A lie detection method and device based on resting-state electroencephalogram microstates

Through the lie detection method based on resting state EEG microstate, pre-processing and principal component analysis are used using EEG data, combined with SVM classification model, the problems of nonspecificity of measurement indicators and anti-lie detection interference in the existing technology are solved. Achieve higher detection accuracy and generalizability.

CN115553775BActive Publication Date: 2024-11-26BEIJING MECHANICAL EQUIP INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211053252.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-30
Publication Date
2024-11-26
Estimated Expiration
2042-08-30

AI Technical Summary

Technical Problem

Existing lie detection methods, including physiological lie detectors and ERP methods based on EEG, have limitations, such as unspecific measurement indicators, large influences by external factors, and high requirements for the testing process, and are easily subject to anti-lie testing. interference.

Method used

Using a lie detection method based on resting state EEG microstate, the EEG data of the subjects in the preset state is collected through the EEG collection device, and preprocessing, principal component analysis and SVM classification model training are performed to generate lie detection results. , reduce the impact of anti-lie tests and reduce the cooperation requirements of the subjects.

Benefits of technology

Effectively reduce the impact of anti-lie detection, reduce the cooperation requirements of the subject, improve the accuracy and popularization of the lie detection, and achieve reliable detection of lies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115553775B_ABST
    Figure CN115553775B_ABST
Patent Text Reader

Abstract

The present disclosure is about a lie detection method, device, electronic device and storage medium based on resting-state EEG microstates. The method includes: based on an EEG acquisition device, collecting EEG data of the person being lied on in a preset state; calculating the microstate characteristics of the person being lied on based on the EEG data; performing principal component analysis on the microstate characteristics to generate characteristic values ​​of the microstate characteristics; using the characteristic values ​​of the microstate characteristics as input, generating lie detection results based on a preset SVM classification model. The resting-state EEG microstate analysis disclosed in the present disclosure determines the lie detection state, which can effectively reduce the impact of counter-lie detection, and has a lower requirement on the cooperation of the person being tested during the test, making it easier to promote and use.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0002] In the early days of lie detection, multi-channel physiological polygraphs were commonly used. These instruments measure the subject's autonomic nervous system responses during questioning, including changes in physiological parameters such as respiration, skin conductance, pulse, and blood pressure, to determine if a lie is being told. This method is based on the idea that when a person lies, psychological states such as guilt, panic, and fear can cause changes in certain physiological parameters. However, this lie detection method has significant limitations, and the specificity and universality of the physiological changes it measures remain uncertain. This is because the measured parameters are easily influenced by various factors, including the subject's physical function and psychological state, the polygraph environment, and the quality of the polygraph examiner. They can even be manipulated by psychologically competent subjects to successfully conceal their deception. Consequently, this method has come under increasing scrutiny.

[0003] In recent years, with the advancement of neuroimaging technologies such as event-related potentials (ERP) and functional magnetic resonance imaging (fMRI), lie detection methods based on central nervous system activity have gradually emerged. These methods are more objective than traditional lie detection techniques that rely on measuring external physiological signals. EEG signals, due to their high temporal resolution, ease of use, and low cost, are widely used. Among them, lie detection methods based on the P300 component of the EEG have been proven effective. This method is based on the principle that events and things experienced by an individual are stored in the brain. When relevant information is presented again, even if the subject conceals this information, the corresponding potential activity is still induced in the brain. This excitation of the cerebral cortex cannot be controlled voluntarily. Typically, this polygraph method asks the subject a series of multiple-choice questions. Each question has one option containing incriminating information and multiple unrelated options that do not. The subject is asked to respond to each option, stating whether they have seen the item in question. For innocent individuals, the options are homogeneous, so their cerebral cortex responds identically to all options. However, for criminals, their brain activity is heightened for the crime-related options. When this pattern recurs, it can be inferred that they are lying. While this ERP-based polygraph method has significant advantages, it also has drawbacks. It requires the subject to be highly cooperative with each answer and is susceptible to counter-intuitive interference, such as intentional twisting, coughing, or swallowing, which can affect the polygraph examiner's interpretation of the EEG during the polygraph task.

[0004] Therefore, one or more methods are needed to solve the above problems.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0006] The purpose of the present disclosure is to provide a lie detection method, device, electronic device and computer-readable storage medium based on resting-state EEG microstates, thereby overcoming one or more problems caused by the limitations and defects of related technologies to at least a certain extent.

[0007] According to one aspect of the present disclosure, a lie detection method based on resting-state EEG microstates is provided, comprising:

[0008] Based on the EEG acquisition equipment, the EEG data of the polygraph subject in the preset state is collected;

[0009] Calculating the microstate characteristics of the polygraph subject based on the EEG data;

[0010] Performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features;

[0011] The characteristic value of the microstate feature is used as input, and a lie detection result is generated based on a preset SVM classification model.

[0012] In an exemplary embodiment of the present disclosure, the method further includes:

[0013] Based on the EEG acquisition equipment, the EEG data of the polygraph subject is collected when the polygraph subject enters a resting state of a first preset duration after completing a preset task.

[0014] In an exemplary embodiment of the present disclosure, the method further includes:

[0015] The preset task is to show the polygraph subject a picture containing preset stimulus materials for a second preset time period, and to enable the polygraph subject to select and perform an operation from a preset operation group after observing the picture.

[0016] In an exemplary embodiment of the present disclosure, the method further includes preprocessing the EEG data:

[0017] Re-referencing the EEG data based on a whole-brain average reference value;

[0018] Performing filtering on the EEG data after the re-reference processing based on a first preset frequency band;

[0019] Segmenting the filtered EEG data based on a third preset time length;

[0020] Checking and replacing bad electrode EEG data in the segmented EEG data based on interpolation;

[0021] Check and remove artifact fragments and data abnormal distribution fragments in the EEG data after replacing the bad electrode EEG data;

[0022] Based on the independent component analysis method, the non-EEG components in the EEG data after the artifact segments and the data abnormal distribution segments are removed are identified and removed, thereby completing the preprocessing of the EEG data.

[0023] In an exemplary embodiment of the present disclosure, the method further includes:

[0024] Based on the preset classification of the EEG data microstates, the microstate characteristics of the average occurrence time, occurrence frequency per second, inter-classification transition probability, and global explained variance of each preset classification of the EEG data microstates of the polygraph subject are calculated according to the EEG data.

[0025] In an exemplary embodiment of the present disclosure, the method further includes:

[0026] The microstate features with a preset proportional variance are extracted to perform principal component analysis on the microstate features, thereby generating characteristic values ​​of the microstate features.

[0027] In an exemplary embodiment of the present disclosure, the method further includes generating and training the preset SVM classification model:

[0028] Recruiting members of a deception group and an innocent group, each comprising a predetermined number of members, and pre-treating the members of the deception group by presenting stimulus materials;

[0029] respectively collecting EEG data of the members of the deception group and the innocent group in a preset state after completing the preset task;

[0030] Calculating the microstate characteristics of the members of the deception group and the innocent group respectively according to the EEG data;

[0031] Performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features;

[0032] An SVM classification model is established, and the SVM classification model is trained based on the characteristic values ​​of the microstate characteristics and preset task data to generate a preset SVM classification model.

[0033] In an exemplary embodiment of the present disclosure, the method further includes pre-setting classification of EEG data microstates:

[0034] Generate single-person EEG data microstates based on the EEG data of the members of the deceiving group and the innocent group in the preset state after completing the preset task;

[0035] Generating group-level EEG data microstates for the deception group and the innocent group based on the single-person EEG data microstates, and generating microstate sequences for each group member based on the single-person EEG data microstates and the group-level EEG data microstates;

[0036] Cluster analysis is performed on the microstate sequences of each group member to generate a preset classification of the EEG data microstates.

[0037] In one aspect of the present disclosure, a lie detection device based on resting-state EEG microstates is provided, comprising:

[0038] The EEG data acquisition module is used to collect EEG data of the polygraph subject in a preset state based on the EEG acquisition equipment;

[0039] A microstate feature calculation module, configured to calculate the microstate features of the polygraph subject based on the EEG data;

[0040] an eigenvalue generating module, configured to perform principal component analysis on the microstate characteristics to generate eigenvalues ​​of the microstate characteristics;

[0041] The lie detection result generating module is used to take the characteristic value of the microstate feature as input and generate a lie detection result based on a preset SVM classification model.

[0042] In one aspect of the present disclosure, there is provided an electronic device, comprising:

[0043] processor; and

[0044] A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the method according to any one of the above items.

[0045] In one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the above items is implemented.

[0046] In an exemplary embodiment of the present disclosure, a lie detection method based on resting-state EEG microstates is disclosed, wherein the method comprises: using an EEG acquisition device to collect EEG data of a lie detector subject in a preset state; calculating the lie detector subject's microstate characteristics based on the EEG data; performing principal component analysis on the microstate characteristics to generate eigenvalues ​​of the microstate characteristics; and generating a lie detection result based on a preset SVM classification model using the eigenvalues ​​of the microstate characteristics as input. The disclosed resting-state EEG microstate analysis method for determining lie detection status can effectively reduce the impact of counter-lie detection, and requires less cooperation from the subject during the test, making it easier to promote and use.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and other features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings.

[0049] Figure 1 A flowchart of a lie detection method based on resting-state EEG microstates according to an exemplary embodiment of the present disclosure is shown;

[0050] Figure 2 shows an EEG electrode distribution diagram of a lie detection method based on resting-state EEG microstates according to an exemplary embodiment of the present disclosure;

[0051] Figure 3 Schematic diagrams showing four types of classic EEG microstates of a lie detection method based on resting-state EEG microstates according to an exemplary embodiment of the present disclosure;

[0052] Figure 4 A schematic block diagram of a lie detection device based on resting-state EEG microstates according to an exemplary embodiment of the present disclosure is shown;

[0053] Figure 5 A block diagram schematically illustrates an electronic device according to an exemplary embodiment of the present disclosure; and

[0054] Figure 6 A schematic diagram schematically illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0056] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, materials, devices, steps, etc. can be adopted. In other cases, well-known structures, methods, devices, implementations, materials or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0057] The blocks shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. Specifically, these functional entities may be implemented in software, or in one or more software-hardened modules, or in different networks and / or processor devices and / or microcontroller devices.

[0058] In this exemplary embodiment, a lie detection method based on resting-state EEG microstates is first provided; Figure 1 As shown in , the lie detection method based on resting-state EEG microstates may include the following steps:

[0059] Step S110, using an EEG acquisition device to collect EEG data of the polygraph subject in a preset state;

[0060] Step S120, calculating the microstate characteristics of the polygraph subject based on the EEG data;

[0061] Step S130, performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features;

[0062] Step S140 , taking the characteristic value of the microstate characteristic as input, and generating a lie detection result based on a preset SVM classification model.

[0063] In an exemplary embodiment of the present disclosure, a lie detection method based on resting-state EEG microstates is disclosed, wherein the method comprises: using an EEG acquisition device to collect EEG data of a lie detector subject in a preset state; calculating the lie detector subject's microstate characteristics based on the EEG data; performing principal component analysis on the microstate characteristics to generate eigenvalues ​​of the microstate characteristics; and generating a lie detection result based on a preset SVM classification model using the eigenvalues ​​of the microstate characteristics as input. The disclosed resting-state EEG microstate analysis method for determining lie detection status can effectively reduce the impact of counter-lie detection, and requires less cooperation from the subject during the test, making it easier to promote and use.

[0064] Below, a lie detection method based on resting-state EEG microstates in this exemplary embodiment will be further described. Example

[0065] In step S110, the EEG data of the polygraph subject in a preset state may be collected based on the EEG collection device.

[0066] In this exemplary embodiment, the method further includes:

[0067] Based on the EEG acquisition equipment, the EEG data of the polygraph subject is collected when the polygraph subject enters a resting state of a first preset duration after completing a preset task.

[0068] In this exemplary embodiment, the method further includes:

[0069] The preset task is to show the polygraph subject a picture containing preset stimulus materials for a second preset time period, and to enable the polygraph subject to select and perform an operation from a preset operation group after observing the picture.

[0070] In the embodiment of this example, the method further includes preprocessing the EEG data:

[0071] Re-referencing the EEG data based on a whole-brain average reference value;

[0072] Performing filtering on the EEG data after the re-reference processing based on a first preset frequency band;

[0073] Segmenting the filtered EEG data based on a third preset time length;

[0074] Checking and replacing bad electrode EEG data in the segmented EEG data based on interpolation;

[0075] Check and remove artifact fragments and data abnormal distribution fragments in the EEG data after replacing the bad electrode EEG data;

[0076] Based on the independent component analysis method, the non-EEG components in the EEG data after the artifact segments and the data abnormal distribution segments are removed are identified and removed, thereby completing the preprocessing of the EEG data.

[0077] In step S120, the microstate characteristics of the polygraph subject may be calculated based on the EEG data.

[0078] In this exemplary embodiment, the method further includes:

[0079] Based on the preset classification of the EEG data microstates, the microstate characteristics of the average occurrence time, occurrence frequency per second, inter-classification transition probability, and global explained variance of each preset classification of the EEG data microstates of the polygraph subject are calculated according to the EEG data.

[0080] In step S130 , principal component analysis may be performed on the microstate features to generate characteristic values ​​of the microstate features.

[0081] In this exemplary embodiment, the method further includes:

[0082] The microstate features with a preset proportional variance are extracted to perform principal component analysis on the microstate features, thereby generating characteristic values ​​of the microstate features.

[0083] In step S140, the feature value of the microstate feature can be used as input to generate a lie detection result based on a preset SVM classification model.

[0084] In the embodiment of this example, the method further includes generating and training the preset SVM classification model:

[0085] Recruiting members of a deception group and an innocent group, each comprising a predetermined number of members, and pre-treating the members of the deception group by presenting stimulus materials;

[0086] respectively collecting EEG data of the members of the deception group and the innocent group in a preset state after completing the preset task;

[0087] Calculating the microstate characteristics of the members of the deception group and the innocent group respectively according to the EEG data;

[0088] Performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features;

[0089] An SVM classification model is established, and the SVM classification model is trained based on the characteristic values ​​of the microstate characteristics and preset task data to generate a preset SVM classification model.

[0090] In the embodiment of this example, the method further includes preset classification of EEG data microstates:

[0091] Generate single-person EEG data microstates based on the EEG data of the members of the deceiving group and the innocent group in the preset state after completing the preset task;

[0092] Generating group-level EEG data microstates for the deception group and the innocent group based on the single-person EEG data microstates, and generating microstate sequences for each group member based on the single-person EEG data microstates and the group-level EEG data microstates;

[0093] Cluster analysis is performed on the microstate sequences of each group member to generate a preset classification of the EEG data microstates. Example

[0094] In this exemplary embodiment, the method includes two parts: a polygraph task and a post-task resting period with eyes closed. EEG is collected during both the polygraph task and the post-task resting period. The purpose of collecting EEG during the polygraph task is to confuse the subject, making them believe they are being lied to during the task. Ultimately, only the post-task resting-state EEG is analyzed and evaluated. Therefore, even if the subject's cooperation during the polygraph task is low or they employ anti-polygraph strategies, a slight degree of cooperation during the resting period will not affect the post-task resting-state EEG-based lie detection. This method is based on the principle that suspects relax their vigilance after the polygraph task. The complex psychological state of unconsciously replaying the suspect's concealment and worrying about whether the concealment will be detected during the task differs significantly from that of innocent individuals, resulting in differences in brain microstate activity patterns, thereby enabling lie detection.

[0095] In this exemplary embodiment, the task design steps included conducting a laboratory-based lie detection simulation task to elicit deceptive behavior and authentic responses. Participants were randomly divided into two groups: a deception group and an innocent group. The day before the lie detection task, participants in the deception group were shown objects and images related to the case investigation and were asked to keep the objects and images confidential. The innocent group was not given this instruction. After the lie detection task began, all participants took a lie test in a random order. During the test, visual stimuli appeared on the computer screen every few seconds. These stimuli consisted of probe stimuli (related to the case investigation) and irrelevant stimuli (unrelated to the case investigation). Participants were instructed to respond to each stimulus by pressing the left mouse button if they had seen the object before, or the right mouse button otherwise. The task lasted approximately 5-10 minutes. After the lie detection task, participants were asked to close their eyes and rest for 3 minutes. EEG was continuously collected throughout the test and during rest.

[0096] In this exemplary embodiment, the EEG data acquisition step includes recording EEG using 32-lead Ag / Ag-Cl electrodes embedded in an EEG cap. The electrodes are arranged according to the 10-20 international system. The reference electrode is the Cz point, and the ground electrode is placed at the center of the forehead. The impedance of all electrodes is kept below 5 kΩ. Figure 2 This is the EEG electrode distribution map.

[0097] In this exemplary embodiment, the resting-state EEG data preprocessing step includes the following: EEG signals collected from the scalp typically contain various noise and artifacts and therefore cannot accurately represent brain neural activity, so the collected raw signals need to be preprocessed. The resting-state EEG data preprocessing steps include: re-referencing, filtering, segmentation, interpolation of bad electrodes, removal of bad segments, and independent component analysis to remove artifacts.

[0098] ①Re-reference: using the whole-brain average reference;

[0099] ②Filtering: The filtering range is 0.5~40 Hz;

[0100] ③ Segmentation: Divide the continuous resting-state EEG information into multiple segments of 2 seconds each;

[0101] ④ Interpolate bad electrodes: Browse the resting state data and use the spherical curve method to interpolate the electrode data that is obviously different from the EEG data of other electrodes;

[0102] ⑤ Eliminate bad segments: Check the resting-state EEG data and eliminate segments with large artifacts or abnormal data distribution;

[0103] ⑥ Independent component analysis to remove artifacts: Use independent component analysis to identify and remove non-EEG components such as electrocardiogram, eye movements, blinks, electromyography, and head movements to obtain clean resting-state EEG data.

[0104] In the embodiment of this example, the resting-state EEG microstate analysis step includes first performing a 2-20 Hz bandpass filter, and then plotting the standard deviation of each acquisition moment into a curve. The EEG topographic map at the local peak position on the curve is selected, and the AAHC algorithm is used to cluster the topographic map pattern. Next, the topographic map of each subject is clustered to obtain a single person's microstate template. Then, for the deception group and the innocent group, the microstate templates of each subject in the group are summarized, and clustered again at the group level to obtain the EEG microstate at the group level. Finally, the topographic map of the single person is matched with the microstate at the group level to obtain the individual microstate sequence. During the cluster analysis, the microstates are divided into four classic categories (A, B, C, D). As Figure 4 Shown are schematic diagrams of four types of classic EEG microstates. The centers of positive and negative charges in the brain topography of microstate A are located in the right frontal lobe and left occipital lobe; the centers of positive and negative charges in the brain topography of microstate B are located in the left frontal lobe and right occipital lobe; the centers of positive and negative charges in the brain topography of microstate C are located in the prefrontal lobe and occipital lobe; the centers of positive and negative charges in the brain topography of microstate D are located in the frontocentral region and occipital lobe.

[0105] Next, the following microstate characteristics were calculated for each subject: ① Average occurrence time: the average length of time each microstate remained stable when it appeared; ② Frequency per second: the average number of times each microstate was dominant per second; ③ Time coverage: the proportion of time each microstate covered in the entire analysis time period; ④ Transition probability: the ratio of the number of switches from one microstate to another to the total number of switches between all microstates; ⑤ Global explained variance: the percentage of the total variance explained by a given microstate.

[0106] In this exemplary embodiment, the step of constructing a classification model based on EEG microstate features includes performing principal component analysis on the aforementioned 20 microstate features and using the resulting eigenvalues ​​to construct an SVM classification model. The resulting binary classification result serves as the lie detection result. Specifically, principal component analysis (maximum 95% variance extraction) is performed on the EEG microstate features of all subjects in the deception and innocent groups to reduce dimensionality, remove redundant features, and prevent overfitting. The reduced dimensionality features are then input into an SVM classifier (with a linear kernel) for model training and testing, with leave-one-out cross-validation performed. This binary classification method then divides the data into deception and innocence, thereby enabling lie detection.

[0107] The classification results for deception and innocence showed an accuracy of 0.88, a precision of 0.87, and a recall of 0.87, indicating that the proposed method has good discriminative ability in detecting lies and has high operability and application value.

[0108] It should be noted that although the steps of the method disclosed herein are depicted in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in that particular order, or that all steps must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one, and / or one step may be decomposed into multiple steps.

[0109] In addition, in this exemplary embodiment, a lie detection device based on resting-state EEG microstates is also provided. Figure 4 As shown, the lie detection device 400 based on resting-state EEG microstates may include: an EEG data acquisition module 410, a microstate feature calculation module 420, a feature value generation module 430, and a lie detection result generation module 440.

[0110] The EEG data acquisition module 410 is used to collect EEG data of the polygraph subject in a preset state based on an EEG acquisition device;

[0111] A microstate feature calculation module 420 is used to calculate the microstate features of the polygraph subject based on the EEG data;

[0112] The eigenvalue generating module 430 is used to perform principal component analysis on the microstate characteristics to generate eigenvalues ​​of the microstate characteristics;

[0113] The lie detection result generating module 440 is configured to take the feature value of the microstate feature as input and generate a lie detection result based on a preset SVM classification model.

[0114] The specific details of each of the above-mentioned lie detection device modules based on resting-state EEG microstates have been described in detail in the corresponding lie detection method based on resting-state EEG microstates, so they will not be repeated here.

[0115] It should be noted that although the above detailed description mentions several modules or units of a lie detection device 400 based on resting-state EEG microstates, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided to be embodied by multiple modules or units.

[0116] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0117] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0118] Refer to the following Figure 5 An electronic device 500 according to such an embodiment of the present invention will be described. Figure 5 The electronic device 500 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0119] like Figure 5 As shown, electronic device 500 is implemented as a general-purpose computing device. Components of electronic device 500 may include, but are not limited to, the aforementioned at least one processing unit 510, the aforementioned at least one storage unit 520, a bus 530 connecting various system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0120] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 510 can perform the following steps: Figure 1 Steps S110 to S140 shown in FIG.

[0121] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 5201 and / or a cache memory unit 5202 , and may further include a read-only memory unit (ROM) 5203 .

[0122] The storage unit 520 may also include a program / utility 5204 having a set (at least one) of program modules 5203, such program modules 5205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0123] Bus 550 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0124] The electronic device 500 can also communicate with one or more external devices 570 (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 500, and / or any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can occur via an input / output (I / O) interface 550. Furthermore, the electronic device 500 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via the bus 550. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for causing a computing device (such as a personal computer, server, terminal device, or network device) to execute the methods according to the embodiments of the present disclosure.

[0126] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, storing a program product capable of implementing the aforementioned methods of this specification. In some possible embodiments, various aspects of the present invention may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0127] refer to Figure 6 , a program product 600 for implementing the above-described method according to an embodiment of the present invention is described. The program product 600 may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0128] The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0129] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0130] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0131] Program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0132] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0133] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0134] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A lie detection method based on resting-state EEG microstates, characterized in that: The method comprises: collecting EEG data of a polygraph subject after completing a preset task and entering a resting state for a first preset duration using an EEG acquisition device; wherein the preset task is a lie detection task, wherein for a second preset duration, the polygraph subject is shown a picture containing preset stimulus material and is prompted to select and perform an operation from a preset operation group after observing the picture; Calculating the microstate characteristics of the polygraph subject based on the EEG data; wherein, based on preset classifications of the microstates of the EEG data, calculating the microstate characteristics of the average occurrence time, occurrence frequency per second, inter-classification transition probability, and global explained variance of each preset classification of the microstates of the EEG data of the polygraph subject based on the EEG data; Performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features; The characteristic value of the microstate feature is used as input, and a lie detection result is generated based on a preset SVM classification model.

2. The method according to claim 1, wherein The method further includes preprocessing the EEG data: Re-referencing the EEG data based on a whole-brain average reference value; Performing filtering on the EEG data after the re-reference processing based on a first preset frequency band; Segmenting the filtered EEG data based on a third preset time length; Checking and replacing bad electrode EEG data in the segmented EEG data based on interpolation; Check and remove artifact fragments and data abnormal distribution fragments in the EEG data after replacing the bad electrode EEG data; Based on the independent component analysis method, non-EEG components in the EEG data are identified and eliminated to complete the preprocessing of the EEG data.

3. The method according to claim 1, wherein The method further comprises: The microstate features with a preset proportional variance are extracted to perform principal component analysis on the microstate features, thereby generating characteristic values ​​of the microstate features.

4. The method according to claim 1, wherein The method further includes generating and training the preset SVM classification model: Recruiting members of a deception group and an innocent group, each comprising a predetermined number of members, and pre-treating the members of the deception group by presenting stimulus materials; Collecting EEG data of the members of the deception group and the innocent group in a preset state after completing a preset task; Calculating the microstate characteristics of the members of the deception group and the innocent group respectively according to the EEG data; Performing principal component analysis on the microstate features to generate characteristic values ​​of the microstate features; An SVM classification model is established, and the SVM classification model is trained based on the characteristic values ​​of the microstate characteristics and preset task data to generate a preset SVM classification model.

5. The method according to claim 4, wherein The method also includes a preset classification of EEG data microstates: Generate single-person EEG data microstates based on the EEG data of the members of the deceiving group and the innocent group in the preset state after completing the preset task; Generating group-level EEG data microstates for the deception group and the innocent group based on the single-person EEG data microstates, and generating microstate sequences for each group member based on the single-person EEG data microstates and the group-level EEG data microstates; Cluster analysis is performed on the microstate sequences of each group member to generate a preset classification of the EEG data microstates.

6. A lie detection device based on resting-state EEG microstates, characterized in that: The device comprises: an EEG data acquisition module, configured to collect EEG data of a polygraph subject, after completing a preset task and entering a resting state for a first preset duration, using an EEG acquisition device; wherein the preset task is a lie detection task, wherein for a second preset duration, the polygraph subject is shown a picture containing preset stimulus material and is prompted to select and perform an operation from a preset operation group after viewing the picture; A microstate feature calculation module is used to calculate the microstate features of the polygraph subject based on the EEG data; wherein the module includes a preset classification of the microstates of the EEG data, and calculates the microstate features of the average occurrence time, occurrence frequency per second, inter-classification transition probability, and global explained variance of each preset classification of the microstates of the EEG data of the polygraph subject based on the EEG data; an eigenvalue generating module, configured to perform principal component analysis on the microstate features to generate eigenvalues ​​of the microstate features; The lie detection result generating module is used to take the characteristic value of the microstate feature as input and generate a lie detection result based on a preset SVM classification model.

7. An electronic device, characterized in that: include processor; and A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions are executed by the processor to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 5 when executed by a processor.