CN115607168A - Control method and device based on electroencephalogram signal, electronic equipment and storage medium - Google Patents

Abstract

The invention discloses a control method and device based on an electroencephalogram signal, electronic equipment and a storage medium. The method comprises the following steps: acquiring an electroencephalogram signal of a target object, and extracting a target category identification characteristic parameter corresponding to a target category identification characteristic in the electroencephalogram signal; determining a default trace identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal; and determining the action state of the target object based on the violation identification result, and executing the processing operation corresponding to the action state. The signal artifacts of the electroencephalogram signals are classified through the predetermined target class identification features and the target class reference parameters, the complexity of the algorithm is reduced, the problem that the existing electromyogram classification algorithm cannot be embedded into a chip is solved, and control operation based on the classes of the electroencephalogram signals and the artifacts is achieved.

Description

Control method and device based on electroencephalogram signal, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of electroencephalogram signal analysis and processing, in particular to a control method and device based on electroencephalogram signals, electronic equipment and a storage medium.

Background

The electroencephalogram signals are very weak relative to other kinds of physiological signals, and the amplitude is in the magnitude order of microvolts. In the process of collecting the electroencephalogram signals, environmental interference or human interference is inevitably introduced to influence the quality of the electroencephalogram signals.

At present, most of common electromyography classification algorithms finish detailed electromyography classification tasks based on a wireless surface electromyography test system, such as judgment of arm moment and direction, and distinction of captured target shapes. However, the existing electromyography analysis algorithms all need a set of complete electromyography signal acquisition system, and the cost is high; and most of the development of the myoelectric classification algorithm is based on common machine learning or deep learning models, and the myoelectric classification algorithm cannot be embedded into a chip in order to meet the demand of computing power. Therefore, it is difficult to implement electroencephalogram signal-based control in a computer device.

Disclosure of Invention

The embodiment of the invention aims to solve the technical problem that the existing myoelectricity classification algorithm cannot be embedded into a chip, so that control based on electroencephalogram signals is difficult to realize.

According to an aspect of the present invention, there is provided a control method based on an electroencephalogram signal, including:

acquiring an electroencephalogram signal of a target object, and extracting a target category identification characteristic parameter corresponding to a target category identification characteristic in the electroencephalogram signal;

determining a default trace identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal;

and determining the action state of the target object based on the identification result of the violation, and executing the processing operation corresponding to the action state.

According to another aspect of the present invention, there is provided a brain electrical signal-based control apparatus including:

the identification feature extraction module is used for acquiring an electroencephalogram signal of a target object and extracting a target category identification feature parameter corresponding to a target category identification feature in the electroencephalogram signal;

the device comprises a default trace identification result determining module, a default trace identification result determining module and a default trace identification result determining module, wherein the default trace identification result determining module is used for determining a default trace identification result in the electroencephalogram signal based on a target category identification characteristic parameter and a target category reference parameter, and the target category identification characteristic and the target category reference parameter are determined in advance based on a characteristic classification result of the sample electroencephalogram signal;

and the processing operation execution module is used for determining the action state of the target object based on the violation identification result and executing the processing operation corresponding to the action state.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the electroencephalogram signal-based control method of any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the electroencephalogram signal-based control method according to any one of the embodiments of the present invention when executed.

According to the technical scheme of the embodiment of the invention, the target category identification characteristic parameters corresponding to the target category identification characteristics in the electroencephalogram signals are extracted by acquiring the electroencephalogram signals of the target object; determining a default trace identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal; and determining the action state of the target object based on the violation identification result, and executing the processing operation corresponding to the action state. The signal artifacts of the electroencephalogram signals are classified through the predetermined target category identification features and the target category reference parameters, the complexity of the algorithm is reduced, the problem that the existing electromyogram classification algorithm cannot be embedded into a chip is solved, and control operation based on the categories of the electroencephalogram signals and the artifacts is achieved.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.

The invention will be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:

fig. 1 is a flowchart of a control method based on electroencephalogram signals according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for determining target feature extraction and target category reference parameters according to a second embodiment of the present invention;

FIG. 3 is a flowchart of a control method based on electroencephalogram signals according to a second embodiment of the present invention;

fig. 4 is a schematic structural diagram of a control device based on electroencephalogram signals according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention;

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Embodiments of the invention are applicable to computer systems/servers operable with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable for use with the computer system/server include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.

The computer system/server may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Example one

Fig. 1 is a flowchart of a control method based on an electroencephalogram signal according to an embodiment of the present invention, where the present embodiment is applicable to a situation when control is performed based on an electroencephalogram signal, the method may be executed by a control device based on an electroencephalogram signal and/or an electroencephalogram signal processing system, the control device based on an electroencephalogram signal and/or the control system based on an electroencephalogram signal may be implemented in a form of hardware and/or software, and the control device based on an electroencephalogram signal may be configured in an electronic device according to an embodiment of the present invention. As shown in fig. 1, the method includes:

s110, acquiring an electroencephalogram signal of a target object, and extracting a target category identification characteristic parameter corresponding to a target category identification characteristic in the electroencephalogram signal.

Wherein the target object may be an object that performs a control operation. The target object may be a user, provided that the movement of the actuator needs to be controlled according to the electroencephalogram signal of the user. The electroencephalogram signal can be an electroencephalogram signal which is acquired based on an electroencephalogram signal acquisition device and contains signal artifacts, wherein the signal artifacts are technical/biological artifacts (technical/biological artifacts) generated due to recording setting errors, good conductivity of scalp and the like in the electroencephalogram signal acquisition process, such as electric signals generated by active power line interference (power line interference), blinking (eye blink) and muscle activity (muscle activity), and are mixed with the electroencephalogram signal to generate interference on the acquisition of the electroencephalogram signal. It should be noted that, in the present embodiment, only biological artifacts in the electroencephalogram signal are classified.

The electroencephalogram signal acquisition device may be, but is not limited to, a brain-computer interface device. In this embodiment, an electroencephalogram signal is acquired by an electroencephalogram signal acquisition device to obtain an electroencephalogram signal to be classified, and then signal artifacts in the acquired electroencephalogram signal are classified to obtain the category of the signal artifacts in the electroencephalogram signal. By classifying the myoelectricity artifacts in the collected electroencephalogram signals, the facial expression, emotional state and the like of the user can be judged according to the category of the myoelectricity artifacts.

The target type identification characteristic is a preset characteristic capable of obviously distinguishing a target type and a non-target type of a contraband signal and is used for identifying the type of signal artifacts in an electroencephalogram signal, and optionally, the target type is at least one of a body electromyogram type, a facial electromyogram type and an eye electromyogram type. Taking the facial myoelectric category as an example of the target category, the facial myoelectric category of the electroencephalogram violation can be identified based on the extracted facial category identification characteristic parameters by extracting the facial category identification characteristic parameters corresponding to the facial category identification characteristics in the electroencephalogram signal.

In this embodiment, the parameters corresponding to the target category identification features in the electroencephalogram signal can be directly extracted as the target category identification feature parameters, and the extracted parameters can be further processed to obtain the target category identification feature parameters.

In one implementation, extracting a target category identification feature parameter corresponding to a target category identification feature in an electroencephalogram signal includes: performing feature extraction of target category identification features on the electroencephalogram signals to obtain extracted electroencephalogram features; and performing dimensionality reduction processing on the extracted electroencephalogram features to obtain target category identification feature parameters. Optionally, the extracted parameters may be used as extracted electroencephalogram features to perform dimension reduction processing, the extracted electroencephalogram features are reduced to a low-dimensional space to obtain target category identification feature parameters, and the electroencephalogram violation identification is performed through the target category identification parameters of the low-dimensional space. The low-dimensional space may be, but is not limited to, a two-dimensional space, a three-dimensional space, and the like. The dimension reduction processing method may be projection, non-negative matrix factorization, correlation analysis, and the like, and is not limited herein.

S120, determining a violation identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal.

And after the target class identification characteristic parameter is determined, calculating the distance between the target class identification characteristic parameter and the target class reference parameter, and identifying the multifunctional illegal trace according to the distance between the target class identification characteristic parameter and the target class reference parameter. Optionally, the target class reference parameter may include a class reference parameter and a non-class reference parameter. In this embodiment, the dimensions of the target category identification characteristic parameters are reduced to a low-dimensional space, and the result of the identification of the violation is determined based on the distances between the target category identification characteristic parameters and the category reference parameters and the non-category reference parameters in the low-dimensional space.

Specifically, the distance between the target category identification characteristic parameter and each target category reference parameter can be calculated, and the category corresponding to the target reference parameter with the minimum distance between the target category identification characteristic and the target category reference parameter is used as the identification result of the illicit mark in the acquired electroencephalogram signal. The violation identification result may include, but is not limited to, facial myoelectricity category, eye myoelectricity category, body myoelectricity category, and other myoelectricity categories, which is not limited herein.

In an embodiment of the present invention, the determining, by the target category reference parameter, a result of the trace violation identification in the electroencephalogram signal based on the target category identification feature parameter and the target category reference parameter may include: determining a first distance between the target class identification characteristic parameter and the class reference parameter and a second distance between the target class identification characteristic parameter and the non-class reference parameter; and taking the category corresponding to the smaller distance of the first distance and the second distance as the violation identification result.

The target category reference parameters include category reference parameters corresponding to a target category and non-category reference parameters corresponding to a non-target category, and the category reference parameters corresponding to the target category may be category reference parameters corresponding to facial myoelectricity categories or category reference parameters corresponding to eye myoelectricity categories, which is not limited herein. The target category reference parameters can be facial myoelectricity reference parameters and eye myoelectricity reference parameters, and correspondingly, the non-category reference parameters are non-facial myoelectricity reference parameters and non-eye myoelectricity reference parameters. In this embodiment, a distance between the target category identification characteristic parameter and the category reference parameter is calculated as a first distance, and a distance between the target category identification characteristic parameter and the non-category reference parameter is calculated as a second distance, the first distance and the second distance are compared, and if the first distance is greater than the second distance, a category corresponding to the second distance is used as a violation identification result; and if the first distance is smaller than the second distance, taking the category corresponding to the first distance as a violation identification result. It should be noted that each target class identification feature parameter corresponds to only one class, and therefore, there is no case where the first distance is equal to the first distance. The first distance and the second distance may be calculated based on, but not limited to, euclidean distance, which is not limited to this.

In this embodiment, the target category identification feature and the target category reference parameter are determined in advance based on the feature classification result of the sample electroencephalogram signal. When the target type of the electroencephalogram signal is identified, the target type identification characteristic parameters of the target type identification characteristics of the electroencephalogram signal are extracted. The target category identification features can be directly selected and determined from a large number of extracted features, the identification features can also be extracted by different feature extraction methods, one or more feature extraction methods are selected as target feature extraction methods, and target category identification feature parameters of the electroencephalogram signals are extracted by the target feature extraction methods. The target feature extraction method may be an electroencephalogram feature extraction method based on wavelet transform, an electroencephalogram feature extraction method based on fast fourier transform, or an electroencephalogram feature extraction method based on frequency domain feature indexes, and is not limited herein.

On the basis of the foregoing embodiment, optionally, the determining of the target class identification characteristic and the target class reference parameter includes:

acquiring a sample electroencephalogram signal and a marking type of the sample electroencephalogram signal, wherein the marking type of the sample electroencephalogram signal is determined based on the type of signal artifacts in the sample electroencephalogram signal;

extracting sample type identification characteristic parameters in the sample electroencephalogram signals to obtain sample electroencephalogram characteristic points of the sample electroencephalogram signals;

determining category reference point position information corresponding to each marking category based on the marking category of each sample electroencephalogram signal and the sample electroencephalogram feature point of each sample electroencephalogram signal;

determining the distance between the mark categories according to the category reference point position information corresponding to each mark category;

when the distance between the mark categories is larger than a set threshold value, taking the sample category identification feature as a target category identification feature, and taking category reference point position information corresponding to each mark category as a target category reference parameter;

and when the distance between the mark classes is not larger than the set threshold, repeatedly executing the steps until the distance between the mark classes determined based on the extracted sample class identification characteristic parameters is larger than the set threshold, taking the sample class identification characteristic as a target class identification characteristic, and taking the class reference point position information corresponding to the current mark classes as a target class reference parameter.

In general, by extracting sample category identification feature parameters of a group of sample category identification features for multiple times, determining the distance between mark categories determined based on the extracted sample category identification feature parameters, selecting a group of sample category identification features from the group of sample category identification features according to the distance between the mark categories as target category identification features, and taking parameters of the mark categories corresponding to the target category identification features as target category reference parameters. Optionally, the sample category identification feature parameters of the multiple groups of sample category identification features may be extracted correspondingly by multiple different feature extraction methods, so as to realize the selection of different sample category identification features. When a plurality of groups of sample category identification features are correspondingly extracted through different feature extraction methods, after the target category identification features are determined, the feature extraction method corresponding to the target category identification features is used as a target extraction method, and when the electroencephalogram default category is identified, the target extraction method is directly adopted to extract the target category identification features.

The sample electroencephalogram signals are electroencephalogram signals containing different signal artifacts in a preset number, and are used for determining a target feature extraction method and a target category reference parameter, and the preset number is set by a person skilled in the art based on experience or requirements and is not limited here. In this embodiment, a preset number of electroencephalogram signals are collected by an electroencephalogram signal collecting device to obtain sample electroencephalogram signals, and a label type of each sample electroencephalogram signal is determined based on a type of a signal artifact in the sample electroencephalogram signals, and optionally, the label type may be a facial electromyogram type and a non-facial electromyogram type, may also be an eye electromyogram type and a non-eye electromyogram type, and may also be a body electromyogram type and a non-body electromyogram type, which is not limited herein.

In this embodiment, the sample class identification feature is determined by the distance between the labeled samples, and then the feature value of the target class identification feature parameter of the target class identification feature corresponding to the labeled sample may be used as the target class reference parameter. Correspondingly, the determining of the target category reference parameter based on the spatial distribution area of the sample electroencephalogram feature point corresponding to each mark category comprises the following steps: and aiming at each mark type, taking the coordinate characteristic value of the sample electroencephalogram characteristic point corresponding to the mark type as a target type reference parameter corresponding to the mark type. Illustratively, for each mark category, determining an extracted identification characteristic parameter of a target category identification characteristic of a sample electroencephalogram signal in the mark category, reducing the dimension of the extracted identification characteristic parameter to a low-dimensional space to obtain a target category identification characteristic parameter, wherein each target category identification characteristic parameter corresponds to one sample characteristic point, and then taking characteristic values of all sample characteristic points in the mark category as target category reference parameters corresponding to the mark category. The coordinate feature value refers to a coordinate value capable of representing a feature point feature corresponding to each mark type, and may be, for example, a coordinate value of a centroid point, a coordinate value of a center point, a variance value, and the like of a sample electroencephalogram feature point corresponding to each mark type.

In one implementation, taking the coordinate feature value of the sample electroencephalogram feature point corresponding to the mark type as a target type reference parameter corresponding to the mark type includes: and taking the coordinate average value of the sample electroencephalogram feature points corresponding to the mark types as the target type reference parameters corresponding to the mark types. In the above example, the extracted identification feature parameters may be reduced to a three-dimensional space, the target category identification feature parameters are used as coordinate points in the three-dimensional space, and the average value of the coordinates of the sample electroencephalogram feature points is directly used as the target category reference parameter corresponding to the mark category.

In another embodiment of the present invention, the object class identification feature and the object class reference parameter may also be determined according to the spatial distribution region of different mark classes. Specifically, after the sample feature points corresponding to each mark type are mapped to a three-dimensional space, a spatial distribution area corresponding to each mark type is determined, and when the spatial distribution areas corresponding to different mark types meet set conditions, the current sample type identification feature is used as a target type identification feature, and a corresponding target type identification parameter is determined.

Optionally, the set distribution condition may be that no overlapping region exists between spatial distribution regions of sample electroencephalogram feature points corresponding to different marker categories. The judgment method of whether the overlapping areas exist among the spatial distribution areas can be that the electroencephalogram feature points of the edge samples of the spatial distribution areas are connected to form closed areas, whether the overlapping areas exist among the spatial distribution areas is judged based on whether the overlapping areas exist among the closed areas, if the overlapping areas exist in the closed areas, the overlapping areas exist among the spatial distribution areas, and if the overlapping areas do not exist in the closed areas, the overlapping areas do not exist among the spatial distribution areas. The method can also comprise the steps of firstly determining the center of each space distribution area, then calculating the distance between all sample electroencephalogram characteristic points and each central point, judging whether the distance between the sample electroencephalogram characteristic points of the non-corresponding mark type and the corresponding central points is smaller than the distance between the sample characteristic points of the corresponding mark type and the corresponding central points, if so, determining that overlapping areas exist among the space distribution areas, and if not, determining that overlapping areas do not exist among the space distribution areas.

Optionally, the set distribution condition may also be that the distance between the central points of the spatial distribution regions of the sample electroencephalogram feature points corresponding to different mark categories is greater than a preset central point distance, specifically, the judgment mode meeting the set distribution condition may be that the central point of the spatial distribution region corresponding to each mark category is determined first, then the distance between any two central points is calculated, and when the distance between any two central points is greater than the preset central point distance, the spatial distribution region of the sample electroencephalogram feature point corresponding to each mark category meets the set distribution condition; the set distribution condition may be that the distance between the feature points of any two spatial distribution regions corresponding to different mark categories is greater than a preset distance, specifically, the judgment mode meeting the set distribution condition may be that the feature points of any two spatial distribution regions are selected, the distance between the two feature points is calculated, and when the distances between the two feature points are greater than the preset distance, the spatial distribution region of the sample electroencephalogram feature point corresponding to each mark category meets the set distribution condition. It should be noted that the preset center point distance and the preset distance are set by those skilled in the art based on experience and requirements, and are not limited herein.

In one embodiment of the present invention, the object categories are a body myoelectric category, a face myoelectric category and an eye myoelectric category, and the determination of the identification result of the contraband in the electroencephalogram signal based on the object category identification feature and the object category reference parameter includes: determining a facial myoelectricity violation identification result in the electroencephalogram signal based on the facial myoelectricity category identification feature and the facial myoelectricity category reference parameter; when the facial myoelectricity violation identification result is a non-facial myoelectricity violation type, determining that the violation identification result is a body myoelectricity type; when the facial myoelectricity violation identification result is the facial myoelectricity violation type, determining an eye myoelectricity violation identification result in the electroencephalogram signal based on the eye myoelectricity type identification feature and the eye myoelectricity type reference parameter, when the eye myoelectricity violation identification result is the non-eye myoelectricity violation type, determining the violation identification result as the facial myoelectricity type, and when the eye myoelectricity violation identification result is the eye myoelectricity violation type, determining the violation identification result as the eye myoelectricity type. That is, the discrimination is performed based on the facial myoelectric category discrimination characteristics and the eye myoelectric category discrimination characteristics in sequence, and any one of the discrimination results of the target category can be obtained.

S130, determining the action state of the target object based on the violation identification result, and executing processing operation corresponding to the action state.

In the embodiment, the action state of the target object is determined according to the identification result of the trace in the electroencephalogram signal, so that corresponding operation is executed according to the action state of the target object. It can be understood that the operation corresponding to the action state may be determined according to the service requirement. When the business requirement is to collect the electroencephalogram signals in a set state, prompt information can be generated to prompt a user to execute a corresponding state; when the business requirement is controlled based on the electroencephalogram signal, the operation corresponding to the action state can be executed.

In one embodiment of the present invention, determining the action state of the target object based on the violation identification result includes: when the identification result of the violation trace is the body myoelectricity category, determining that the action state of the target object is an excitation state; when the identification result of the illegal trace is the facial myoelectricity category, determining the action state of the target object as the non-concentration state; and when the violation identification result is the eye myoelectric category, determining that the action state of the target object is the meditation state. When the identification type of the violation is a body myoelectric type, representing that the body muscle is active, and judging that the action state of the target object is a motion excitation state; when the identification type of the contraband is the facial myoelectricity type, representing that facial muscles are active, judging that the action state of the target object is a non-concentration state; when the violation identification type is the eye muscle type, the characterization eye muscle is active, and the action state of the target object can be judged to be the meditation state.

On the basis of the scheme, the processing operation corresponding to the action state is executed, and the processing operation comprises the following steps: determining posture adjustment prompt information according to the motion state, and outputting the posture adjustment prompt information; and acquiring the electroencephalogram signals of the target object after executing the posture adjustment mode corresponding to the posture adjustment prompt information as target electroencephalogram signals. In this embodiment, if the service requirement is to acquire electroencephalogram signals in a resting state, posture adjustment prompt information is generated according to the motion state of the target object for outputting (displaying or broadcasting), and then the electroencephalogram signals in the resting state are acquired after the user adjusts the posture according to the posture adjustment prompt information. For example, if the exercise state is an excited state, the posture adjustment prompt information "please keep still" may be generated and output, if the exercise state is a non-concentration state, the posture adjustment prompt information "please keep concentration" may be generated and output, and if the exercise state is a meditation state, the posture adjustment prompt information "please see the front and do not move" may be generated and output.

On the basis of the scheme, the processing operation corresponding to the action state is executed, and the processing operation comprises the following steps: and determining the action executing mechanism corresponding to the action state, and controlling the action executing mechanism to execute the corresponding movement operation. In this embodiment, the service requirement is to perform motion control based on electroencephalogram signals, for example, to perform control of the brain-computer swing mechanism based on electroencephalogram signals, an open-close state corresponding to each action state may be preset, a target open-close state is determined based on the action state of a target object, and an open-close degree of the brain-computer swing mechanism is adjusted based on the target open-close state. For example, the open/close state corresponding to the excited state may be set to a large open/close state, the open/close state corresponding to the inattentive state may be set to a small open/close state, and the open/close state corresponding to the meditation state may be set to a shaking state. The specific execution modes of the large opening and closing operation, the small opening and closing operation and the shaking operation can be preset, and are not limited herein.

It should be noted that the control method based on electroencephalogram signals provided in this embodiment may be executed by a brain-computer interface device, or may be executed by an independent processing device. Illustratively, a brain-computer interface device may collect brain electrical signals, and a processing device executes a control method based on brain electrical signals provided by any embodiment of the present invention to generate control instructions to execute corresponding control operations. The execution control operation can be executed by an independent device or a brain-computer interface device. When the business requirement is based on the electroencephalogram signal for motion control, the electroencephalogram signal can be collected by the brain-computer interface device for processing, and after a control instruction is obtained, the control instruction is sent to the execution mechanism, so that the execution mechanism can execute corresponding operation.

According to the technical scheme of the embodiment, the target category identification characteristic parameters corresponding to the target category identification characteristics in the electroencephalogram signals are extracted by acquiring the electroencephalogram signals of the target object; determining a default trace identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal; and determining the action state of the target object based on the violation identification result, and executing the processing operation corresponding to the action state. The signal artifacts of the electroencephalogram signals are classified through the predetermined target class identification features and the target class reference parameters, the complexity of the algorithm is reduced, the problem that the existing electromyogram classification algorithm cannot be embedded into a chip is solved, and control operation based on the classes of the electroencephalogram signals and the artifacts is achieved.

Example two

This embodiment provides a preferred embodiment. In this embodiment, taking facial myoelectricity, eye myoelectricity and body myoelectricity as signal artifacts of an electroencephalogram signal as an example, a determination process of a target feature extraction method and a target category reference parameter and a classification process of the electroencephalogram signal artifacts are exemplarily explained.

Fig. 2 is a flowchart of a method for determining target feature extraction and target category reference parameters according to a second embodiment of the present invention. As shown in fig. 2, firstly, taking a large amount of collected electroencephalogram signals mixed with different myoelectric artifacts as sample electroencephalogram signals, performing feature extraction on the sample electroencephalogram signals to obtain extracted features, and performing data preprocessing on the extracted features; then screening the extracted features based on the current facial myoelectric feature extraction method, and screening the extracted features into facial myoelectric features and non-facial myoelectric features; then respectively carrying out data dimension reduction processing on the screened features to obtain a spatial distribution region of facial myoelectric feature points and a spatial distribution region of non-facial myoelectric feature points, judging whether the spatial distribution regions of the facial myoelectric feature points and the non-facial myoelectric feature points are not superposed, if not, determining that the current facial myoelectric feature extraction method is a facial myoelectric feature extraction method Fa, and determining a centroid A of the facial myoelectric feature points and a centroid B of the non-facial myoelectric feature points as facial myoelectric reference parameters; and if the coincidence exists, obtaining a new facial myoelectric feature extraction method to re-screen the facial myoelectric features and the non-facial myoelectric features, and continuing the process until the spatial distribution area of the facial myoelectric feature points and the non-facial myoelectric feature points does not coincide. Similarly, for the extracted features after data preprocessing, determining an eye electromyography feature extraction method Fb based on the same process, and determining a centroid C of the eye electromyography feature points and a centroid D of the non-eye electromyography feature points as eye electromyography reference parameters.

It should be noted that in fig. 2, the facial electromyography feature extraction method Fa is used to distinguish facial electromyography features from non-facial electromyography features, and the eye electromyography feature extraction method Fb is used to distinguish eye electromyography features from non-eye electromyography features. Therefore, the facial electromyogram feature extraction method Fa is different from the eye electromyogram feature extraction method Fb, and therefore, in order to accurately determine the category of the electroencephalogram violation, the corresponding feature extraction method is obtained based on the target category in this embodiment.

Fig. 3 is a flowchart of a control method based on electroencephalogram signals according to a second embodiment of the present invention. As shown in fig. 3, extracting target category identification features (namely, facial myoelectricity category features and eye myoelectricity category features) based on a determined facial myoelectricity feature extraction method Fa and an eye myoelectricity feature extraction method Fb, preprocessing the target category identification features and performing data dimension reduction to obtain target category identification feature points, judging whether the distance between the target category identification feature points and a centroid B is smaller than that between the target category identification feature points and a centroid a, if so, determining that the violation identification result is a body myoelectricity category; if not, judging whether the distance between the target type identification feature point and the mass center C is smaller than that between the target type identification feature point and the mass center D, if so, determining that the identification result of the contraband is the eye myoelectricity type, and if not, determining that the contraband is the face myoelectricity type.

And after the identification result of the violation of the trace is determined, executing corresponding operation based on the violation of the trace identification structure. For specific execution operations, reference may be made to the above embodiments, which are not described herein again.

According to the technical scheme, the electromyographic artifacts in the electroencephalogram signals are classified, and the electromyographic artifacts are classified into facial electromyographic categories, eye electromyographic categories and body electromyographic categories, so that corresponding operations can be executed based on the categories of the violations.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a control device based on electroencephalogram signals according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes:

the identification feature extraction module 310 is configured to obtain an electroencephalogram signal of a target object, and extract a target category identification feature parameter corresponding to a target category identification feature in the electroencephalogram signal;

a violation identification result determining module 320, configured to determine a violation identification result in the electroencephalogram signal based on the target category identification feature parameter and the target category reference parameter, where the target category identification feature and the target category reference parameter are determined in advance based on the feature classification result of the sample electroencephalogram signal;

and the processing operation executing module 330 is configured to determine an action state of the target object based on the violation identification result, and execute a processing operation corresponding to the action state.

On the basis of the foregoing embodiment, optionally, the identifying feature extracting module 310 is specifically configured to:

performing feature extraction of target category identification features on the electroencephalogram signals to obtain extracted electroencephalogram features;

and performing dimension reduction processing on the extracted electroencephalogram characteristics to obtain target category identification characteristic parameters.

On the basis of the foregoing embodiment, optionally, the target category reference parameter includes a category reference parameter corresponding to the target category and a non-category reference parameter corresponding to the non-target category, and the violation identification result determining module 320 is specifically configured to:

determining a first distance between the target class identification characteristic parameter and the class reference parameter and a second distance between the target class identification characteristic parameter and the non-class reference parameter;

and taking the category corresponding to the smaller distance of the first distance and the second distance as the violation identification result.

On the basis of the foregoing embodiment, optionally, the apparatus further includes a characteristic parameter determining module, configured to:

acquiring a sample electroencephalogram signal and a marking type of the sample electroencephalogram signal, wherein the marking type of the sample electroencephalogram signal is determined based on the type of signal artifacts in the sample electroencephalogram signal;

extracting sample category identification characteristic parameters in the sample electroencephalogram signals to obtain sample electroencephalogram characteristic points of the sample electroencephalogram signals;

determining category reference point position information corresponding to each marking category based on the marking category of each sample electroencephalogram signal and the sample electroencephalogram feature point of each sample electroencephalogram signal;

determining the distance between the mark categories according to the category reference point position information corresponding to each mark category;

when the distance between the mark categories is larger than a set threshold value, taking the sample category identification feature as a target category identification feature, and taking category reference point position information corresponding to each mark category as a target category reference parameter;

and when the distance between the mark classes is not larger than the set threshold, repeatedly executing the steps until the distance between the mark classes determined based on the extracted sample class identification characteristic parameters is larger than the set threshold, taking the sample class identification characteristic as a target class identification characteristic, and taking the class reference point position information corresponding to the current mark classes as a target class reference parameter.

On the basis of the foregoing embodiment, optionally, the target class reference parameter determining unit is configured to, for each mark class, use a coordinate feature value of the sample electroencephalogram feature point corresponding to the mark class as the target class reference parameter corresponding to the mark class.

On the basis of the foregoing embodiment, optionally, the target category reference parameter determining unit is configured to use a coordinate average value of the sample electroencephalogram feature point corresponding to the mark category as the target category reference parameter corresponding to the mark category.

On the basis of the above embodiment, optionally, the object categories are a body myoelectric category, a face myoelectric category and an eye myoelectric category, and the violation identification result determining module 320 is specifically configured to:

determining a facial myoelectricity violation identification result in the electroencephalogram signal based on the facial myoelectricity category identification characteristics and the facial myoelectricity category reference parameters;

when the facial myoelectricity violation identification result is a non-facial myoelectricity violation type, determining that the violation identification result is a body myoelectricity type;

when the facial myoelectricity violation identification result is the facial myoelectricity violation type, determining an eye myoelectricity violation identification result in the electroencephalogram signal based on the eye myoelectricity type identification feature and the eye myoelectricity type reference parameter, when the eye myoelectricity violation identification result is the non-eye myoelectricity violation type, determining the violation identification result as the facial myoelectricity type, and when the eye myoelectricity violation identification result is the eye myoelectricity violation type, determining the violation identification result as the eye myoelectricity type.

On the basis of the foregoing embodiment, optionally, the processing operation executing module 330 is specifically configured to:

when the identification result of the violation trace is the body myoelectricity category, determining that the action state of the target object is an excitation state;

when the identification result of the illegal trace is the facial myoelectricity category, determining the action state of the target object as the non-concentration state;

and when the violation identification result is the eye myoelectric category, determining that the action state of the target object is the meditation state.

On the basis of the foregoing embodiment, optionally, the processing operation execution module 330 is specifically configured to:

determining posture adjustment prompt information according to the motion state, and outputting the posture adjustment prompt information;

and acquiring the electroencephalogram signals of the target object after executing the posture adjustment mode corresponding to the posture adjustment prompt information as target electroencephalogram signals.

On the basis of the foregoing embodiment, optionally, the processing operation executing module 330 is specifically configured to:

and determining the action executing mechanism corresponding to the action state, and controlling the action executing mechanism to execute the corresponding movement operation.

The electroencephalogram signal-based control device provided by the embodiment of the invention can execute the electroencephalogram signal-based control method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example four

Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a brain electrical signal-based control method.

In some embodiments, the brain electrical signal-based control method may be implemented as a computer program that is tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the electroencephalogram-based control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the electroencephalogram-based control method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

The computer program for implementing the brain electrical signal-based control method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

EXAMPLE five

An embodiment of the present invention further provides a computer-readable storage medium, where a computer instruction is stored, where the computer instruction is used to enable a processor to execute a control method based on an electroencephalogram signal, and the method includes:

acquiring an electroencephalogram signal of a target object, and extracting a target category identification characteristic parameter corresponding to a target category identification characteristic in the electroencephalogram signal;

determining a default trace identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on the characteristic classification result of the sample electroencephalogram signal;

and determining the action state of the target object based on the identification result of the violation, and executing the processing operation corresponding to the action state.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The method and system of the present invention may be implemented in a number of ways. For example, the methods and systems of the present invention may be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically indicated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as a program recorded in a recording medium, the program including machine-readable instructions for implementing a method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims (10)

1. A control method based on electroencephalogram signals is characterized by comprising the following steps:

acquiring an electroencephalogram signal of a target object, and extracting a target category identification characteristic parameter corresponding to a target category identification characteristic in the electroencephalogram signal;

determining a mark violation identification result in the electroencephalogram signal based on the target class identification characteristic parameter and the target class reference parameter, wherein the target class identification characteristic and the target class reference parameter are determined in advance based on a characteristic classification result of a sample electroencephalogram signal;

and determining the action state of the target object based on the violation identification result, and executing processing operation corresponding to the action state.

2. The method of claim 1, wherein the extracting of the target category identification feature parameters corresponding to the target category identification features in the electroencephalogram signal comprises:

performing feature extraction of the target category identification features on the electroencephalogram signals to obtain extracted electroencephalogram features;

and performing dimensionality reduction processing on the extracted electroencephalogram features to obtain the target category identification feature parameters.

3. The method of claim 1, wherein the object class reference parameters comprise a class reference parameter corresponding to an object class and a non-class reference parameter corresponding to a non-object class, and the determining the result of the identification of the contraband in the electroencephalogram signal based on the object class identification feature parameter and the object class reference parameter comprises:

determining a first distance between the target class identification feature parameter and the class reference parameter and a second distance between the target class identification feature parameter and the non-class reference parameter;

and taking the category corresponding to the smaller distance of the first distance and the second distance as the violation identification result.

4. The method of claim 1, wherein the determining of the object class identifying characteristic and the object class reference parameter comprises:

acquiring a sample brain electrical signal and a mark type of the sample brain electrical signal, wherein the mark type of the sample brain electrical signal is determined based on the type of signal artifacts in the sample brain electrical signal;

extracting sample category identification characteristic parameters in the sample electroencephalogram signals to obtain sample electroencephalogram characteristic points of the sample electroencephalogram signals;

determining category reference point position information corresponding to each label category based on the label category of each sample electroencephalogram signal and the sample electroencephalogram feature point of each sample electroencephalogram signal;

determining the distance between the mark categories according to the category reference point position information corresponding to each mark category;

when the distance between the mark categories is larger than a set threshold value, taking the sample category identification features as the target category identification features, and taking category reference point position information corresponding to each mark category as the target category reference parameters;

when the distance between the mark categories is not larger than a set threshold, the steps are repeatedly executed until the distance between the mark categories determined based on the extracted sample category identification feature parameter is larger than the set threshold, the sample category identification feature is used as the target category identification feature, and the category reference point position information corresponding to each mark category at present is used as the target category reference parameter.

5. The method of claim 4, wherein the determining the target class reference parameter based on the spatially distributed region of the sample brain electrical feature point corresponding to each of the labeled classes comprises:

and regarding each mark type, taking the coordinate characteristic value of the sample electroencephalogram characteristic point corresponding to the mark type as a target type reference parameter corresponding to the mark type.

6. The method according to claim 1, wherein the performing the processing operation corresponding to the action state comprises:

determining posture adjustment prompt information according to the motion state, and outputting the posture adjustment prompt information;

and acquiring the electroencephalogram signals of the target object after executing the posture adjustment mode corresponding to the posture adjustment prompt information as target electroencephalogram signals.

7. The method according to claim 1, wherein the executing the processing operation corresponding to the action state comprises:

and determining the action executing mechanism corresponding to the action state, and controlling the action executing mechanism to execute corresponding movement operation.

8. A control device based on electroencephalogram signals, comprising:

the identification feature extraction module is used for acquiring an electroencephalogram signal of a target object and extracting a target category identification feature parameter corresponding to a target category identification feature in the electroencephalogram signal;

the disobey identification result determining module is used for determining a disobey identification result in the electroencephalogram signal based on the target category identification characteristic parameter and the target category reference parameter, wherein the target category identification characteristic and the target category reference parameter are determined in advance based on a characteristic classification result of a sample electroencephalogram signal;

and the processing operation executing module is used for determining the action state of the target object based on the violation identification result and executing the processing operation corresponding to the action state.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the brain electrical signal based control method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a processor to implement the electroencephalogram signal-based control method of any one of claims 1 to 7 when executed.

Images