Cognitive ability prediction method and system, electronic equipment and readable storage medium

Abstract

The invention discloses a cognitive ability prediction method and system, electronic equipment and a readable storage medium. The method comprises the following steps: extracting frequency domain features of electroencephalogram signals; extracting functional connection characteristics of the electroencephalogram signals; constructing a neurocognitive double-effect hypothesis equation based on the frequency domain features and the functional connection features; calculating a cognitive ability value according to a neurocognitive double-effect hypothesis equation; and performing cognitive ability prediction based on the cognitive ability value to obtain a cognitive ability prediction result. According to the method, the overall neural calculation efficiency can be quantified by integrating neural energy consumption, network connection lines and task difficulty, and the accuracy of cognitive ability prediction can be improved.

Description

Technical Field

[0001] This application relates to the field of cognitive neuroscience technology, and in particular to a cognitive ability prediction method, system, electronic device, and readable storage medium. Background Technology

[0002] Cognitive abilities encompass fluid intelligence (the ability to solve new problems), crystallized intelligence (accumulated knowledge), working memory capacity, processing speed, and attentional control. Cognitive abilities represent observable manifestations of human brain function at the behavioral level. Higher cognitive abilities translate into better task performance at the behavioral level and are associated with more efficient neural processing mechanisms at the neural level. Unveiling the neural basis behind differences in cognitive performance is crucial for understanding the core nature of intelligence, individual variability, cognitive development, healthy aging, and the mechanisms of neurological diseases. Research in this field not only promises to advance our fundamental understanding of the principles governing brain organization but will also provide key insights for optimizing educational strategies, guiding neuroergonomic design, enhancing clinical neuropsychological assessments, and advancing brain-inspired artificial intelligence.

[0003] Despite significant advancements in current technologies, fundamental limitations remain in our systematic understanding of the relationship between neural activity and behavior. A major limitation is the lack of integrative models. Current research often isolates different aspects: neural efficiency (e.g., reduced local power), network dynamics (e.g., connectivity strength), or task difficulty effects. Crucially, there is a lack of a theoretical framework and empirical model that clearly integrates these three core components. Key unresolved questions include: how the expression of local efficiency (low power) interacts with the need for functional network integration (high connectivity); how task difficulty non-linearly modulates the relationship between specific neural traits (power and connectivity) and behavioral performance; and whether there are trade-offs or synergies between reducing local metabolic expenditure and the potential energy costs of maintaining precise synchronization. Summary of the Invention

[0004] This application aims to propose a cognitive ability prediction method, system, electronic device, and readable storage medium that can quantify overall neural computation efficiency by integrating neural energy consumption (i.e., local efficiency), network connectivity, and task difficulty, and can also improve the accuracy of cognitive ability prediction.

[0005] In a first aspect, embodiments of this application provide a cognitive ability prediction method, the method comprising: Extracting frequency domain features from EEG signals; Extract the functional connectivity features of the electroencephalogram (EEG) signals; Based on the frequency domain features and the functional connectivity features, a neurocognitive dual-effect hypothesis equation is constructed. Calculate cognitive ability values ​​based on the aforementioned neurocognitive dual-effect hypothesis equation; Based on the cognitive ability value, cognitive ability is predicted to obtain the cognitive ability prediction result.

[0006] Compared with the prior art, the first aspect of this application has the following beneficial effects: This method extracts frequency domain features from EEG signals and functional connectivity features from EEG signals. Based on these frequency domain and functional connectivity features, it constructs a neurocognitive dual-effect hypothesis equation. Cognitive ability values ​​are calculated using this hypothesis equation, and cognitive ability predictions are made based on these values. Thus, by constructing a neurocognitive dual-effect hypothesis equation based on frequency domain and functional connectivity features, and using this equation to calculate cognitive ability values, the overall neural computational efficiency can be quantified by integrating neural energy consumption (i.e., local efficiency), network connectivity, and task difficulty. This also improves the accuracy of cognitive ability predictions.

[0007] In some implementations, the extraction of frequency domain features of the EEG signal includes: The EEG signal is preprocessed to obtain the preprocessed EEG signal; Fourier transform was used to convert the preprocessed EEG signals into frequency domain signals; Based on the frequency domain signal, the power spectral density of different frequency bands is calculated, and the power spectral density is used as a frequency domain feature.

[0008] In some implementations, calculating the power spectral density of different frequency bands based on the frequency domain signal includes: ; in, This represents the power spectral density at different frequency bands. Indicates the sampling period. Indicates the number of samples within a time period. Represents frequency domain signals, Indicates the sampling frequency.

[0009] In some implementations, extracting the functional connectivity features of the EEG signal includes: The EEG signal was bandpass filtered to obtain the filtered EEG signal. The instantaneous phase of the filtered EEG signal is extracted using Hilbert transform; Calculate the phase difference between the electrode pairs based on the instantaneous phase; Based on the phase difference, a corrected imaginary part phase-locked value equation is constructed; The corrected imaginary phase-locked value is calculated using the corrected imaginary phase-locked value equation, and the corrected imaginary phase-locked value is used as a functional connection feature.

[0010] In some implementations, constructing the corrected imaginary part phase-locked value equation based on the phase difference includes: ; in, This represents the value of the corrected imaginary part of the phase-locked loop. Indicates the imaginary part. Indicates a time period. The prefix indicating imaginary numbers, Indicates phase difference, Indicates the real part.

[0011] In some implementations, constructing the neurocognitive dual-effect hypothesis equation based on the frequency domain features and the functional connectivity features includes: ; in, Indicates cognitive ability value, Indicates the number of brain regions. Indicates the number of frequency bands. This indicates the integration weight between brain regions and frequency bands. Indicates the precision modulation coefficient. Indicates brain regions and frequency band Phase synchronization accuracy, Indicates the energy weighting coefficient. Indicates brain regions and frequency band Metabolic energy consumption, This represents the task complexity index. This represents the critical phase transition threshold. This indicates the scaling factor for the transition zone.

[0012] In some implementations, the step of predicting cognitive ability based on the cognitive ability value to obtain a cognitive ability prediction result includes: Preset a first threshold and a second threshold; If the cognitive ability value is greater than the first threshold, then the cognitive ability prediction result is high cognitive performance; If the cognitive ability value is greater than or equal to the second threshold and less than or equal to the first threshold, then the cognitive ability prediction result is moderate cognitive performance. If the cognitive ability value is less than the second threshold, the cognitive ability prediction result is low cognitive performance.

[0013] Secondly, embodiments of this application also provide a cognitive ability prediction system, the system comprising: The first feature extraction unit is used to extract the frequency domain features of the EEG signal; The second feature extraction unit is used to extract the functional connectivity features of the electroencephalogram (EEG) signal. The hypothesis equation construction unit is used to construct a neurocognitive dual-effect hypothesis equation based on the frequency domain features and the functional connectivity features. A cognitive ability value calculation unit is used to calculate a cognitive ability value based on the neurocognitive dual-effect hypothesis equation. A cognitive ability prediction unit is used to predict cognitive ability based on the cognitive ability value and obtain a cognitive ability prediction result.

[0014] Thirdly, embodiments of this application also provide an electronic device, including at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, the instructions being executed by the at least one control processor to enable the at least one control processor to perform a cognitive ability prediction method as described above.

[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a cognitive ability prediction method as described above.

[0016] It is understood that the beneficial effects of the second to fourth aspects compared with the related technologies are the same as the beneficial effects of the first aspect compared with the related technologies. Please refer to the relevant description in the first aspect above, which will not be repeated here. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart illustrating an embodiment of the cognitive ability prediction method provided in this application; Figure 2 This is a schematic diagram of the neurocognitive dual-effect hypothesis model architecture in the best embodiment of the cognitive ability prediction method provided in this application; Figure 3 This is a schematic diagram of the structure of an embodiment of the cognitive ability prediction system provided in this application; Figure 4 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application. Detailed Implementation

[0018] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0019] In the description of this application, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0020] In the description of this application, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0021] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] Despite significant advancements in current technologies, fundamental limitations remain in our systematic understanding of the relationship between neural activity and behavior. A major limitation is the lack of an integrated model. Current research often isolates different aspects: neural efficiency (e.g., reduced local power), network dynamics (e.g., connectivity strength), or task difficulty effects. Crucially, there is a lack of a theoretical framework and empirical model that clearly integrates these three core components. Key unresolved questions include: how the expression of local efficiency (low power) interacts with the need for network integration (high connectivity); how task difficulty non-linearly modulates the relationship between specific neural traits (power, connectivity) and behavioral performance; and whether there are trade-offs or synergies between reducing local metabolic expenditure and the potential energy costs of maintaining precise synchronization.

[0023] To address the key unresolved issues in existing technologies, this application proposes a cognitive ability prediction method, system, electronic device, and readable storage medium.

[0024] Reference Figure 1 This application provides a schematic flowchart of a cognitive ability prediction method. This method is applied to an electronic device, which may be a server or a mobile terminal, etc. Figure 1 As shown, this cognitive ability prediction method may include the following steps: Step S101: Extract the frequency domain features of the EEG signal; Step S102: Extract the functional connectivity features of the EEG signal; Step S103: Based on frequency domain features and functional connectivity features, construct the neurocognitive dual-effect hypothesis equation; Step S104: Calculate the cognitive ability value based on the neurocognitive dual-effect hypothesis equation; Step S105: Based on the cognitive ability value, perform cognitive ability prediction to obtain the cognitive ability prediction result.

[0025] In this embodiment, frequency domain features of EEG signals are extracted; functional connectivity features of EEG signals are extracted; a neurocognitive dual-effect hypothesis equation is constructed based on the frequency domain features and functional connectivity features; cognitive ability values ​​are calculated based on the neurocognitive dual-effect hypothesis equation; and cognitive ability prediction is performed based on the cognitive ability values ​​to obtain the cognitive ability prediction results. Thus, by constructing a neurocognitive dual-effect hypothesis equation based on frequency domain features and functional connectivity features, and by calculating cognitive ability values ​​using this equation, the overall neural computation efficiency can be quantified by integrating neural energy consumption (i.e., local efficiency), network connectivity, and task difficulty, thereby improving the accuracy of cognitive ability prediction.

[0026] The above-mentioned extraction of frequency domain features of EEG signals can be achieved by converting the preprocessed EEG signals into frequency domain signals through Fourier transform, then analyzing the signals in different frequency domains to obtain the corresponding frequency domain information, obtaining the power spectral density of different frequency bands based on the frequency domain information, and using the power spectral density as the frequency domain feature.

[0027] The functional connectivity features extracted from the above-mentioned EEG signals can be quantified using the Corrected Imaginary Phase-Locking Value (ciPLV) to obtain the functional connectivity features.

[0028] In some implementations, frequency domain features of the EEG signal are extracted, including: The EEG signal is preprocessed to obtain the preprocessed EEG signal; Fourier transform was used to convert the preprocessed EEG signals into frequency domain signals; Based on the frequency domain signal, the power spectral density of different frequency bands is calculated, and the power spectral density is used as a frequency domain feature.

[0029] In this embodiment, by calculating the power spectral density of different frequency bands and using the power spectral density as a frequency domain feature, it is possible to simulate local neural energy consumption (quantified by the power spectral density change of task modulation), laying a good data foundation for constructing the neurocognitive dual-effect hypothesis equation.

[0030] In some implementations, power spectral density is calculated for different frequency bands based on the frequency domain signal, including: ; in, This represents the power spectral density at different frequency bands. Indicates the sampling period. Indicates the number of samples within a time period. Represents frequency domain signals, Indicates the sampling frequency.

[0031] In some implementations, the functional connectivity features of the EEG signals are extracted, including: Bandpass filtering is performed on the EEG signal to obtain the filtered EEG signal; The Hilbert transform was used to extract the instantaneous phase from the filtered EEG signal; Calculate the phase difference between the electrode pairs based on the instantaneous phase; Based on the phase difference, a corrected imaginary part phase-locked value equation is constructed; The corrected imaginary phase-locked value is calculated using the corrected imaginary phase-locked value equation, and then used as a functional connection feature.

[0032] In this embodiment, the corrected imaginary phase-locked value is calculated through the corrected imaginary phase-locked value equation. The corrected imaginary phase-locked value is used as a functional connectivity feature, which enables functional network integration (quantified by task-related phase-locked values), laying a good data foundation for constructing the neurocognitive dual-effect hypothesis equation.

[0033] In some implementations, a corrected imaginary part phase-locked value equation is constructed based on the phase difference, including: ; in, This represents the value of the corrected imaginary part of the phase-locked loop. Indicates the imaginary part. Indicates a time period. The prefix indicating imaginary numbers, Indicates phase difference, Indicates the real part.

[0034] In some implementations, a neurocognitive dual-effect hypothesis equation is constructed based on frequency domain features and functional connectivity features, including: ; in, Indicates cognitive ability value, Indicates the number of brain regions. Indicates the number of frequency bands. This indicates the integration weight between brain regions and frequency bands. Indicates the precision modulation coefficient. Indicates brain regions and frequency band Phase synchronization accuracy, Indicates the energy weighting coefficient. Indicates brain regions and frequency band Metabolic energy consumption, This represents the task complexity index. This represents the critical phase transition threshold. This indicates the scaling factor for the transition zone.

[0035] In this embodiment, a unified mathematical formula (i.e., the neurocognitive dual-effect hypothesis equation) is constructed and verified. This neurocognitive dual-effect hypothesis equation quantifies the overall neural computation efficiency by integrating neural energy consumption, network connectivity, and task difficulty.

[0036] The above brain regions and frequency band The phase synchronization accuracy can be achieved by mapping the corrected imaginary part phase-locked value to the corresponding channel according to the preset electrode positioning, thus obtaining the accuracy of each channel. In frequency band The original synchronization strength value is then converted to the range [0,1] through min-max normalization. value.

[0037] The above brain regions and frequency band Metabolic energy consumption can be calculated by measuring the activity of each electrode in a specific frequency band. The power spectral density value was obtained, and then compared with the resting baseline power to obtain the relative power change. Finally, normalization was performed to obtain... parameter.

[0038] In some implementations, cognitive ability prediction is performed based on cognitive ability values ​​to obtain cognitive ability prediction results, including: Preset a first threshold and a second threshold; If the cognitive ability score is greater than the first threshold, the cognitive ability prediction result is high cognitive performance; If the cognitive ability value is greater than or equal to the second threshold and less than or equal to the first threshold, the cognitive ability prediction result is moderate cognitive performance. If the cognitive ability score is less than the second threshold, the cognitive ability prediction result is low cognitive performance.

[0039] In this embodiment, cognitive ability is predicted by calculating an accurate cognitive ability value, i.e., the cognitive ability value. As a comprehensive neurocognitive efficiency index, its value directly reflects an individual's cognitive performance level. It can not only improve the efficiency of cognitive ability value calculation, but also obtain accurate cognitive ability prediction results.

[0040] The aforementioned preset first threshold and second threshold can be set according to actual conditions, and this embodiment does not impose specific limitations.

[0041] To facilitate understanding by those skilled in the art, a set of preferred embodiments is provided below: Cognitive abilities encompass fluid intelligence (the ability to solve new problems), crystallized intelligence (accumulated knowledge), working memory capacity, processing speed, and attentional control. Cognitive abilities represent observable manifestations of human brain function at the behavioral level. Higher cognitive abilities translate into better task performance at the behavioral level and are associated with more efficient neural processing mechanisms at the neural level. Unveiling the neural basis behind differences in cognitive performance is crucial for understanding the core nature of intelligence, individual variability, cognitive development, healthy aging, and the mechanisms of neurological diseases. Research in this field not only promises to advance our fundamental understanding of the principles governing brain organization but will also provide key insights for optimizing educational strategies, guiding neuroergonomic design, enhancing clinical neuropsychological assessments, and advancing brain-inspired artificial intelligence.

[0042] Despite significant advancements in current technologies, fundamental limitations remain in our systematic understanding of the relationship between neural activity and behavior. A major limitation is the lack of integrative models. Current research often isolates different aspects: neural efficiency (e.g., reduced local power), network dynamics (e.g., connectivity strength), or task difficulty effects. Crucially, there is a lack of a theoretical framework and empirical model that clearly integrates these three core components. Key unresolved questions include: how the expression of local efficiency (low power) interacts with the need for functional network integration (high connectivity); how task difficulty non-linearly modulates the relationship between specific neural traits (power and connectivity) and behavioral performance; and whether there are trade-offs or synergies between reducing local metabolic expenditure and the potential energy costs of maintaining precise synchronization.

[0043] To fill these gaps, this embodiment proposes a unified neural computation framework, namely the neurocognitive dual-effect hypothesis. Its core objectives are: (1) to simultaneously simulate the interaction between local neural energy consumption (quantified by changes in power spectral density modulated by the task) and functional network integration (quantified by task-related phase-locked values) across multiple cognitively relevant frequency bands (θ, α, β, γ); (2) to develop and incorporate a quantified, nonlinear task difficulty model to elucidate its modulating effect on neural and cognitive relationships; and (3) to construct and validate a unified mathematical formula that quantifies overall neural computation efficiency by integrating neural energy consumption, network connectivity, and task difficulty.

[0044] The technical solution adopted in this embodiment to solve its technical problem is to construct a neural and cognitive dual-effect hypothesis for cognitive ability prediction. By integrating a computational framework of local neural efficiency, global network integration, and nonlinear difficulty modulation, this embodiment proposes that high performance stems from a balance between metabolically efficient processing (reflected in reduced spectral power) and precise information connectivity (increased measurement through phase synchronization). The model of this embodiment introduces a nonlinear modulator that can capture key shifts in the relationship between the brain and behavior as task difficulty increases, indicating that neural efficiency involves context-sensitive resource allocation rather than simple energy reduction. This hypothesis reconciles major neurocognitive theories and provides a unified neural computational foundation for assessing cognitive abilities and designing personalized interventions. The method mainly includes the following steps: 1) Conduct cognitive experiments based on multi-target tracking, logical reasoning, and map memory, set experimental parameters to continuously change the difficulty of the task, and collect the EEG signals of the subjects.

[0045] 2) Preprocess the EEG data to extract the frequency domain (power spectral density) and functional connectivity features (corrected imaginary phase-locked value) of the EEG signals of different subjects.

[0046] 3) The Neurocognitive Dual-Effect Hypothesis (NCDEH) is proposed, which correlates discrete neural characteristics (energy consumption, connection strength) with continuous behavioral performance through mathematical formalization, thereby achieving a quantitative explanatory index for cognitive ability. This index can be further used to predict cognitive performance. Specifically: First, the participants' electroencephalogram (EEG) signals are collected. In this embodiment, the EEG signal acquisition device uses the Neuracle wireless EEG acquisition system, which is compatible with a 32-channel EEG cap. The acquisition system consists of an EEG amplifier, an EEG cap (including electrodes), a multi-parameter synchronizer, an intelligent synchronization system, and EEG acquisition and recording software. This device transmits data wirelessly, ensuring convenience during the acquisition process. The passband range is 0Hz to 200Hz, the sampling rate is 1000Hz, T7 and T8 are reference electrodes, Fz is the ground electrode, and the electrode impedance is less than 10kΩ.

[0047] The EEG signals were then preprocessed. Since EEG signals are weak and contain various noises (artifacts), the raw EEG data needed to be preprocessed before feature extraction to remove artifacts and interference as much as possible. EEG signal preprocessing used the EEGLAB toolbox in MATLAB. First, a bandpass filter from 0.1Hz to 40Hz was used to eliminate high-frequency noise. Then, a bandpass filter from 48Hz to 52Hz was used to eliminate power frequency interference. Finally, the Automatic Artifact Removal (AAR) toolbox was used to automatically remove electrooculography (EOG) artifacts. For feature extraction, frequency domain features and functional connectivity features of the EEG signals were extracted separately. First, the frequency domain features were calculated, converting the EEG signals into frequency domain signals and dividing them into four frequency bands: δ (1Hz to 3Hz), θ (4Hz to 7Hz), α (8Hz to 12Hz), and β (13Hz to 30Hz). Fourier transform was then used to convert the preprocessed EEG signals back into frequency domain signals. Specifically: ; in, It is the Fourier transform of the EEG signal (i.e., the frequency domain signal). It is a prefix for imaginary numbers. express Quantity, express EEG signals at any given time Indicates the number of samples taken within a time period.

[0048] Analyzing signals in different frequency domains yields corresponding frequency domain information, and based on this information, the power spectral density (PSD) for different frequency bands is obtained. Specifically: ; in, , and These represent the sampling period, the number of samples within a time period, and the sampling frequency, respectively. This represents the power spectral density of the corresponding frequency band.

[0049] Functional connectivity features of EEG signals were quantified using the Corrected Imaginary Phase-Locking Value (ciPLV), a method that mitigates volume conduction artifacts by ignoring zero-hysteresis correlation. For each frequency band, the EEG signals were bandpass filtered, and the instantaneous phase was extracted using Hilbert transform. For electrode pairs Calculate the phase difference . The definition is as follows: ; in, The duration is the length of the time period. and These represent the imaginary and real parts, respectively. Thus, 1984 ciPLV features (496 electrode pairs × 4 frequency bands) can be generated for each time period.

[0050] After feature extraction, the extracted power spectral density (PSD) and corrected imaginary phase-locked value (ciPLV) are substituted into the Neurocognitive Dual-Effect Hypothesis (NCDEH) formula: ; NCDEH integrates brain regions, frequency bands, and difficulty dimensions to obtain a representation of cognitive ability. The value (i.e. cognitive ability value) and the meaning of each parameter in the formula are shown in Table 1.

[0051] Table 1. Parameter Description of the Neurocognitive Dual-Effect Hypothesis (NCDEH)

[0052] The above Table 1 The parameters are derived from the ciPLV values ​​as follows: First, the ciPLV values ​​of the 496 electrode pairs are mapped to the corresponding channels according to the preset electrode positioning, thus obtaining the parameters for each channel. In frequency band The original synchronization strength value is then converted to the range [0,1] through min-max normalization. value.

[0053] The above Table 1 The parameters are derived from the power spectral density values ​​by first calculating the values ​​of each electrode in a specific frequency band. The power spectral density value was obtained, and then compared with the resting baseline power to obtain the relative power change. Finally, normalization was performed to obtain... parameter.

[0054] like Figure 2 As shown, the core hypotheses derived from NCDEH are: (1) High-performance characteristics: Individuals exhibiting superior performance will show significantly lower task-related power spectral density in task-related bands and regions (indicating reduced local metabolic costs in task-related regions), while showing significantly higher and more specific phase-locked values ​​in task-critical specific band networks (indicating enhanced functional network integration). (2) Nonlinear difficulty modulation: The relationship between neural efficiency (quantified by power spectral density) and behavioral performance shows a context-dependent pattern modulated by task difficulty, with a critical threshold effect under which the negative correlation between energy and performance is reversed.

[0055] The values ​​obtained from the NCDEH model serve as a comprehensive neurocognitive efficiency index, and their magnitude directly reflects an individual's cognitive performance level. Based on large-sample calibration studies, the following judgment criteria are recommended: (1) Total>0.67: indicates high cognitive performance, characterized by efficient local energy utilization and accurate functional network integration; (2) 0.33≤Stotal≤0.67: indicates moderate cognitive performance, and neural efficiency is in a transitional state; (3) Total < 0.33: indicates low cognitive performance, insufficient allocation of neural resources or network integration disorder.

[0056] In this embodiment, the first threshold is set to 0.67 and the second threshold is set to 0.33. It should be noted that the two thresholds in this embodiment can be optimized and adjusted through receiver operating characteristic (ROC) analysis according to specific application scenarios, and this embodiment does not impose specific limitations.

[0057] Reference Figure 3 This application also provides a cognitive ability prediction system, which includes a first feature extraction unit 301, a second feature extraction unit 302, a hypothesis equation construction unit 303, a cognitive ability value calculation unit 304, and a cognitive ability prediction unit 305, wherein: The first feature extraction unit 301 is used to extract the frequency domain features of the EEG signal; The second feature extraction unit 302 is used to extract the functional connectivity features of the electroencephalogram (EEG) signal. Hypothesis equation building unit 303 is used to construct a neurocognitive dual-effect hypothesis equation based on frequency domain features and functional connectivity features; The cognitive ability value calculation unit 304 is used to calculate the cognitive ability value based on the neurocognitive dual-effect hypothesis equation. The cognitive ability prediction unit 305 is used to predict cognitive ability based on cognitive ability value and obtain cognitive ability prediction result.

[0058] It should be noted that since the cognitive ability prediction system in this embodiment is based on the same inventive concept as the cognitive ability prediction method described above, the corresponding content in the method embodiment is also applicable to this system embodiment, and will not be described in detail here.

[0059] Reference Figure 4 This application also provides an electronic device, which includes: At least one memory; At least one processor; At least one program; The program is stored in memory, and the processor executes at least one program to implement the cognitive ability prediction method described above in this disclosure.

[0060] This electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), and in-vehicle computers.

[0061] The electronic devices according to embodiments of this application will now be described in detail.

[0062] The processor 1600 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure. The memory 1700 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1700 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1700 and is called and executed by the processor 1600 to execute the cognitive ability prediction method of the embodiments of this disclosure.

[0063] The input / output interface 1800 is used to implement information input and output. The communication interface 1900 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 2000 transmits information between various components of the device (e.g., processor 1600, memory 1700, input / output interface 1800, and communication interface 1900); The processor 1600, memory 1700, input / output interface 1800 and communication interface 1900 are connected to each other within the device via bus 2000.

[0064] This disclosure also provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the above-described cognitive ability prediction method.

[0065] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0066] The embodiments described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided by this disclosure. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by this disclosure are also applicable to similar technical problems.

[0067] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this disclosure, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0069] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0070] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0071] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. The embodiments of this application have been described in detail above with reference to the accompanying drawings, but this application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of this application.

[0076] The embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of this application.

Claims

1. A cognitive ability prediction method characterized by comprising: The method comprises: extracting frequency domain features of the electroencephalogram signal; extracting functional connection features of the electroencephalogram signal; constructing a neuro-cognitive double-effect hypothesis equation based on the frequency domain features and the functional connection features; calculating a cognitive ability value according to the neuro-cognitive double-effect hypothesis equation; performing cognitive ability prediction based on the cognitive ability value to obtain a cognitive ability prediction result.

2. The cognitive ability prediction method according to claim 1, characterized by, The extraction of the frequency domain features of the electroencephalogram signal comprises: preprocessing the electroencephalogram signal to obtain a preprocessed electroencephalogram signal; converting the preprocessed electroencephalogram signal into a frequency domain signal by using Fourier transform; calculating power spectral densities of different frequency bands based on the frequency domain signal, and taking the power spectral densities as the frequency domain features.

3. The cognitive ability prediction method according to claim 2, characterized by, The calculation of the power spectral densities of different frequency bands based on the frequency domain signal comprises: ； wherein, denotes the power spectral density of different frequency bands, denotes the sampling period, denotes the number of samples in a time period, denotes the frequency domain signal, denotes the sampling frequency.

4. The cognitive ability prediction method according to claim 1, characterized by, The extraction of the functional connection features of the electroencephalogram signal comprises: performing band-pass filtering on the electroencephalogram signal to obtain a filtered electroencephalogram signal; extracting instantaneous phases in the filtered electroencephalogram signal by using Hilbert transform; calculating phase differences between electrode pairs according to the instantaneous phases; constructing a corrected imaginary phase-locked value equation based on the phase differences; calculating corrected imaginary phase-locked values by using the corrected imaginary phase-locked value equation, and taking the corrected imaginary phase-locked values as the functional connection features.

5. The cognitive ability prediction method according to claim 4, characterized by, The construction of the corrected imaginary phase-locked value equation based on the phase differences comprises: ； wherein, represents a corrected imaginary phase-locked value, represents an imaginary part, represents a time period, represents a prefix of imaginary number, represents a phase difference, represents a real part.

6. The cognitive ability prediction method according to claim 1, characterized by, The construction of the neuro-cognitive double-effect hypothesis equation based on the frequency domain features and the functional connection features comprises: ； wherein, represents a cognitive ability value, represents a number of brain regions, represents a number of frequency bands, represents an integration weight between brain regions and frequency bands, represents an accuracy modulation coefficient, represents a phase synchronization accuracy of brain regions and frequency bands, represents an energy weighting coefficient, represents a metabolic energy consumption of brain regions and frequency bands, represents a task complexity index, represents a critical phase transition threshold, represents a transition zone scaling coefficient.​​ 7. The cognitive ability prediction method according to claim 1, characterized by, The cognitive ability prediction based on the cognitive ability value to obtain a cognitive ability prediction result comprises: presetting a first threshold value and a second threshold value; if the cognitive ability value is greater than the first threshold value, the cognitive ability prediction result is high cognitive performance; if the cognitive ability value is greater than or equal to the second threshold value and less than or equal to the first threshold value, the cognitive ability prediction result is medium cognitive performance; if the cognitive ability value is less than the second threshold value, the cognitive ability prediction result is low cognitive performance.

8. A cognitive ability prediction system characterized by, The system comprises: a first feature extraction unit configured to extract frequency domain features of an electroencephalogram signal; a second feature extraction unit configured to extract functional connection features of the electroencephalogram signal; a hypothesis equation construction unit configured to construct a neuro-cognitive double-effect hypothesis equation based on the frequency domain features and the functional connection features; a cognitive ability value calculation unit configured to calculate a cognitive ability value according to the neuro-cognitive double-effect hypothesis equation; a cognitive ability prediction unit configured to perform cognitive ability prediction based on the cognitive ability value to obtain a cognitive ability prediction result.

9. An electronic device, comprising: The computer readable storage medium stores computer executable instructions for causing a computer to perform the cognitive ability prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to perform the cognitive ability prediction method according to any one of claims 1 to 7.

Images