Brain wave signal dynamic feature extraction method and device and evaluation index determination method and device

Abstract

The invention relates to a brain wave signal dynamic feature extraction method and device and an evaluation index determination method and device, and the method comprises the steps: carrying out the disassembly of a brain wave time sequence of each channel according to a carrier frequency band and an amplitude modulation frequency band, and obtaining an amplitude modulation time sequence; determining M target channels in the N channels to obtain a target brain function connection fragment; for any target brain function connection fragment, classifying amplitude modulation time sequences which are from different target channels and have the same carrier frequency band and amplitude modulation frequency band into a set; for each set, on the basis of an electroencephalogram micro-state transition normal form recognition rule base, the occurrence frequency and sequence of various electroencephalogram micro-state transition normal forms included in the set are determined, and then electroencephalogram signal dynamic characteristics of the target object are determined; the invention provides a method for extracting brain wave signal dynamic characteristics capable of reflecting a transient and highly dynamic neural activity mode.

Description

Technical Field

[0001] The present disclosure relates to the technical field of brain wave signal processing, and in particular to a method for extracting dynamic features of brain wave signals, a method for determining evaluation indicators, and a device. This application claims priority. The application number of the prior application is: 2023106781704, and the name is: A system and method for diagnosing functional brain diseases and multidimensional intelligence assessment based on amplitude modulation brain functional connection decomposition technology, and the priority date is June 8, 2023. Background Art

[0002] As a cutting-edge discipline that explores the nature of human thinking and behavior, the progress of neuroscience has profoundly changed our understanding of how the brain works. Traditionally, the study of brain electrophysiological activity, especially electroencephalogram (EEG) analysis, has played a vital role. By monitoring the weak electrical signals generated by the brain, researchers can gain insight into many neural activity phenomena such as cognitive processes, emotional states, and even sleep cycles. Research in this field usually revolves around spectrum analysis, which is to analyze the energy distribution, phase synchronization, and amplitude fluctuations of different frequency bands, providing a window for understanding brain function.

[0003] However, these analyses belong to EEG signal analysis from a static perspective, and most of them are based on time-averaged statistical methods, which aim to extract stable trends or features, but inevitably blur the details of instant changes.

[0004] However, in reality, the brain operates as a highly dynamic, interactive, and complex system. In this system, groups of neurons fire in concert at millisecond speeds, forming ever-changing activity patterns that regulate all mental processes, including perception, thinking, decision-making, and even emotional expression. These rapidly changing dynamic features, including short-term fluctuations in time series, instant reorganization of spatial distribution, and cross-regional synergies, together constitute the essence of brain activity. Therefore, although traditional spectral analysis methods depict the basic framework of brain activity at the macro level, they are still unable to capture those fleeting, highly dynamic neural activity patterns. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method for extracting dynamic features of brain wave signals, a method and a device for determining evaluation indicators.

[0006] In a first aspect, the present disclosure provides a method for extracting dynamic features of brain wave signals, comprising:

[0007] Obtain N channels of brain wave time series of the target object;

[0008] According to the carrier frequency band and the amplitude modulation frequency band, the brain wave time series of each channel is disassembled to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands;

[0009] Determining M target channels among the N channels to obtain target brain function connection segments;

[0010] For any target brain function connection segment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained;

[0011] For each of the sets, based on the EEG microstate transition paradigm recognition rule base, the occurrence frequency and order of the various EEG microstate transition paradigms included in the set are determined; the EEG microstate transition paradigm recognition rule base corresponds to the set, the EEG microstate transition paradigm recognition rule base includes a plurality of EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules, and the EEG microstate transition paradigm is used to describe the changes in EEG microstates within a preset time period;

[0012] Determining the dynamic characteristics of the brain wave signal of the target object based on the occurrence frequency and order of the various brain wave microstate transition paradigms included in each of the sets;

[0013] Among them, M, N and P are all positive integers, and M≤N.

[0014] In a second aspect, the present disclosure further provides a method for determining an evaluation index, comprising:

[0015] Obtaining N channels of brain wave time series of multiple candidate objects;

[0016] Taking the candidate object as the target object, using the method for extracting dynamic features of brain wave signals as described above, determining dynamic features of brain wave signals originating from different brain function connection segments corresponding to the candidate object;

[0017] Based on the evaluation purpose, the candidate subjects are divided into a control group and an experimental group;

[0018] Calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment;

[0019] Based on the first similarity distance, the second similarity distance and the third similarity distance, it is determined which target brain function connection segment is used as an evaluation indicator for an evaluation purpose.

[0020] In a third aspect, the present disclosure further provides a device for extracting dynamic features of brain wave signals, comprising:

[0021] The first acquisition module is used to acquire N channels of brain wave time series of the target object;

[0022] A disassembly module is used to disassemble the brain wave time series of each channel according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands;

[0023] A first determination module is used to determine M target channels from the N channels to obtain target brain function connection segments;

[0024] A first division module is used for classifying the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band into one set for any target brain function connection segment, and obtaining a total of P sets;

[0025] An identification module is used to determine, for each of the sets, the occurrence frequency and order of the various EEG microstate transition paradigms included in the set based on the EEG microstate transition paradigm identification rule base; the EEG microstate transition paradigm identification rule base corresponds to the set, the EEG microstate transition paradigm identification rule base includes a plurality of EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm identification rules, and the EEG microstate transition paradigm is used to describe the change of EEG microstates within a preset time period;

[0026] A second determination module is used to determine the dynamic characteristics of the brain wave signal of the target object based on the occurrence frequency and order of the various brain wave microstate transition paradigms included in each of the sets;

[0027] Among them, M, N and P are all positive integers, and M≤N.

[0028] In a fourth aspect, the present disclosure provides an evaluation index determination device, comprising:

[0029] The second acquisition module is used to acquire brain wave time series of N channels of multiple candidate objects;

[0030] A third determination module is used to use the candidate object as a target object, and the brain wave signal dynamic feature extraction device as described above determines the brain wave signal dynamic features originating from different brain function connection segments corresponding to the candidate object;

[0031] A second division module is used to divide the candidate objects into a control group and an experimental group based on the evaluation purpose;

[0032] a calculation module, used for calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment;

[0033] The fourth determination module is used to determine which target brain function connection segment is used as an evaluation indicator for an evaluation purpose based on the first similarity distance, the second similarity distance and the third similarity distance.

[0034] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0035] In the technical solution provided by the embodiment of the present disclosure, the EEG time series of each channel is decomposed according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands; M target channels are determined in N channels to obtain target brain function connection fragments; for any target brain function connection fragment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained; for each set, based on the EEG microstate transfer The paradigm recognition rule base determines the occurrence frequency and order of various EEG microstate transition paradigms included in the set; the EEG microstate transition paradigm recognition rule base corresponds to the set, and the EEG microstate transition paradigm recognition rule base includes multiple EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules. The EEG microstate transition paradigm is used to describe the changes in EEG microstates within a preset time period; based on the occurrence frequency and order of various EEG microstate transition paradigms included in each set, the dynamic characteristics of the EEG signal of the target object are determined, which provides a method for extracting dynamic characteristics of EEG signals that can reflect fleeting and highly dynamic neural activity patterns, which can make up for the shortcomings of the existing technology in this regard. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 A flowchart of a method for extracting dynamic features of brain wave signals provided in an embodiment of the present disclosure;

[0039] Figure 2 A schematic diagram of arranging electrodes in the human brain using the international 10-20 system provided in an embodiment of the present disclosure;

[0040] Figure 3 A schematic diagram of the result of decomposing a brain wave time series provided by an embodiment of the present disclosure;

[0041] Figure 4 A schematic diagram of the definitions of six microstates provided for an embodiment of the present disclosure;

[0042] Figure 5 A schematic diagram of the principle of determining the occurrence frequency and order of various EEG microstate transition paradigms included in a set provided by an embodiment of the present disclosure;

[0043] Figure 6 A flowchart of a method for determining an evaluation index provided by an embodiment of the present disclosure;

[0044] Figure 7 A schematic diagram of the structure of a device for extracting dynamic features of brain wave signals provided in an embodiment of the present disclosure;

[0045] Figure 8 A schematic diagram of the structure of an evaluation index determination device provided in an embodiment of the present disclosure;

[0046] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0049] Figure 1 is a flowchart of a method for extracting dynamic features of brain wave signals provided by an embodiment of the present disclosure, see Figure 1 , the method comprising:

[0050] S110, obtaining N channels of brain wave time series of the target object.

[0051] The target object may be, for example, a human or an animal.

[0052] Optionally, in practice, the international 10-20 system or 128-lead montage electrode arrangement method may be used to arrange electrodes near the target subject's brain, and the EEG time series collected by each electrode is regarded as a channel of EEG time series.

[0053] S120. According to the carrier frequency band and the amplitude modulation frequency band, the brain wave time series of each channel is disassembled to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands.

[0054] The carrier frequency band is used as a standard for decomposing the EEG time series of each channel. The amplitude modulation frequency band is determined according to the carrier frequency band. Optionally, the amplitude modulation frequency band has a lower frequency than the carrier frequency band.

[0055] In practice, the frequency bands of brain waves can be set to multiple bands as needed; or internationally common frequency bands can be used.

[0056] For example, in practice, the frequency bands of brain waves can be divided into j, which are represented as D1, D2, ..., Di, ..., Dj. From the first frequency band D1 to the jth frequency band Dj, the frequency gradually increases. Based on this, it can be set that the number of carrier frequency bands is j, that is, each brain wave frequency band is regarded as a carrier frequency band. For any carrier frequency band Di, its corresponding amplitude modulation frequency band is D1, D2, ..., Di-1.

[0057] For another example, the frequency band commonly used internationally is adopted, that is, the number of carrier frequency bands is set to 5, namely 0Hz-4Hz (Delta wave), 4Hz-8Hz (Theta wave), 8Hz-12Hz (Alpha wave), 12Hz-40Hz (Beta) wave, and 40Hz-100Hz (Gamma wave). The amplitude modulation frequency band corresponding to the carrier frequency band 40Hz-100Hz (Gamma wave) includes: 0Hz-4Hz (Delta wave), 4Hz-8Hz (Theta wave), 8Hz-12Hz (Alpha wave), 12Hz-40Hz (Beta) wave. In this way, the requirement of "the amplitude modulation frequency band frequency is lower than the carrier frequency band frequency" can be met when determining the amplitude modulation frequency band.

[0058] It should be noted that in the above examples, the carrier frequency band and the amplitude modulation frequency band both use the same frequency band division standard, which means that for example, for the carrier frequency band Di, its corresponding amplitude modulation frequency band is D1, D2, ..., Di-1, that is, for the i-th carrier frequency band Di, it corresponds to i-1 amplitude modulation frequency bands.

[0059] In practice, different frequency band division standards can be used for the carrier frequency band and the amplitude modulation frequency band. For example, there are two frequency band division standards: under the first frequency band division standard, the frequency can be divided into six frequency bands: 1Hz-2Hz, 2Hz-4Hz, 4Hz-8Hz, 8Hz-16Hz, 16Hz-32Hz, and 32Hz-64Hz. Under the second frequency band division standard, the wave frequency can be divided into seven frequency bands: 0.5Hz-1Hz, 1Hz-2Hz, 2Hz-4Hz, 4Hz-8Hz, 8Hz-16Hz, 16Hz-32Hz, and 32Hz-64Hz. When determining the carrier frequency band, it can be determined in the first frequency band division standard. When determining the amplitude modulation frequency band, it can be determined in the second frequency band division standard, as long as the requirement of "the amplitude modulation frequency band frequency is lower than the carrier frequency band frequency" is met. In this case, for the third carrier frequency band 8 Hz-12 Hz, the corresponding amplitude modulation frequency bands include: 0.5 Hz-1 Hz, 1 Hz-2 Hz and 2 Hz-4 Hz, a total of 3.

[0060] There are many methods for implementing this step, and the present application does not impose any restrictions on this. In one example, the method for implementing this step includes: for the brain wave time series of each channel, according to the preset brain wave carrier frequency band, the brain wave time series is first disassembled respectively to obtain carrier time series corresponding to the carrier frequency band of each brain wave, so that different carrier time series correspond to different carrier frequency bands; each carrier time series is subjected to Hilbers transformation to obtain an amplitude time series corresponding to each carrier time series; based on the carrier frequency band corresponding to each carrier time series, an amplitude modulation frequency band is determined; the frequency of the amplitude modulation frequency band is lower than the carrier frequency band; based on the amplitude modulation frequency band, the amplitude time series corresponding to each carrier time series is secondarily disassembled to obtain an amplitude modulation time series corresponding to each carrier time series.

[0061] Specifically, in order to extract the amplitude modulation time series, the EEG time series needs to undergo two stages of signal processing. In the first stage, the EEG time series S(t) of each channel is split into the superposition of several frequency band carrier time series, expressed as S(t) = C1(t) + C2(t) + ... + C n (t)+R(t), where C1(t) to C n (t) represents the carrier time series of n specific carrier frequency bands, and R(t) is the residual signal. Each carrier time series is converted into the amplitude phase time series of the corresponding carrier time through Hilbert transform, that is, C n (t) = A n (t)cos(θ n (t), where A n (t) is the amplitude time series, θ n (t) is the phase time series. In the second stage, each amplitude time series is further decomposed into multiple amplitude modulation time series, expressed as A n (t) = AM n,1 (t)+AM n,2 (t)+...+AM n,m (t)+AR n (t). Here AM n,m (t) is the mth amplitude modulation time series extracted based on the amplitude time series of the nth carrier, AR n (t) is the residual. This process ensures in-depth analysis of the signal, revealing the frequency modulation characteristics of different frequency bands, thereby enhancing the understanding of EEG activity.

[0062] It should be emphasized that the second stage of disassembly is essentially signal modulation, and the type of modulation is frequency modulation, not amplitude modulation. However, because the object of modulation is the amplitude time series, it is called amplitude modulated time series.

[0063] It should be noted that if two frequency band division standards are set: under the first frequency band division standard, the frequency can be divided into six frequency bands: 1Hz-2Hz, 2Hz-4Hz, 4Hz-8Hz, 8Hz-16Hz, 16Hz-32Hz, and 32Hz-64Hz. Under the second frequency band division standard, the wave frequency can be divided into seven frequency bands: 0.5Hz-1Hz, 1Hz-2Hz, 2Hz-4Hz, 4Hz-8Hz, 8Hz-16Hz, 16Hz-32Hz, and 32Hz-64Hz. When determining the carrier frequency band, it can be determined in the first frequency band division standard. When determining the amplitude modulation frequency band, it can be determined in the second frequency band division standard. For the brain wave time series of any channel, after the first disassembly, 6 carrier time series will be obtained, and each carrier time series corresponds to a carrier frequency band. Next, after the second disassembly of each carrier time series, a total of (6+1)×6 / 2=21 amplitude modulation time series will be obtained.

[0064] Optionally, when performing the first stage and the second stage disassembly, a bandpass filtering technique such as a hardware filter, a digital filter or a nonlinear filter may be used.

[0065] For example, in Figure 2 It is shown in the figure that in one scenario, the international 10-20 system is used to collect brain wave time series in the human brain. If one of them is set as the reference electrode and the other 22 are effective electrodes, a total of 22 channels of brain wave time series can be obtained. Using the two frequency band division standards in the above example, for each channel of the brain wave time series, after two decompositions, 21 amplitude modulation time series can be obtained. The 22-channel brain wave time series are decomposed into 21 amplitude modulation time series, and a total of 22×21 amplitude modulation time series are obtained. At least one of the source channels, carrier frequency bands, and amplitude modulation frequency bands of any two amplitude modulation time series is different. The amplitude modulation time series with the same carrier frequency band and amplitude modulation frequency band but different source channels are plotted in the same coordinate system, and the final result is as follows. Figure 3 As shown. Figure 3 In each coordinate system, the top 22 lines represent the amplitude modulation time series from different channels but with the same carrier frequency band and amplitude modulation frequency band. Figure 3 In the same column coordinate system, the carrier frequency bands of the amplitude modulation time series are the same. And along the direction from left to right, the carrier frequency bands corresponding to each column gradually increase. In any column, along the direction from top to bottom, the amplitude modulation frequency bands of each amplitude modulation time series gradually decrease.

[0066] S130, determining M target channels from the N channels, and obtaining target brain function connection segments, wherein M, N and P are all positive integers, and M≤N.

[0067] The target brain function connection segment can be understood as a collection of amplitude modulation time series from the target channel. The target brain function connection segment can also be simply described as a combination of target channels.

[0068] In this step, the specific value of M is not limited in this application. In practice, the value of M can be determined as needed.

[0069] The target channel is the channel that needs to be focused on in a specific scenario.

[0070] In some examples, the specific scenario may be, for example, a scenario in which the target object's performance in certain aspects (such as intelligence, disease, etc.) is evaluated. Intelligence may specifically include one or more of the following: language, space, calculation, art, and music. In this scenario, if the evaluation method is clear, the target channel is usually also clear and associated with the evaluation purpose. In this case, the specific implementation method of S130 may include: according to the correspondence between the evaluation purpose and the target channel, M target channels are determined in N channels to obtain the target brain function connection fragment. The correspondence between the evaluation purpose and the target channel is pre-constructed, which indicates which channels' brain wave time series need to be used in order to achieve a certain evaluation purpose, and these channels that need to be used are the target channels.

[0071] In other examples, the specific scenario may be, for example, to select a better channel combination (i.e., brain function connection fragment) from all channels for evaluating the performance of a subject in a certain aspect (such as intelligence, disease, etc.). In this case, the value of M can be specified in advance. After the value of M is determined, brain function connection fragments. The method is to consider part or all of a brain function connection segment to determine whether the brain function connection segment is suitable as a target channel for evaluating performance in a certain aspect (such as intelligence, disease, etc.).

[0072] S140. For any target brain function connection segment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained.

[0073] Exemplarily, if M=3, the target brain function connection segment includes data from three channels. Assume that the three channels include channel 1, channel 2, and channel 3. Among them, based on the EEG time series of channel 1, 21 amplitude modulation time series corresponding to channel 1 are finally obtained. Based on the EEG time series of channel 2, 21 amplitude modulation time series corresponding to channel 2 are finally obtained. Based on the EEG time series of channel 3, 21 amplitude modulation time series corresponding to channel 3 are finally obtained.

[0074] If each amplitude modulation time series is marked using carrier frequency band-amplitude modulation frequency band. If the carrier frequency band a used by a certain amplitude modulation time series is obtained, and the amplitude modulation frequency band is b, it can be recorded as an amplitude modulation time series ab. The amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set. In the above example, it can specifically mean that the amplitude modulation time series ab corresponding to channel 1, the amplitude modulation time series ab corresponding to channel 2, and the amplitude modulation time series ab corresponding to channel 3 are regarded as elements in the same set. In this way, all other amplitude modulation time series are classified, and a total of 21 sets will be obtained. The carrier frequency band and / or amplitude modulation frequency band of any two amplitude modulation time series in different sets are different.

[0075] S150. For each set, based on the EEG microstate transition paradigm recognition rule base, determine the occurrence frequency and order of various EEG microstate transition paradigms included in the set; the EEG microstate transition paradigm recognition rule base corresponds to the set, and the EEG microstate transition paradigm recognition rule base includes multiple EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules. The EEG microstate transition paradigm is used to describe the changes in EEG microstates within a preset time period.

[0076] EEG microstate refers to the electrical activity of the brain showing a relatively stable EEG static characteristic on a very short time scale. The EEG microstate transition paradigm is an EEG dynamic characteristic composed of a series of discrete, stable but short-lived EEG microstates. In an EEG microstate transition paradigm, multiple EEG microstates can be included, and each EEG microstate is arranged in a certain order. Different EEG microstate transition paradigms involve different categories and / or arrangement orders of each EEG microstate.

[0077] The EEG microstate transition paradigm recognition rule base includes multiple EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules. The EEG microstate transition paradigm identifier is used to distinguish different EEG microstate transition paradigms. For example, it can be the name and / or number of the EEG microstate transition paradigm. The EEG microstate transition paradigm recognition rule is used to describe the changes in the EEG microstates within a preset time period in the corresponding EEG microstate transition paradigm. Optionally, the EEG microstate transition paradigm recognition rule includes the categories and arrangement order of each EEG microstate involved in the EEG microstate transition paradigm.

[0078] The specific implementation method of this step may include: determining the microstate occurrence time node for each set; determining the microstate corresponding to the microstate occurrence time node in the set based on the size relationship of the amplitudes of each amplitude modulation time series in the set at the microstate occurrence time node; based on the EEG microstate transition paradigm recognition rule base and the microstate corresponding to the microstate occurrence time node; determining the type and number of EEG microstate transition paradigms included in the set; based on the type and number of EEG microstate transition paradigms included in the set, determining the occurrence frequency and order of various EEG microstate transition paradigms included in the set.

[0079] The microstate occurrence time node is the specific moment when a microstate occurs. The microstate occurrence time node usually corresponds to the moment when the amplitude in the amplitude modulation time series reaches an extreme value (such as a maximum value or a minimum value). In practice, in one embodiment, the moment when the amplitude of any amplitude modulation time series in the set reaches an extreme value point can be used as the microstate occurrence time node. In another embodiment, the amplitudes of all amplitude modulation time series in the set can also be superimposed to obtain a superposition result, and the moment when the amplitude in the superposition result reaches an extreme value point can be used as the microstate occurrence time node.

[0080] In another embodiment, the carrier frequency band corresponding to the amplitude modulation time series included in the set can also be used as the target carrier frequency band, and the amplitude modulation frequency band corresponding to the amplitude modulation time series included in the set can be used as the target amplitude modulation frequency band; the amplitudes of the amplitude modulation time series from all channels corresponding to the target carrier frequency band and the target amplitude modulation frequency band are superimposed to obtain a global superposition result, and the moment when the amplitude in the global superposition result reaches the extreme value point is used as the time node of the microstate occurrence.

[0081] For example, in Figure 3 In the figure, the lines in each coordinate system correspond to the same carrier frequency band and amplitude modulation frequency band. The bottom line in each coordinate system is the superposition result of the amplitude modulation time series from the 22 channels above in the coordinate system, that is, the global superposition result GFAM. The moment when the amplitude reaches the extreme value in the global superposition result GFAM is the time node of the microstate occurrence.

[0082] There are many specific implementation methods for "determining the microstate corresponding to the microstate occurrence time node in the set based on the magnitude relationship of the amplitudes of each amplitude modulation time series in the set at the microstate occurrence time node", and the present application does not limit this. Exemplarily, multiple microstates and microstate identification criteria can be predefined, and the microstate discrimination condition describes the magnitude relationship of the amplitudes in each amplitude modulation time series in the set at the microstate occurrence time node. In the step of "determining the microstate corresponding to the microstate occurrence time node in the set based on the magnitude relationship of the amplitudes of each amplitude modulation time series in the set at the microstate occurrence time node", first determine the amplitudes of each amplitude modulation time series in the set at the microstate occurrence time node, and then determine the microstate corresponding to the microstate occurrence time node in the set based on the magnitude relationship of the amplitudes of each amplitude modulation time series in the set at the microstate occurrence time node and the microstate identification criteria.

[0083] For example, see Figure 4 , if a set includes 3 amplitude modulation time series, these 3 amplitude modulation time series come from channel Fpz, channel Fp2 and channel Fp1 respectively. According to the magnitude relationship of the amplitudes of these three channels (i.e. channel Fpz, channel Fp2 and channel Fp1) at the same microstate occurrence time node, a total of 6 microstates can be defined. Figure 4 These six microstates are given in detail, and the identification criteria for each microstate are given.

[0084] exist Figure 5 Above, the amplitude adjustment time series from channels Fpz, Fp2, and Fp1 in a certain set are given. According to the magnitude relationship of the amplitudes of the amplitude modulation time series in the set at the time node of the microstate occurrence, combined with Figure 4 According to the definition in , we can get the EEG microstates corresponding to the time nodes of each microstate occurrence.

[0085] There are many specific implementation methods for "based on the EEG microstate transition paradigm identification rule base, and the microstates corresponding to the microstate occurrence time nodes; determining the types and quantities of EEG microstate transition paradigms included in the set", and this application does not impose any restrictions on this.

[0086] In one embodiment, if the EEG microstate transition paradigm includes a microstates arranged in a preset order; the amplitude modulation time series in the set includes P microstate occurrence time nodes; the specific implementation method of "based on the EEG microstate transition paradigm identification rule base, and the microstates corresponding to the microstate occurrence time nodes; determining the types and quantities of EEG microstate transition paradigms included in the set" may include: setting j=1, repeating the following EEG microstate transition paradigm identification steps until j=P-a+1; according to the arrangement order of the microstates corresponding to the jth to j+a-1th microstate occurrence time nodes in the set, determining the target EEG microstate transition paradigm in the EEG microstate transition paradigm identification rule base; adding 1 to the count value corresponding to the target EEG microstate transition paradigm; updating j so that the difference between the value of j after the update and the value of j before the update is 1.

[0087] Exemplarily, if the EEG microstate transition paradigm includes 3 microstates arranged in a preset order; the amplitude modulation time series in the set includes 300 microstate occurrence time nodes. First, let j=1, based on the EEG microstates and arrangement order corresponding to the 1st to 3rd microstate occurrence time nodes in the set, the EEG microstate transition paradigm corresponding to the 1st to 3rd microstate occurrence time nodes can be determined. Assuming that the EEG microstate transition paradigm is EEG microstate transition paradigm 1, the count value of EEG microstate transition paradigm 1 is increased by 1. Then let j=2, based on the EEG microstates and arrangement order corresponding to the 2nd to 4th microstate occurrence time nodes in the set, the EEG microstate transition paradigm corresponding to the 2nd to 4th microstate occurrence time nodes can be determined. Assuming that the EEG microstate transition paradigm is EEG microstate transition paradigm 2, the count value of EEG microstate transition paradigm 2 is increased by 1. By repeating this process, we can obtain the types and quantities of all EEG microstate transition paradigms included in the set.

[0088] The essence of this setting is that when analyzing the target EEG microstate transition paradigm, adjacent analysis ranges overlap. For example, when j = 1, the analysis range is from the 1st to the 3rd microstate occurrence time nodes; when j = 2, the analysis range is from the 2nd to the 4th microstate occurrence time nodes. The overlapping objects of the two analyses are the 2nd and 3rd microstate occurrence time nodes. The advantage of this setting is that it can enhance the temporal resolution, more carefully capture the possible rapid transition or mixed state between two consecutive microstates, and reveal potential functional coherence.

[0089] S160. Determine the dynamic characteristics of the target object's EEG signal based on the occurrence frequency and order of various EEG microstate transition paradigms included in each set.

[0090] Optionally, the occurrence frequencies and orderings of various EEG microstate transition paradigms included in each set may be used as dynamic features of the EEG signal of the target object.

[0091] In the above technical scheme, the EEG time series of each channel is decomposed according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands; M target channels are determined in N channels to obtain target brain function connection fragments; for any target brain function connection fragment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained; for each set, based on the EEG microstate transfer paradigm, The invention relates to a rule base for distinguishing appearance frequencies and rankings of various EEG microstate transition paradigms included in the set; the EEG microstate transition paradigm identification rule base corresponds to the set, and the EEG microstate transition paradigm identification rule base includes multiple EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm identification rules. The EEG microstate transition paradigm is used to describe the changes of EEG microstates within a preset time period; based on the appearance frequencies and rankings of various EEG microstate transition paradigms included in each set, the dynamic characteristics of the EEG signal of the target object are determined, which provides a method for extracting dynamic characteristics of EEG signals that can reflect fleeting and highly dynamic neural activity patterns, which can make up for the shortcomings of the prior art in this regard.

[0092] The dynamic characteristics of the target object's brain wave signal obtained by the above technical solution can be subsequently used in a variety of scenarios, such as scenarios for evaluating the target object's performance in certain aspects (such as intelligence, disease, etc.), or scenarios for screening out better brain function connection fragments from all channels for evaluating the object's performance in certain aspects (such as intelligence, disease, etc.).

[0093] For the scenario of evaluating the performance of the target object in a certain aspect (such as intelligence, disease, etc.), based on the above technical solution, optionally, the method may also include: obtaining dynamic characteristics of brain wave signals of a reference object; determining the similarity distance between the target object and the reference object based on the dynamic characteristics of the brain wave signals of the target object and the dynamic characteristics of the brain wave signals of the reference object; and evaluating the target object based on the similarity distance between the target object and the reference object.

[0094] The reference object can be, for example, a person or an animal. The reference object can be regarded as an evaluation standard, such as a person with high IQ, a person with a certain ability (such as music, painting), a person with a certain mental illness, a person without a certain ability, etc. The target object is the object being evaluated.

[0095] Both the method for acquiring the dynamic features of the brain wave signal of the reference object and the method for acquiring the dynamic features of the brain wave signal of the target object can be obtained by using the method for extracting the dynamic features of the brain wave signal provided in the present application.

[0096] There are many specific implementation methods for “determining the similarity distance between the target object and the reference object based on the dynamic characteristics of the brain wave signal of the target object and the dynamic characteristics of the brain wave signal of the reference object”, and this application does not limit this. For example, it can be set as follows: for any set, based on the following formula, determine the similarity distance D between the target object and the reference object m (S1, S2)

[0097]

[0098] Among them, S1 is the target object, S2 is the reference object, I1(k) is the number of the EEG microstate transfer paradigm with the probability of occurrence ranked k corresponding to the target object; I2(k) is the number of the EEG microstate transfer paradigm with the probability of occurrence ranked k corresponding to the reference object; W(I1(k), I2(k)) represents the difference weight of two EEG microstate transfer paradigms with different numbers; p1(I1(k)) is the probability of the EEG microstate transfer paradigm numbered I1(k) occurring in the target object, and p2(I2(k)) is the probability of the EEG microstate transfer paradigm numbered I2(k) occurring in the target object.

[0099] Optionally, the greater the difference between two EEG microstate transition paradigms with different numbers, the greater the difference weight W(I1(k), I2(k)) of the two EEG microstate transition paradigms with different numbers.

[0100] It should be noted that, in practice, if there are P sets corresponding to the same target brain function connection fragment, each set will obtain a similarity distance between the target object and the reference object, and a total of P similarity distances will be obtained. In practice, the target object can be evaluated based on one or more of the P similarity distances. If the target object is evaluated based on multiple of the P similarity distances, optionally, the final similarity distance between the target object and the reference object is determined based on multiple of the P similarity distances; the target object is evaluated based on the final similarity distance between the target object and the reference object.

[0101] If the similarity distance between the target object and the reference object is smaller, it means that the target object is more similar to the reference object. If the evaluation purpose is to evaluate whether the target object has a talent for painting, and the reference object is a person with a talent for painting, if the final similarity distance between the target object and the reference object is less than the set threshold, it is judged that the target object is similar to the reference object and has a talent for painting. Or, if the final similarity distance between the target object and the reference object is greater than or equal to the set threshold, it is judged that the target object is not similar to the reference object and does not have a talent for painting.

[0102] For the scenario of selecting a better channel combination (i.e., brain function connection fragment) from all channels for evaluating the performance of the subject in a certain aspect (such as intelligence, disease, etc.). Based on the same inventive concept, the present application also provides a method for determining an evaluation index, see Figure 7 , the evaluation index determination method includes:

[0103] S310, obtaining N channels of brain wave time series of multiple candidate objects.

[0104] S320. Taking the candidate object as the target object, using the method for extracting dynamic features of brain wave signals provided in the present application, determine the dynamic features of brain wave signals corresponding to the candidate object and originating from different target brain function connection segments.

[0105] S330. Based on the evaluation purpose, the candidate subjects are divided into a control group and an experimental group.

[0106] S340, calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between the candidate objects in the experimental group and the candidate objects in the control group for the same brain function connection segment.

[0107] It should be emphasized that the first similarity distance reflects the similarity within the control group, the second similarity distance reflects the similarity within the experimental group, and the third similarity distance reflects the similarity across groups.

[0108] S350: Based on the first similarity distance, the second similarity distance, and the third similarity distance, determine which target brain function connection segment is used as an evaluation indicator for the evaluation purpose.

[0109] Optionally, the implementation method of this step may include: determining the score of the brain function connection segment based on the first similarity distance, the second similarity distance and the third similarity distance; and determining whether to use the brain function connection segment as an evaluation indicator for the evaluation purpose based on the score of the brain function connection segment.

[0110] Optionally, in the scenario of determining whether a subject has a certain mental illness, the score of the brain function connection segment can specifically be the area under the receiver operating characteristic curve (Area Under the Receiver Operating Characteristic Curve, AUC).

[0111] If the score of the brain function connection segment is greater than the set threshold, it is determined that the brain function connection segment will be used as an evaluation indicator for the evaluation purpose; if the score of the brain function connection segment is less than or equal to the set threshold, it is determined not to use the brain function connection segment as an evaluation indicator for the evaluation purpose.

[0112] Exemplarily, if it is desired to determine the brain function connection segment (i.e., evaluation index) used to evaluate whether the object has a certain ability (such as painting ability), multiple candidate objects (i.e., subjects) can be determined. Some of these candidate objects have the ability, and some do not have the ability. All candidate objects with the ability are used as members of the control group, and all candidate objects without the ability are used as members of the control group. Using the above-mentioned brain wave signal dynamic feature extraction method, the brain wave signal dynamic features of all brain function connection segments of each candidate object in the control group, as well as the brain wave signal dynamic features of all brain function connection segments of each candidate object in the experimental group are extracted. Calculate the first similarity distance between different candidate objects in the control group for the same brain function connection segment, the second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and the third similarity distance between the candidate objects in the experimental group and the control group for the same brain function connection segment.

[0113] Since there are P sets corresponding to the same brain function connection segment, for each set, the similarity distance of the same set can be calculated based on formula (1), and the similarity distances of the P sets can be obtained in total. Subsequently, the similarity distance of the brain function connection segment can be obtained based on the similarity distances of the P sets.

[0114] Since the first similarity distance and the second similarity distance are both similarity distances within a group, the smaller the first similarity distance and the second similarity distance, the more similar the members within the group are. The third similarity distance is the similarity distance between groups, and the larger the third similarity distance, the less similar the members of different groups are. Accordingly, if for a certain brain function connection segment, the smaller the first similarity distance and the second similarity distance, the larger the third similarity distance, the more valuable the brain function connection segment is for evaluation purposes.

[0115] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0116] Figure 7 This is a schematic diagram of the structure of a device for extracting dynamic features of brain wave signals proposed in an embodiment of the present disclosure. Figure 7 As shown, the device comprises:

[0117] A first acquisition module 410 is used to acquire N channels of brain wave time series of the target object;

[0118] The disassembling module 420 is used to disassemble the brain wave time series of each channel according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands;

[0119] A first determination module 430 is used to determine M target channels from the N channels to obtain target brain function connection segments;

[0120] A first division module 440 is used for classifying the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band into one set for any target brain function connection segment, and obtaining a total of P sets;

[0121] The identification module 450 is used to determine the occurrence frequency and order of various EEG microstate transition paradigms included in the set for each of the sets based on the EEG microstate transition paradigm identification rule base; the EEG microstate transition paradigm identification rule base corresponds to the set, the EEG microstate transition paradigm identification rule base includes multiple EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm identification rules, and the EEG microstate transition paradigm is used to describe the change of EEG microstates within a preset time period;

[0122] A second determination module 460 is used to determine the dynamic characteristics of the EEG signal of the target object based on the occurrence frequency and order of the various EEG microstate transition paradigms included in each of the sets;

[0123] Among them, M, N and P are all positive integers, and M≤N.

[0124] Further, the disassembly module 420 is used to:

[0125] For the brain wave time series of each channel, according to the preset brain wave carrier frequency band, the brain wave time series is first disassembled to obtain carrier time series corresponding to the carrier frequency bands of the brain waves, so that different carrier time series correspond to different carrier frequency bands;

[0126] Performing a Hilbert transformation on each of the carrier time series to obtain an amplitude time series corresponding to each of the carrier time series;

[0127] Determine an amplitude modulation frequency band based on the carrier frequency band corresponding to each of the carrier time series; the amplitude modulation frequency band has a frequency lower than the carrier frequency band;

[0128] Based on the amplitude modulation frequency band, the amplitude time series corresponding to each of the carrier time series is decomposed for the second time to obtain the amplitude modulation time series corresponding to each of the carrier time series.

[0129] Furthermore, the identification module 450 is used to:

[0130] For each of the sets, determining a microstate occurrence time node;

[0131] Determine the microstate corresponding to the microstate occurrence time node in the set according to the magnitude relationship between the amplitudes of the amplitude modulation time series in the set at the microstate occurrence time node;

[0132] Based on the EEG microstate transition paradigm recognition rule base and the microstates corresponding to the microstate occurrence time nodes, determining the types and quantities of the EEG microstate transition paradigms included in the set;

[0133] Based on the types and quantities of the EEG microstate transition paradigms included in the set, the occurrence frequencies and rankings of the various EEG microstate transition paradigms included in the set are determined.

[0134] Furthermore, if the EEG microstate transition paradigm includes a microstates arranged in a preset order; the amplitude modulation time series in the set includes P microstate occurrence time nodes; the identification module 450 is used to:

[0135] Let j = 1, and repeat the following steps of EEG microstate transition paradigm identification until j = P-a+1;

[0136] According to the arrangement order of the microstates corresponding to the jth to j+a-1th microstate occurrence time nodes in the set, determining the target EEG microstate transition paradigm in the EEG microstate transition paradigm recognition rule base;

[0137] Add 1 to the count value corresponding to the target EEG microstate transition paradigm;

[0138] Update j so that the difference between the value of j after the update and the value of j before the update is 1.

[0139] Furthermore, the device also includes an evaluation module, which is used to:

[0140] Acquire the dynamic characteristics of the brain wave signal of the reference object;

[0141] Determining a similarity distance between the target object and the reference object based on the dynamic characteristics of the brain wave signal of the target object and the dynamic characteristics of the brain wave signal of the reference object;

[0142] The target object is evaluated based on the similarity distance between the target object and the reference object.

[0143] Furthermore, the evaluation module is used to:

[0144] For any of the above sets, the similarity distance D between the target object and the reference object is determined based on the following formula: m (S1, S2)

[0145]

[0146] Wherein, S1 is the target object, S2 is the reference object, I1(k) is the number of the EEG microstate transition paradigm ranked k in terms of occurrence probability corresponding to the target object; I2(k) is the number of the EEG microstate transition paradigm ranked k in terms of occurrence probability corresponding to the reference object; W(I1(k), I2(k)) represents the difference weights of two EEG microstate transition paradigms with different numbers; p1(I1(k)) is the probability of the EEG microstate transition paradigm numbered I1(k) occurring in the target object, and p2(I2(k)) is the probability of the EEG microstate transition paradigm numbered I2(k) occurring in the target object.

[0147] Figure 8 This is a schematic diagram of the structure of an evaluation index determination device proposed in an embodiment of the present disclosure, such as Figure 8 As shown, the device comprises:

[0148] The second acquisition module 510 is used to acquire brain wave time series of N channels of multiple candidate objects;

[0149] The third determination module 520 is used to use the candidate object as the target object, and use the above-mentioned brain wave signal dynamic feature extraction device to determine the dynamic features of the brain wave signals originating from different brain function connection segments corresponding to the candidate object;

[0150] A second division module 530 is used to divide the candidate objects into a control group and an experimental group based on the evaluation purpose;

[0151] A calculation module 540 is used to calculate a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment;

[0152] The fourth determination module 550 is used to determine which target brain function connection segment is used as an evaluation indicator for an evaluation purpose based on the first similarity distance, the second similarity distance and the third similarity distance.

[0153] The device disclosed in the above embodiments can implement the process of the method disclosed in the above method embodiments, and has the same or corresponding beneficial effects. To avoid repetition, it will not be described here.

[0154] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure is shown in FIG. Fig. 9 As shown, the electronic device may include a smart terminal such as a mobile phone or a PAD, and the electronic device includes:

[0155] One or more processors 301, Fig. 9 A processor 301 is taken as an example;

[0156] Memory 302;

[0157] The electronic device may further include: an input device 303 and an output device 304 .

[0158] The processor 301, memory 302, input device 303 and output device 304 in the electronic device may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0159] The memory 302 is a non-transitory computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method for extracting dynamic features of brain wave signals or the method for determining evaluation indicators in the embodiments of the present disclosure. The processor 301 executes various functional applications and data processing of the server by running the software programs, instructions and modules stored in the memory 302, that is, implementing the method for extracting dynamic features of brain wave signals or the method for determining evaluation indicators in the above method embodiments.

[0160] The memory 302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 302 may optionally include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the terminal device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0161] The input device 303 may be used to receive input digital or character information and generate signal input related to user settings and function control of the electronic device. The output device 304 may include a display device such as a display screen.

[0162] The present disclosure also provides a computer-readable storage medium storing a program or instruction, which enables a computer to execute a method for extracting dynamic features of brain wave signals, the method comprising:

[0163] Obtain N channels of brain wave time series of the target object;

[0164] According to the carrier frequency band and the amplitude modulation frequency band, the brain wave time series of each channel is disassembled to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands;

[0165] Determining M target channels among the N channels to obtain target brain function connection segments;

[0166] For any target brain function connection segment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained;

[0167] For each of the sets, based on the EEG microstate transition paradigm recognition rule base, the occurrence frequency and order of the various EEG microstate transition paradigms included in the set are determined; the EEG microstate transition paradigm recognition rule base corresponds to the set, the EEG microstate transition paradigm recognition rule base includes a plurality of EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules, and the EEG microstate transition paradigm is used to describe the changes in EEG microstates within a preset time period;

[0168] Determining the dynamic characteristics of the brain wave signal of the target object based on the occurrence frequency and order of the various brain wave microstate transition paradigms included in each of the sets;

[0169] Among them, M, N and P are all positive integers, and M≤N.

[0170] The embodiment of the present disclosure also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute a method for determining an evaluation index when the program or instruction is executed, the method comprising:

[0171] Obtaining N channels of brain wave time series of multiple candidate objects;

[0172] Taking the candidate object as the target object, using the method for extracting dynamic features of brain wave signals according to any one of claims 1 to 5, determining dynamic features of brain wave signals originating from different brain function connection segments corresponding to the candidate object;

[0173] Based on the evaluation purpose, the candidate subjects are divided into a control group and an experimental group;

[0174] Calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment;

[0175] Based on the first similarity distance, the second similarity distance and the third similarity distance, it is determined which target brain function connection segment is used as an evaluation indicator for an evaluation purpose.

[0176] Optionally, when executed by a computer processor, the computer executable instructions can also be used to execute the technical solutions of the method for extracting dynamic features of brain wave signals or the method for determining evaluation indicators provided in any embodiment of the present disclosure.

[0177] Through the above description of the implementation methods, the technical personnel in the relevant field can clearly understand that the present disclosure can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0178] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0179] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for extracting dynamic features of brain wave signals, characterized in that: include: Obtain N channels of brain wave time series of the target object; According to the carrier frequency band and the amplitude modulation frequency band, the brain wave time series of each channel is disassembled to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands; Determining M target channels among the N channels to obtain target brain function connection segments; For any target brain function connection segment, the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band are grouped into one set, and a total of P sets are obtained; For each of the sets, based on the EEG microstate transition paradigm recognition rule base, the occurrence frequency and order of the various EEG microstate transition paradigms included in the set are determined; the EEG microstate transition paradigm recognition rule base corresponds to the set, the EEG microstate transition paradigm recognition rule base includes a plurality of EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm recognition rules, and the EEG microstate transition paradigm is used to describe the changes in EEG microstates within a preset time period; Determining the dynamic characteristics of the brain wave signal of the target object based on the occurrence frequency and order of the various brain wave microstate transition paradigms included in each of the sets; Among them, M, N and P are all positive integers, and M≤N.

2. The method for extracting dynamic features of brain wave signals according to claim 1, characterized in that: The step of decomposing the brainwave time series of each channel according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series includes: For the brain wave time series of each channel, according to the preset brain wave carrier frequency band, the brain wave time series is first disassembled to obtain carrier time series corresponding to the carrier frequency bands of the brain waves, so that different carrier time series correspond to different carrier frequency bands; Performing a Hilbert transformation on each of the carrier time series to obtain an amplitude time series corresponding to each of the carrier time series; Determine an amplitude modulation frequency band based on the carrier frequency band corresponding to each of the carrier time series; the frequency of the amplitude modulation frequency band is lower than the carrier frequency band; Based on the amplitude modulation frequency band, the amplitude time series corresponding to each of the carrier time series is decomposed for the second time to obtain the amplitude modulation time series corresponding to each of the carrier time series.

3. The method for extracting dynamic features of brain wave signals according to claim 1, characterized in that: For each of the sets, based on the EEG microstate transition paradigm recognition rule base, determining the occurrence frequency and order of various EEG microstate transition paradigms included in the set includes: For each of the sets, determining a microstate occurrence time node; Determine the microstate corresponding to the microstate occurrence time node in the set according to the magnitude relationship between the amplitudes of the amplitude modulation time series in the set at the microstate occurrence time node; Based on the EEG microstate transition paradigm recognition rule base and the microstates corresponding to the microstate occurrence time nodes, determining the types and quantities of the EEG microstate transition paradigms included in the set; Based on the types and quantities of the EEG microstate transition paradigms included in the set, the occurrence frequencies and rankings of the various EEG microstate transition paradigms included in the set are determined.

4. The method for extracting dynamic features of brain wave signals according to claim 3, characterized in that: If the EEG microstate transition paradigm includes a microstates arranged in a preset order; the amplitude modulation time series in the set includes P microstate occurrence time nodes; the type and quantity of the EEG microstate transition paradigm included in the set are determined based on the EEG microstate transition paradigm recognition rule base and the microstates corresponding to the microstate occurrence time nodes, including: Let j = 1, and repeat the following steps of EEG microstate transition paradigm identification until j = P-a+1; According to the arrangement order of the microstates corresponding to the jth to j+a-1th microstate occurrence time nodes in the set, determining the target EEG microstate transition paradigm in the EEG microstate transition paradigm recognition rule base; Add 1 to the count value corresponding to the target EEG microstate transition paradigm; Update j so that the difference between the value of j after the update and the value of j before the update is 1.

5. The method for extracting dynamic features of brain wave signals according to claim 1, characterized in that: Also includes: Acquire the dynamic characteristics of the brain wave signal of the reference object; Determining a similarity distance between the target object and the reference object based on the dynamic characteristics of the brain wave signal of the target object and the dynamic characteristics of the brain wave signal of the reference object; The target object is evaluated based on the similarity distance between the target object and the reference object.

6. The method for extracting dynamic features of brain wave signals according to claim 5, characterized in that: The determining the similarity distance between the target object and the reference object based on the dynamic characteristics of the brain wave signal of the target object and the dynamic characteristics of the brain wave signal of the reference object includes: For any of the above sets, the similarity distance D between the target object and the reference object is determined based on the following formula: m (S1, S2) Wherein, S1 is the target object, S2 is the reference object, I1(k) is the number of the EEG microstate transition paradigm ranked k in terms of occurrence probability corresponding to the target object; I2(k) is the number of the EEG microstate transition paradigm ranked k in terms of occurrence probability corresponding to the reference object; W(I1(k), I2(k)) represents the difference weights of two EEG microstate transition paradigms with different numbers; p1(I1(k)) is the probability of the EEG microstate transition paradigm numbered I1(k) occurring in the target object, and p2(I2(k)) is the probability of the EEG microstate transition paradigm numbered I2(k) occurring in the target object.

7. A method for determining an evaluation index, characterized in that: include: Obtaining N channels of brain wave time series of multiple candidate objects; Taking the candidate object as the target object, using the method for extracting dynamic features of brain wave signals according to any one of claims 1 to 5, determining dynamic features of brain wave signals originating from different brain function connection segments corresponding to the candidate object; Based on the evaluation purpose, the candidate subjects are divided into a control group and an experimental group; Calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment; Based on the first similarity distance, the second similarity distance and the third similarity distance, it is determined which target brain function connection segment is used as an evaluation indicator for an evaluation purpose.

8. A device for extracting dynamic features of brain wave signals, characterized in that: include: The first acquisition module is used to acquire N channels of brain wave time series of the target object; A disassembly module is used to disassemble the brain wave time series of each channel according to the carrier frequency band and the amplitude modulation frequency band to obtain the amplitude modulation time series; each channel corresponds to P amplitude modulation time series; among the P amplitude modulation time series corresponding to the same channel, different amplitude modulation time series correspond to different carrier frequency bands and / or amplitude modulation frequency bands; A first determination module is used to determine M target channels from the N channels to obtain target brain function connection segments; A first division module is used for classifying the amplitude modulation time series from different target channels with the same carrier frequency band and amplitude modulation frequency band into one set for any target brain function connection segment, and obtaining a total of P sets; An identification module is used to determine, for each of the sets, the occurrence frequency and order of the various EEG microstate transition paradigms included in the set based on the EEG microstate transition paradigm identification rule base; the EEG microstate transition paradigm identification rule base corresponds to the set, the EEG microstate transition paradigm identification rule base includes a plurality of EEG microstate transition paradigm identifiers and their corresponding EEG microstate transition paradigm identification rules, and the EEG microstate transition paradigm is used to describe the change of EEG microstates within a preset time period; A second determination module is used to determine the dynamic characteristics of the brain wave signal of the target object based on the occurrence frequency and order of the various brain wave microstate transition paradigms included in each of the sets; Among them, M, N and P are all positive integers, and M≤N.

9. An evaluation index determination device, characterized in that: include: The second acquisition module is used to acquire the brain wave time series of N channels of multiple candidate objects; A third determination module is used to use the candidate object as a target object, and use the brain wave signal dynamic feature extraction device described in claim 8 to determine the dynamic features of the brain wave signals originating from different brain function connection segments corresponding to the candidate object; A second division module is used to divide the candidate objects into a control group and an experimental group based on the evaluation purpose; a calculation module, used for calculating a first similarity distance between different candidate objects in the control group for the same brain function connection segment, a second similarity distance between different candidate objects in the experimental group for the same brain function connection segment, and a third similarity distance between candidate objects in the experimental group and candidate objects in the control group for the same brain function connection segment; The fourth determination module is used to determine which target brain function connection segment is used as an evaluation indicator for an evaluation purpose based on the first similarity distance, the second similarity distance and the third similarity distance.

Images