control module;

The analysis control module is connected to the ultrasonic cerebral blood flow imaging module, and is used to obtain the initial cerebral blood flow imaging information, determine a control signal according to the initial cerebral blood flow imaging information, and send the control signal to the execution device; wherein the execution device includes an action device and/or an ultrasonic stimulation device;

The execution device is connected to the analysis control module, and is used to receive the control signal and execute a response action according to the control signal.

According to another aspect of the present invention, a control method for an acoustic wave non-invasive brain-computer interface is provided, the method comprising:

Based on the ultrasonic cerebral blood flow imaging module, initial cerebral blood flow imaging information of the target object is acquired, and the initial cerebral blood flow imaging information is sent to the analysis control module;

Based on the analysis control module, the initial cerebral blood flow imaging information is obtained, a control signal is determined according to the initial cerebral blood flow imaging information, and the control signal is sent to an execution device; wherein the execution device includes an action device and/or an ultrasonic stimulation device;

Based on the execution device, the control signal is received, and a response action is executed according to the control signal.

The technical solution of the embodiment of the present invention obtains initial cerebral blood flow imaging information of the target object based on the ultrasonic cerebral blood flow imaging module, and sends the initial cerebral blood flow imaging information to the analysis control module, obtains the initial cerebral blood flow imaging information based on the analysis control module, determines a control signal according to the initial cerebral blood flow imaging information, and sends the control signal to the execution device, receives the control signal based on the execution device, and executes a response action according to the control signal, which solves the problems of high risk, poor real-time performance and low accuracy of invasive brain-computer interface, and achieves the effect of improving the real-time performance and accuracy of brain-computer interface, reducing the risk of brain-computer interface, and improving the spatiotemporal resolution of stimulating neurons in the brain and identifying the spatiotemporal resolution of neural activities in the brain.

It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

FIG1 is a schematic diagram of the structure of an acoustic wave non-invasive brain-computer interface provided by Embodiment 1 of the present invention;

FIG2 is a schematic diagram of the structure of an acoustic wave non-invasive brain-computer interface provided by Embodiment 2 of the present invention;

FIG3 is a schematic diagram of the structure of another acoustic wave non-invasive brain-computer interface provided by Embodiment 2 of the present invention;

FIG4 is a schematic diagram of the structure of another acoustic wave non-invasive brain-computer interface provided by Embodiment 2 of the present invention;

FIG5 is a flow chart of a control method for an acoustic non-invasive brain-computer interface provided in Embodiment 3 of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

It should be noted that the terms "initial", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

Embodiment 1

Figure 1 is a schematic diagram of the structure of an acoustic wave non-invasive brain-computer interface provided in Example 1 of the present invention. This embodiment can be applied to situations where neural regulation is performed through ultrasonic stimulation, and then the execution device is controlled to perform a response action. The brain-computer interface can execute the control method of the acoustic wave non-invasive brain-computer interface. The acoustic wave non-invasive brain-computer interface can be implemented in the form of hardware and/or software, and the acoustic wave non-invasive brain-computer interface can be configured in an electronic device.

As shown in FIG1 , the brain-computer interface includes: an ultrasonic cerebral blood flow imaging module 1 , an analysis control module 2 and an execution device 3 .

Among them, the ultrasonic cerebral blood flow imaging module 1 is used to obtain the initial cerebral blood flow imaging information of the target object in real time, and send the initial cerebral blood flow imaging information to the analysis control module 2; the analysis control module 2 is connected to the ultrasonic cerebral blood flow imaging module 1, and is used to obtain the initial cerebral blood flow imaging information, determine the control signal according to the initial cerebral blood flow imaging information, and send the control signal to the execution device 3; wherein the execution device 3 includes an action device 31 and/or an ultrasonic stimulation device 32; the execution device 3 is connected to the analysis control module 2, and is used to receive the control signal and perform a response action according to the control signal.

The ultrasonic cerebral blood flow imaging module 1 is used to obtain the initial cerebral blood flow imaging information of the target object in real time, and send the initial cerebral blood flow imaging information to the analysis control module 2.

The target object may be an object that performs a response action through the neural control execution device 3, and may also be understood as an object that performs subsequent ultrasonic neural regulation, which may be a person or an animal, etc. The action intention may be a subsequent action performed by the control execution device 5. The initial cerebral blood flow imaging information may be related information of a three-dimensional cerebral blood flow map acquired through ultrasonic non-invasive brain function imaging, such as Doppler imaging or super-resolution imaging.

Specifically, the cerebral blood flow imaging information of the target object can be collected and read by non-invasive ultrasonic brain function imaging, that is, the initial cerebral blood flow imaging information. Then, the initial cerebral blood flow imaging information is sent to the analysis control module 2 for further analysis and processing.

The analysis control module 2 is used to obtain initial cerebral blood flow imaging information, determine a control signal according to the initial cerebral blood flow imaging information, and send the control signal to the execution device 3.

Among them, the execution device 3 can be a device for performing a response action in response to the control signal, and the execution device 3 includes an action device 31 and/or an ultrasonic stimulation device 32. The action device 31 can be at least one of a voice device, a mechanical arm, and a wheelchair. The ultrasonic stimulation device 32 can be a device for triggering subsequent ultrasonic nerve regulation actions. The control signal can be a signal for controlling the execution device 3 to perform a response action, and can be a signal obtained by converting the initial cerebral blood flow imaging information.

It should be noted that the voice device may be a device capable of outputting voice information. The robot arm may be a robot arm, which is usually a programmable device having similar functions to a human arm. The wheelchair may be an electric wheelchair, which may be a device that moves according to an external control signal.

Specifically, the analysis control module 2 can receive the initial cerebral blood flow imaging information sent by the ultrasonic cerebral blood flow imaging module 1. Furthermore, the analysis control module 2 can analyze the initial cerebral blood flow imaging information, for example, it can process the initial cerebral blood flow imaging information through a pre-established analysis model, etc., to obtain a control signal, and send the control signal to the execution device 3 to control the execution device 3 to execute a response action.

Exemplarily, the initial cerebral blood flow imaging information may be processed, for example, by improving the signal-to-noise ratio through preprocessing, obtaining characteristic values through feature extraction, etc. A model for identifying the relationship between cerebral blood flow signals and control signals is pre-established through machine learning or artificial intelligence, and the initial cerebral blood flow imaging information is input into the model, so that a control signal corresponding to the initial cerebral blood flow imaging information can be obtained.

The execution device 3 is used to receive the control signal and execute a response action according to the control signal.

The response action may be an action executed by the execution device 3 .

Specifically, the execution device 3 may receive the control signal sent by the analysis control module 2 and respond to the control signal. In this case, the execution device 3 may execute the response action corresponding to the control signal.

Optionally, when the execution device 3 is an ultrasonic stimulation device 32, the ultrasonic stimulation device 32 is used to:

A control signal is received, an ultrasonic stimulation parameter corresponding to the control signal is determined according to the control signal, and ultrasonic stimulation is performed on the target object according to the ultrasonic stimulation parameter.

Among them, the ultrasonic stimulation parameters include ultrasonic frequency, pulse length, pulse repetition frequency, duty cycle, sound pressure, stimulation time, etc.

Specifically, the ultrasonic stimulation device 32 can receive the control signal sent by the analysis control module 2. Then, the ultrasonic stimulation parameters required for the ultrasonic stimulation to be performed are determined according to the control signal, and the target object can be ultrasonically stimulated according to the ultrasonic stimulation parameters to regulate brain nerve activity through ultrasonic stimulation.

The technical solution of the embodiment of the present invention obtains initial cerebral blood flow imaging information of the target object based on the ultrasonic cerebral blood flow imaging module, and sends the initial cerebral blood flow imaging information to the analysis control module, obtains the initial cerebral blood flow imaging information based on the analysis control module, determines a control signal according to the initial cerebral blood flow imaging information, and sends the control signal to the execution device, receives the control signal based on the execution device, and executes a response action according to the control signal, which solves the problems of high risk, poor real-time performance and low accuracy of invasive brain-computer interface, and achieves the effect of improving the real-time performance and accuracy of brain-computer interface, reducing the risk of brain-computer interface, and improving the spatiotemporal resolution of stimulating neurons in the brain and identifying the spatiotemporal resolution of neural activities in the brain.

Embodiment 2

FIG2 is a schematic diagram of the structure of an acoustic non-invasive brain-computer interface provided by the second embodiment of the present invention. On the basis of the above-mentioned embodiment, the initial EEG information of the target object can be collected by the EEG information collection module so as to control the execution of the device action according to the parameter EEG signal. The specific implementation method can refer to the detailed description of the technical solution. The explanation of the terms that are the same or corresponding to the above-mentioned embodiments will not be repeated here.

As shown in FIG. 2 , the brain-computer interface includes: an ultrasonic cerebral blood flow imaging module 1 , an analysis control module 2 , and an execution device 3 , and also includes: an electroencephalogram information acquisition module 4 .

The EEG information acquisition module 4 is used to obtain the initial EEG information of the target object and send the initial EEG information to the analysis control module 2 .

The initial EEG information may be information related to EEG signals collected by an EEG device, or may be information related to EEG signals collected by an EEG device.

Specifically, the EEG information acquisition module 4 can acquire and read the EEG signal of the target object to obtain the initial EEG information, and then send the initial EEG information to the analysis control module 2 so that the analysis control module 2 can analyze and subsequently control the initial EEG information.

It should be noted that relevant information on brain neural activity can also be obtained through magnetoencephalography, functional near-infrared spectroscopy, and functional magnetic resonance imaging, and the process is similar to obtaining initial cerebral blood flow imaging information and initial EEG information. Therefore, it is not specifically described in this embodiment.

Correspondingly, the analysis control module 2 is also used for:

Acquire initial EEG information, determine a control signal based on the initial EEG information, and send the control signal to the execution device 3.

Specifically, the analysis control module 2 can receive the initial EEG information sent by the EEG information acquisition module 4. Further, the initial EEG information can be processed, for example: improving the signal-to-noise ratio through preprocessing, obtaining feature values through feature extraction, etc. A model for identifying the relationship between EEG signals and action intentions is pre-established through machine learning or artificial intelligence, and the processing results are input into the model to obtain a control signal corresponding to the initial EEG information. Then, the control signal is sent to the execution device 3 to control the execution device 3 to perform a response action.

Based on the above example, after acquiring the initial EEG information, the analysis control module 2 can also integrate the initial EEG information and the initial cerebral blood flow imaging information to obtain a more accurate control signal. The analysis control module 2 is also used to:

Initial cerebral blood flow imaging information and initial electroencephalogram information are obtained, a control signal is determined according to the initial cerebral blood flow imaging information and the initial electroencephalogram information, and the control signal is sent to the execution device 3.

Specifically, the analysis control module 2 can receive the parameter cerebral blood flow imaging information sent by the ultrasonic cerebral blood flow imaging module 1, and receive the initial EEG information sent by the EEG information acquisition module 4, and perform a comprehensive analysis on the initial cerebral blood flow imaging information and the initial EEG information. For example, the initial cerebral blood flow imaging information and the initial EEG information can be jointly processed through a pre-established analysis model, etc., to obtain a control signal, and the control signal is sent to the execution device 3 to control the execution device 3 to perform a response action.

FIG3 is a schematic diagram of the structure of another acoustic non-invasive brain-computer interface provided by the second embodiment of the present invention. Based on the above embodiment, the specific structure of the analysis control module and the ultrasonic stimulation device can refer to the detailed description of the technical solution. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

As shown in FIG3 , the brain-computer interface includes: an ultrasonic cerebral blood flow imaging module 1, an analysis control module 2 and an execution device 3. The analysis control module 2 includes: a preprocessing and feature extraction unit 21, a control signal determination unit 22 and a control signal output unit 23.

The preprocessing and feature extraction unit 21 is used to obtain initial cerebral blood flow imaging information, preprocess the initial cerebral blood flow imaging information, perform feature extraction on the preprocessed initial cerebral blood flow imaging information, determine feature information corresponding to the initial cerebral blood flow imaging information, and send the feature information to the control signal determination unit 22.

The characteristic information may be a characteristic value obtained by extracting the characteristic of parameter cerebral blood flow imaging information, and is used to describe the brain nerve movement of the target object.

Specifically, the preprocessing and feature extraction unit 21 can preprocess the received parameter cerebral blood flow imaging information to remove artifacts, remove power frequency, etc., which can be amplification, filtering, analog-to-digital conversion, etc., to obtain preprocessed initial cerebral blood flow imaging information. Further, feature extraction can be performed on the preprocessed initial cerebral blood flow imaging information through feature extraction methods such as time domain, frequency domain, and spatial domain to obtain feature information, and the feature information is sent to the control signal determination unit 22.

The control signal determination unit 22 is connected to the preprocessing and feature extraction unit 21, and is used to obtain feature information, and input the feature information into a pre-established cerebral blood flow signal classification model to obtain an initial control signal corresponding to the initial cerebral blood flow imaging information, and send the initial control signal to the control signal output unit 23.

Among them, the cerebral blood flow signal classification model can be a model for analyzing the control signal corresponding to the characteristic information of the cerebral blood flow image information, and can be a machine learning model, a deep learning model, an artificial intelligence model, etc. It should be noted that the cerebral blood flow signal classification model can be a model trained based on sample cerebral blood flow image information, characteristic information corresponding to the sample cerebral blood flow image information, and control signals corresponding to the sample cerebral blood flow image information, so as to identify and classify the characteristic information through the cerebral blood flow signal classification model, and determine the control signal corresponding to the characteristic information, that is, the initial control signal. The initial control signal can be a signal output by the cerebral blood flow signal classification model, which is used to indicate the control intention, rather than a control signal that can be recognized by different types of execution devices 3.

Specifically, the control signal determination unit 22 can receive the feature information sent by the preprocessing and feature extraction unit 21, and input the feature information into a pre-established cerebral blood flow signal classification model to obtain an output result, which is an initial control signal corresponding to the initial cerebral blood flow imaging information. Then, the initial control signal is sent to the control signal output unit 23.

The control signal output unit 23 is connected to the control signal determination unit 22 , and is used to receive the initial control signal, convert the initial control signal into a target control signal corresponding to the execution device 3 , and send the target control signal to the execution device 3 .

The target control signal may be a signal determined according to the initial control signal for controlling the execution device 3 to execute a response action, which may be understood as a specific instruction for controlling the execution device 3 and may be recognized by the execution device 3. For example, the execution device 3 is a robotic arm, and the initial control signal is upward, then the target control signal may be an instruction signal for controlling the robotic arm to lift upward.

Specifically, the control signal output unit 23 may receive the initial control signal sent by the control signal determination unit 22, and determine the target control signal for controlling the execution device 3 to perform an action according to the initial control signal, which may be determined according to the pre-established correspondence between the initial control signal and the target control signal. Then, the target control signal is sent to the execution device 3 to control the execution device 3 to perform a response action.

Optionally, as shown in FIG. 3 , the execution device 3 includes an ultrasonic stimulation device 32 , and the ultrasonic stimulation device 32 includes: an ultrasonic stimulation parameter determination unit 321 and an ultrasonic transmitter 322 .

The ultrasonic stimulation parameter determination unit 321 is used to receive the control signal, and determine the ultrasonic stimulation parameters corresponding to the control signal according to the pre-established correspondence between the control signal and the ultrasonic stimulation parameters, and set the parameters of the ultrasonic transmitter 322 according to the ultrasonic stimulation parameters.

It should be noted that a correspondence between control signals and ultrasonic stimulation parameters can be established in advance. For example, a correspondence between control signals and ultrasonic frequencies can be established. The pulse length, pulse repetition frequency, duty cycle, sound pressure, stimulation time, etc. used for ultrasonic stimulation can also be established so as to better regulate brain neural activity through ultrasonic stimulation.

Specifically, the ultrasonic stimulation parameter determination unit 321 can receive the control signal sent by the analysis control module 2, and determine the ultrasonic stimulation parameter corresponding to the control signal according to the pre-established correspondence between the control signal and the ultrasonic stimulation parameter, so as to subsequently perform ultrasonic stimulation on the target object according to the ultrasonic stimulation parameter. Furthermore, the ultrasonic transmitter 322 can be parameterized according to the ultrasonic stimulation parameter so that the ultrasonic wave emitted by the ultrasonic transmitter 322 is consistent with the demand.

It should also be noted that if certain ultrasonic stimulation parameters cannot be determined, the default parameter values can be used for setting, and adjustments can be made during subsequent stimulation and feedback, and the correspondence between the control signal and the ultrasonic stimulation parameters can be updated according to the adjusted parameter values.

The ultrasonic transmitter 322 is connected to the ultrasonic stimulation parameter determination unit 321 and is used to perform ultrasonic stimulation on the target object when the parameter setting is completed.

Specifically, after setting the parameters of the ultrasonic transmitter 322, ultrasonic stimulation can be performed on the target part of the target object (such as the brain) through the ultrasonic transmitter 322 to cause the brain neural activity of the target object to correspond to the control signal, thereby regulating the brain neural activity.

It should be noted that after the ultrasonic stimulation parameters are determined by the response action performed by the ultrasonic stimulation device 32 and the target object is ultrasonically stimulated, the target cerebral blood flow imaging information during the ultrasonic stimulation can be further obtained by the ultrasonic cerebral blood flow imaging module 1 to determine whether to continue to perform neural regulation on the target object through the ultrasonic stimulation device 32. Therefore, a closed-loop brain-computer interface can be realized through the above technical solution.

Optionally, the ultrasonic cerebral blood flow imaging module 1 is also used for:

The target cerebral blood flow imaging information is acquired when the ultrasonic stimulation device 321 performs ultrasonic stimulation on the target object.

The target cerebral blood flow imaging information may be related information of a three-dimensional cerebral blood flow map acquired by ultrasonic non-invasive brain function imaging, such as Doppler imaging or super-resolution imaging, when the target object is subjected to ultrasonic stimulation.

Specifically, when the ultrasonic stimulation device 321 performs ultrasonic stimulation on the target object, the ultrasonic cerebral blood flow imaging module 1 can obtain the target cerebral blood flow imaging information non-invasively and in real time.

Optionally, the parsing control module 2 is further used for:

The target cerebral blood flow imaging information is acquired. When the target cerebral blood flow imaging information does not meet the preset condition, the control signal is updated according to the target cerebral blood flow imaging information, and the updated control signal is sent to the ultrasonic stimulation device 321 .

The preset condition may be a pre-set condition for stopping the ultrasonic stimulation device 321 from continuing the ultrasonic stimulation, such as an epilepsy detection condition.

Specifically, the target cerebral blood flow imaging information sent by the ultrasonic cerebral blood flow imaging module 1 is obtained, and it is determined whether the target cerebral blood flow imaging information meets the preset conditions. If so, the control signal is stopped from being generated, and the ultrasonic regulation of the target object is stopped. If not, the control signal corresponding to the target cerebral blood flow imaging information is determined according to the target cerebral blood flow imaging information to update the control signal. Then, the updated control signal can be sent to the ultrasonic stimulation device 321 to perform ultrasonic regulation on the target object through the ultrasonic stimulation device 321.

It should be noted that the process of determining the control signal corresponding to the target cerebral blood flow imaging information is similar to the process of determining the control signal corresponding to the initial cerebral blood flow imaging information, which will not be described in detail here.

Exemplarily, the initial cerebral blood flow imaging information of the target object is obtained through the ultrasonic cerebral blood flow imaging module 1, and the analysis control module 2 analyzes the initial cerebral blood flow imaging information to determine that the target object is currently in an epileptic seizure state, and generates an epilepsy control signal to send to the ultrasonic stimulation device 321, so as to perform neurological regulation on the target object through the ultrasonic stimulation device 321. Then, the target cerebral blood flow imaging information of the target object is continuously and in real time obtained through the ultrasonic cerebral blood flow imaging module 1, and the analysis control module 2 analyzes the target cerebral blood flow imaging information to determine whether the target object is still in an epileptic seizure state. If so, the epilepsy control signal is continuously generated and sent to the ultrasonic stimulation device 321, so as to perform neurological regulation on the target object through the ultrasonic stimulation device 321. If not, it indicates that the target object has returned to normal and subsequent operations can be stopped.

FIG4 is a schematic diagram of the structure of another acoustic wave non-invasive brain-computer interface provided in Embodiment 2 of the present invention.

As shown in FIG. 4 , the brain-computer interface includes: a signal acquisition module, a brain nerve signal preprocessing and feature extraction module, a cerebral blood flow signal classification module, a control output module and a non-invasive neural encoding module.

Signal acquisition module: It realizes the real-time acquisition and reading of brain neural activity signals. It can use non-invasive ultrasonic brain function imaging (Doppler imaging, super-resolution imaging, etc.) to read the brain's cerebral blood flow signals (initial cerebral blood flow imaging information or target cerebral blood flow imaging information). The signal acquisition module can also be used to collect cerebral blood flow signals and other EEG signals, near-infrared and other imaging signals to perform multi-modal brain neural signal acquisition.

Cerebral nerve signal preprocessing and feature extraction module: preprocess the cerebral blood flow signal read by the signal acquisition module to improve the signal-to-noise ratio and provide high signal-to-noise ratio data for feature extraction. Then, extract the characteristic value (feature information) corresponding to the preprocessed cerebral blood flow signal.

Cerebral blood flow signal classification module: Use machine learning or artificial intelligence methods to establish the relationship between cerebral blood flow signal characteristics and control signals, and determine the control signal (initial control signal) corresponding to the characteristic value output by the brain nerve signal preprocessing and feature extraction module.

Control output module: converts the control signal output by the above-mentioned cerebral blood flow signal classification module into a specific instruction (target control signal) for controlling an external device (executing device) to realize the control of the external device. The control output module may include external devices such as voice modules, prostheses, wheelchairs, etc. The external device responds to the specific instruction and performs the corresponding action (response action).

Non-invasive neural coding module: Use external devices to control ultrasound to stimulate the brain and regulate central nervous system activity. Specifically, ultrasound stimulation parameters can be determined based on the response actions performed by the external device to perform ultrasound stimulation.

Through the above-mentioned acoustic non-invasive brain-computer interface, non-invasive ultrasonic brain functional imaging technology can be used to read the brain's neural activity in real time and dynamically, and then converted into a signal that can be recognized by the computer through amplification, filtering, analog-to-digital conversion and other processing. Further, the signal is pre-processed and characteristic signals are extracted. These characteristic signals are then used for pattern recognition and decoding of neural information. Finally, the neural information is converted into specific instructions for controlling external devices to achieve control of external devices.

Through the above-mentioned acoustic wave non-invasive brain-computer interface, it is also possible to use existing neural information reading technologies such as electroencephalograms to read brain neural activity in real time and dynamically, and then convert it into a signal that can be recognized by the computer through amplification, filtering, analog-to-digital conversion and other processing. Further, the signal is pre-processed to extract characteristic signals, and then these characteristic signals are used for pattern recognition, decoding neural information, and finally the neural information is converted into specific instructions to control external devices, and the external devices respond to the instructions and perform response actions. The response action of the external device can trigger the non-invasive ultrasonic neural regulation technology, perform ultrasonic stimulation on the target object, achieve "recoding" of brain neural activity, and realize a closed-loop brain-computer interface.

Through the above-mentioned acoustic wave non-invasive brain-computer interface, non-invasive ultrasonic brain functional imaging technology can also be used to read the brain's neural activity in real time and dynamically, and then converted into a signal that can be recognized by the computer through amplification, filtering, analog-to-digital conversion and other processing. Further, the signal is pre-processed and characteristic signals are extracted, and then these characteristic signals are used for pattern recognition, decoding neural information, and converting neural information into specific instructions to control external devices. The external device responds to the instructions and performs response actions. The response action of the external device can trigger the non-invasive ultrasonic neural regulation technology, perform ultrasonic stimulation on the target object, achieve "recoding" of brain neural activity, and realize a non-invasive ultrasonic closed-loop brain-computer interface.

The technical solution of the embodiment of the present invention obtains the initial EEG information of the target object based on the EEG information acquisition module, and sends the initial EEG information to the analysis control module, obtains the initial EEG information based on the analysis control module, determines the control signal according to the initial EEG information, and sends the control signal to the execution device, which solves the problems of single method of obtaining neural signals inside the brain and inaccurate analysis, and achieves the improvement of the accuracy of brain neural signal analysis, thereby improving the accuracy of brain-computer interface, and improving the effect of improving the spatiotemporal resolution of neural activities in the brain.

Embodiment 3

FIG5 is a flow chart of a control method of an acoustic wave non-invasive brain-computer interface provided in Embodiment 3 of the present invention. As shown in FIG5 , the method is applied to an acoustic wave non-invasive brain-computer interface, and the acoustic wave non-invasive brain-computer interface includes: an ultrasonic cerebral blood flow imaging module, an analysis control module, and an execution device. The method includes:

S510: Based on the ultrasonic cerebral blood flow imaging module, initial cerebral blood flow imaging information of the target object is obtained, and the initial cerebral blood flow imaging information is sent to the analysis control module.

S520: Based on the analysis control module, initial cerebral blood flow imaging information is obtained, a control signal is determined according to the initial cerebral blood flow imaging information, and the control signal is sent to the execution device.

Among them, the execution device includes an action device and/or an ultrasonic stimulation device.

S530: Based on the execution device, receive the control signal and execute a response action according to the control signal.

Optionally, the execution device includes an ultrasonic stimulation device, and the method further includes: based on the ultrasonic stimulation device, receiving the control signal, determining ultrasonic stimulation parameters corresponding to the control signal according to the control signal, and performing ultrasonic stimulation on the target object according to the ultrasonic stimulation parameters.

Optionally, the ultrasonic stimulation device includes: an ultrasonic stimulation parameter determination unit and an ultrasonic transmitter, and the method further includes: based on the ultrasonic stimulation parameter determination unit, receiving the control signal, and determining the ultrasonic stimulation parameters according to a pre-established correspondence between the control signal and the ultrasonic stimulation parameters, and setting parameters of the ultrasonic transmitter according to the ultrasonic stimulation parameters; based on the ultrasonic transmitter, when the parameter setting is completed, performing ultrasonic stimulation on the target object.

Optionally, the method further includes: based on an ultrasonic cerebral blood flow imaging module, acquiring target cerebral blood flow imaging information when the ultrasonic stimulation device performs ultrasonic stimulation on the target object.

Optionally, the method further includes: based on the analysis control module, obtaining the target cerebral blood flow imaging information, and when the target cerebral blood flow imaging information does not meet a preset condition, updating the control signal according to the target cerebral blood flow imaging information, and sending the updated control signal to the ultrasonic stimulation device.

Optionally, the brain-computer interface also includes: an EEG information acquisition module; the method also includes: based on the EEG information acquisition module, acquiring initial EEG information of the target object, and sending the initial EEG information to the analysis and control module; correspondingly, it also includes: based on the analysis and control module, acquiring the initial EEG information, determining a control signal based on the initial EEG information, and sending the control signal to the execution device.

Optionally, the brain-computer interface also includes: an EEG information acquisition module; the method also includes: based on the analysis control module, obtaining the initial cerebral blood flow imaging information and the initial EEG information, determining a control signal according to the initial cerebral blood flow imaging information and the initial EEG information, and sending the control signal to the execution device.

Optionally, the analysis control module includes: a preprocessing and feature extraction unit, a control signal determination unit and a control signal output unit; the method also includes: based on the preprocessing and feature extraction unit, acquiring the initial cerebral blood flow imaging information, preprocessing the initial cerebral blood flow imaging information, and extracting features from the preprocessed initial cerebral blood flow imaging information, determining feature information corresponding to the initial cerebral blood flow imaging information, and sending the feature information to the control signal determination unit; based on the control signal determination unit, acquiring the feature information, and inputting the feature information into a pre-established cerebral blood flow signal classification model to obtain an initial control signal corresponding to the initial cerebral blood flow imaging information, and sending the initial control signal to the control signal output unit; based on the control signal output unit, receiving the initial control signal, converting the initial control signal into a target control signal corresponding to the execution device, and sending the target control signal to the execution device.

Optionally, the execution device includes an action device, and the action device includes at least one of a voice device, a robotic arm and a wheelchair.

The technical solution of the embodiment of the present invention obtains initial cerebral blood flow imaging information of the target object based on the ultrasonic cerebral blood flow imaging module, and sends the initial cerebral blood flow imaging information to the analysis control module, obtains the initial cerebral blood flow imaging information based on the analysis control module, determines a control signal according to the initial cerebral blood flow imaging information, and sends the control signal to the execution device, receives the control signal based on the execution device, and executes a response action according to the control signal, which solves the problems of high risk, poor real-time performance and low accuracy of invasive brain-computer interface, and achieves the effect of improving the real-time performance and accuracy of brain-computer interface, reducing the risk of brain-computer interface, and improving the spatiotemporal resolution of stimulating neurons in the brain and identifying the spatiotemporal resolution of neural activities in the brain.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. An acoustic wave noninvasive brain-computer interface, comprising: the device comprises an ultrasonic cerebral blood flow imaging module, an analysis control module and execution equipment; wherein,

The ultrasonic cerebral blood flow imaging module is used for acquiring initial cerebral blood flow imaging information of a target object in real time and sending the initial cerebral blood flow imaging information to the analysis control module;

The analysis control module is connected with the ultrasonic cerebral blood flow imaging module and is used for acquiring the initial cerebral blood flow imaging information, determining a control signal according to the initial cerebral blood flow imaging information and sending the control signal to the execution equipment; wherein the execution device comprises an action device and/or an ultrasonic stimulation device;

The execution device is connected with the analysis control module and is used for receiving the control signal and executing response action according to the control signal;

the execution device comprises an ultrasonic stimulation device for:

Determining ultrasonic stimulation parameters according to response actions executed by the execution equipment, and performing ultrasonic stimulation on the target object according to the ultrasonic stimulation parameters;

The ultrasonic cerebral blood flow imaging module is further used for:

Acquiring target cerebral blood flow imaging information based on ultrasonic stimulation of the ultrasonic stimulation equipment on the target object, wherein the target cerebral blood flow imaging information can be related information of a three-dimensional cerebral blood flow chart acquired by the ultrasonic cerebral blood flow imaging module when the ultrasonic stimulation is carried out on the target object;

the analysis control module is further configured to:

acquiring the target cerebral blood flow imaging information, updating the control signal according to the target cerebral blood flow imaging information under the condition that the target cerebral blood flow imaging information does not meet the preset condition, and sending the updated control signal to the ultrasonic stimulation equipment.

2. The brain-computer interface according to claim 1, wherein the ultrasound stimulation device is further configured to:

and receiving the control signal, determining ultrasonic stimulation parameters corresponding to the control signal according to the control signal, and performing ultrasonic stimulation on the target object according to the ultrasonic stimulation parameters.

3. The brain-computer interface according to claim 2, wherein the ultrasound stimulation device comprises: an ultrasonic stimulation parameter determination unit and an ultrasonic transmitter; wherein,

The ultrasonic stimulation parameter determining unit is used for receiving the control signal, determining ultrasonic stimulation parameters according to the corresponding relation between the control signal and the ultrasonic stimulation parameters, and setting parameters of the ultrasonic transmitter according to the ultrasonic stimulation parameters;

The ultrasonic transmitter is connected with the ultrasonic stimulation parameter determining unit and is used for carrying out ultrasonic stimulation on the target object when parameter setting is completed.

4. The brain-computer interface according to claim 1, further comprising: a brain electricity acquisition module; wherein,

The electroencephalogram information acquisition module is used for acquiring initial electroencephalogram information of a target object and sending the initial electroencephalogram information to the analysis control module;

correspondingly, the analysis control module is further used for:

And acquiring the initial electroencephalogram information, determining a control signal according to the initial electroencephalogram information, and sending the control signal to an execution device.

5. The brain-computer interface according to claim 4, wherein the parsing control module is further configured to:

And acquiring the initial cerebral blood flow imaging information and the initial cerebral electricity information, determining a control signal according to the initial cerebral blood flow imaging information and the initial cerebral electricity information, and sending the control signal to an execution device.

6. The brain-computer interface according to claim 1, wherein the parsing control module comprises: the device comprises a preprocessing and feature extraction unit, a control signal determination unit and a control signal output unit; wherein,

The preprocessing and feature extraction unit is used for acquiring the initial cerebral blood flow imaging information, preprocessing the initial cerebral blood flow imaging information, extracting features of the preprocessed initial cerebral blood flow imaging information, determining feature information corresponding to the initial cerebral blood flow imaging information, and sending the feature information to the control signal determination unit;

The control signal determining unit is connected with the preprocessing and feature extracting unit and is used for acquiring the feature information, inputting the feature information into a pre-established cerebral blood flow signal classification model, obtaining an initial control signal corresponding to the initial cerebral blood flow imaging information and sending the initial control signal to the control signal output unit;

the control signal output unit is connected with the control signal determining unit and is used for receiving the initial control signal, converting the initial control signal into a target control signal corresponding to the execution equipment and sending the target control signal to the execution equipment.

7. The brain-computer interface according to claim 1, wherein the execution device comprises an action device comprising at least one of a voice device, a robotic arm, and a wheelchair.

8. A method for controlling an acoustic non-invasive brain-computer interface, comprising:

Based on an ultrasonic cerebral blood flow imaging module, acquiring initial cerebral blood flow imaging information of a target object, and sending the initial cerebral blood flow imaging information to an analysis control module;

based on the analysis control module, acquiring the initial cerebral blood flow imaging information, determining a control signal according to the initial cerebral blood flow imaging information, and sending the control signal to an execution device; wherein the execution device comprises an action device and/or an ultrasonic stimulation device;

Based on the execution device, receiving the control signal and executing a response action according to the control signal;

the execution device comprises an ultrasonic stimulation device for:

Determining ultrasonic stimulation parameters according to response actions executed by the execution equipment, and performing ultrasonic stimulation on the target object according to the ultrasonic stimulation parameters;

The ultrasonic cerebral blood flow imaging module is further used for:

Acquiring target cerebral blood flow imaging information based on ultrasonic stimulation of the ultrasonic stimulation equipment on the target object, wherein the target cerebral blood flow imaging information can be related information of a three-dimensional cerebral blood flow chart acquired by the ultrasonic cerebral blood flow imaging module when the ultrasonic stimulation is carried out on the target object;

the analysis control module is further configured to:

acquiring the target cerebral blood flow imaging information, updating the control signal according to the target cerebral blood flow imaging information under the condition that the target cerebral blood flow imaging information does not meet the preset condition, and sending the updated control signal to the ultrasonic stimulation equipment.