Anesthesia depth monitoring system based on electroencephalogram signals

Abstract

The invention relates to an anesthesia depth monitoring system based on electroencephalogram signals. Comprises: a first acquisition module for acquiring an electroencephalogram signal of a preset time length; the solving module is used for solving a segmentation scheme adopted when the electroencephalogram signals are subjected to time-frequency analysis on the basis of a genetic algorithm; the segmentation module is used for carrying out segmentation processing on the electroencephalogram signals with the preset time duration based on a segmentation scheme so as to obtain a plurality of electroencephalogram signal segments; the Fourier transform module is used for respectively performing Fourier transform on the plurality of electroencephalogram signal fragments so as to obtain frequency domain representation information corresponding to the plurality of electroencephalogram signal fragments; and the second acquisition module is used for performing time-frequency analysis on the basis of the frequency domain representation information and the time period information corresponding to the plurality of electroencephalogram signal fragments so as to obtain anesthesia depth information. According to the method, high time resolution and frequency resolution are obtained at the same time during time-frequency analysis, a more reliable basis is provided for subsequent signal analysis and processing, and the anesthesia depth monitoring accuracy is further improved.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the field of signal monitoring technology, and specifically to an anesthesia depth monitoring system based on electroencephalogram signals. Background Art

[0002] Anesthesia depth monitoring is a key link in modern anesthesiology, which aims to ensure that patients are in an appropriate state of anesthesia during surgery, neither too deep to cause unstable vital signs nor too shallow to cause intraoperative awakening and pain. With the increasing complexity of surgery and the improvement of patient safety awareness, accurate monitoring of anesthesia depth has become particularly important.

[0003] However, the accuracy of anesthesia depth monitoring is not yet high enough. Traditional methods mainly rely on clinical observation and empirical judgment, such as the patient's blood pressure, heart rate, breathing and other vital signs, but these indicators are affected by many factors and cannot directly reflect the brain's anesthesia state. In addition, although there is a method of anesthesia depth monitoring through EEG signals in existing monitoring technologies, there are still large errors.

[0004] Therefore, a method that can accurately monitor the depth of anesthesia is urgently needed. Summary of the invention

[0005] The embodiments of this specification provide an anesthesia depth monitoring system based on EEG signals, which can accurately monitor the anesthesia depth.

[0006] The technical solution is as follows: The embodiment of this specification provides an anesthesia depth monitoring system based on EEG signals, including: A first acquisition module acquires an EEG signal of a preset time length; The solution module solves the segmentation scheme used in the time-frequency analysis of EEG signals based on the genetic algorithm; A segmentation module, which processes the EEG signal of a preset time length in segments based on a segmentation scheme to obtain multiple EEG signal segments; A Fourier transform module performs Fourier transform on the multiple EEG signal segments respectively to obtain frequency domain representation information corresponding to each of the multiple EEG signal segments; The second acquisition module performs time-frequency analysis based on the frequency domain representation information and time period information corresponding to each of the multiple EEG signal segments to obtain anesthesia depth information; The segmentation scheme obtained in the solution module allows segmentation of different length time windows at different positions of the EEG signal; When solving the segmentation scheme used in the time-frequency analysis of the EEG signal based on the genetic algorithm in the solution module, the fitness function used simultaneously considers the total time resolution data and the total frequency resolution data of the EEG signal of the preset time length under the segmentation scheme; In the solution module, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Acquire multiple EEG signal segments under the segmentation scheme, and acquire signal change information corresponding to each of the multiple EEG signal segments; Based on the signal change information corresponding to each of the multiple EEG signal segments and the time window lengths corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained.

[0007] As a preferred solution, the signal change information of the EEG signal segment includes the overall signal variance information of the segment; In the solution module, based on the signal change information corresponding to each of the multiple EEG signal segments and the time window length corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Based on the overall signal variance information of the segments corresponding to the multiple EEG signal segments and the time window lengths corresponding to the multiple EEG signal segments, the segment time resolution data and the segment frequency resolution data corresponding to the multiple EEG signal segments are obtained; Based on the fragment time resolution data corresponding to each of the multiple EEG signal fragments, the total time resolution data of the EEG signal under the segmentation scheme is obtained; Based on the segment frequency resolution data corresponding to each of the multiple EEG signal segments, the total frequency resolution data of the EEG signal under the segmentation scheme is obtained.

[0008] As a preferred solution, the segmentation solution obtained by the solution module also allows overlap between two adjacent EEG signal segments.

[0009] As a preferred solution, the segmentation solution obtained by the solution module also allows different overlapping lengths between two adjacent EEG signal segments.

[0010] As a preferred solution, in the solution module, when solving the segmentation scheme used in time-frequency analysis of EEG signals based on a genetic algorithm, the fitness function used also simultaneously considers the total amount of signal data and total signal coherence data of the EEG signals of a preset time length under the segmentation scheme.

[0011] As a preferred solution, in the solution module, the total amount of signal data of the EEG signal under the segmentation solution is obtained, including: Obtaining the time window lengths corresponding to each of the multiple EEG signal segments; Based on the time window lengths corresponding to the multiple EEG signal segments, the total amount of signal data of the EEG signal under the segmentation scheme is obtained.

[0012] As a preferred solution, in the solution module, the acquisition of total signal coherence data of the EEG signal under the segmentation scheme includes: Based on the signal change information corresponding to each of the multiple EEG signal segments, the time window length corresponding to each of the multiple EEG signal segments, and the overlapping information corresponding to each of the multiple EEG signal segments, obtaining segment signal coherence data corresponding to each of the multiple EEG signal segments; Based on the segment signal coherence data corresponding to each of the multiple EEG signal segments, the total signal coherence data of the EEG signal under the segmentation scheme is obtained.

[0013] As a preferred solution, the signal change information of the EEG signal segment includes signal variance information of the beginning part of the segment and signal variance information of the end part of the segment; The overlapping information of the EEG signal segment includes the overlapping length information of the starting part of the segment and the overlapping length information of the ending part of the segment.

[0014] As a preferred solution, the overlapping length of the beginning part of the segment and the overlapping length of the end part of the segment are both less than half of the overall length of the EEG signal segment.

[0015] As a preferred solution, in the solution module, obtaining the segment signal coherence data for each EEG signal segment includes: The EEG signal segment for which segment signal coherence data is currently acquired is regarded as a target EEG signal segment; When only the beginning of the target EEG signal segment overlaps: Based on the signal variance information of the starting part of the target EEG signal segment and the signal variance information of the ending part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When only the end portion of the target EEG signal segment overlaps: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the ending part of the segment, and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When the beginning and end of the target EEG signal segment overlap at the same time: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the starting part and the overlapping length of the ending part of the segment, the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When the beginning and end of the target EEG signal segment do not overlap: Based on the signal variance information of the beginning part of the target EEG signal segment and the signal variance information of the end part of the segment, the segment signal coherence data of the target EEG signal segment is obtained.

[0016] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: The genetic algorithm is used to optimize the segmentation scheme used in the time-frequency analysis of EEG signals, and when constructing the fitness function, the total time resolution data and total frequency resolution data of the EEG signals of the preset time length under the segmentation scheme are comprehensively considered. Among them, the calculation of the total time resolution data and the total frequency resolution data is not only based on the time window length characteristics of the EEG signal segments, but also deeply considers the signal change information corresponding to each of the multiple EEG signal segments. This design aims to ensure that when performing time-frequency analysis on EEG signals, high time resolution and frequency resolution can be obtained at the same time, so as to more accurately capture the time-frequency characteristics in the signal, provide a more reliable basis for subsequent signal analysis and processing, and improve the accuracy of monitoring the depth of anesthesia based on EEG signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a structural schematic diagram of an anesthesia depth monitoring system based on EEG signals provided in an embodiment of this specification.

[0019] Figure 2 It is a flowchart of an anesthesia depth monitoring method based on EEG signals provided in an embodiment of this specification.

[0020] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification.

[0022] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0023] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present specification. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described with respect to some examples may be combined in other examples.

[0024] Reference Figure 1 As shown, Figure 1 A schematic diagram of a system for monitoring the depth of anesthesia based on electroencephalogram signals provided in an embodiment of this specification may at least include: A first acquisition module acquires an EEG signal of a preset time length; The solution module solves the segmentation scheme used in the time-frequency analysis of EEG signals based on the genetic algorithm; A segmentation module, which processes the EEG signal of a preset time length in segments based on a segmentation scheme to obtain multiple EEG signal segments; A Fourier transform module performs Fourier transform on the multiple EEG signal segments respectively to obtain frequency domain representation information corresponding to each of the multiple EEG signal segments; The second acquisition module performs time-frequency analysis based on the frequency domain representation information and time period information corresponding to each of the multiple EEG signal segments (Note: the time period information of the EEG signal segment is the time information of the EEG signal segment in the preset time length. For example, if the preset length is 3 minutes, the time period information of the EEG signal segment may be from 30s to 35s or from 35s to 45s, etc.) to obtain the anesthesia depth information; The segmentation scheme obtained in the solution module allows segmentation of different length time windows at different positions of the EEG signal (note: it allows segmentation processing of the EEG signal without using a mode of equal length time windows); When solving the segmentation scheme used in the time-frequency analysis of the EEG signal based on the genetic algorithm in the solution module, the fitness function used simultaneously considers the total time resolution data and the total frequency resolution data of the EEG signal of the preset time length under the segmentation scheme; In the solution module, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Acquire multiple EEG signal segments under the segmentation scheme, and acquire signal change information corresponding to each of the multiple EEG signal segments; Based on the signal change information corresponding to each of the multiple EEG signal segments and the time window lengths corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained.

[0025] It can be understood that the embodiment of this specification optimizes and solves the segmentation scheme used in the time-frequency analysis of EEG signals through genetic algorithms, and when constructing the fitness function, the total time resolution data and total frequency resolution data of the EEG signals of a preset time length under the segmentation scheme are comprehensively considered. Among them, the calculation of the total time resolution data and the total frequency resolution data is not only based on the time window length characteristics of the EEG signal segments, but also deeply considers the signal change information corresponding to each of the multiple EEG signal segments. This design is intended to ensure that when performing time-frequency analysis on EEG signals, higher time resolution and frequency resolution can be obtained at the same time, so as to more accurately capture the time-frequency characteristics in the signal, provide a more reliable basis for subsequent signal analysis and processing, and improve the accuracy of monitoring the depth of anesthesia based on EEG signals.

[0026] It should be noted that the genetic algorithm is a search heuristic algorithm that simulates natural selection and genetics and is used to solve optimization and search problems. In the genetic algorithm, each potential solution is represented as a "chromosome", and the fitness function can be used to evaluate the fitness of each chromosome, that is, the quality of the solution. The genetic algorithm is a conventional algorithm and will not be described in detail here.

[0027] It should be noted that time-frequency analysis is a signal processing technique used to simultaneously analyze the time domain and frequency domain characteristics of a signal. Traditional Fourier transform can convert a time domain signal into a frequency domain representation, but this method can only provide the overall frequency components of the signal, but cannot provide information about how these frequency components change over time. Time-frequency analysis makes up for this deficiency by showing how the frequency components of a signal change over time, thereby providing a more comprehensive description of the signal's characteristics. Time-frequency analysis is a conventional algorithm and will not be described in detail here.

[0028] In some embodiments of the present specification, the signal change information of the EEG signal segment includes the overall signal variance information of the segment; In the solution module, based on the signal change information corresponding to each of the multiple EEG signal segments and the time window length corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Based on the overall signal variance information of the segments corresponding to the multiple EEG signal segments and the time window lengths corresponding to the multiple EEG signal segments, the segment time resolution data and the segment frequency resolution data corresponding to the multiple EEG signal segments are obtained; Based on the fragment time resolution data corresponding to each of the multiple EEG signal fragments, the total time resolution data of the EEG signal under the segmentation scheme is obtained; Based on the segment frequency resolution data corresponding to each of the multiple EEG signal segments, the total frequency resolution data of the EEG signal under the segmentation scheme is obtained.

[0029] It can be understood that the total time resolution data of the EEG signal is related to the fragment time resolution data corresponding to each of the multiple EEG signal fragments, and the total frequency resolution data of the EEG signal is related to the fragment frequency resolution data corresponding to each of the multiple EEG signal fragments. The fragment time resolution data and the fragment frequency resolution data of the EEG signal fragment are both related to the time window length of the EEG signal fragment. And when other conditions are the same, the shorter the time window length of the EEG signal fragment, the higher the fragment time resolution of the EEG signal fragment, and the shorter the time window length of the EEG signal fragment, the lower the fragment frequency resolution of the EEG signal fragment.

[0030] In addition, it can be understood that the size of the signal variance will affect the results of time-frequency analysis. If the signal variance is large, that is, the signal fluctuates violently, then a higher time resolution may be required to capture these rapid changes (conversely, it can also be understood that a shorter time window length is required to achieve the expected time resolution). At the same time, in order to accurately identify different frequency components, a higher frequency resolution may also be required (conversely, it can also be understood that a longer time window length is required to achieve the expected frequency resolution). Therefore, when obtaining the fragment time resolution data and fragment frequency resolution data corresponding to each of the multiple EEG signal fragments, it is based not only on the time window length corresponding to each of the multiple EEG signal fragments, but also on the overall signal variance information of the fragments corresponding to each of the multiple EEG signal fragments.

[0031] In some embodiments of the present specification, the segmentation scheme obtained by the solution module also allows overlap between two adjacent EEG signal segments.

[0032] In some embodiments of the present specification, the segmentation scheme obtained by the solution module further allows different overlapping lengths between two adjacent EEG signal segments.

[0033] It is understandable that when performing time-frequency analysis, the overlap of time windows can make the signal transition smoothly, reduce edge effects, and improve signal coherence, thereby improving the quality and accuracy of subsequent time-frequency analysis. In addition, the overlap length between time windows is allowed to change flexibly and can be adaptively adjusted according to signal characteristics, which not only enhances the adaptability, flexibility and accuracy of time-frequency analysis, but also reduces redundant calculations, making it more efficient to capture the non-stationarity and local changes of the signal.

[0034] It can be understood that since overlap is allowed between two adjacent EEG signal segments and the overlap lengths between two adjacent EEG signal segments are allowed to be different, the total amount of signal data under different segmentation schemes is different, and the larger the total amount of signal data, the higher the complexity of time-frequency analysis will be.

[0035] It is also understandable that the signal coherence of each EEG signal segment under different segmentation schemes itself has certain differences, and on the basis of allowing overlap between each adjacent EEG signal segment and allowing different overlap lengths between each adjacent EEG signal segment, the difference in signal coherence of each EEG signal segment will be greater. Therefore, in some embodiments of the present specification, in the solution module, when solving the segmentation scheme used when performing time-frequency analysis of EEG signals based on genetic algorithms, the fitness function used also considers the total amount of signal data and total signal coherence data of EEG signals of a preset time length under the segmentation scheme.

[0036] In some embodiments of the present specification, in the solution module, the total amount of signal data of the EEG signal under the segmentation scheme is obtained, including: Obtaining the time window lengths corresponding to each of the multiple EEG signal segments; Based on the time window lengths corresponding to the multiple EEG signal segments, the total amount of signal data of the EEG signal under the segmentation scheme is obtained.

[0037] That is, the total amount of signal data is reflected by the sum of the time window lengths of multiple EEG signal segments.

[0038] In some embodiments of the present specification, in the solution module, the acquisition of total signal coherence data of the EEG signal under the segmentation scheme includes: Based on the signal change information corresponding to each of the multiple EEG signal segments, the time window length corresponding to each of the multiple EEG signal segments, and the overlapping information corresponding to each of the multiple EEG signal segments, obtaining segment signal coherence data corresponding to each of the multiple EEG signal segments; Based on the segment signal coherence data corresponding to each of the multiple EEG signal segments, the total signal coherence data of the EEG signal under the segmentation scheme is obtained.

[0039] It can be understood that by comprehensively considering the signal change information, time window length and overlap of each EEG signal segment, the signal coherence data of each segment is accurately obtained, and then the total signal coherence data of the EEG signal under the segmentation scheme is obtained.

[0040] It is understandable that a segment of an EEG signal has two ends, so its signal coherence should also be considered at both ends. Therefore, in order to consider the signal coherence in more detail, in some embodiments of this specification, the signal change information of the EEG signal segment includes the signal variance information of the starting part of the segment and the signal variance information of the ending part of the segment; The overlapping information of the EEG signal segment includes the overlapping length information of the starting part of the segment and the overlapping length information of the ending part of the segment.

[0041] In some embodiments of the present specification, the overlapping length of the beginning part of the segment and the overlapping length of the end part of the segment are both less than half of the overall length of the EEG signal segment.

[0042] In some embodiments of the present specification, in the solution module, obtaining the segment signal coherence data for each EEG signal segment includes: The EEG signal segment for which segment signal coherence data is currently acquired is regarded as a target EEG signal segment; Case 1: When only the beginning of the target EEG signal segment overlaps: Based on the signal variance information of the starting part of the target EEG signal segment and the signal variance information of the ending part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; It can be understood that for the coherence of the target EEG signal segment, first of all, it is necessary to consider the change fluctuation of the target EEG signal segment. If the change fluctuation of the target EEG signal segment itself is small, the coherence of the target EEG signal segment is stronger; secondly, it is necessary to consider the overlap of the target EEG signal segment. The longer the overlapping part of the target EEG signal segment, the smoother the signal transition, the reduced edge effect, and the improved signal coherence; thirdly, it is also necessary to consider the time window length of the EEG signal segment that overlaps with the target EEG signal segment. As for why it is necessary to consider the time window length of the EEG signal segment that overlaps with the target EEG signal segment, the following example is used to illustrate: Assumption 1: Assume that the length of the target EEG signal segment is 10s, the time window length of the overlapping EEG signal segment that overlaps with the target EEG signal segment is 5s, and the overlapping part of the target EEG signal segment is 3s; Assumption 2: Assume that the length of the target EEG signal segment is 10s, the time window length of the overlapping EEG signal segment that overlaps with the target EEG signal segment is 6s, and the overlapping part of the target EEG signal segment is 3s; In the case of hypothesis 2, although the length of the overlapping part of the target EEG signal segment is the same as that of hypothesis 1, the time window length of the overlapping EEG signal segment is longer. This means that in hypothesis 2, the overlapping EEG signal segment contains more information related to the overlapping part of the target EEG signal segment. Therefore, in order to more accurately analyze the coherence of the target EEG signal segment, it is also necessary to consider the time window length of the overlapping EEG signal segment that has an overlapping relationship with the target EEG signal segment.

[0043] Therefore, in the following case, the specific steps of obtaining the segment signal coherence data of the target EEG signal segment may include: Based on the signal variance information of the starting part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment, the signal coherence data of the starting part of the target EEG signal segment is obtained; Based on the signal variance information of the end part of the target EEG signal segment, the signal coherence data of the end part of the target EEG signal segment is obtained (Note: because there is no overlap at the end, only the signal variance information of the end part of the segment is considered); Based on the signal continuity data of the initial part and the signal continuity data of the terminal part of the target EEG signal segment, the segment signal continuity data of the target EEG signal segment is obtained.

[0044] Case 2: When only the end part of the target EEG signal segment overlaps: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the ending part of the segment, and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; For the second case, the specific steps for obtaining the segment signal coherence data of the target EEG signal segment are similar to those for the first case, and may include: Based on the signal variance information of the initial part of the target EEG signal segment, obtaining the signal coherence data of the initial part of the target EEG signal segment; Based on the signal variance information of the end portion of the segment, the overlapping length of the end portion of the segment, and the time window length of the EEG signal segment overlapping with the end portion of the target EEG signal segment, obtaining the signal coherence data of the end portion of the target EEG signal segment; Based on the signal continuity data of the initial part and the signal continuity data of the terminal part of the target EEG signal segment, the segment signal continuity data of the target EEG signal segment is obtained.

[0045] Case 3: When the beginning and end of the target EEG signal segment overlap at the same time: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the starting part and the overlapping length of the ending part of the segment, the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; It can be understood that when the starting part and the ending part overlap at the same time, the signal coherence of the starting part of the target EEG signal segment is related to the signal variance information of the starting part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment; the signal coherence of the ending part of the target EEG signal segment is related to the signal variance information of the ending part of the segment, the overlapping length of the ending part of the segment, and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment. Therefore, the specific steps for obtaining the segment signal coherence data of the target EEG signal segment may include: Based on the signal variance information of the starting part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment, the signal coherence data of the starting part of the target EEG signal segment is obtained; Based on the signal variance information of the end portion of the segment, the overlapping length of the end portion of the segment, and the time window length of the EEG signal segment overlapping with the end portion of the target EEG signal segment, obtaining the signal coherence data of the end portion of the target EEG signal segment; Based on the signal continuity data of the initial part and the signal continuity data of the terminal part of the target EEG signal segment, the segment signal continuity data of the target EEG signal segment is obtained.

[0046] Case 4: When the beginning and end of the target EEG signal segment do not overlap: Based on the signal variance information of the beginning part of the target EEG signal segment and the signal variance information of the end part of the segment, obtaining the segment signal coherence data of the target EEG signal segment; It can be understood that when there is no overlap, the signal coherence is only related to the signal variance information. Therefore, obtaining the segment signal coherence data of the target EEG signal segment may specifically include: Based on the signal variance information of the initial part of the target EEG signal segment, obtaining the signal coherence data of the initial part of the target EEG signal segment; Based on the signal variance information of the terminal part of the target EEG signal segment, obtaining the signal coherence data of the terminal part of the target EEG signal segment; Based on the signal continuity data of the initial part and the signal continuity data of the terminal part of the target EEG signal segment, the segment signal continuity data of the target EEG signal segment is obtained.

[0047] It should be noted that: The above fitness function can be but is not limited to: ; Among them, F represents the fitness function, T 总 represents the total time resolution data, P 总 Represents the total frequency resolution data, Indicates the inverse of the total amount of signal data, L 总 Indicates the total signal coherence data, A, B, C, and D are the weight coefficients corresponding to the total time resolution data, total frequency resolution data, total signal data, and total signal coherence data, respectively. Among them, the total time resolution data consideration item, the total frequency resolution data consideration item, the total signal data consideration item, and the total signal coherence data consideration item can be deleted according to actual needs. If all are considered, they are all retained. And when using this calculation formula, the larger the value of F, the better the solution.

[0048] The above total time resolution data may be, but is not limited to: ; ; Among them, t n Represents the time resolution data of the nth EEG signal segment, It represents the inverse of the length of the time window corresponding to the nth EEG signal segment, and E represents the weight coefficient for calculating the segment time resolution data corresponding to the EEG signal segment.

[0049] The above total frequency resolution data may be, but is not limited to: ; ; Among them, P n represents the frequency resolution data of the nth EEG signal segment, S n represents the time window length corresponding to the nth EEG signal segment, and H represents the weight coefficient for calculating the segment frequency resolution data corresponding to the EEG signal segment.

[0050] The total amount of the above signal data may be, but is not limited to: .

[0051] For the segment signal coherence data, when there is no overlap, the segment signal coherence data is only related to the signal variance information, which may be but is not limited to: ; ; Among them, l n Represents the segment signal coherence data corresponding to the nth segment of the EEG signal, Represents the inverse of the signal variance information of the beginning part of the nth EEG signal segment, It represents the inverse of the signal variance information of the end part of the nth EEG signal segment, and G represents the weight coefficient for calculating the segment signal coherence data corresponding to the EEG signal segment.

[0052] For fragment signal continuity data, when both the beginning and the end overlap: ; Among them, J n起 S represents the overlapping length of the starting part of the nth EEG signal segment. n-1 represents the time window length of the EEG signal segment that overlaps with the starting part of the nth EEG signal segment, J n末 S represents the overlapping length of the end of the nth EEG signal segment. n+1 Indicates the time window length of the EEG signal segment that overlaps with the end portion of the nth EEG signal segment.

[0053] For segment signal continuity data, when only the initial part overlaps: ; For fragment signal continuity data, when only the ends overlap: ; Furthermore, there is no limitation on the specific calculation formulas corresponding to the fitness function, segment time resolution data, segment frequency resolution data, total time resolution data, total frequency resolution data, total signal data, segment signal continuity data, total signal continuity data, etc. involved in the above schemes, and they only need to satisfy the above-mentioned corresponding acquisition principles.

[0054] See next Figure 2 , Figure 2 A flowchart of a method for monitoring depth of anesthesia based on EEG signals provided in an embodiment of this specification is shown, which may at least include: Step 202: obtaining an EEG signal of a preset time length; Step 204, solving the segmentation scheme used in time-frequency analysis of the EEG signal based on the genetic algorithm; Step 206: Segment the EEG signal of a preset time length based on the segmentation scheme to obtain a plurality of EEG signal segments; Step 208: Perform Fourier transform on the multiple EEG signal segments respectively to obtain frequency domain representation information corresponding to each of the multiple EEG signal segments; Step 210: performing time-frequency analysis based on the frequency domain representation information and time period information corresponding to each of the multiple EEG signal segments to obtain anesthesia depth information; In step 204, the segmentation scheme obtained by solving allows segmentation of different lengths of time windows at different locations of the EEG signal; In step 204, when solving the segmentation scheme used in performing time-frequency analysis on the EEG signal based on the genetic algorithm, the fitness function used simultaneously considers the total time resolution data and total frequency resolution data of the EEG signal of the preset time length under the segmentation scheme; The total time resolution data and total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Acquire multiple EEG signal segments under the segmentation scheme, and acquire signal change information corresponding to each of the multiple EEG signal segments; Based on the signal change information corresponding to each of the multiple EEG signal segments and the time window lengths corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained.

[0055] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the anesthesia depth monitoring method embodiment, since it is basically similar to the anesthesia depth monitoring system embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the anesthesia depth monitoring system embodiment.

[0056] See also Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0057] like Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 303 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0058] The communication bus 302 may be used to realize the connection and communication among the above-mentioned components.

[0059] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0060] The network interface 303 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0061] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts within the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of DSP, FPGA, and PLC. The processor 301 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0062] Among them, the memory 305 may include RAM or ROM. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be at least one storage device located away from the aforementioned processor 301. The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an anesthesia depth monitoring application. The processor 301 can be used to call the anesthesia depth monitoring program stored in the memory 305 and execute the steps of the anesthesia depth monitoring method mentioned in the aforementioned embodiment.

[0063] The embodiments of this specification also provide a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in the above-mentioned anesthesia depth monitoring method embodiment. If the component modules of the above-mentioned electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0064] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0065] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0066] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. An anesthesia depth monitoring system based on EEG signals, characterized in that: include: A first acquisition module acquires an EEG signal of a preset time length; The solution module solves the segmentation scheme used in the time-frequency analysis of EEG signals based on the genetic algorithm; A segmentation module, which processes the EEG signal of a preset time length in segments based on a segmentation scheme to obtain multiple EEG signal segments; A Fourier transform module performs Fourier transform on the multiple EEG signal segments respectively to obtain frequency domain representation information corresponding to each of the multiple EEG signal segments; The second acquisition module performs time-frequency analysis based on the frequency domain representation information and time period information corresponding to each of the multiple EEG signal segments to obtain anesthesia depth information; The segmentation scheme obtained in the solution module allows segmentation of different length time windows at different positions of the EEG signal; When solving the segmentation scheme used in the time-frequency analysis of the EEG signal based on the genetic algorithm in the solution module, the fitness function used simultaneously considers the total time resolution data and the total frequency resolution data of the EEG signal of the preset time length under the segmentation scheme; In the solution module, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Acquire multiple EEG signal segments under the segmentation scheme, and acquire signal change information corresponding to each of the multiple EEG signal segments; Based on the signal change information corresponding to each of the multiple EEG signal segments and the time window lengths corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained.

2. The anesthesia depth monitoring system based on EEG signals according to claim 1, characterized in that: The signal change information of the EEG signal segment includes the overall signal variance information of the segment; In the solution module, based on the signal change information corresponding to each of the multiple EEG signal segments and the time window length corresponding to each of the multiple EEG signal segments, the total time resolution data and the total frequency resolution data of the EEG signal under the segmentation scheme are obtained, including: Based on the overall signal variance information of the segments corresponding to the multiple EEG signal segments and the time window lengths corresponding to the multiple EEG signal segments, the segment time resolution data and the segment frequency resolution data corresponding to the multiple EEG signal segments are obtained; Based on the fragment time resolution data corresponding to each of the multiple EEG signal fragments, the total time resolution data of the EEG signal under the segmentation scheme is obtained; Based on the segment frequency resolution data corresponding to each of the multiple EEG signal segments, the total frequency resolution data of the EEG signal under the segmentation scheme is obtained.

3. The anesthesia depth monitoring system based on EEG signals according to claim 1, characterized in that: The segmentation scheme obtained by the solution module also allows overlap between two adjacent EEG signal segments.

4. The anesthesia depth monitoring system based on EEG signals according to claim 3, characterized in that: The segmentation scheme obtained by the solution module also allows different overlapping lengths between two adjacent EEG signal segments.

5. The anesthesia depth monitoring system based on EEG signals according to claim 4, characterized in that: In the solution module, when solving the segmentation scheme used in time-frequency analysis of EEG signals based on a genetic algorithm, the fitness function used also considers the total amount of signal data and total signal coherence data of the EEG signals of a preset time length under the segmentation scheme.

6. The anesthesia depth monitoring system based on EEG signals according to claim 5, characterized in that: In the solution module, the total amount of signal data of the EEG signal under the segmentation scheme is obtained, including: Obtaining the time window lengths corresponding to each of the multiple EEG signal segments; Based on the time window lengths corresponding to the multiple EEG signal segments, the total amount of signal data of the EEG signal under the segmentation scheme is obtained.

7. The anesthesia depth monitoring system based on EEG signals according to claim 5, characterized in that: In the solution module, the total signal coherence data of the EEG signal under the segmentation scheme is obtained, including: Based on the signal change information corresponding to each of the multiple EEG signal segments, the time window length corresponding to each of the multiple EEG signal segments, and the overlapping information corresponding to each of the multiple EEG signal segments, obtaining segment signal coherence data corresponding to each of the multiple EEG signal segments; Based on the segment signal coherence data corresponding to each of the multiple EEG signal segments, the total signal coherence data of the EEG signal under the segmentation scheme is obtained.

8. The anesthesia depth monitoring system based on EEG signals according to claim 7, characterized in that: The signal change information of the EEG signal segment includes the signal variance information of the beginning part of the segment and the signal variance information of the end part of the segment; The overlapping information of the EEG signal segment includes the overlapping length information of the starting part of the segment and the overlapping length information of the ending part of the segment.

9. The anesthesia depth monitoring system based on EEG signals according to claim 8, characterized in that: The overlapping lengths at the beginning and end of the segments are both less than half of the overall length of the EEG signal segment.

10. The anesthesia depth monitoring system based on EEG signals according to claim 8, characterized in that: In the solution module, the acquisition of segment signal coherence data for each EEG signal segment includes: The EEG signal segment for which segment signal coherence data is currently acquired is regarded as a target EEG signal segment; When only the beginning of the target EEG signal segment overlaps: Based on the signal variance information of the starting part of the target EEG signal segment and the signal variance information of the ending part of the segment, the overlapping length of the starting part of the segment, and the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When only the end portion of the target EEG signal segment overlaps: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the ending part of the segment, and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When the beginning and end of the target EEG signal segment overlap at the same time: Based on the signal variance information of the starting part and the signal variance information of the ending part of the target EEG signal segment, the overlapping length of the starting part and the overlapping length of the ending part of the segment, the time window length of the EEG signal segment overlapping with the starting part of the target EEG signal segment and the time window length of the EEG signal segment overlapping with the ending part of the target EEG signal segment, the segment signal coherence data of the target EEG signal segment is obtained; When the beginning and end of the target EEG signal segment do not overlap: Based on the signal variance information of the beginning part of the target EEG signal segment and the signal variance information of the end part of the segment, the segment signal coherence data of the target EEG signal segment is obtained.

Images