Methods, devices, and equipment for determining personality types based on finite-lead EEG signals

Abstract

This disclosure provides a method, apparatus, and device for determining personality types based on few-lead EEG signals. The method includes: acquiring few-lead EEG signals from a target object using a few-lead EEG acquisition device; determining the power spectral density characteristics corresponding to a preset frequency band based on the few-lead EEG signals, wherein the preset frequency band includes at least one pre-determined frequency band related to personality determination; determining the target personality type of the target object using a pre-trained personality index regression prediction model based on the power spectral density characteristics corresponding to the preset frequency band; and outputting the target personality type of the target object. This disclosure enables real-time online personality type determination and output based on few-lead EEG signals, effectively improving the convenience and universality of personality type determination. It is applicable to most scenarios in daily life and solves the problem that the application scenarios of existing multi-lead EEG signals are limited by the acquisition equipment.

Description

Technical Field

[0001] This disclosure relates to computer technology, and in particular to a method, apparatus, and device for determining personality types based on few-lead electroencephalogram (EEG) signals. Background Technology

[0002] Personality is the unique pattern that constitutes a person's thoughts, feelings, and behaviors. This unique pattern includes stable and consistent typical psychological qualities that distinguish one person from another. The determination of personality types has been extensively studied in the field of psychology and has high application value in clinical psychology, health psychology, developmental psychology, vocational psychology, management psychology, and industrial psychology. Among related technologies, the Big Five personality type is representative. The Big Five personality type uses five traits to cover various aspects of personality description: neuroticism, extraversion, openness, agreeableness, and conscientiousness. In recent years, the use of physiological indicators to determine personality types has begun to emerge. This involves recording physiological indicators such as electrocardiogram (ECG), electrodermal conductance (EDA), and electroencephalogram (EEG) signals of the target subjects (subjects) when determining other personality types. Physiological changes in inner emotions can better avoid social desirability bias and deception. Among them, EEG signals, as a type of online real-time continuous physiological data, have unique advantages such as being tamper-proof and tamper-proof. In related technologies, multi-lead EEG signals are usually used to determine the personality type of the target object. However, the acquisition of multi-lead EEG signals is limited by the EEG signal acquisition equipment, which makes it inconvenient to determine the personality type based on multi-lead EEG signals, severely restricting the application scenarios and preventing real-time online personality type determination. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and device for determining personality types based on few-lead EEG signals, thereby improving the convenience of personality type determination.

[0004] One aspect of this disclosure provides a method for determining personality types based on few-lead EEG signals, including:

[0005] Acquire low-lead EEG signals from the target subject using a low-lead EEG acquisition device;

[0006] Based on the few-lead EEG signal, the power spectral density characteristics corresponding to a preset frequency band are determined. The preset frequency band includes at least one frequency band that is pre-determined and related to personality determination. The power spectral density characteristics corresponding to the preset frequency band are features that are highly correlated with personality type among various features determined by a preset analysis method.

[0007] Based on the power spectral density characteristics corresponding to the preset frequency band, the target personality type of the target object is determined by using a pre-trained personality index regression prediction model.

[0008] Output the target personality type to which the target object belongs.

[0009] Another aspect of this disclosure provides a personality type determination device based on few-lead EEG signals, comprising:

[0010] The acquisition module is used to acquire the few-lead EEG signals of the target object from the few-lead EEG acquisition device;

[0011] The first processing module is used to determine the power spectral density characteristics corresponding to a preset frequency band based on the few-lead EEG signal. The preset frequency band includes at least one frequency band that is pre-determined and related to personality determination. The power spectral density characteristics corresponding to the preset frequency band are features that are highly correlated with personality type among various features determined by a preset analysis method.

[0012] The second processing module is used to determine the target personality type of the target object based on the power spectral density characteristics corresponding to the preset frequency band and using a pre-trained personality index regression prediction model.

[0013] The output module is used to output the target personality type to which the target object belongs.

[0014] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the personality type determination method based on few-lead EEG signals described in any of the above embodiments of the present disclosure.

[0015] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0016] Memory, used to store computer program products;

[0017] A processor is configured to execute a computer program product stored in the memory, and when the computer program product is executed, to implement the personality type determination method based on few-lead EEG signals as described in any of the above embodiments of this disclosure.

[0018] According to another aspect of the embodiments of this disclosure, a personality type determination system based on few-lead EEG signals is provided, comprising:

[0019] Low-lead EEG acquisition equipment is used to acquire low-lead EEG signals from target subjects;

[0020] The personality type determination device based on few-lead EEG signals provided by any of the above aspects is used to determine the target personality type of the target object based on the few-lead EEG signals of the target object, and output it to a display device;

[0021] A display device for displaying the target personality type to which the target object belongs.

[0022] The method, apparatus, and device for determining personality types based on few-lead EEG signals disclosed herein acquire few-lead EEG signals from a target subject using a few-lead EEG acquisition device. Based on the few-lead EEG signals, the power spectral density characteristics corresponding to a preset frequency band are determined. Based on the power spectral density characteristics corresponding to the preset frequency band, a pre-trained personality index regression prediction model is used to determine the target personality type of the target subject and output the target personality type. This achieves personality type determination based on few-lead EEG signals, effectively improving the convenience of personality type determination and thus enhancing the versatility of the method. It can be applied to most scenarios in daily life, solving the problem that the application scenarios are limited by the acquisition device of multi-lead EEG signals in existing technologies. Furthermore, the method disclosed herein can achieve real-time online personality type determination and rapid real-time output.

[0023] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0025] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein:

[0026] Figure 1 This is a flowchart illustrating a method for determining personality types based on few-lead EEG signals provided in an exemplary embodiment of this disclosure;

[0027] Figure 2 This is a flowchart illustrating a method for determining personality types based on few-lead EEG signals provided in another exemplary embodiment of this disclosure;

[0028] Figure 3 This is a flowchart illustrating step 202 provided in an exemplary embodiment of this disclosure;

[0029] Figure 4 This is a schematic diagram of the structure of a residual block provided in an exemplary embodiment of this disclosure;

[0030] Figure 5 This is a schematic diagram of the overall network structure of the personality index regression prediction model provided in an exemplary embodiment of this disclosure;

[0031] Figure 6 This is a schematic diagram of the overall network structure of a personality index regression prediction model provided in another exemplary embodiment of this disclosure;

[0032] Figure 7 This is a schematic diagram illustrating the display method of the target personality type provided in an exemplary embodiment of this disclosure;

[0033] Figure 8 This is a schematic diagram illustrating the process for determining features that are highly correlated with personality type, provided in an exemplary embodiment of this disclosure.

[0034] Figure 9 This is a schematic diagram of the structure of a personality type determination device based on few-lead EEG signals provided in an exemplary embodiment of this disclosure;

[0035] Figure 10 This is a schematic diagram of the structure of a personality type determination device based on few-lead EEG signals provided in another exemplary embodiment of this disclosure;

[0036] Figure 11 This is a schematic diagram of the structure of a personality type determination system based on few-lead EEG signals provided in an exemplary embodiment of this disclosure;

[0037] Figure 12 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Detailed Implementation

[0038] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0039] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0040] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0041] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0042] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0043] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0044] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0045] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0046] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0047] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0048] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0049] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0050] This disclosure outlines

[0051] In the process of realizing this disclosure, the inventors discovered that EEG signals, as a type of online real-time continuous physiological data, have unique advantages such as being tamper-proof and tamper-proof. In related technologies, multi-lead EEG signals are usually used to determine the personality type of a target object. However, the acquisition of multi-lead EEG signals is limited by the EEG signal acquisition equipment, which makes it inconvenient to determine the personality type based on multi-lead EEG signals, and the application scenarios are severely restricted.

[0052] Exemplary Overview

[0053] In human resource recruitment scenarios, a few-lead EEG acquisition device can be used to collect few-lead EEG signals from applicants. Using the personality type determination method based on few-lead EEG signals disclosed herein, applicants are selected as target subjects. The few-lead EEG signals from the target subjects are acquired using the few-lead EEG acquisition device. Based on the few-lead EEG signals, the power spectral density characteristics corresponding to a preset frequency band are determined. Based on the power spectral density characteristics corresponding to the preset frequency band, a pre-trained personality index regression prediction model is used to determine the target personality type of the target subject and output the target personality type. Recruiters can then use the target personality type of each applicant as a reference to determine whether they are suitable for the job. For suitable applicants, more appropriate job content can be assigned based on their target personality type, and so on. The few-lead EEG signal is determined in contrast to the multi-lead EEG signal, which typically has 32 or more leads. The few-lead EEG signal disclosed herein can be a 1-lead, 2-lead, or 8-lead EEG signal, etc. This disclosure enables the determination of personality types based on a few-lead EEG signals, effectively improving the convenience of personality type determination and thus enhancing the versatility of the method. It can be applied to most scenarios in daily life, solving the problem that the application scenarios of existing technologies are limited by the acquisition equipment for multi-lead EEG signals.

[0054] Exemplary methods

[0055] Figure 1 This is a flowchart illustrating a method for determining personality types based on few-lead EEG signals, provided in an exemplary embodiment of this disclosure. The method includes the following steps:

[0056] Step 201: Acquire the low-lead EEG signal from the target subject using the low-lead EEG acquisition device.

[0057] The few-lead EEG acquisition device can be a 1-lead, 2-lead, or 8-lead device with fewer acquisition points. The target subject can be any person whose personality type needs to be determined, such as job applicants in a human resources recruitment scenario, or individuals whose mental health needs to be determined in a mental health scenario, etc. This disclosure does not impose any limitations. When the few-lead EEG acquisition device collects the target subject's few-lead EEG signals, the target subject can be placed in an environment that can induce their emotions. For example, the target subject can wear a portable few-lead EEG acquisition device and watch a pre-prepared video containing emotion-inducing materials. The EEG signals collected by the few-lead EEG acquisition device during the target subject's viewing are used as the target subject's few-lead EEG signals. The specific emotion-inducing materials and methods are not limited and can be set according to actual needs.

[0058] Step 202: Based on the few-lead EEG signal, determine the power spectral density characteristics corresponding to the preset frequency band. The preset frequency band includes at least one frequency band that is pre-determined and related to personality determination. The power spectral density characteristics corresponding to the preset frequency band are the characteristics with a high correlation to personality type among various characteristics determined by the preset analysis method.

[0059] Power spectral density (PSD) is a frequency domain characteristic of a signal, reflecting the signal power within a unit frequency band. The power spectral density characteristics of the target object in a preset frequency band can be extracted using any feasible method, such as extraction based on Fast Fourier Transform, or other methods; no specific limitation is imposed.

[0060] In one optional embodiment, the power spectral density characteristics of the preset frequency bands are features that are highly correlated with personality types, determined in advance through feature selection methods such as correlation analysis, principal component analysis, and sparse elastic regression networks. The specific determination process includes: pre-collecting few-lead EEG signals from multiple subjects (or test subjects) and obtaining the personality scale scores filled out by these subjects after the test; extracting various features based on the few-lead EEG signals of these subjects, such as time-domain features, frequency-domain features, and nonlinear features; and then performing correlation analysis, principal component analysis, and personality score regression using sparse elastic regression networks based on the extracted features and the subjects' personality scale scores to determine the features that are highly correlated with personality types. It was found that these features include features in five frequency bands, which are used as preset frequency bands. It was determined that the power spectral density characteristics of the five frequency bands are most effective for determining personality types. Therefore, the power spectral density characteristics of the preset frequency bands can be used alone for determining personality types.

[0061] In one optional embodiment, the preset frequency band includes five pre-determined frequency bands related to personality determination, specifically including five frequency bands: α (8-14Hz), β (14-32Hz), δ (1-4Hz), θ (4-8Hz), and γ (32-50Hz).

[0062] Step 203: Based on the power spectral density characteristics corresponding to the preset frequency band, use the personality index regression prediction model obtained through pre-training to determine the target personality type of the target object.

[0063] The personality index regression prediction model can employ any feasible neural network architecture, and this embodiment is not limited to any particular architecture. The output of the personality index regression prediction model can be the predicted score of the target object for each preset personality type, and then the target personality type to which the target object belongs can be determined based on the score. For example, the preset personality type with the highest score can be used as the target personality type, and the specific settings can be configured according to actual needs.

[0064] Step 204: Output the target personality type of the target object.

[0065] The output method can be set according to actual needs. For example, it can be output to other electronic devices (such as servers or terminal devices for statistical analysis) for other applications, or output to display devices for display. The specific settings can be set according to actual needs. The display device can be any device with display function, such as monitors, mobile phones, etc., without any specific limitations.

[0066] In an optional embodiment, step 204, which outputs the target personality type of the target object, may include: real-time online output of the target personality type of the target object.

[0067] The personality type determination method based on few-lead EEG signals provided in this disclosure acquires few-lead EEG signals from a target object using a few-lead EEG acquisition device. Based on the few-lead EEG signals, it determines the power spectral density characteristics corresponding to a preset frequency band. Based on the power spectral density characteristics corresponding to the preset frequency band, it uses a pre-trained personality index regression prediction model to determine the target personality type of the target object and outputs the target personality type. This method achieves personality type determination based on few-lead EEG signals, effectively improving the convenience of personality type determination and thus enhancing the versatility of the method. It can be applied to most scenarios in daily life, solving the problem that the application scenarios are limited by the acquisition device limitations of multi-lead EEG signals in existing technologies. Furthermore, because the few-lead EEG acquisition device is convenient and the most relevant features to personality type are determined, the method of this disclosure has high efficiency in determining personality type, enabling real-time online personality type determination and output. This solves the problem that existing technologies cannot perform real-time online personality type determination and output, effectively improving the user experience.

[0068] Figure 2 This is a flowchart illustrating a method for determining personality types based on few-lead EEG signals, provided in another exemplary embodiment of this disclosure.

[0069] In an optional embodiment, step 202, determining the power spectral density characteristics corresponding to a preset frequency band based on a few-lead EEG signals, includes:

[0070] Step 2021: Preprocess the few-lead EEG signal to obtain the preprocessed first EEG signal.

[0071] Preprocessing may include at least one of normalization, filtering, and independent component analysis, which can be set according to actual needs and is not limited in this embodiment. Normalization is used to normalize the EEG signals of a few leads to the [0-1] range to retain as many effective signal features as possible. Filtering is used to filter out artifacts that exceed the normal frequency range of EEG. Independent component analysis is used to analyze and remove artifacts such as electromyography (EMG) and electrooculography (EOG). Preprocessing can improve the effectiveness of EEG signals.

[0072] Step 2022: Extract features from the first EEG signal to obtain the power spectral density features corresponding to the preset frequency band.

[0073] The extraction method for power spectral density features can be set according to actual needs, such as using fast Fourier transform for extraction.

[0074] This embodiment improves the effectiveness of EEG signals by preprocessing the fewer-lead EEG signals, thereby enhancing the accuracy of the determined personality type.

[0075] Figure 3 This is a flowchart illustrating step 202 provided in an exemplary embodiment of this disclosure.

[0076] In an optional embodiment, step 2021, which preprocesses the few-lead EEG signal to obtain a preprocessed first EEG signal, includes:

[0077] Step 20211: Normalize the fewer-lead EEG signal to obtain the normalized second EEG signal.

[0078] The normalization process is used to normalize the EEG signals of a few leads to the range of [0-1] in order to preserve the effective signal features as much as possible.

[0079] Step 20212: Filter the second EEG signal to remove artifact interference that exceeds the preset frequency band range, and obtain the filtered third EEG signal.

[0080] The preset frequency band range can be determined based on the frequency band range of the EEG signal, and is used to characterize the normal frequency band range of the EEG signal. The second EEG signal is filtered to remove artifacts and interference that exceed the normal frequency band range of the EEG, further improving the effectiveness of the EEG signal.

[0081] In one alternative embodiment, filtering of the second EEG signal can be achieved based on Fourier transform or other filtering methods, which can be set according to actual needs.

[0082] Step 20213: Perform independent component analysis on the third EEG signal to remove artifact components and obtain the first EEG signal.

[0083] Independent Component Analysis (ICA) is a signal processing method used to separate multivariate signals into sub-components. In this disclosure, it is used to decompose the real EEG signal and other artifact components from the third EEG signal. The artifact components may include components such as electromyography (EMG) signals and electrooculography (EOG) signals, thereby removing the artifact components and further improving the effectiveness of the EEG signal.

[0084] This embodiment preserves effective signal features as much as possible through normalization processing, removes artifact interference that exceeds the normal frequency range of EEG through filtering processing, and removes artifact components such as electrooculogram (EOG) and electromyogram (EMG) signals through independent component analysis, thereby further improving the effectiveness of EEG signals and thus improving the accuracy of the determined personality type.

[0085] In an optional embodiment, step 2022, which involves feature extraction from the first EEG signal to obtain power spectral density features corresponding to a preset frequency band, includes:

[0086] Step 20221: Process the first EEG signal based on Fast Fourier Transform to obtain the power spectral density characteristics corresponding to the preset frequency band. The preset frequency band includes five frequency bands: α band, β band, δ band, θ band and γ band.

[0087] The frequency ranges are as follows: α band: 8Hz-14Hz; β band: 14Hz-32Hz; δ band: 1Hz-4Hz; θ band: 4Hz-8Hz; and γ band: 32Hz-50Hz.

[0088] Through pre-analysis and feature selection, five frequency bands—α, β, δ, θ, and γ—were identified as relevant to personality prediction. To obtain a more accurate personality type, this embodiment uses Fast Fourier Transform to extract the power spectral density features corresponding to these five frequency bands from the first EEG signal for subsequent personality type determination, further improving the accuracy of the determined personality type.

[0089] In an optional embodiment, the personality index regression prediction model includes a spatial information extraction network, a feature fusion network, and a temporal information extraction network; step 203, based on the power spectral density features corresponding to a preset frequency band, uses the pre-trained personality index regression prediction model to determine the target personality type of the target object, including:

[0090] Step 2031: Using a spatial information extraction network, spatial features are extracted from the power spectral density features corresponding to the preset frequency band to obtain spatial feature information. The spatial information extraction network is a lightweight residual neural network.

[0091] In an optional example, the lightweight residual neural network may include a first number of residual blocks, which can be set according to actual needs, such as 4. The obtained spatial feature information is high-dimensional.

[0092] In one optional example, the lightweight residual neural network may include a first number of residual blocks.

[0093] In one optional example, Figure 4 This is a schematic diagram of the structure of a residual block provided in an exemplary embodiment of this disclosure. Each residual block may include a convolutional layer (Conv2d), a batch normalization layer (BatchNorm), and an activation layer (ReLU). The specific structure of each layer can be set according to actual needs, and this disclosure does not limit it.

[0094] Step 2032: Use a feature fusion network to perform feature fusion on the spatial feature information to obtain the fused first feature information.

[0095] In an optional example, the feature fusion network may include a second number of residual blocks or convolutional layers. Feature fusion is used to reduce the dimensionality of spatial feature information by fusing high-dimensional channel features of spatial feature information into low-dimensional features. The second number can be set according to actual needs; for example, the second number can be set to 1 or other values. This embodiment does not limit this.

[0096] Step 2033: The first feature information is processed using a time information extraction network to obtain the scores of the target object in each preset personality type. The time information extraction network is a long short-term memory network.

[0097] Since the spatial information of the few-lead EEG signal is limited, this embodiment further extracts the temporal dimension features of the EEG signal based on a temporal information extraction network and performs regression prediction of personality scores. The specific structure of the long short-term memory network used in the temporal information extraction network can be set according to actual needs, and this disclosure does not limit it. The preset personality type can be set according to actual needs. For example, the preset personality type may include the Big Five personality types: neuroticism, extraversion, openness, agreeableness, and conscientiousness.

[0098] Step 2034: Based on the scores of the target object in each preset personality type, determine the target personality type to which the target object belongs.

[0099] This allows you to set mapping rules between scores and personality types. For example, you can set the preset personality type with the highest score as the target personality type. The specific mapping rules can be set according to actual needs.

[0100] This embodiment extracts spatial and temporal features of the power spectral density characteristics of a preset frequency band for personality type prediction, effectively improving the accuracy of the prediction results.

[0101] In one optional example, Figure 5This is a schematic diagram of the overall network structure of the personality index regression prediction model provided in an exemplary embodiment of this disclosure. LSTM (Long Short-Term Memory) represents a long short-term memory network, serving as the temporal information extraction network. LSTM is a special type of recurrent neural network (RNN), which performs better with longer sequences; the specific structure can be set according to actual needs. Mapping is used to determine the target personality type of the target object based on the scores and mapping rules corresponding to each preset personality type. The spatial information extraction network includes four residual blocks. Considering the small amount of EEG signal data in few leads, this example uses a lightweight residual neural network as the spatial information extraction network. Specifically, the lightweight residual neural network in this example only retains four residual blocks of the ResNet network for spatial feature extraction. The feature fusion network includes one residual block. While the spatial information extraction network fully extracts the high-dimensional spatial information of the few-lead EEG signals, excessive dimensionality can easily lead to data redundancy. This example uses a feature fusion network to fuse high-dimensional channel features into low-dimensional features, reducing feature dimensionality, thereby reducing redundancy and improving feature effectiveness. Skip Connection represents a skip connection. ⊕ represents add. Skip connections are used to connect the output of residual block 1 to ⊕, adding it to the output of residual block 4 to obtain spatial feature information for subsequent feature fusion. This is an exemplary network structure of the model and is not a limitation of this disclosure. In practical applications, the specific structure of each part can be set to other structures according to actual needs.

[0102] In an optional example, the LSTM can employ a single-layer unidirectional network structure with a hidden layer size of 5. Since the LSTM is tasked with both extracting temporal features and performing score regression prediction, its output will be directly used as the prediction result. However, the LSTM output ranges between (-1, 1), while the predicted label ranges between (0, 100). Therefore, a linear transformation is performed on the LSTM output to map it to a score within the range of (0, 100).

[0103] In one optional example, Figure 6This is a schematic diagram of the overall network structure of a personality index regression prediction model provided in another exemplary embodiment of this disclosure. In this example, the spatial information extraction network includes four residual blocks, an additive layer (⊕), and an activation layer (ReLU). The output of residual block 1 is downsampled by a convolutional layer with a kernel of 1×1 and a stride of 8, and then added to the output of residual block 4. The result of the addition is output after passing through the ReLU activation function. The feature fusion network includes a residual block (residual block 5) or a convolutional layer (e.g., a 3×3 convolutional layer), which downsamples the output of the spatial information extraction network in the channel dimension, reducing the feature dimension of the input LSTM. See other parts for further details. Figure 5 This will not be elaborated upon here.

[0104] In an optional example, each residual block of the spatial information extraction network can include a 3×3 convolutional kernel with padding set to 1, and the stride of the convolutional layers in residual blocks 3 and 4 can be set to 2.

[0105] In an optional embodiment, step 204 outputs the target personality type to which the target object belongs, including:

[0106] Step 2041: Send the target personality type of the target object and the corresponding description information to the display device so that the display device displays the target personality type and the corresponding description information according to the preset display method.

[0107] The descriptive information corresponding to the target personality type describes the traits possessed by individuals with that personality type. This information can be customized according to actual needs. For example, descriptive information can be pre-defined and stored for each preset personality type. Once the target personality type is determined, the descriptive information corresponding to the target personality type is obtained based on the correspondence between the preset personality types and their descriptive information. For instance, the descriptive information for the openness personality type might be described as having traits such as imagination, aesthetics, rich emotions, a desire for difference, creativity, and intelligence. The specific content of the descriptive information is not limited. The preset display method can be customized according to actual needs. For example, it could display the scores for each personality type in the Big Five personality types using a radar chart (or pentagon chart), and display the target personality type and its corresponding descriptive information via text. For example... Figure 7 This is a schematic diagram illustrating the display method of the target personality type provided in an exemplary embodiment of this disclosure.

[0108] In an optional embodiment, step 204, which outputs the target personality type of the target object, includes: sending the target personality type of the target object and the corresponding description information to the display device online in real time, so that the display device displays the target personality type and the corresponding description information according to a preset display method.

[0109] Because this disclosure utilizes a convenient few-lead EEG acquisition device to obtain few-lead EEG signals, and the personality index regression prediction model is a lightweight model, and the power spectral density characteristics corresponding to a preset frequency band are pre-analyzed and determined to be highly correlated with personality type, it can quickly and accurately determine the target personality type of the target object, facilitating real-time online personality type determination. Compared with existing technologies based on multi-lead EEG signals for personality type determination, this disclosure significantly improves real-time performance. Furthermore, existing technologies based on multi-lead EEG signals for personality type determination are limited by multi-lead EEG acquisition devices, involve large data volumes, and have complex processing methods, resulting in long computation times from data input to result output, making real-time online personality determination impossible. This disclosure, however, enables real-time online personality determination and output.

[0110] In one optional embodiment, the display device can be a display device connected to the present disclosure device in any manner. For example, it can be the display part of the electronic device in which the present disclosure device is located, or it can be a display device independent of the electronic device in which the present disclosure device is located. For example, the electronic device in which the present disclosure device is located is a server, and the display device is a terminal device with display function connected to the server. The specific details are not limited.

[0111] Figure 8 This is a schematic diagram illustrating the process for determining features that are highly correlated with personality type, provided by an exemplary embodiment of this disclosure.

[0112] In an optional embodiment, the method of this disclosure further includes:

[0113] Step 301: Collect the EEG signals of multiple subjects under the influence of a preset experimental paradigm using a portable low-lead EEG acquisition device, and obtain the personality scale scores corresponding to each subject.

[0114] The subjects are selected users who consent to participate. The number of subjects can be determined based on actual needs. The pre-set experimental paradigm is a video or scene played according to certain rules, intended for viewing by the subjects to influence their EEG signals; its specific format is not limited. The personality scale rating is the score provided by the subjects after viewing the pre-set experimental paradigm, based on their actual feelings. The personality scale rating can determine the personality type of the subject under the influence of the pre-set paradigm, serving as a reference true value.

[0115] Step 302: Preprocess the EEG signals of the few leads to be analyzed for each subject to obtain the first preprocessed EEG signal to be analyzed for each subject.

[0116] Preprocessing can include normalization, filtering, and independent component analysis, which can be set according to actual needs.

[0117] Step 303: Extract features from the first EEG signal to be analyzed for each subject to obtain features of a preset type for each first EEG signal to be analyzed. The preset types include time-domain type, frequency-domain type and nonlinear type. The features of each preset type include at least one feature.

[0118] For example, time-domain features may include mean, maximum, minimum, peak-to-peak value, skewness coefficient, and kurtosis coefficient. Frequency-domain features may include power spectral density and other relevant frequency-domain features for five frequency bands: α (8–14 Hz), β (14–32 Hz), δ (1–4 Hz), θ (4–8 Hz), and γ (32–50 Hz). Nonlinear features may include wavelet entropy, detrending analysis, Hearst exponent, fractal dimension, sample entropy, permutation entropy, and Hjorth parameter. Specific features can be set according to actual needs.

[0119] Step 304: Based on the features of each preset type corresponding to the first EEG signal to be analyzed and the personality scale scores corresponding to each subject, a preset analysis method is used to determine the correlation between the features of each preset type and the personality type.

[0120] The preset analysis methods can include correlation analysis, feature selection, and personality score prediction of selected target features, used to determine the correlation between various features and personality types. Specific settings can be configured according to actual needs.

[0121] Step 305: Based on the correlation between the features of each preset type and the personality type, determine that the power spectral density feature of the preset frequency band is the feature with a high correlation to the personality type.

[0122] Following the aforementioned analysis process, the power spectral density characteristics of the five frequency bands α (8-14Hz), β (14-32Hz), δ (1-4Hz), θ (4-8Hz), and γ (32-50Hz) were determined to be the most effective features for determining personality type. Therefore, the power spectral density characteristics of these five frequency bands were taken as the features with the highest (or greatest) correlation with personality type.

[0123] In an optional embodiment, step 304, based on the features of each preset type corresponding to the first EEG signals to be analyzed and the personality scale scores corresponding to each subject, uses a preset analysis method to determine the correlation between the features of each preset type and the personality type, including:

[0124] 1. Based on the features of each of the first EEG signals to be analyzed and the personality scale scores of each subject, correlation analysis was used to determine the correlation coefficients between each feature and the personality type.

[0125] 2. Based on the correlation coefficients between various features and personality types, principal component analysis algorithm is used to process the features of the preset type to obtain the processed target features.

[0126] 3. Based on the processed target features, a pre-trained sparse elastic regression network is used to predict personality scores, obtaining the personality score prediction results corresponding to each target feature.

[0127] The sparse elastic regression network is a pre-trained neural network used to predict personality scores. The predicted personality scores can include scores corresponding to each personality type. Based on this, the effectiveness of the target feature for the personality type can be determined; higher scores indicate stronger effectiveness and greater correlation.

[0128] 4. Based on the personality score prediction results corresponding to each target feature, determine the correlation between each target feature and personality type.

[0129] The mapping relationship between different personality score prediction results and correlation can be preset, or the score value can be directly used as the correlation value. The specific settings can be set according to actual needs, and this disclosure does not limit them.

[0130] In an alternative embodiment, the traits most relevant to personality type can be determined through the following process:

[0131] I. Establishing an experimental paradigm for personality determination:

[0132] 1. Select Chinese words that can evoke emotions from the emotional vocabulary database as emotional triggering materials.

[0133] 2. Determine the duration, time interval, and order of occurrence of emotional words.

[0134] 3. Determine the experimental instructions and rest time.

[0135] For example, a total of 200 two-character emotional words were identified, such as the positive word "admiration", the negative word "fear", and the neutral word "Zhang San". The duration, time interval and order of appearance of the emotional words were determined, for example, each emotional word appeared for 200ms, the time interval was 2200ms, and they appeared in a fixed order. The experimental instructions (such as please press the button to start the experiment, please close your eyes for 1 minute, etc.) and rest time (the rest time at each stage of the experiment) were determined.

[0136] II. Data Acquisition by Portable Low-Lead EEG Acquisition Device:

[0137] 1. Subjects wore portable low-lead EEG acquisition devices and watched the personality determination experiment paradigm.

[0138] 2. Automatic acquisition and segmentation program for subject's electroencephalogram (EEG) signals.

[0139] For example, the data collected included EEG data from 124 subjects, as well as corresponding Big Five personality traits scores and keystroke logs.

[0140] 3. Constructing a dataset for personality determination using low-lead EEG:

[0141] This mainly includes: EEG data of subjects watching the personality identification experimental paradigm; and documents recording the order and timing of word appearance in the experimental paradigm.

[0142] III. Preprocessing of Fewer Lead EEG Signals:

[0143] 1. Normalization of EEG signals: Normalize the EEG signals to obtain normalized EEG signals.

[0144] 2. EEG signal filtering: The normalized EEG signal is filtered to remove artifacts that are outside the normal frequency range of EEG, and the EEG signal after interference removal is obtained.

[0145] 3. Perform independent component analysis on the interference-free EEG signal to remove artifacts such as electromyography (EMG) and electrooculography (EOG) signals obtained from the analysis results, and obtain the preprocessed EEG signal.

[0146] IV. Extraction of EEG features from fewer leads:

[0147] 1. Extract the temporal features of the preprocessed EEG signal, such as extracting some statistical features of the EEG signal, which may include mean, maximum, minimum, peak-to-peak value, skewness coefficient, kurtosis coefficient, etc.

[0148] For example, the preprocessed EEG data is segmented and normalized features are extracted, including mean, standard deviation, root mean square value, skewness, kurtosis, peak-to-mean ratio, percentage of maximum-to-minimum difference, etc.

[0149] 2. Extract the frequency domain features of the preprocessed EEG signal, such as calculating the power spectral density of the five frequency bands α (8-14Hz), β (14-32Hz), δ (1-4Hz), θ (4-8Hz), and γ (32-50Hz) based on Fast Fourier Transform.

[0150] 3. Extract nonlinear features from preprocessed EEG signals, such as features that represent nonlinear brain activity, including wavelet entropy, detrending analysis, Hearst exponent, fractal dimension, sample entropy, permutation entropy, Hjorth parameter, etc.

[0151] V. Assessment and Selection of Personality-Related EEG Characteristics:

[0152] Based on the characteristics of few-lead EEG signals, and with limited data, the features that best represent personality traits are extracted. The specific process is as follows:

[0153] 1. Using correlation analysis, analyze the correlation coefficients between all extracted EEG features and personality scores.

[0154] Specifically, the Pearson correlation coefficients of all traits and the scores (obtained from the Big Five Personality Inventory) corresponding to the five personality types are calculated to obtain the correlation between each trait and the five scores.

[0155] 2. The feature selection method, mainly the principal component analysis algorithm, is used to reduce the dimensionality of high-dimensional features and analyze the features obtained after dimensionality reduction.

[0156] Specifically, the PCA (Principal Component Analysis) algorithm can be used to reduce high-dimensional features to low-dimensional features, thus achieving feature selection. The results show that the selected dimensions are all within the power spectral density.

[0157] 3. The dimensionality-reduced EEG features were further used in a sparse elastic regression network for personality score prediction, and the effectiveness of the features was determined. Ultimately, the power spectral density of the five frequency bands α (8–14 Hz), β (14–32 Hz), δ (1–4 Hz), θ (4–8 Hz), and γ (32–50 Hz) were found to be effective for personality prediction.

[0158] In an optional embodiment, step 201, acquiring the few-lead EEG signal from the target object of the few-lead EEG acquisition device, may include: receiving the few-lead EEG signal uploaded by the few-lead EEG acquisition device.

[0159] In this process, after the target subjects have finished observing the personality determination experimental paradigm, the portable sparse-lead EEG acquisition device will automatically stop acquiring data and upload it in real time to the device disclosed herein. The device disclosed herein can then acquire the sparse-lead EEG signals of the target subjects from the sparse-lead EEG acquisition device. Understandably, during the process of determining the preset frequency bands related to personality, the EEG signals of each subject can also be uploaded from the sparse-lead EEG acquisition device to an electronic device used for analysis to determine the effective preset frequency bands.

[0160] Specifically, the software of the few-lead EEG acquisition device can be set to automatically pause after the experimental paradigm is completed via a portable network interface, while saving the acquired EEG data and uploading it to the server. The specific upload method is not limited.

[0161] Any of the personality type determination methods based on few-lead EEG signals provided in this disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers. Alternatively, any of the personality type determination methods based on few-lead EEG signals provided in this disclosure can be executed by a processor, such as by a processor executing any of the personality type determination methods based on few-lead EEG signals mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated upon below.

[0162] Exemplary device

[0163] Figure 9 This is a schematic diagram of a personality type determination device based on few-lead EEG signals provided in an exemplary embodiment of this disclosure. The device in this embodiment can be used to implement corresponding method embodiments of this disclosure, such as… Figure 9 The device shown includes: an acquisition module 501, a first processing module 502, a second processing module 503, and an output module 504.

[0164] Acquisition module 501 is used to acquire the few-lead EEG signal of the target object from the few-lead EEG acquisition device;

[0165] The first processing module 502 is used to determine the power spectral density characteristics corresponding to a preset frequency band based on the few-lead EEG signal. The preset frequency band includes at least one frequency band that is pre-determined and related to the determination of personality. The power spectral density characteristics corresponding to the preset frequency band are features that are highly correlated with personality type among various features determined by a preset analysis method.

[0166] The second processing module 503 is used to determine the target personality type of the target object based on the power spectral density characteristics corresponding to the preset frequency band and using a pre-trained personality index regression prediction model.

[0167] Output module 504 is used to output the target personality type to which the target object belongs.

[0168] In an optional embodiment, the first processing module 502 is specifically used for:

[0169] The few-lead EEG signal is preprocessed to obtain a preprocessed first EEG signal; feature extraction is performed on the first EEG signal to obtain the power spectral density features corresponding to the preset frequency band.

[0170] In an optional embodiment, the first processing module 502 is specifically used for:

[0171] The few-lead EEG signal is normalized to obtain a normalized second EEG signal; the second EEG signal is filtered to remove artifact interference that exceeds the preset frequency band range to obtain a filtered third EEG signal; independent component analysis is performed on the third EEG signal to remove artifact components and obtain the first EEG signal.

[0172] In an optional embodiment, the first processing module 502 is specifically used for:

[0173] The first EEG signal is processed based on Fast Fourier Transform to obtain the power spectral density characteristics corresponding to the preset frequency band. The preset frequency band includes five frequency bands: α band, β band, δ band, θ band, and γ band. The frequency range corresponding to the α band is 8Hz-14Hz, the frequency range corresponding to the β band is 14Hz-32Hz, the frequency range corresponding to the δ band is 1Hz-4Hz, the frequency range corresponding to the θ band is 4Hz-8Hz, and the frequency range corresponding to the γ band is 32Hz-50Hz.

[0174] In an optional embodiment, the personality index regression prediction model includes a spatial information extraction network, a feature fusion network, and a temporal information extraction network; the second processing module 503 is specifically used for:

[0175] Using the spatial information extraction network, spatial features are extracted from the power spectral density features corresponding to the preset frequency band to obtain spatial feature information. The spatial information extraction network is a residual neural network, and the spatial information extraction network includes a first number of residual blocks. The spatial feature information is fused using the feature fusion network to obtain fused first feature information. The feature fusion network includes a second number of residual blocks. The first feature information is processed using the temporal information extraction network to obtain the scores of the target object corresponding to each preset personality type. The temporal information extraction network is a long short-term memory network. Based on the scores of the target object corresponding to each preset personality type, the target personality type to which the target object belongs is determined.

[0176] In an optional embodiment, the output module 504 is specifically used for:

[0177] The target personality type to which the target object belongs and the corresponding description information are sent to the display device so that the display device displays the target personality type and the corresponding description information according to a preset display method.

[0178] Figure 10 This is a schematic diagram of the structure of a personality type determination device based on few-lead EEG signals provided in another exemplary embodiment of this disclosure.

[0179] In an optional embodiment, the apparatus of this disclosure may further include: a third processing module 505, a fourth processing module 506, a fifth processing module 507, a sixth processing module 508, and a seventh processing module 509.

[0180] The third processing module 505 is used to collect the few-lead EEG signals of multiple subjects under the influence of a preset experimental paradigm based on a portable few-lead EEG acquisition device, and to obtain the personality scale scores corresponding to each subject.

[0181] The fourth processing module 506 is used to preprocess the few-lead EEG signals to be analyzed corresponding to each of the subjects, and obtain the preprocessed first EEG signals to be analyzed corresponding to each of the subjects.

[0182] The fifth processing module 507 is used to extract features from the first EEG signals to be analyzed corresponding to each of the subjects, and obtain features of a preset type corresponding to each of the first EEG signals to be analyzed. The preset type includes time-domain type, frequency-domain type and nonlinear type, and the features of each preset type include at least one feature.

[0183] The sixth processing module 508 is used to determine the correlation between the features of each preset type and the personality type based on the features of each of the first EEG signals to be analyzed and the personality scale scores of each of the subjects, using preset analysis rules.

[0184] The seventh processing module 509 is used to determine, based on the correlation between the features of each preset type and the personality type, that the power spectral density feature of the preset frequency band is a feature with a high correlation to the personality type.

[0185] In an optional embodiment, the sixth processing module 508 is specifically used for:

[0186] Based on the features of the preset types corresponding to each of the first EEG signals to be analyzed and the personality scale scores corresponding to each of the subjects, correlation analysis is used to determine the correlation coefficients between various features and personality types. Based on the correlation coefficients between various features and personality types, principal component analysis is used to process the features of the preset types to obtain processed target features. Based on each processed target feature, a pre-trained sparse elastic regression network is used to predict personality scores to obtain personality score prediction results corresponding to each target feature. Based on the personality score prediction results corresponding to each target feature, the correlation between each target feature and personality type is determined.

[0187] Figure 11 This is a schematic diagram of a personality type determination system based on few-lead EEG signals provided in an exemplary embodiment of this disclosure. The system of this embodiment can be used to implement the corresponding method embodiments of this disclosure. The system includes: a few-lead EEG acquisition device 61, a display device 62, and a personality type determination apparatus 50 based on few-lead EEG signals as provided in any of the above embodiments.

[0188] The low-lead EEG acquisition device 61 is used to acquire low-lead EEG signals from a target subject.

[0189] The personality type determination device 50 based on the few-lead EEG signal is used to determine the target personality type of the target object based on the few-lead EEG signal of the target object, and output it to the display device 62.

[0190] Display device 62 is used to display the target personality type to which the target object belongs.

[0191] Exemplary electronic devices

[0192] In addition, this disclosure also provides an electronic device, including:

[0193] A memory is used to store computer programs; a processor is used to execute the computer programs stored in the memory, and when the computer programs are executed, they implement the personality type determination method based on few-lead EEG signals described in any of the above embodiments of this disclosure.

[0194] Figure 12 This is a schematic diagram of the structure of one application embodiment of the electronic device disclosed herein. For example... Figure 12 As shown, the electronic device includes one or more processors and memory.

[0195] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0196] The memory can store one or more computer program products, and the memory can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program products can be stored on the computer-readable storage medium, and the processor can run the computer program products to implement the methods of the various embodiments of this disclosure described above and / or other desired functions.

[0197] In one example, the electronic device may also include input devices and output devices, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0198] In addition, the input device may also include, for example, a keyboard, a mouse, etc.

[0199] This output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0200] Of course, for the sake of simplicity, Figure 12 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0201] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of this disclosure as described in the foregoing portions of this specification.

[0202] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0203] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this disclosure described in the foregoing portion of this specification.

[0204] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0205] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0206] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0207] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0208] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0209] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0210] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0211] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0212] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for determining personality types based on few-lead EEG signals, characterized in that, include: Acquire low-lead EEG signals from the target subject using a low-lead EEG acquisition device; Based on the few-lead EEG signal, the power spectral density characteristics corresponding to a preset frequency band are determined. The preset frequency band includes at least one frequency band that is pre-determined and related to personality determination. The power spectral density characteristics corresponding to the preset frequency band are features that are highly correlated with personality type among various features determined by a preset analysis method. Based on the power spectral density characteristics corresponding to the preset frequency band, the target personality type of the target object is determined by using a pre-trained personality index regression prediction model. Output the target personality type to which the target object belongs; The personality index regression prediction model includes a spatial information extraction network, a feature fusion network, and a temporal information extraction network. The step of determining the target personality type of the target object based on the power spectral density features corresponding to the preset frequency band using the pre-trained personality index regression prediction model includes: using the spatial information extraction network to extract spatial features from the power spectral density features corresponding to the preset frequency band, obtaining spatial feature information; the spatial information extraction network is a lightweight residual neural network; using the feature fusion network to fuse the spatial feature information, obtaining fused first feature information; using the temporal information extraction network to process the first feature information, obtaining the score of the target object corresponding to each preset personality type, the temporal information extraction network being a long short-term memory network; and determining the target personality type of the target object based on the score of the target object corresponding to each preset personality type.

2. The method according to claim 1, characterized in that, Also includes: The portable low-lead EEG acquisition device was used to acquire low-lead EEG signals of multiple subjects under the influence of a preset experimental paradigm, and the personality scale scores of each subject were obtained. The few-lead EEG signals to be analyzed corresponding to each of the subjects are preprocessed to obtain the first preprocessed EEG signals to be analyzed corresponding to each of the subjects. Feature extraction is performed on the first EEG signal to be analyzed corresponding to each of the subjects to obtain features of a preset type corresponding to each of the first EEG signals to be analyzed. The preset type includes time domain type, frequency domain type and nonlinear type. The features of each preset type include at least one feature. Based on the features of the preset types corresponding to each of the first EEG signals to be analyzed and the personality scale scores corresponding to each of the subjects, preset analysis rules are used to determine the correlation between the features of each preset type and the personality type. Based on the correlation between the features of each preset type and the personality type, the power spectral density feature of the preset frequency band is determined to be a feature with a high correlation to the personality type.

3. The method according to claim 2, characterized in that, Based on the features of the preset types corresponding to each of the first EEG signals to be analyzed and the personality scale scores corresponding to each of the subjects, a preset analysis rule is used to determine the correlation between the features of each preset type and the personality type, including: Based on the features of the preset type corresponding to each of the first EEG signals to be analyzed and the personality scale scores corresponding to each of the subjects, the correlation analysis method is used to determine the correlation coefficients between various features and personality types. Based on the correlation coefficients between various features and personality types, principal component analysis algorithm is used to process the features of the preset type to obtain the processed target features; Based on the processed target features, a pre-trained sparse elastic regression network is used to predict personality scores, and the personality score prediction results corresponding to each target feature are obtained. Based on the personality score prediction results corresponding to each of the target features, the correlation between each target feature and the personality type is determined.

4. The method according to claim 1, characterized in that, The step of determining the power spectral density characteristics corresponding to a preset frequency band based on the few-lead EEG signal includes: The few-lead EEG signal is preprocessed to obtain the preprocessed first EEG signal; Feature extraction is performed on the first EEG signal to obtain the power spectral density features corresponding to the preset frequency band.

5. The method according to claim 1, characterized in that, The step of outputting the target personality type to which the target object belongs includes: The target personality type to which the target object belongs and the corresponding description information are sent to the display device so that the display device displays the target personality type and the corresponding description information according to a preset display method.

6. A personality type determination device based on few-lead EEG signals, characterized in that, include: The acquisition module is used to acquire the few-lead EEG signals of the target object from the few-lead EEG acquisition device; The first processing module is used to determine the power spectral density characteristics corresponding to a preset frequency band based on the few-lead EEG signal. The preset frequency band includes at least one frequency band that is pre-determined and related to personality determination. The power spectral density characteristics corresponding to the preset frequency band are features that are highly correlated with personality type among various features determined by a preset analysis method. The second processing module is used to determine the target personality type of the target object based on the power spectral density characteristics corresponding to the preset frequency band and using a pre-trained personality index regression prediction model. The output module is used to output the target personality type to which the target object belongs; The personality index regression prediction model includes a spatial information extraction network, a feature fusion network, and a temporal information extraction network. The second processing module is specifically used for: using the spatial information extraction network to extract spatial features from the power spectral density features corresponding to the preset frequency band, obtaining spatial feature information; the spatial information extraction network is a lightweight residual neural network; using the feature fusion network to fuse the spatial feature information, obtaining fused first feature information; using the temporal information extraction network to process the first feature information, obtaining the scores of the target object for each preset personality type, the temporal information extraction network being a long short-term memory network; and determining the target personality type to which the target object belongs based on the scores of the target object for each preset personality type.

7. An electronic device, characterized in that, include: Memory, used to store computer program products; A processor is configured to execute a computer program product stored in the memory, wherein, when the computer program product is executed, it implements the method described in any one of claims 1-5.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-5.

9. A personality type determination system based on few-lead EEG signals, characterized in that, include: Low-lead EEG acquisition equipment is used to acquire low-lead EEG signals from target subjects; The personality type determination device based on few-lead EEG signals as described in claim 6 is used to determine the target personality type of the target object based on the few-lead EEG signals of the target object, and output the result to a display device; A display device for displaying the target personality type to which the target object belongs.

Images