Security certification system based on virtual reality helmet brain grain collection

[0027] In order to solve the problem that there is no security authentication system and method based on brainprint collection in the prior art, the present invention provides a security authentication system and method based on brainprint collection. For further details. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0028] According to the device embodiment of the present invention, a security authentication system based on brainprint collection is provided, figure 1 It is a schematic structural diagram of a security authentication system based on brainprint collection in an embodiment of the device of the present invention, as shown in figure 1 As shown, the security authentication system based on brainprint collection according to the device embodiment of the present invention includes: a data access module 110, a brainprint generation module 120, and a security authentication module 130. The following describes each module of the device embodiment of the present invention in detail illustrate.

[0029] Specifically, the data access module 110 is configured to receive the input of user identity information, combine with the preset local database of brain prints, and generate the first brain print characteristic parameters corresponding to the user identity information, the local brain print database stores Several pieces of user identity information and brainprint feature parameters corresponding to the user identity information.

[0030] In the device embodiment of the present invention, the data access module 110 can use various terminals, such as computers. The data access module 110 is also used to trigger the brain print generation module when receiving the input of the identity information of the new user in the new user mode.

[0031] The brainprint generation module 120 is used to acquire digital brainwave signals generated by the user under the stimulation of audio and video signals, perform feature extraction and analysis on the digital brainwave signals, and obtain second brainprint feature parameters.

[0032] The brain pattern generation module 120 is also used to obtain the brain wave digital signal generated by the new user under the stimulation of audio and video signals after receiving the trigger of the data access module 110 in the new user mode, and to the Feature extraction and analysis are performed on the digital brain wave signal to obtain new brain pattern feature parameters, which are associated with the new user identity information and stored in the brain pattern local database.

[0033] The brainprint generation module 120 is also used to associate the second brainprint with user identity information and store it in the local brainprint database through the wireless transceiver module, so that the user can quickly view and process the currently recorded brainprint and analysis.

[0034] Current neuroscience research proves that the same person's brain responds almost identically to the same picture or the same piece of audio and video. The principle of selecting video and audio is to enable each person to produce a special and different response from others under the stimulation of the video and/or audio signal.

[0035] Specifically, the brain pattern generation module 120 includes a brain wave acquisition sub-module, a brain wave feature extraction sub-module, and a brain pattern analysis sub-module.

[0036] More specifically, the brain wave acquisition sub-module is used to acquire the brain wave analog signal generated by the user under the stimulation of the video signal, and amplify, filter, and analog-to-digital convert the brain wave analog signal to obtain the brain wave digital signal. figure 2It is a schematic diagram of brain wave analog signals collected by the brain wave acquisition sub-module of the device embodiment of the present invention within a certain time interval. In brain waves, it is common to see multi-morphic composite waveforms composed of β, α, θ, and δ waves overlapped disorderly. Quantity (index or index).

[0037] The brainwave acquisition sub-module can be a virtual reality helmet, virtual reality glasses or other head-mounted multimedia devices. image 3 It is a structural block diagram of an example of the virtual reality helmet in the device embodiment of the present invention. Specifically, the virtual reality helmet includes a helmet bracket, brain wave acquisition electrodes, video playback unit, audio playback unit, low noise amplifier, filter, high-precision analog-to-digital conversion chip, DC power supply, brain wave feature extraction sub-module, brain pattern generation Sub-modules, storage modules, wireless transceiver modules, etc. Among them, the brain wave acquisition electrodes, low noise amplifiers, filters, high-precision analog-to-digital conversion chips, brain wave feature extraction sub-modules, and brain pattern analysis sub-modules all belong to the brain pattern generation module.

[0038] Wherein, several electroencephalogram collecting electrodes are arranged on the helmet bracket, and are used for collecting the brain wave analog signal that the user produces under the stimulation of the content played by the video playback unit and/or audio playback unit; The low noise amplifier, filter, The analog-to-digital conversion chip is used for amplifying, filtering and analog-to-digital conversion of the brain wave analog signal to obtain the brain wave digital signal.

[0039] The internal bracket of the virtual reality helmet can arrange brain wave acquisition electrodes in multiple specific positions. The electrodes are placed outside the skull and are in close contact with the scalp through dry electrodes to collect scalp electrode EEG. Now the international 10-20 system is routinely used for scalp electrode EEG. The 10-20 system includes 19 recording electrodes and 2 reference electrodes. The arrangement of electrode positions is proportional to the size and shape of the skull, that is, no matter whether the head is large or small or the shape of the skull varies, the placement positions are comparable, because the 10-20 system is placed according to the percentage of the head itself. While the user is using the VR glasses in the virtual reality (VR) helmet, the electric wave acquisition electrode collects the corresponding brain wave analog signal of the user, and the brain wave analog signal passes through the amplifier (because the EEG signal is very weak, it is mv or uv level, and it is obtained After the attenuation of the skull and scalp, it needs to be magnified by millions of times to be displayed), filter (to reduce interference), high-precision analog-to-digital conversion, and finally form a brain wave digital signal.

[0040] In order to obtain more effective digital brain wave signals to facilitate the extraction of brain pattern characteristic parameters, the brain pattern generation module of the device embodiment of the present invention also includes a control sub-module for analyzing the brain wave generated by the user under the stimulation of audio and video signals within a period of time. Brain wave digital signal, if the feature of the brain wave digital signal is not obvious, the audio and video signal is changed.

[0041] The brain wave acquisition sub-module of the device embodiment of the present invention uses a virtual reality helmet to collect brain waves by wearing a virtual reality helmet to watch virtual reality videos or pictures, making the traditional boring brain wave acquisition process more entertaining. By adding an audio playback system, the user's experience is more pleasant, and it is beneficial to generate more brainprint features, and the helmet bracket in virtual reality can place multiple electrodes at specific positions to meet the requirements for brain wave collection.

[0042] The brainwave feature extraction submodule is used to perform feature extraction on the brainwave digital signal according to the brainprint feature parameters retrieved from the brainprint local database to obtain the brainwave digital signal containing the brainprint feature parameters .

[0043] In the device embodiment of the present invention, feature extraction includes but is not limited to the following methods: clustering of EEG signals, multiple linear regression, power spectral density calculation, mean and variance calculation, wavelet transform or Fourier transform followed by time domain Frequency domain analysis, channel characteristic analysis, Lyapunov exponent calculation, principal component analysis and independent component analysis, common spatial pattern method, sparse coding, integrated support vector machine and matched filter method.

[0044] The brain wave feature extraction sub-module is also used to intercept part of the brain wave digital signal containing the brain pattern feature parameters, compress and output. The purpose of intercepting part of the data is to simplify the data and reduce the data sent to the brainprint batch processing module. Methods for intercepting part of the data include but are not limited to the following methods: retain the brain wave simulation signals containing the EEG characteristic parameters and eliminate the brain wave simulation signals repeatedly containing the same EEG characteristic parameters. The input of the brainwave feature extraction sub-module is the brainwave digital signal and the brainprint feature parameters in the brainprint local database, and the output is the brainwave digital signal containing the brainprint feature parameters and the filtered brainwave digital signal.

[0045] Further, the security authentication system also includes a brainprint batch processing module, a brainprint feature and identity information cloud database module.

[0046] The brainprint batch processing module is used for clustering and processing the received batches of brainwave digital signals of the same user to obtain new brainprint characteristic parameters of the user.

[0047] Specifically, the brain pattern batch processing module can be deployed on a distributed big data cloud platform, and the software and hardware resources of the cloud platform are used to realize the feature extraction of brain waves. The big data cloud platform already has large sample statistical analysis, On the basis of deep learning neural network, machine learning and other clustering algorithms, according to the actual characteristics of the brain wave feature extraction project, the software and hardware resources of the cloud platform can be evaluated from several aspects such as algorithm operation efficiency, feature extraction accuracy, and feature validity. Performance is optimized. The brain pattern batch processing module includes a brain wave clustering sub-module, and a brain wave feature extraction and enhancement sub-module.

[0048] The brain wave clustering sub-module is used to cluster the received batches of brain wave digital signals of the same user to obtain a brain wave parameter clustering result.

[0049] The brainwave clustering sub-module clusters the characteristic parameters of the brainwaves of the current user and the characteristic parameters of the brainwaves of users who have used the brainprint collection virtual reality helmet and other brainprint collection virtual reality helmets to find out the brainwave characteristics of all users. The distribution and regularity among the characteristic parameters of the brain wave parameters. The input of the brain wave clustering module is the filtered and compressed brain wave digital signal of the brain wave feature extraction sub-module, and the output is the clustering result of the brain wave parameters of all users.

[0050] The brainwave feature extraction and enhancement sub-module is used to obtain new brainprint feature parameters based on the known brainwave features and implicit correlations between brainwave parameters and according to brainwave parameter clustering results.

[0051] The brain wave feature extraction and enhancement sub-module uses the association algorithm to mine association rules, utilizes the implicit association relationship between feature key information and the known features of brain waves, and retains the effective EEG feature parameters with high recognition rate. The electrical characteristic parameters are summarized as brainprint characteristic parameters. The input of the brain wave feature extraction and enhancement sub-module is the brain wave parameter clustering result and the known features of the brain wave, and the output is the brain pattern feature parameter.

[0052] There are many known characteristics of brain waves, for example: the frequency of α brain waves is 8-12 Hz, the frequency of β brain waves is 14-100 Hz, the frequency of θ brain waves is 4-8 Hz, and the frequency of δ brain waves is 0.5-4 Hz. Another example: when "cognizing" a certain target stimulus (singular stimulus), a group of waves can be recorded from the scalp, mainly including N1, P2, N2, and P300 (P3), which are collectively called event-related potentials (ERP). The latency of P300 potential elicited by the target stimulus is shorter than that of the non-target stimulus, and the amplitude is also higher. The difficulty of the task can affect the latency and amplitude changes. The greater the difficulty, the more obvious the P300 potential. In addition, whether there is a reward after completing the trial, that is, the incentive value of the stimulus also affects the P3 wave.

[0053] The brainprint feature and identity information cloud database module is used to receive the new brainprint feature parameters and feed them back to the local brainprint database, so that the local brainprint database can update the brainprint corresponding to the user.

[0054] The brainprint feature and identity information cloud database stores the brainprint, user identity information and brainprint feature parameters collected by all brainprint collection virtual reality helmets within a certain period of time. The brain pattern is obtained from the local brain pattern database to update the brain pattern database, increasing the data volume of the cloud platform's brain pattern characteristics and identity information cloud database, which is convenient for statistical analysis and network query. The brain wave feature extraction and enhancement sub-module outputs the brain pattern feature parameters to the cloud database. The brainprint feature and identity information cloud database outputs the brainprint feature parameters to the brainprint local database. The brainprint feature and identity information cloud database provides a brainprint database interface for software programs such as scientific research, medical treatment, sports, entertainment, and business applications. The input of the brainprint feature and identity information cloud database is the brainprint feature parameters of the brainwave feature extraction and enhancement sub-module and the brainprint data of the local database of the brainprint, and the output is the brainprint database interface and the brainprint parameter category.

[0055] The brain pattern analysis sub-module is used to analyze and process the brain wave digital signal containing the brain pattern characteristic parameters to obtain the brain pattern characteristic parameters, and the brain pattern characteristic parameters are the same as those retrieved from the brain pattern local database. After correlating the user identity information, the brainprint feature parameters corresponding to the user are obtained, and according to the preset normal brainprint feature parameters, it is judged whether the brainprint feature parameters corresponding to the user are normal or abnormal. The characteristic parameter of the brain pattern is the second characteristic parameter of the brain pattern, and the second characteristic parameter of the brain pattern is sent to the security authentication module; if it is abnormal, the characteristic parameter of the brain pattern corresponding to the user is sent to the preset abnormal In the brainprint information interface.

[0056] The input of the brain-print analysis sub-module is the brain wave digital signal including the brain-print feature parameters and the user identity information in the brain-print local database, and the output is the second brain-print feature parameters and abnormal brain-print feature parameters. The abnormal brain pattern feature parameters are used to judge whether the currently recorded brain pattern is valid, and can also judge whether the user has an abnormal mental state or cognitive state.

[0057] Figure 4 It is a schematic diagram of the interaction between the brainprint generation module, the batch processing module and other modules in the security authentication system based on brainprint collection in the device embodiment of the present invention. A certain number of brainprint feature parameters and user identity information generated by using the current brainprint collection virtual reality helmet are stored in the brainprint local database. Based on the brain pattern collection virtual reality helmet, the brain pattern feature parameters generated by the brain pattern generation module are transmitted to the brain pattern local database through the wireless transceiver module, which is convenient for users to quickly view, process and analyze the currently recorded brain pattern feature parameters. The brain pattern local database outputs the user identity information to the brain pattern analysis sub-module for the brain pattern characteristic parameters to be associated with the identity information. The brain pattern local database outputs the brain pattern feature parameters to the brain pattern feature extraction sub-module for the brain pattern feature extraction module to quickly process the brain wave information to obtain the brain pattern parameters. The input of the local database of the brain pattern is the characteristic parameters of the brain pattern generated by the brain pattern generation module and the identity information of the user when logging in, and the output is the interface of the local database of the brain pattern, the characteristic parameters of the brain pattern generated by the brain pattern generation module, and the User identity information and brainprint feature parameters.

[0058] The security authentication module 130 is configured to compare the first brainprint feature parameter with the second brainprint feature parameter, and perform identification and security authentication on the user identity according to the comparison result.

[0059] Specifically, the security authentication module 130 includes a comparison submodule, an identity identification submodule, and a security authentication submodule;

[0060] The comparison sub-module is used to compare the first brainprint feature parameter with the second brainprint feature parameter to obtain a comparison result;

[0061] The identity recognition sub-module is used to determine whether the user identity is an authorized user or an unauthorized user according to the comparison result, if the similarity between the user's first brainprint characteristic parameter and the second brainprint characteristic parameter is within an acceptable range, Then the user is an authorized user; if the similarity between the user's first brainprint feature parameter and the second brainprint feature parameter is within an unacceptable range, or the user's second brainprint feature parameter is consistent with all brainprint feature parameters in the local brainprint database If the feature parameters do not match, the user is an unauthorized user;

[0062]The security authentication sub-module is used to open permissions to authorized users, give early warning of visitor intrusion to unauthorized users, and store the second brainprint feature parameters into the preset non-real-name-authenticated brainprint sub-database.

[0063] Figure 5 is a schematic diagram of a security authentication system based on brainprint collection in an embodiment of the device of the present invention, as shown in Figure 5 As shown, the brainprint is collected through the brainprint collection virtual reality helmet or other brainprint collection tools, and the brainprint is compared with the information claimed by the user's identity. If the brainprint is within the acceptable range, the user is considered to be a user pre-registered in the brainprint database.

[0064] In the embodiment of the device of the present invention, the cloud platform and big data are used to process the brain pattern, so that the brain wave data can better serve scientific research and engineering, and the extracted brain pattern is more accurate. At the same time, after storing more brainprint data in the database of the cloud platform, it is beneficial to discover some unknown brainprint features and other brain wave phenomena through the statistical analysis method of large samples. Moreover, the brain pattern batch processing module accurately extracts and predicts the characteristics of brain waves through large sample statistical analysis, deep learning neural network and other methods, thus providing parameter basis for online brain pattern extraction. The offline system uses the software and hardware resources in the cloud platform for calculation.

[0065] According to the method embodiment of the present invention, a security authentication method based on brainprint collection is provided, Image 6 It is a flow chart of the security authentication method based on brainprint collection in the method embodiment of the present invention, such as Image 6 As shown, the security authentication method based on brainprint collection according to the embodiment of the present invention includes the following processing:

[0066] Step 601, receiving the input of user identity information, combined with the preset local brainprint database, to generate the first brainprint characteristic parameters corresponding to the user identity information, the brainprint local database stores several user identity information and the corresponding The brainprint feature parameters corresponding to the user identity information;

[0067] Step 602, acquiring digital brainwave signals generated by the user under the stimulation of audio and video signals, performing feature extraction and analysis on the digital brainwave signals, and obtaining second brainprint feature parameters;

[0068] Step 603, comparing the first brainprint feature parameter with the second brainprint feature parameter, and performing identification and security authentication on the user identity according to the comparison result.

[0069] The security authentication method based on brainprint collection in the method embodiment of the present invention also includes the following steps:

[0070] In the new user mode, receive the input of the new user identity information;

[0071] Obtain the brain wave digital signal generated by the new user under the stimulation of the video signal, perform feature extraction and analysis on the brain wave digital signal, obtain the new brain pattern feature parameter, and combine the new brain pattern feature parameter with the newly added After the user identity information is associated, it is stored in the brainprint local database.

[0072] Specifically, step 602 specifically includes the following steps;

[0073] Acquiring the analog brain wave signal generated by the user under the stimulation of audio and video signals, and amplifying, filtering, and analog-to-digital conversion of the analog brain wave signal to obtain a digital brain wave signal;

[0074] According to the brainprint feature parameters retrieved from the brainprint local database, feature extraction is performed on the brainwave digital signal to obtain the brainwave digital signal containing the brainprint feature parameters;

[0075] Analyzing and processing the brainwave digital signal containing the brainprint feature parameters to obtain the brainprint feature parameters, and correlating the brainprint feature parameters with the user identity information retrieved from the brainprint local database to obtain the corresponding According to the preset normal brain pattern characteristic parameters, it is judged whether the brain pattern characteristic parameters corresponding to the user are normal or abnormal. If normal, the brain pattern characteristic parameters corresponding to the user are the second brain pattern characteristic parameters. if abnormal, send the corresponding brainprint feature parameters to the preset abnormal brainprint information interface.

[0076] The security authentication method based on brainprint collection in the method embodiment of the present invention also includes the following steps:

[0077] Intercept part of the data from the brain wave digital signal, and compress it to obtain a batch of brain wave digital signals;

[0078] Clustering and processing the received batches of brainwave digital signals of the same user to obtain the new brainprint feature parameters of the user;

[0079] The new brainprint feature parameters are received and fed back to the local brainprint database, so that the brainprint local database updates the brainprint feature parameters corresponding to the user.

[0080] Specifically, the clustering and processing of the received batches of brainwave digital signals of the same user to obtain the new brainprint feature parameters of the user specifically includes the following steps;

[0081] Clustering the received batches of brainwave digital signals of the same user to obtain the brainwave parameter clustering results;

[0082] Based on the implicit correlation between known features of brain waves and brain wave parameters, new brainprint feature parameters are obtained according to the clustering results of brain wave parameters.

[0083] Specifically, step 603 includes the following steps:

[0084] Comparing the first brainprint feature parameter with the second brainprint feature parameter to obtain a comparison result;

[0085] According to the comparison result, it is judged whether the user identity is an authorized user or an unauthorized user, if the similarity between the first brainprint characteristic parameter and the second brainprint characteristic parameter of the user is within an acceptable range, then the user is an authorized user; if the user The similarity between the first and second brainprint feature parameters of the user is within an unacceptable range, or the user's second brainprint feature parameters do not match all the brainprint feature parameters in the local brainprint database, then the user as an unauthorized user;

[0086] Authorized users are granted permission, visitor intrusion warnings are given to unauthorized users, and the second brainprint feature parameters are stored in the preset non-real-name-authenticated brainprint sub-database.

[0087] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and equivalent technologies thereof, the present invention also intends to include these modifications and variations.