阅读说明：本技术 对注意力进行识别的方法、装置、终端及介质 (Method, device, terminal and medium for recognizing attention ) 是由 王晓岸 卢树强 邹婧 沈阳 于 2021-08-13 设计创作，主要内容包括：本申请公开了一种对注意力进行识别的方法、装置、终端及介质。其中方法包括：确定待处理的目标脑电信号；将目标脑电信号变换为功率谱；确定功率谱中指定脑电波的特征值；依据预构建的注意力等级分类器,确定特征值所属的注意力等级。本申请实现了对注意力进行自动化识别的目的,还提高了注意力识别的效率,扩大了注意力识别的应用场景,为不同应用场景的用户进行干预提供了必要的数据基础。(The application discloses a method, a device, a terminal and a medium for recognizing attention. The method comprises the following steps: determining a target electroencephalogram signal to be processed; transforming the target brain electrical signal into a power spectrum; determining a characteristic value of a designated brain wave in the power spectrum; and determining the attention level to which the characteristic value belongs according to a pre-constructed attention level classifier. The method and the device achieve the purpose of automatically identifying the attention, improve the efficiency of the attention identification, expand the application scenes of the attention identification and provide necessary data basis for the intervention of users in different application scenes.)

1. A method of identifying attention, comprising:

determining a target electroencephalogram signal to be processed;

transforming the target brain electrical signal into a power spectrum;

determining a characteristic value of a designated brain wave in the power spectrum;

and determining the attention level to which the characteristic value belongs according to a pre-constructed attention level classifier.

2. The method of claim 1, wherein the step of determining the attention level to which the feature value belongs according to a pre-constructed attention level classifier is preceded by the method further comprising:

acquiring a plurality of characteristic values aiming at the specified brain waves;

determining respective attention levels of a plurality of the characteristic values;

and training a preset classifier according to the plurality of feature values and the attention grades of the feature values to obtain the attention grade classifier.

3. The method of claim 2, wherein the step of determining the attention level of each of the plurality of feature values comprises:

acquiring identification operation aiming at a plurality of characteristic values based on a preset interface;

and determining the attention level of each of the characteristic values according to the identification operation.

4. The method according to claim 1, wherein the step of determining the characteristic value of the brain waves specified in the power spectrum comprises:

determining a spectral region in the power spectrum for the specified brain wave;

and determining a characteristic value of the Shannon entropy of the frequency spectrum region aiming at the appointed brain wave according to a preset Shannon entropy algorithm.

5. The method of claim 1, wherein the step of determining the target brain electrical signal to be processed comprises:

acquiring an electroencephalogram signal of a target user;

and carrying out segmentation processing on the electroencephalogram signals according to preset segmentation time to obtain a plurality of sections of target electroencephalogram signals to be processed.

6. The method of claim 1, wherein prior to the step of transforming the brain electrical signal into a power spectrum, the method further comprises:

and filtering and removing the false from the electroencephalogram signals.

7. The method of claim 1, further comprising:

determining a selected target application scene according to a plurality of preset application scenes;

and determining intervention information matched with the attention level to which the characteristic value belongs based on an intervention strategy aiming at the target application scene so as to perform intervention processing according to the intervention information.

8. An apparatus for recognizing attention, comprising:

the target signal determination module is used for determining a target electroencephalogram signal to be processed;

the target signal conversion module is used for converting the target brain electrical signal into a power spectrum;

the characteristic value determining module is used for determining the characteristic value of the appointed brain wave in the power spectrum;

and the attention identification module is used for determining the attention level to which the characteristic value belongs according to a pre-constructed attention level classifier.

9. A terminal, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a terminal, and a medium for recognizing attention.

Background

With the development and progress of society, the occupation ratio of mental labor in human activities is higher and higher, and the research on whether attention is focused is more and more important. Especially in the fields of driving, learning, etc. For example, in the driving field, the distraction of the user may cause a serious traffic accident; in the field of learning, the distraction of the user may lead to a problem of a decline in learning performance.

In the related art, whether attention is focused or not depends mainly on observation by an outside user, and attention cannot be ranked.

Disclosure of Invention

In order to solve at least one of the above technical problems, the present application provides a method, an apparatus, a terminal, and a medium for recognizing attention.

According to a first aspect of the present application, there is provided a method of identifying attention, the method comprising:

determining a target electroencephalogram signal to be processed;

transforming the target brain electrical signal into a power spectrum;

determining a characteristic value of a designated brain wave in the power spectrum;

and determining the attention level to which the characteristic value belongs according to a pre-constructed attention level classifier.

According to a second aspect of the present application, there is provided an apparatus for identifying attention, the apparatus comprising:

the target signal determination module is used for determining a target electroencephalogram signal to be processed;

the target signal conversion module is used for converting the target brain electrical signal into a power spectrum;

the characteristic value determining module is used for determining the characteristic value of the specified brain wave in the power spectrum;

and the attention recognition module is used for determining the attention level to which the characteristic value belongs according to the pre-constructed attention level classifier.

According to a third aspect of the present application, there is provided a terminal comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the above method of identifying attention.

According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method of recognizing attention.

According to the method, the target electroencephalogram signal to be processed is determined, the target electroencephalogram signal is converted into the power spectrum, the characteristic value of the designated electroencephalogram in the power spectrum is determined, the attention level to which the characteristic value belongs is determined according to the pre-constructed attention level classifier, and the attention is identified through the attention level classifier, so that the purpose of automatically identifying the attention is achieved, the efficiency of the attention identification is improved, the application scene of the attention identification is expanded, and a necessary data basis is provided for the intervention of users in different application scenes.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.

Fig. 1 is a schematic flowchart of a method for recognizing attention according to an embodiment of the present disclosure; and

fig. 2 is a block diagram structure schematic diagram of an apparatus for recognizing attention according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart.

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

According to an embodiment of the present application, there is provided a method of recognizing attention, as shown in fig. 1, the method including steps S101 to S105.

Step S101: and determining a target electroencephalogram signal to be processed.

Specifically, the electronic device determines a target brain electrical signal to be processed. The electronic device can be electroencephalogram signal EEG acquisition equipment, brain computer interface BCI equipment, a mobile phone, a tablet, a PC (personal computer), a server and the like.

Specifically, the target electroencephalogram signal may be an electroencephalogram signal acquired according to a preset acquisition period, or may be a certain segment obtained by performing segmentation processing on the electroencephalogram signal.

For example, if the electronic device acquires a 10-second electroencephalogram signal, the target electroencephalogram signal may be the 10-second electroencephalogram signal, or may be a 3-second electroencephalogram signal captured from the 10-second electroencephalogram signal.

Step S102: the target brain electrical signal is transformed into a power spectrum.

Specifically, the target electroencephalogram signal may be converted according to a preset frequency conversion algorithm. For example, the target brain electrical signal is subjected to transform processing according to a fourier transform algorithm.

Step S103: characteristic values of the specified brain waves in the power spectrum are determined.

In the embodiment of the present application, the power spectrum is used to characterize the distribution of the signal power in the frequency domain. The power spectrum includes a variety of brain waves, such as: alpha brain waves with a wavelength of 8-12 Hz; beta brain waves with a wavelength of 14-100 Hz; theta brain waves with a wavelength of 4-8 Hz; delta brain waves with a wavelength of 0.5-4Hz, etc.

Specifically, the designated brain waves may be set to one or several of the brain waves. For example, the designated brain wave is set as a β brain wave, and the feature value of the β brain wave is calculated according to this step.

Step S104: and determining the attention level to which the characteristic value belongs according to a pre-constructed attention level classifier.

In particular, the SVM classifier may be trained to derive an attention-level classifier.

Specifically, the attention level classifier may include a plurality of one-to-many multi-mode classifiers, and when the application is performed, each two classifiers included in the attention level classifier respectively output corresponding parameters, and the attention level to which the feature value belongs is determined according to the two classifiers outputting the specified parameters.

Specifically, the attention level classifier may include a plurality of one-to-one mode two classifiers, and when the application is performed, each two classifiers included in the attention level classifier respectively output corresponding parameters, and the attention level to which the feature value belongs is determined according to the two classifiers outputting the specified parameters.

In the embodiment of the present application, attention ranks are set to three ranks: high level attention, moderate level attention, and low level attention.

It should be noted that, in practical applications, the corresponding attention level may be set according to an application scenario, which is not listed here.

According to the method and the device, the target electroencephalogram signal to be processed is determined, the target electroencephalogram signal is converted into the power spectrum, the characteristic value of the designated electroencephalogram in the power spectrum is determined, the attention level to which the characteristic value belongs is determined according to the pre-constructed attention level classifier, and the attention is identified through the attention level classifier, so that the purpose of automatically identifying the attention is achieved, the identification efficiency of the attention level is improved, the application scene of the attention identification is expanded, and necessary data basis is provided for the intervention of users in different application scenes.

In some embodiments, as shown in fig. 1, before the step of determining the attention level to which the feature value belongs in step S104 according to a pre-constructed attention level classifier, the method further includes: step S1041, step S1042, and step S1043 (not shown in the figure).

Step S1041: acquiring a plurality of characteristic values aiming at the specified brain waves;

step S1042: determining the attention level of each of the plurality of characteristic values;

step S1043: and training a preset classifier according to the plurality of characteristic values and the respective attention grades of the plurality of characteristic values to obtain an attention grade classifier.

Specifically, a plurality of feature values and respective attention levels of the feature values are used as sample data, the sample data can be divided into training data and verification data during training, so that the training is performed through a training data SVM classifier, and the output result of the SVM classifier is verified by using the verification data.

Specifically, the attention level of each feature value may be pre-labeled, that is, each acquired feature value is labeled with information on the attention level. For example, when the attention collecting device acquires a plurality of feature values and finishes labeling operation on the feature values, the feature values are reported to the electronic device, so that the electronic device may acquire the feature values with attention level labels.

Specifically, after obtaining each feature value, a preset interface is provided to enable a user to perform labeling operation on each feature value, so as to obtain an attention level corresponding to each feature value, that is, the attention level corresponding to each feature value is obtained by labeling the user in real time.

Specifically, the characteristic value may include a power spectrum energy value of an α wave, a β wave, a θ wave, a δ wave, a γ wave, or the like, and may further include a power spectrum energy value of any two of these waves.

In some embodiments, the step S1042 of determining the attention level of each of the plurality of feature values further comprises:

acquiring identification operation aiming at a plurality of characteristic values based on a preset interface;

according to the identification operation, the attention level of each of the characteristic values is determined.

Specifically, an interactive interface for performing identification processing on a plurality of feature values may be provided through a preset interface, and when the interactive interface is applied, each feature value is detected by the interactive interface, so as to ensure that each feature value has a corresponding attention level. More specifically, the attention levels respectively corresponding to the feature values may be identified by using preset level identifiers. For example, T1 indicates a high level of attention in the attention rank, T2 indicates a medium level of attention in the attention rank, T3 indicates a low level of attention in the attention rank, and so on.

In some embodiments, the step S103 of determining the feature value of the designated brain wave in the power spectrum further includes:

determining a spectral region of the designated brain wave based on the power spectrum;

and determining the characteristic value of the Shannon entropy of the frequency spectrum region of the appointed brain wave according to a preset Shannon entropy algorithm.

In the embodiment of the present application, shannon entropy is used to quantify brain waves.

In some embodiments, the step S101 of determining the target brain electrical signal to be processed further comprises:

acquiring an electroencephalogram signal of a target user;

and carrying out segmentation processing on the electroencephalogram signals according to the preset segmentation duration to obtain a plurality of target electroencephalogram signals to be processed.

Specifically, the electroencephalogram of the target user may be acquired from the electroencephalogram EEG acquisition device according to a preset reporting period, or may be read from a local cache.

Specifically, the segment duration is generally set according to the duration of the electroencephalogram acquired by the word. For example, the segment duration is 0.2 times the brain electrical signal duration.

In some embodiments, before transforming the brain electrical signal into a power spectrum at step S102, the method further comprises:

and filtering and removing false processing are carried out on the electroencephalogram signals.

Specifically, the electroencephalogram signal conforming to the predetermined frequency range can be acquired according to a preset high-pass filter and a preset low-pass filter. For example, a signal of 0.5Hz-60Hz is extracted from the brain electrical signal by the filtering process of a high-pass filter and a low-pass filter. More specifically, the 50Hz signal in the 0.5Hz-60Hz signals can be filtered to eliminate the mains interference.

Specifically, principal component analysis (ICA) may be employed to identify and remove brain electrical artifacts. When the method is applied, a JADE algorithm can be adopted to compress a four-order cumulant matrix (or a second-order correlation matrix) of the whitened mixed signal into a diagonal matrix through U transformation, so that the matrix U is solved, and the removal of artifacts such as electrooculogram and myoelectricity is realized.

In some embodiments, the method further comprises:

determining a selected target application scene according to a plurality of application scenes provided in advance;

and determining intervention information matched with the attention level to which the characteristic value belongs based on the intervention strategy aiming at the target application scene so as to perform intervention processing according to the intervention information.

Specifically, different application scenarios correspond to different intervention strategies. The application scenarios may include learning, listening to songs, meditation, etc. For example, if the application scenario is listening to songs, the corresponding intervention policy may be a preset song playing policy (e.g., a policy for playing songs according to the user's interest points).

Specifically, when a selected operation for a plurality of application scenarios provided in advance is detected, a target application scenario corresponding to the selected operation is determined, and intervention information is determined according to an intervention strategy for the target application scenario.

In particular, the intervention information may comprise voice prompt instructions. When the method is applied, the electronic equipment issues the intervention information to the attention detection equipment, so that the attention detection equipment intervenes the wearing user, and the attention of the wearing user is improved.

Yet another embodiment of the present application provides an apparatus for recognizing attention, as shown in fig. 2, the apparatus 20 including: a target signal determination module 201, a target signal conversion module 202, a feature value determination module 203, and an attention recognition module 204.

A target signal determination module 201, configured to determine a target electroencephalogram signal to be processed;

a target signal conversion module 202, configured to convert a target electroencephalogram signal into a power spectrum;

a feature value determination module 203, configured to determine a feature value of a designated brain wave in the power spectrum;

and the attention recognition module 204 is used for determining the attention level to which the characteristic value belongs according to the pre-constructed attention level classifier.

According to the method and the device, the target electroencephalogram signal to be processed is determined, the target electroencephalogram signal is converted into the power spectrum, the characteristic value of the designated electroencephalogram in the power spectrum is determined, the attention level to which the characteristic value belongs is determined according to the pre-constructed attention level classifier, and the attention is identified through the attention level classifier, so that the purpose of automatically identifying the attention is achieved, the efficiency of the attention identification is improved, the application scene of the attention identification is expanded, and a necessary data basis is provided for the intervention of users in different application scenes.

Further, before the step of determining the attention level to which the feature value belongs according to the pre-constructed attention level classifier, the attention identification module further includes:

the data acquisition sub-module is used for acquiring a plurality of characteristic values aiming at the specified brain waves;

the grade determining submodule is used for determining the attention grade of each of a plurality of characteristic values;

and the classifier training submodule is used for training a preset classifier according to the plurality of characteristic values and the attention grades of the characteristic values to obtain the attention grade classifier.

Further, the classifier training sub-module includes:

the operation acquisition unit is used for acquiring identification operations aiming at a plurality of characteristic values based on a preset interface;

and the grade determining unit is used for determining the attention grade of each of the characteristic values according to the identification operation.

Further, the feature value determination module includes:

a frequency spectrum region determining submodule for determining a frequency spectrum region for the specified brain wave in the power spectrum;

and the characteristic value operator module is used for determining the characteristic value of the Shannon entropy of the frequency spectrum region aiming at the appointed brain wave according to a preset Shannon entropy algorithm.

Further, the target signal determination module includes:

the electroencephalogram signal acquisition sub-module is used for acquiring an electroencephalogram signal of a target user;

and the signal segmentation processing submodule is used for carrying out segmentation processing on the electroencephalogram signals according to preset segmentation time to obtain a plurality of sections of target electroencephalogram signals to be processed.

Further, before transforming the electroencephalogram signal into a power spectrum, the target signal conversion module further includes:

and the signal preprocessing submodule can be used for filtering and removing false from the electroencephalogram signals.

Further, the apparatus further comprises:

the scene determining module is used for determining the selected target application scene according to a plurality of preset application scenes;

and the intervention information determining module is used for determining intervention information matched with the attention level to which the characteristic value belongs based on an intervention strategy aiming at the target application scene so as to perform intervention processing according to the intervention information.

The attention recognizing device of the present embodiment can execute the attention recognizing method provided in the embodiments of the present application, and the implementation principles thereof are similar and will not be described herein again.

Another embodiment of the present application provides a terminal, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program, to implement the above-mentioned method of identifying attention.

In particular, the processor may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like.

In particular, the processor is coupled to the memory via a bus, which may include a path for communicating information. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.

The memory may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

Optionally, the memory is used for storing codes of computer programs for executing the scheme of the application, and the processor is used for controlling the execution. The processor is configured to execute the application program code stored in the memory to implement the actions of the apparatus for recognizing attention provided by the above-mentioned embodiments.

Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the above-mentioned method of identifying attention.

The above-described embodiments of the apparatus are merely illustrative, and the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.

While the present invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.