Object control method, device, equipment and medium based on power imagination

Abstract

The present invention discloses an object control method, device, equipment and medium based on force imagination. The method acquires a plurality of continuous EEG signals of a user when imagining controlling an object, so as to analyze the EEG signals of the user through imagination. For each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain the difference feature and correlation feature of the EEG signal, so as to analyze the difference and power correlation of the EEG signal in the spatial domain. The method uses a preset classifier to identify the EEG signal according to the difference feature and the correlation feature to obtain a force classification value, so as to identify the force type imagined by the user. Finally, the force value corresponding to each of the EEG signals is determined according to the force classification value, and the object is continuously controlled based on the plurality of force values, so as to realize continuous simulation of EEG signals of different forces when the user imagines movement.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to an object control method, device, equipment and medium based on force imagination. Background Art

[0002] Brain-computer interfaces only require "thinking" to execute corresponding control actions, which can help disabled or even paralyzed people do things that are difficult to do normally, such as controlling the movement of wheelchairs, controlling robotic arms to pick up objects, etc. At present, related technologies mainly analyze the EEG signals of users when they use different forces, but cannot achieve continuous control of different forces through motor imagination. Summary of the invention

[0003] The present invention provides an object control method, device, equipment and medium based on force imagination to solve the technical problem that the current technology cannot achieve continuous control of different forces through motion imagination.

[0004] In order to solve the above technical problems, in a first aspect, the present invention provides an object control method based on force imagination, comprising:

[0005] Acquire multiple continuous EEG signals of the user when the user imagines controlling a virtual object;

[0006] For each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain difference features and correlation features of the EEG signal;

[0007] Using a preset classifier, the EEG signal is identified according to the difference feature and the correlation feature to obtain a strength classification value;

[0008] Determine the power value corresponding to each of the EEG signals according to the power classification value;

[0009] Based on the multiple force values, the virtual object is continuously controlled.

[0010] Preferably, for each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain difference features and correlation features of the EEG signal, including:

[0011] For each of the EEG signals, band-pass filtering is performed on the EEG signal to obtain the target band signal;

[0012] Performing spatial domain filtering on the target band signal to obtain differential features of the target band signal;

[0013] A correlation comparison is performed on the target band signal to obtain a correlation feature of the target band signal.

[0014] Preferably, the performing spatial domain filtering on the target band signal to obtain the difference characteristics of the target band signal includes:

[0015] By using a preset spatial domain filtering algorithm, the variance value difference between the target band signal and the transposed signal is maximized to obtain a conversion matrix of the target band signal, wherein the conversion matrix is ​​the difference feature, the transposed signal is the transposition of the target band signal, and the preset spatial domain filtering algorithm is:

[0016] ;

[0017] is the covariance matrix between the target band signal and the transposed signal, A signal matrix representing the target band signal, represents the matrix of the transposed signal, express Trace of.

[0018] Preferably, performing correlation comparison on the target band signal to obtain the correlation feature of the target band signal includes:

[0019] Calculating the frequency band power of the target band signal in each electrode channel;

[0020] Using a preset correlation comparison algorithm, the correlation between the channels is calculated according to the frequency band power to obtain a coherence matrix, where the coherence matrix is ​​the correlation feature. The preset correlation comparison algorithm is:

[0021] ;

[0022] represents the correlation matrix, Indicates that the target band signal is Electrode channels and The total power of the electrode channel, The target band signal is The frequency band power of the electrode channel, The target band signal is The frequency band power of the electrode channel.

[0023] Preferably, the using of a preset classifier to identify the EEG signal according to the difference feature and the correlation feature to obtain a strength classification value includes:

[0024] The difference feature and the correlation feature are input into a pre-trained SVM classifier to identify the EEG signal, and a strength classification value output by the SVM classifier is obtained.

[0025] Preferably, the step of determining the strength value corresponding to each of the EEG signals according to the strength classification value comprises:

[0026] The power value corresponding to the EEG signal is calculated according to the classification value using a preset power calculation formula, and the preset power calculation formula is:

[0027] ;

[0028] is the strength value, and is a constant, is a classification value for the strength.

[0029] Preferably, the continuously controlling the virtual object based on the multiple force values ​​comprises:

[0030] Based on the multiple force values, force is continuously applied to the virtual object to continuously control the movement of the virtual object, wherein the direction of the force is determined based on the force classification value.

[0031] In a second aspect, the present invention provides an object control device based on force imagination, comprising:

[0032] An acquisition module, used to acquire a plurality of continuous EEG signals of a user when the user imagines controlling a virtual object;

[0033] An extraction module, for extracting features of a target band signal of each EEG signal to obtain difference features and correlation features of the EEG signal;

[0034] An identification module, used to identify the EEG signal using a preset classifier according to the difference feature and the correlation feature to obtain a strength classification value;

[0035] A determination module, used to determine the strength value corresponding to each of the EEG signals according to the strength classification value;

[0036] A control module is used to continuously control the virtual object based on the multiple force values.

[0037] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the object control method based on force imagination as described in the first aspect is implemented.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the object control method based on force imagination as described in the first aspect.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention acquires multiple continuous EEG signals of the user when imagining controlling a virtual object, so as to analyze the EEG signals of the user through imagination; and for each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain the difference feature and correlation feature of the EEG signal, so as to analyze the spatial difference and power correlation of the EEG signal; and a preset classifier is used to identify the EEG signal according to the difference feature and the correlation feature to obtain a strength classification value, so as to identify the type of strength imagined by the user; finally, the strength value corresponding to each of the EEG signals is determined according to the strength classification value, and based on the multiple strength values, the virtual object is continuously controlled, so as to realize continuous simulation of EEG signals of different strengths when the user imagines movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of an object control method based on force imagination according to an embodiment of the present invention;

[0042] Figure 2 It is a structural schematic diagram of an object control device based on force imagination according to an embodiment of the present invention;

[0043] Figure 3 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0045] Please refer to Figure 1 , Figure 1 The flowchart of a method for controlling an object based on force imagination provided by an embodiment of the present invention is shown below. The method for controlling an object based on force imagination provided by an embodiment of the present invention can be applied to electronic devices, including but not limited to smart phones, laptops, tablet computers, virtual reality (VR) devices, and the like. Figure 1As shown, the object control method based on force imagination of this embodiment includes steps S101 to S105, which are described in detail as follows:

[0046] Step S101, obtaining a plurality of continuous EEG signals of a user when the user imagines controlling a virtual object.

[0047] In this step, the EEG signal of the user when he / she believes in controlling the stage is collected by an EEG device such as an EEG cap. For example, in a virtual reality scene, the user selects the corresponding virtual object through a handle and imagines the force of controlling the virtual object, such as imagining lifting the virtual object with great force, and the EEG signal of the imagination process is collected by the EEG cap worn on the user's head, and the collected EEG signal is transmitted to the electronic device to which the present invention is applied.

[0048] Step S102: for each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain difference features and correlation features of the EEG signal.

[0049] In this step, the EEG signal is a kind of waveform data, and its spectrum information can reflect most of the brain activity signals. The target band signals include α band signals and β band signals, wherein α band refers to the signal in the 8-13Hz band of the EEG signal, and β band refers to the signal in the 13-40Hz band of the EEG signal. Optionally, Fourier transform is performed on the EEG signal to extract the signals in the α and β bands, and the CSP (Common Spatial Pattern, spatial filtering) features and Coherence (correlation) features of the α band signal and the β band signal are calculated.

[0050] In some embodiments, for each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain the difference feature and correlation feature of the EEG signal, including:

[0051] For each of the EEG signals, band-pass filtering is performed on the EEG signal to obtain the target band signal;

[0052] Performing spatial domain filtering on the target band signal to obtain differential features of the target band signal;

[0053] A correlation comparison is performed on the target band signal to obtain a correlation feature of the target band signal.

[0054] In this embodiment, the EEG signal is band-pass filtered by a Butterworth filter to filter out signals of two frequency bands, α and β, respectively, as data for feature extraction in the next step.

[0055] Optionally, performing spatial domain filtering on the target band signal to obtain a difference feature of the target band signal includes:

[0056] By using a preset spatial domain filtering algorithm, the variance value difference between the target band signal and the transposed signal is maximized to obtain a conversion matrix of the target band signal, wherein the conversion matrix is ​​the difference feature, and the transposed signal is the transpose of the target band signal.

[0057] In this embodiment, spatial filtering is a spatial filtering feature extraction algorithm for two classification tasks, which aims to maximize the variance value difference between the two types of signals. The preset spatial filtering algorithm is:

[0058] ;

[0059] is the covariance matrix between the target band signal and the transposed signal, A signal matrix representing the target band signal, represents the matrix of the transposed signal, express The trace of , which is the sum of the diagonal elements of the matrix.

[0060] Optionally, It can be expressed as , It can also be expressed as ,in for The characteristic matrix of is the corresponding eigenvalue, then the whitening transformation is expressed as ,get , for two EEG signals, ,but , ,and , the EEG signal projected onto the first and last feature matrices is used to maximize the distinction between the two signals.

[0061] Optionally, performing correlation comparison on the target band signal to obtain a correlation feature of the target band signal includes:

[0062] Calculating the frequency band power of the target band signal in each electrode channel;

[0063] Using a preset correlation comparison algorithm, the correlation between the channels is calculated according to the frequency band power to obtain a coherence matrix, where the coherence matrix is ​​the correlation feature. The preset correlation comparison algorithm is:

[0064] ;

[0065] represents the correlation matrix, Indicates that the target band signal is Electrode channels and The total power of the electrode channel, The target band signal is The frequency band power of the electrode channel, The target band signal is The frequency band power of the electrode channel.

[0066] In this embodiment, the Coherence feature of the target band signal is extracted. Coherence refers to the correlation between the signals of two EEG electrode channels, and its value is [0, 1]. The stronger the correlation, the more similar the signals collected by the two electrodes are. By calculating the coherence between the two EEG electrode channels, the Coherence matrix can be obtained.

[0067] Step S103, using a preset classifier, the EEG signal is identified according to the difference feature and the correlation feature to obtain a strength classification value.

[0068] In this step, the preset classifier may be a support vector machine (SVM) classifier.

[0069] Optionally, the difference feature and the correlation feature are input into a pre-trained SVM classifier to identify the EEG signal and obtain a strength classification value output by the SVM classifier.

[0070] Exemplarily, the SVM classifier training process may include: the user first wears the EEG cap, the user lifts unused objects in the real environment, and collects the EEG signals of the user when lifting different objects to collect the EEG signals of the user's perception of different weights. The EEG signal is bandpass filtered to filter out the 0-50Hz EEG signal; the conversion matrix is ​​obtained by training CSP, and applied to the filtered EEG signal to distinguish the EEG signals under the two tasks; the power of the 8-30Hz frequency band of each channel of the EEG signal is calculated, and the corresponding Coherence is calculated. The EEG signals of all training tasks are finally converted into a coherence matrix, and 70% of the data in the training process can be used as a training set and 30% of the data as a test set to train the SVM classifier. When the SVM classifier is in use, the EEG signal will also be converted through the above process. The output of the SVM classifier contains two parts [f, p], where f is the identified task type (represented by -1 and 1 here), and p is the confidence of this classification result, with a value of 0-1.

[0071] Step S104, determining the strength value corresponding to each of the EEG signals according to the strength classification value.

[0072] In this step, the strength classification value is a classification value to distinguish whether the strength imagined by the user is large or small. For example, -1 means that the strength imagined by the user is small, and 1 means that the strength imagined by the user is large. The strength value represents the description of the brain-computer interface of the size of the strength imagined by the user at this time.

[0073] In some embodiments, determining the strength value corresponding to each of the EEG signals according to the strength classification value includes: using a preset strength calculation formula to calculate the strength value corresponding to the EEG signal according to the classification value, and the preset strength calculation formula is:

[0074] ;

[0075] is the strength value, and is a constant (when the user has just completed training, a=1, b=0), which can be adjusted according to the user's state to ensure that the output i can adjust the value range according to the user's state. is the strength classification value, , its value range is [-1, 1].

[0076] Step S105: continuously controlling the virtual object based on the multiple force values.

[0077] In this step, optionally, based on the multiple force values, a force is continuously applied to the virtual object to continuously control the movement of the virtual object, wherein the direction of the force is determined based on the force classification value.

[0078] The EEG device collects the user's EEG signals, identifies the size of the user's imaginary force at this time, and applies a force to the virtual object based on the size of the judged imaginary force. The calculation formula is as follows:

[0079] ;

[0080] ;

[0081] ;

[0082] Where P represents the position of the virtual object in the virtual world, v represents the moving speed at that time, t represents time, m represents the real weight of the virtual object in reality, F represents the force on the virtual object, c is a constant, and g is the gravitational constant, which is 9.8.

[0083] When the user imagines that the ball is lighter in virtual reality, SVM recognizes the EEG signal and outputs f as -1. The specific confidence level changes according to the actual situation. The virtual object is controlled to move downward, otherwise it moves upward. The algorithm of this embodiment can continuously simulate the different forces imagined by the user's movement, realize the expansion of the SVM classifier, and apply it to the control of virtual objects.

[0084] In order to execute the object control method based on force imagination corresponding to the above method embodiment, so as to achieve the corresponding functions and technical effects. Figure 2 , Figure 2 The structural block diagram of an object control device based on power imagination provided by an embodiment of the present invention is shown. For the convenience of explanation, only the parts related to this embodiment are shown. The object control device based on power imagination provided by an embodiment of the present invention includes:

[0085] An acquisition module 201 is used to acquire a plurality of continuous EEG signals of a user when the user imagines controlling a virtual object;

[0086] An extraction module 202 is used to extract features of a target band signal of each EEG signal to obtain difference features and correlation features of the EEG signal;

[0087] The identification module 203 is used to identify the EEG signal using a preset classifier according to the difference feature and the correlation feature to obtain a strength classification value;

[0088] A determination module 204, configured to determine a strength value corresponding to each of the EEG signals according to the strength classification value;

[0089] The control module 205 is used to continuously control the virtual object based on the multiple force values.

[0090] In some embodiments, the extraction module 202 includes:

[0091] A bandpass filtering unit, used for performing bandpass filtering on each of the EEG signals to obtain the target band signal;

[0092] A spatial domain filtering unit, used for performing spatial domain filtering on the target band signal to obtain differential features of the target band signal;

[0093] The comparison unit is used to perform correlation comparison on the target band signal to obtain the correlation feature of the target band signal.

[0094] In some embodiments, the spatial domain filtering unit is specifically used to:

[0095] By using a preset spatial domain filtering algorithm, the variance value difference between the target band signal and the transposed signal is maximized to obtain a conversion matrix of the target band signal, wherein the conversion matrix is ​​the difference feature, the transposed signal is the transposition of the target band signal, and the preset spatial domain filtering algorithm is:

[0096] ;

[0097] is the covariance matrix between the target band signal and the transposed signal, A signal matrix representing the target band signal, represents the matrix of the transposed signal, express Trace of.

[0098] In some embodiments, the comparison unit is specifically used for:

[0099] Calculating the frequency band power of the target band signal in each electrode channel;

[0100] Using a preset correlation comparison algorithm, the correlation between the channels is calculated according to the frequency band power to obtain a coherence matrix, where the coherence matrix is ​​the correlation feature. The preset correlation comparison algorithm is:

[0101] ;

[0102] represents the correlation matrix, Indicates that the target band signal is Electrode channels and The total power of the electrode channel, The target band signal is The frequency band power of the electrode channel, The target band signal is The frequency band power of the electrode channel.

[0103] In some embodiments, the identification module 203 is specifically used to:

[0104] The difference feature and the correlation feature are input into a pre-trained SVM classifier to identify the EEG signal, and a strength classification value output by the SVM classifier is obtained.

[0105] In some embodiments, the determining module 204 is specifically configured to:

[0106] The power value corresponding to the EEG signal is calculated according to the classification value using a preset power calculation formula, and the preset power calculation formula is:

[0107] ;

[0108] is the strength value, and is a constant, is a classification value for the strength.

[0109] In some embodiments, the control module 205 is specifically used to:

[0110] Based on the multiple force values, force is continuously applied to the virtual object to continuously control the movement of the virtual object, wherein the direction of the force is determined based on the force classification value.

[0111] The above-mentioned object control device based on force imagination can implement the object control method based on force imagination of the above-mentioned method embodiment. The options in the above-mentioned method embodiment are also applicable to this embodiment and will not be described in detail here. The rest of the contents of the embodiment of the present invention can refer to the contents of the above-mentioned method embodiment and will not be described in detail in this embodiment.

[0112] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 3 of this embodiment includes: at least one processor 30 ( Figure 3 Only one is shown in the figure) a processor, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, and when the processor 30 executes the computer program 32, the steps in any of the above method embodiments are implemented.

[0113] The electronic device 3 may be a computing device such as a smart phone, a tablet computer, a desktop computer, and a cloud server. The electronic device may include but is not limited to a processor 30 and a memory 31. Those skilled in the art will understand that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0114] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0115] In some embodiments, the memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. In other embodiments, the memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the electronic device 3. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0116] In addition, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0117] An embodiment of the present invention provides a computer program product. When the computer program product is run on an electronic device, the electronic device implements the steps in the above-mentioned method embodiments when executing the computer program product.

[0118] In several embodiments provided by the present invention, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0119] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling an electronic device to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0120] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling an object based on force imagination, characterized in that: include: Acquire multiple continuous EEG signals of the user when the user imagines controlling a virtual object; For each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain difference features and correlation features of the EEG signal; Using a preset classifier, the EEG signal is identified according to the difference feature and the correlation feature to obtain a strength classification value; Determine the power value corresponding to each of the EEG signals according to the power classification value; Determining the strength value corresponding to each of the EEG signals according to the strength classification value includes: The power value corresponding to the EEG signal is calculated according to the classification value using a preset power calculation formula, and the preset power calculation formula is: ； is the strength value, and is a constant, a classification value for said strength; Based on the plurality of force values, continuously controlling the virtual object; The continuously controlling the virtual object based on the multiple force values ​​includes: Based on the multiple force values, continuously applying force to the virtual object to continuously control the movement of the virtual object, wherein the direction of the force is determined based on the force classification value; According to the magnitude of the judged imaginary force, a force is applied to the virtual object, and the calculation formula is as follows: ； ； ； Where P represents the position of the virtual object in the virtual world, v represents the moving speed at that time, t represents time, m represents the real weight of the virtual object in reality, F represents the force on the virtual object, c is a constant, and g is the gravitational constant, which is 9.

8.

2. The object control method based on power imagination as claimed in claim 1, characterized in that: For each of the EEG signals, feature extraction is performed on the target band signal of the EEG signal to obtain difference features and correlation features of the EEG signal, including: For each of the EEG signals, band-pass filtering is performed on the EEG signal to obtain the target band signal; Performing spatial domain filtering on the target band signal to obtain differential features of the target band signal; A correlation comparison is performed on the target band signal to obtain a correlation feature of the target band signal.

3. The object control method based on power imagination as claimed in claim 2, characterized in that: The performing spatial domain filtering on the target band signal to obtain the difference characteristics of the target band signal includes: By using a preset spatial domain filtering algorithm, the variance value difference between the target band signal and the transposed signal is maximized to obtain a conversion matrix of the target band signal, wherein the conversion matrix is ​​the difference feature, the transposed signal is the transposition of the target band signal, and the preset spatial domain filtering algorithm is: ； is the covariance matrix between the target band signal and the transposed signal, A signal matrix representing the target band signal, represents the matrix of the transposed signal, express Trace of.

4. The object control method based on power imagination as claimed in claim 2, characterized in that: The performing correlation comparison on the target band signal to obtain the correlation feature of the target band signal includes: Calculating the frequency band power of the target band signal in each electrode channel; Using a preset correlation comparison algorithm, the correlation between the channels is calculated according to the frequency band power to obtain a coherence matrix, where the coherence matrix is ​​the correlation feature. The preset correlation comparison algorithm is: ； represents the correlation matrix, Indicates that the target band signal is Electrode channels and The total power of the electrode channel, The target band signal is The frequency band power of the electrode channel, The target band signal is The frequency band power of the electrode channel.

5. The object control method based on power imagination as claimed in claim 1, characterized in that: The method of using a preset classifier to identify the EEG signal according to the difference feature and the correlation feature to obtain a strength classification value includes: The difference feature and the correlation feature are input into a pre-trained SVM classifier to identify the EEG signal, and a strength classification value output by the SVM classifier is obtained.

6. An object control device based on power imagination, characterized in that: include: An acquisition module, used to acquire a plurality of continuous EEG signals of a user when the user imagines controlling a virtual object; An extraction module, for extracting features of a target band signal of each EEG signal to obtain difference features and correlation features of the EEG signal; An identification module, used to identify the EEG signal using a preset classifier according to the difference feature and the correlation feature to obtain a strength classification value; A determination module, used to determine the strength value corresponding to each of the EEG signals according to the strength classification value; Determining the strength value corresponding to each of the EEG signals according to the strength classification value includes: The power value corresponding to the EEG signal is calculated according to the classification value using a preset power calculation formula, and the preset power calculation formula is: ； is the strength value, and is a constant, a classification value for said strength; A control module, configured to continuously control the virtual object based on the plurality of force values; The continuously controlling the virtual object based on the multiple force values ​​includes: Based on the multiple force values, continuously applying force to the virtual object to continuously control the movement of the virtual object, wherein the direction of the force is determined based on the force classification value; According to the magnitude of the judged imaginary force, a force is applied to the virtual object, and the calculation formula is as follows: ； ； ； Where P represents the position of the virtual object in the virtual world, v represents the moving speed at that time, t represents time, m represents the real weight of the virtual object in reality, F represents the force on the virtual object, c is a constant, and g is the gravitational constant, which is 9.

8.

7. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the object control method based on force imagination as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the object control method based on force imagination as described in any one of claims 1 to 5.

Images