A method, device, system, medium and product for recognizing emotional bias

Abstract

This disclosure relates to a method, apparatus, system, medium, and product for identifying emotional bias. The method includes: playing a dual-channel stimulation signal to a target user and simultaneously acquiring the target user's original electroencephalogram (EEG) signal; wherein the dual-channel stimulation signal includes a left-channel stimulation signal and a right-channel stimulation signal, both of which are composed of various emotional sounds distributed with neutral intervals, the emotional sounds in the two channel stimulation signals are time-aligned, and the two time-aligned emotional sound segments have different emotional types; extracting neutral EEG signals corresponding to neutral sounds from the original EEG signal, and extracting left-channel EEG signals corresponding to each emotional type in the left channel and right-channel EEG signals corresponding to each emotional type in the right channel from the original EEG signal; determining the target user's emotional bias based on the extracted EEG signals, thus overcoming the inherent defects of traditional stimulation paradigms and improving the efficiency and accuracy of emotional bias identification.

Description

Technical Field

[0001] This disclosure relates to the field of electroencephalogram (EEG) signal processing technology, and in particular to a method, device, system, medium, and product for identifying emotional bias. Background Technology

[0002] Emotional bias refers to an individual's cognitive tendency to consistently exhibit a processing advantage over specific emotional cues (such as negative or positive) in the environment over a period of time. For example, processing negative cues more quickly and intensely, or processing positive cues more efficiently. Research shows that emotional bias is closely related to an individual's mental health; for instance, depressed individuals often exhibit a processing bias towards negative cues, while irritable individuals tend to overprocess anger cues.

[0003] Accurately identifying an individual's emotional biases is of great significance for fields such as mental health assessment, early intervention, and human-computer interaction.

[0004] Currently, the stimulus paradigms for assessing emotional bias are mainly divided into two types: visual stimulus paradigm and acoustic stimulus paradigm. Visual stimulus paradigm involves presenting visual images with emotional content on a computer screen, while acoustic stimulus paradigm involves playing sound clips with different emotional connotations through headphones. Both paradigms collect the individual's electroencephalogram (EEG) signals simultaneously with the presentation of the emotional stimulus, and identify the individual's emotional bias by analyzing the response characteristics of the EEG signals under different emotional stimuli.

[0005] However, the visual stimulus paradigm requires a high-performance computer host and display screen, placing high demands on hardware. Furthermore, subjects must maintain a fixed posture while looking at the screen, requiring a high degree of cooperation from the subjects, thus limiting the flexibility and universality of its application scenarios. While the acoustic stimulus paradigm has relatively lower requirements for hardware and subject posture, existing acoustic stimulus paradigms mainly present sound stimuli of a single emotion type at different time periods, resulting in insufficient sensitivity in emotion bias recognition. In addition, when there are many emotion types, it is necessary to set up independent test blocks for each emotion type, making the entire recognition process cumbersome and time-consuming, and its practicality also has obvious shortcomings. Summary of the Invention

[0006] This disclosure provides a method, apparatus, system, medium, and product for identifying emotional bias, overcoming the shortcomings of traditional stimulus paradigms in terms of hardware dependence, subject cooperation, and identification efficiency, and improving the sensitivity, convenience, and practicality of emotional bias identification.

[0007] One aspect of this disclosure provides a method for identifying sentiment bias, comprising: A dual-channel stimulation signal is played to the target user, and the target user's original EEG signal is collected simultaneously; wherein, the dual-channel stimulation signal includes a left channel stimulation signal and a right channel stimulation signal, both channels are composed of multiple emotional sounds with a neutral sound distribution at intervals, the emotional sounds in the two channels are aligned in time, and the two time-aligned emotional sounds have different emotional types. The neutral EEG signal corresponding to the neutral sound is extracted from the original EEG signal, and the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel are extracted from the original EEG signal. The emotional bias of the target user is determined based on the neutral EEG signal, the left duct EEG signal, and the right duct EEG signal.

[0008] Another aspect of this disclosure provides an apparatus for identifying emotional bias, comprising: A dual-channel stimulation signal playback module is used to play dual-channel stimulation signals to a target user and simultaneously acquire the target user's original electroencephalogram (EEG) signals; wherein, the dual-channel stimulation signals include a left channel stimulation signal and a right channel stimulation signal, both channel stimulation signals are composed of multiple emotional sounds with a neutral sound distribution at intervals, the emotional sounds in the two channel stimulation signals are time-aligned, and the two time-aligned emotional sound segments have different emotional types. The raw EEG signal extraction module is used to extract the neutral EEG signal corresponding to the neutral sound from the raw EEG signal, and to extract the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel from the raw EEG signal. The emotion bias determination module is used to determine the emotion bias of the target user based on the neutral EEG signal, the left channel EEG signals, and the right channel EEG signals.

[0009] Another aspect of this disclosure provides an emotion bias recognition system, comprising: a terminal device, a sound output device communicatively connected to the terminal device, and an electroencephalogram (EEG) acquisition device communicatively connected to the terminal device; The sound output device is used to play a dual-channel stimulus signal to a target user. The dual-channel stimulus signal includes a left channel stimulus signal and a right channel stimulus signal. Both channel stimulus signals are composed of multiple emotional sounds distributed with neutral intervals. The emotional sounds in the two channel stimulus signals are aligned in time, and the two time-aligned emotional sounds have different emotional types. The EEG acquisition device is used to synchronously acquire the raw EEG signals of the target user; The terminal device includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the emotion bias recognition method according to any embodiment of this disclosure.

[0010] Another aspect of this disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to execute and implement the emotion bias recognition method described in any embodiment of this disclosure.

[0011] Another aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the emotion bias recognition method described in any embodiment of this disclosure.

[0012] The technical solutions of this disclosure can achieve at least the following beneficial effects: 1. By adopting an acoustic stimulation paradigm, the limitations of the visual stimulation paradigm on hardware devices and user cooperation are overcome, which improves the diversity of applicable scenarios and groups for emotion bias recognition. For example, it is applicable to primary healthcare institutions, home environments, and users such as the elderly, children, and special groups who cannot maintain a fixed posture for a long time.

[0013] 2. This disclosure provides a competitive emotional stimulation paradigm for binaural hearing. The emotional sounds of the two channels in the dual-channel stimulation signal are aligned in time, ensuring the temporal consistency of the emotional stimulation presentation, eliminating irrelevant variables introduced by time deviation, and utilizing the spatial separation characteristics of the left and right auditory pathways, so that the target user needs to process two different emotional information at the same time, realizing the competitive selection of the target user in the emotional processing process, thereby improving the sensitivity and accuracy of emotional bias recognition.

[0014] 3. By arranging emotional sounds and neutral sounds alternately, on the one hand, the EEG intervals corresponding to different emotional sounds can be accurately divided in the time dimension, avoiding the overlap and interference of EEG waveforms of different emotions; on the other hand, the neutral sounds are distributed throughout the stimulus sequence, which can provide a dynamic baseline reference for EEG signal analysis, eliminate the interference caused by baseline shift, and improve the stability and reliability of emotion bias recognition.

[0015] 4. By designing an integrated rotating stimulus sequence for multiple emotional sounds, data collection for multiple emotional sounds can be completed in a single stimulus process without the need for frequent switching of stimulus sequences. This not only improves the overall recognition efficiency of emotional bias but also reduces user fatigue and attention distraction caused by multiple sequence switching, further ensuring the reliability of emotional bias recognition.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for identifying sentiment bias provided in one embodiment of this disclosure; Figure 2 This is a timing diagram of a dual-channel stimulation signal provided in one embodiment of the present disclosure; Figure 3 A flowchart illustrating another method for identifying sentiment bias provided in one embodiment of this disclosure; Figure 4 A schematic diagram illustrating a contralateral projection advantage provided in one embodiment of this disclosure; Figure 5 This is a comparative schematic diagram of a contralateral mismatch response and an ipsilateral mismatch response provided in an embodiment of the present disclosure; Figure 6 This is a schematic diagram of the structure of an emotion bias recognition device provided in one embodiment of the present disclosure; Figure 7 This is a schematic diagram of the structure of an emotion bias recognition system provided in one embodiment of the present disclosure; Figure 8 This is a schematic diagram illustrating a specific example of an emotion bias recognition system provided in one embodiment of this disclosure; Figure 9 This is a schematic diagram of the structure of a terminal device provided in one embodiment of the present disclosure. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0020] It should be noted that the terms "target," "preset," "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure 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 disclosure 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, such as a process, method, system, product, or device that includes a series of steps or units, not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] Figure 1 This is a flowchart illustrating an embodiment of an emotion bias identification method provided by this disclosure. This embodiment is applicable to situations where the emotion bias of a target user needs to be identified. The method can be executed by an emotion bias identification device, which can be implemented in hardware and / or software and can be configured in a terminal device. Figure 1 As shown, the method includes: S110. Play a dual-channel stimulation signal to the target user and simultaneously collect the target user's original EEG signal.

[0022] In this embodiment, the dual-channel stimulation signal includes a left channel stimulation signal and a right channel stimulation signal. Both channel stimulation signals are composed of various emotional sounds with a neutral sound distribution at intervals. The emotional sounds in the two channel stimulation signals are aligned in time, and the two time-aligned emotional sounds have different emotional types.

[0023] The neutral voice refers to an audio sample without obvious emotional bias, while the emotional voice refers to an audio sample that can induce a specific emotional response in the target user.

[0024] Specifically, the neutral sound and the different emotional sounds can be generated by adjusting parameters such as the rhythm, tone and timbre of a single note. For example, a single note can be "ah", "ha", "um" or "ou". The neutral sound can also be white noise, ambient background sound or a calm speech segment, while the emotional sound can be a speech segment with obvious emotional color, such as laughter expressing happiness, crying expressing sadness, shouting expressing anger or screaming expressing fear.

[0025] This embodiment is merely an illustrative example of the specific presentation of neutral and emotional sounds and does not constitute a limitation on the scope of protection of this disclosure. In practical applications, appropriate audio samples can be selected or generated according to actual needs.

[0026] In one optional embodiment, the interval between two adjacent emotional sounds in the same vocal tract stimulus signal is a fixed value. Specifically, the frequency of occurrence of the emotional sounds on the time axis remains consistent, for example, an emotional sound is set every 3 neutral sounds.

[0027] In another optional embodiment, the distribution interval between two adjacent emotional sounds in the same vocal tract stimulus signal is a random value that satisfies a preset interval range. Specifically, the frequency of occurrence of the emotional sounds on the time axis is random. For example, an emotional sound is set after an interval of 3 neutral sounds, and then the next emotional sound is set after an interval of 5 neutral sounds. Each selected distribution interval is randomly selected within a preset distribution range. For example, the preset interval range can be 3-6 neutral sounds, but is not limited to the given example.

[0028] This embodiment sets emotional sounds to appear randomly on the timeline, making the location of the emotional sounds unpredictable. This reduces the target user's expectation of the location of the emotional sound, thereby enhancing the suddenness and stimulation effect of the emotional sounds and further ensuring the effectiveness and stability of the emotional induction.

[0029] Based on the above embodiments, optionally, in the same vocal tract stimulus signal, two adjacent emotional sounds have different emotional types.

[0030] The advantage of this setup is that it avoids the repetition of the same emotional type of sound within a short period of time, reducing the target user's adaptation and fatigue to specific emotional sounds, thereby enhancing the freshness and diversity of emotional stimulation, and ensuring the effectiveness of each emotional induction and the sustainability of the entire emotional induction process.

[0031] In one optional embodiment, the total number of occurrences of the emotional sound corresponding to each emotion type in the binaural stimulation signal is the same, and the number of occurrences of the emotional sound in both vocal tract stimulation signals is the same.

[0032] For example, if the two-channel stimulus signal contains N emotional sounds, then each of the two channel stimulus signals contains N / 2 emotional sounds. Assuming there are M emotion types, the emotional sound corresponding to each emotion type appears N / (2M) times in the two channel stimulus signals respectively.

[0033] This embodiment avoids stimulation bias caused by excessive concentration of emotional sounds of the same emotional type in a single channel by adopting a balanced distribution principle, thereby ensuring that the left and right channels have a consistent effect on inducing emotions in the target user and improving the symmetry and reliability of emotion induction.

[0034] Figure 2 This is a timing diagram illustrating a dual-channel stimulation signal provided in one embodiment of the present disclosure. Specifically, in the left channel stimulation signal corresponding to the left ear, angry sounds, sad sounds, and happy sounds appear sequentially with intervals of 3 and 5 neutral sound segments, respectively. In the right channel stimulation signal corresponding to the right ear, happy sounds, angry sounds, and sad sounds also appear sequentially with intervals of 3 and 5 neutral sound segments, respectively. Specifically, the fear sound in the left channel stimulation signal aligns with the happy sound in the right channel stimulation signal at time T1; the sad sound in the left channel stimulation signal aligns with the angry sound in the right channel stimulation signal at time T2; and the happy sound in the left channel stimulation signal aligns with the sad sound in the right channel stimulation signal at time T3. The order of occurrence of angry sounds, sad sounds, and happy sounds differs in the two channel stimulation signals, but their frequency of occurrence remains balanced.

[0035] In one specific embodiment, a two-channel background signal composed of multiple neutral sound segments is acquired, and an insertion time sequence is determined according to a fixed distribution interval or a preset distribution range. Using a balanced allocation principle, an emotional sound pair corresponding to each insertion time is determined, and one emotional sound from each pair is inserted into the left channel background signal of the two-channel background signal, while the other emotional sound is inserted into the right channel background signal of the two-channel background signal, thus obtaining a two-channel stimulation signal. Here, the insertion time in the insertion time sequence represents the insertion position of an emotional sound segment.

[0036] Based on the above embodiments, optionally, playing the two-channel stimulation signal to the target user includes: performing loudness consistency processing on the two-channel stimulation signals to obtain a processed two-channel stimulation signal, and playing the processed two-channel stimulation signal to the target user.

[0037] For example, the loudness consistency processing can be implemented using the root mean square normalization method or the peak normalization method to ensure that the loudness levels of the two vocal tract stimulation signals are consistent, and to avoid the target user's perception deviation of the emotional sound on one side due to loudness differences.

[0038] For example, left and right channel calibration can also be performed on sound output devices, such as headphones and speakers, to ensure that the output gain of the left and right channels is consistent, thereby further eliminating loudness differences at the hardware level.

[0039] The raw EEG signal represents the EEG response on the target user's scalp surface during the playback of the dual-channel stimulation signal. Specifically, the raw EEG signal includes EEG data corresponding to multiple electrode channels, with each electrode channel corresponding to a sampling location for recording potential changes in different brain regions.

[0040] S120. Extract the neutral EEG signal corresponding to the neutral sound from the original EEG signal, and extract the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel from the original EEG signal.

[0041] The neutral EEG signal comprises multiple neutral EEG segments, each corresponding to a neutral sound; the left channel EEG signal comprises multiple emotional EEG segments corresponding to different emotion types, each corresponding to an emotional sound appearing in the left channel stimulation signal; the right channel EEG signal comprises multiple emotional EEG segments corresponding to different emotion types, each corresponding to an emotional sound appearing in the right channel stimulation signal.

[0042] Specifically, by marking the start time of each neutral sound segment, a neutral EEG signal is obtained by extracting an EEG segment within a preset time window from the original EEG signal; for each emotion type, the start time of each emotional sound segment of that emotion type in the left channel stimulation signal is marked, and an EEG segment within a preset time window is extracted from the original EEG signal to obtain a left channel EEG signal composed of multiple emotional EEG segments of that emotion type; the start time of each emotional sound segment of that emotion type in the right channel stimulation signal is marked, and an EEG segment within a preset time window is extracted from the original EEG signal to obtain a right channel EEG signal composed of multiple emotional EEG segments of that emotion type.

[0043] For example, the preset time window can be 300ms-600ms after the start time, but is not limited to the given example.

[0044] S130. Determine the emotional bias of the target user based on the neutral EEG signal, each of the left vocal tract EEG signals, and each of the right vocal tract EEG signals.

[0045] In an optional embodiment, determining the target user's emotional bias based on the neutral EEG signal, each of the left-channel EEG signals, and each of the right-channel EEG signals includes: performing baseline correction on each of the left-channel and right-channel EEG signals based on the neutral EEG signal; for each emotion type, performing feature extraction on the baseline-corrected left-channel and right-channel EEG signals corresponding to the emotion type to obtain the left-channel feature value and right-channel feature value corresponding to the emotion type; and determining the average processing intensity corresponding to the emotion type based on the left-channel and right-channel feature values; and determining the emotion type with the highest average processing intensity as the target user's emotional bias.

[0046] For example, the feature indicators used in the feature extraction can be power spectral density, differential entropy, or the maximum amplitude of event-related potential in a specific frequency band, but are not limited to the given example.

[0047] Wherein, the left channel feature value represents the processing intensity of the right hemisphere on the emotion type, the right channel feature value represents the processing intensity of the left hemisphere on the emotion type, and the average processing intensity is the mean of the left channel feature value and the right channel feature value, representing the degree to which the target user is biased towards the emotion type during competitive emotion processing.

[0048] In another optional embodiment, determining the target user's emotional bias based on the neutral EEG signal, each of the left-channel EEG signals, and each of the right-channel EEG signals includes: performing baseline correction on each of the left-channel EEG signals and each of the right-channel EEG signals based on the neutral EEG signal; inputting the baseline-corrected left-channel EEG signal and right-channel EEG signal corresponding to each emotion type into a trained emotion classification model to obtain the output emotional bias of the target user.

[0049] The emotion classification model can be built based on convolutional neural networks or support vector machines, but is not limited to the given example.

[0050] The technical solution of this embodiment overcomes the limitations of the visual stimulation paradigm on hardware devices and user cooperation by adopting an auditory stimulation paradigm, thereby improving the diversity of applicable scenarios and target groups for emotion bias recognition. By using a competitive emotion stimulation paradigm with binaural hearing, the spatial separation characteristics of the left and right auditory pathways are utilized to improve the sensitivity and accuracy of emotion bias recognition. By designing an integrated rotating stimulation sequence for multiple emotional sounds, user fatigue and attention distraction caused by multiple sequence switching are reduced, further ensuring the reliability of emotion bias recognition.

[0051] Figure 3This is a flowchart of another emotion bias identification method provided in one embodiment of the present disclosure. This embodiment further refines the "determining the emotion bias of the target user based on the neutral EEG signal, each of the left vocal tract EEG signals and each of the right vocal tract EEG signals" in the above embodiment. In this embodiment, determining the target user's emotional bias based on the neutral EEG signal, each of the left channel EEG signals, and each of the right channel EEG signals includes: averaging each neutral EEG segment in the neutral EEG signal to obtain a baseline feature signal; averaging each emotional EEG segment in each left channel EEG signal to obtain a left channel feature signal; and averaging each emotional EEG segment in each right channel EEG signal to obtain a right channel feature signal; subtracting each left channel feature signal from the baseline feature signal channel-by-channel to obtain a left channel mismatch response; and subtracting each right channel feature signal from the baseline feature signal channel-by-channel to obtain a right channel mismatch response; and determining the target user's emotional bias based on each left channel mismatch response and each right channel mismatch response. Figure 3 As shown, the method includes: S210. Play a dual-channel stimulation signal to the target user and simultaneously collect the target user's original EEG signal.

[0052] Specifically, the electrode group corresponding to the original EEG signal includes at least one electrode pair arranged symmetrically on both sides.

[0053] In an optional embodiment, the electrode group includes a temporal T7 electrode and a temporal T8 electrode, wherein the temporal T7 electrode is mainly used to collect the EEG response corresponding to the right vocal tract stimulation signal, and the temporal T8 electrode is mainly used to collect the EEG response corresponding to the left vocal tract stimulation signal.

[0054] The T7 and T8 electrodes in the temporal lobe are located on the lateral side of the temporal cortex, corresponding to the auditory cortex regions on the left and right sides of the brain, respectively. They are capable of accurately capturing neural responses induced by different sound channels during binaural hearing tasks, effectively ensuring the targeted and effective acquisition of EEG signals. As an example, the electrode group can be further supplemented with TP7 and TP8 electrodes, FT7 and FT8 electrodes, etc., to expand the electrode coverage and enhance the signal acquisition capability of the peripheral temporal lobe region, thereby improving the spatial resolution and signal stability of the raw EEG signals.

[0055] In another alternative embodiment, the electrode set further includes a frontal electrode pair and / or a central electrode pair, wherein the frontal electrode pair includes F3 and F4 electrodes, and the central electrode pair includes C3 and C4 electrodes; wherein the frontal electrode pair is used to collect EEG responses related to emotion processing, and the central electrode pair is used to collect EEG responses related to attention allocation.

[0056] Specifically, the F3 and F4 electrodes are located on the left and right sides of the prefrontal cortex. This area is closely related to physiological processes such as emotion regulation and cognitive appraisal, and can reflect the differences in the emotional valence of target users in processing stimuli from different sound channels. The C3 and C4 electrodes are located on both sides of the central sulcus. This area is the core associated area for attention resource allocation and can reveal the degree of attentional bias of target users towards left and right sound channel stimuli in binaural listening tasks.

[0057] In this embodiment, the EEG signals from the frontal electrode pair can be used for emotion-related analysis, thereby providing a neurophysiological basis for determining emotional bias; the EEG signals from the central electrode pair can be used to analyze attention allocation patterns, thereby providing evidence for the determination of emotional bias at the level of attention resource allocation. By jointly analyzing the EEG characteristics of the frontal and central electrode pairs, the emotional bias of the target user under different auditory stimuli can be identified more comprehensively and accurately, improving the robustness and generalization ability of emotional bias recognition.

[0058] Furthermore, the selection of reference electrodes is crucial to signal quality during the acquisition of raw EEG signals. For example, mastoid electrodes or nasal tip electrodes can be used as reference electrodes. Both types of electrodes can effectively reduce the interference of environmental and physiological noise on the acquired signals, reduce signal distortion, and significantly improve the purity and reliability of the raw EEG signals, laying a solid foundation for subsequent signal processing and analysis.

[0059] S220. Extract the neutral EEG signal corresponding to the neutral sound from the original EEG signal, and extract the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel from the original EEG signal.

[0060] S220 in this embodiment is the same as in the previous embodiment. Figure 1 The S120 shown is similar and will not be described again here.

[0061] S230. Average each neutral EEG segment in the neutral EEG signal to obtain a reference feature signal; average each emotional EEG segment in each left channel EEG signal to obtain a left channel feature signal; and average each emotional EEG segment in each right channel EEG signal to obtain a right channel feature signal.

[0062] The baseline feature signal characterizes the target user's baseline EEG activity level under no emotional stimulation conditions. The left channel feature signal characterizes the target user's average EEG response level under left channel emotional stimulation conditions, and the right channel feature signal characterizes the target user's average EEG response level under right channel emotional stimulation conditions. Specifically, the baseline feature signal, the left channel feature signal, and the right channel feature signal each contain average EEG waveforms corresponding to multiple electrode channels.

[0063] S240. Subtract each left channel feature signal from the reference feature signal channel by channel to obtain the left channel mismatch response, and subtract each right channel feature signal from the reference feature signal channel by channel to obtain the right channel mismatch response.

[0064] The mismatch response (MMR) refers to the difference in electroencephalogram (EEG) signals generated by a target user under emotional stimulation conditions compared to their baseline state. Specifically, the left tract mismatch response characterizes the change in EEG activity induced by emotional stimulation in the left tract relative to the baseline level, and the right tract mismatch response characterizes the change in EEG activity induced by emotional stimulation in the right tract relative to the baseline level.

[0065] By subtracting signals channel by channel, baseline differences between individuals and systematic biases caused by electrode channels can be effectively eliminated, thereby more accurately extracting the EEG activity characteristics induced by emotional stimuli themselves. This differentiated processing method helps to highlight the specific EEG response patterns induced by different emotion types under left and right vocal tract conditions, providing more discriminative feature evidence for subsequent emotion bias identification and brain function lateralization analysis.

[0066] S250. Determine the emotional bias of the target user based on the left channel mismatch response and the right channel mismatch response.

[0067] In an optional embodiment, determining the target user's emotional bias based on each of the left channel mismatch responses and each of the right channel mismatch responses includes: for each emotion type, averaging the left channel mismatch responses and right channel mismatch responses corresponding to the emotion type to obtain an average mismatch response; extracting features from the average mismatch responses to obtain emotional processing features corresponding to the emotion type; and determining the target user's emotional bias based on each of the emotional processing features.

[0068] In another optional embodiment, determining the target user's emotional bias based on each of the left channel mismatch responses and each of the right channel mismatch responses includes: for each emotional type, selecting contralateral mismatch responses from the left channel mismatch responses and right channel mismatch responses corresponding to the emotional type, and extracting features from the contralateral mismatch responses to obtain contralateral processing features corresponding to the emotional type; and determining the target user's emotional bias based on each of the contralateral processing features.

[0069] For example, the emotional processing features and the contralateral processing features can be power spectral density, absolute amplitude increase of mismatch response, onset latency, peak latency, waveform slope, and latency in specific frequency bands. The specific frequency bands are mainly theta waves (4-8Hz), alpha waves (8-13Hz), and beta waves (13-30Hz), with different frequency bands corresponding to different stages of emotional processing. Theta waves participate in emotional memory encoding and retrieval, reflecting the brain's rapid recognition of emotional stimuli; alpha waves are related to emotional regulation and attention allocation, showing significant inhibition under negative emotional stimuli, reflecting cognitive control ability; and beta waves are responsible for the refined processing of emotional information, quantifying individual differences in preference for positive and negative emotions to achieve accurate judgment of emotional bias.

[0070] In this embodiment, the contralateral mismatch response includes the single-channel mismatch response corresponding to the right electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the left electrode channel in the right channel mismatch response; the ipsilateral mismatch response includes the single-channel mismatch response corresponding to the left electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the right electrode channel in the right channel mismatch response.

[0071] In the auditory neural pathway, sound information received by one ear is primarily projected to the contralateral cerebral hemisphere via the contralateral ascending pathway. Specifically, information received from the left ear is primarily processed by the right cerebral hemisphere, while information received from the right ear is primarily processed by the left cerebral hemisphere; this characteristic is known as contralateral projection dominance. Taking left duct mismatch responses as an example, the categorized contralateral mismatch responses include single-channel mismatch responses corresponding to the T8, F4, and C4 electrodes in the temporal region, respectively. The categorized ipsilateral mismatch responses include single-channel mismatch responses corresponding to the T7, F3, and C3 electrodes in the temporal region, respectively.

[0072] Figure 4This is a schematic diagram of a contralateral projection advantage provided in one embodiment of the present disclosure, wherein the left tract stimulation signal received by the left ear is mainly projected to the right primary auditory cortex via the right brainstem nuclei and thalamus, and is processed emotionally by the right cerebral hemisphere. Its EEG response is mainly collected and recorded by the T8 electrode in the temporal region; the right tract stimulation signal received by the right ear is mainly projected to the left primary auditory cortex via the left brainstem nuclei and thalamus, and is processed emotionally by the left cerebral hemisphere. Its EEG response is mainly collected and recorded by the T7 electrode in the temporal region.

[0073] Figure 5 This is a comparative schematic diagram of contralateral mismatch response and ipsilateral mismatch response provided in an embodiment of this disclosure. The solid red line represents the contralateral mismatch response within a 300ms-600ms window after the emotional sound appears, and the dashed blue line represents the ipsilateral mismatch response within the same 300ms-600ms window. Figure 5 It can be seen that the waveform amplitude of the contralateral mismatch response is significantly higher than that of the ipsilateral mismatch response, and the peak latency is shorter, indicating that the contralateral cerebral hemisphere has higher sensitivity and timeliness in emotional processing.

[0074] Taking the absolute amplitude of the contralateral processing feature as an example, the emotion type corresponding to the maximum value of the absolute amplitude of the contralateral mismatch response is taken as the emotion bias of the target user.

[0075] This embodiment, by specifically capturing and analyzing contralateral mismatch responses, can efficiently and accurately identify the processing patterns of emotional stimuli in the auditory pathway, especially highlighting the dominant characteristics of the contralateral hemisphere in emotional information processing. This not only enhances the sensitivity and specificity of emotion bias identification but also helps to reveal and quantify the lateralization neural mechanisms exhibited by the brain in processing emotional information in a more detailed and precise manner, thus providing more reliable empirical evidence for a deeper understanding of hemispheric asymmetry in emotional processing.

[0076] Based on the above embodiments, optionally, before determining the emotional bias of the target user according to each of the contralateral processing features, the method further includes: playing a control stimulus signal corresponding to each emotion type to the target user and simultaneously acquiring the control EEG signal of the target user; determining the hemispherical effect and ear-specific effect of the target user according to each of the control EEG signals; and correcting the contralateral mismatch response corresponding to the emotion type according to the hemispherical effect and ear-specific effect.

[0077] Specifically, the control stimulus signal includes a monophonic stimulus signal composed of emotional sounds corresponding to the emotion type and a monophonic stimulus signal composed of neutral sounds, which are played synchronously through the left and right ears respectively; the hemispherical effect characterizes the asymmetry of the target user's processing of emotional sounds in the left and right hemispheres, and the ear-specific effect characterizes the asymmetry of the target user's processing of emotional sounds in the left and right ear receiving channels.

[0078] By introducing correction mechanisms for hemispherical and ear-specific effects, systematic biases caused by differences in auditory pathway structure or innate lateralization tendencies between individuals are effectively eliminated, thereby further improving the accuracy and reliability of contralateral mismatch response in emotion bias identification.

[0079] Based on the above embodiments, the method may optionally further include: classifying the left tract mismatch response and the right tract mismatch response corresponding to the emotional bias to obtain ipsilateral mismatch response and contralateral mismatch response; and determining the lateralization result of the target user's emotional bias based on the ipsilateral mismatch response and the contralateral mismatch response.

[0080] For example, the lateralization result includes at least one of the following: lateralization index, lateralization difference, lateralization ratio, and lateralization intensity. The lateralization index can be obtained by calculating the ratio of the difference between the contralateral mismatch response and the ipsilateral mismatch response to their sum. The lateralization difference is the difference between the contralateral mismatch response and the ipsilateral mismatch response. The lateralization ratio is the ratio between the contralateral mismatch response and the ipsilateral mismatch response. The lateralization intensity can be quantified by calculating the root mean square difference between the contralateral mismatch response and the ipsilateral mismatch response. This is merely an illustrative example of several calculation methods for lateralization results; in practical applications, appropriate indicators can be selected according to research objectives and experimental requirements.

[0081] The advantage of introducing lateralization results in this embodiment is that it further reveals the neural basis of emotional bias at the hemispheric level of the brain, thereby elevating the identification of emotional bias from the behavioral level to the neural mechanism level. It can be widely applied in fields such as emotional disorder screening, auditory cognitive training, and human-computer interaction emotion recognition, providing objective quantitative reference for clinical disease screening and diagnosis, personalized cognitive training program customization, and emotion recognition algorithm optimization.

[0082] The technical solution of this embodiment reduces the recognition bias caused by abnormal fluctuations in a single segment of EEG signal by averaging the neutral EEG signal, the left channel EEG signal, and the right channel EEG signal. At the same time, the mismatch response of the left and right channels can more stably reflect the specific neural response induced by emotional stimulation compared with the baseline-corrected EEG signal, and is more in line with the neurophysiological mechanism of emotional processing, thereby further improving the accuracy and reliability of emotional bias recognition.

[0083] The following are embodiments of the emotion bias identification device provided in this disclosure. This device and the emotion bias identification method described in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the emotion bias identification device, please refer to the content of the emotion bias identification method in the above embodiments.

[0084] Figure 6 This is a schematic diagram of the structure of an emotion bias recognition device provided in one embodiment of the present disclosure. Figure 6 As shown, the device includes: a dual-channel stimulation signal playback module 310, a raw EEG signal interception module 320, and an emotion bias determination module 330.

[0085] The dual-channel stimulation signal playback module 310 is used to play dual-channel stimulation signals to the target user and simultaneously acquire the target user's original electroencephalogram (EEG) signals. The dual-channel stimulation signals include a left channel stimulation signal and a right channel stimulation signal. Both channels are composed of various emotional sounds with a neutral sound distribution at intervals. The emotional sounds in the two channels are time-aligned, and the two time-aligned emotional sounds have different emotional types. The raw EEG signal extraction module 320 is used to extract the neutral EEG signal corresponding to the neutral sound from the raw EEG signal, and to extract the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel from the raw EEG signal. The emotion bias determination module 330 is used to determine the emotion bias of the target user based on the neutral EEG signal, the left channel EEG signals and the right channel EEG signals.

[0086] The technical solution of this embodiment overcomes the limitations of the visual stimulation paradigm on hardware devices and user cooperation by adopting an auditory stimulation paradigm, thereby improving the diversity of applicable scenarios and target groups for emotion bias recognition. By using a competitive emotion stimulation paradigm with binaural hearing, the spatial separation characteristics of the left and right auditory pathways are utilized to improve the sensitivity and accuracy of emotion bias recognition. By designing an integrated rotating stimulation sequence for multiple emotional sounds, user fatigue and attention distraction caused by multiple sequence switching are reduced, further ensuring the reliability of emotion bias recognition.

[0087] In one optional embodiment, in the same vocal tract stimulation signal, the distribution interval between two adjacent emotional sounds is a random value that satisfies a preset interval range. The total number of occurrences of the emotional sound corresponding to each emotion type is the same in the binaural stimulation signal, and the number of occurrences of the emotional sound is the same in both vocal tract stimulation signals.

[0088] In an optional embodiment, the dual-channel stimulus signal playback module 310 is specifically used for: The loudness consistency of the two audio stimulation signals is processed to obtain the processed binaural stimulation signal, and the processed binaural stimulation signal is played to the target user.

[0089] In an optional embodiment, the sentiment bias determination module 330 includes: The right channel feature signal determination unit is used to average each neutral EEG segment in the neutral EEG signal to obtain a reference feature signal, average each emotional EEG segment in each left channel EEG signal to obtain a left channel feature signal, and average each emotional EEG segment in each right channel EEG signal to obtain a right channel feature signal. The right channel mismatch response determination unit is used to subtract each left channel feature signal from the reference feature signal channel by channel to obtain the left channel mismatch response, and to subtract each right channel feature signal from the reference feature signal channel by channel to obtain the right channel mismatch response. The emotion bias determination unit is used to determine the emotion bias of the target user based on each of the left channel mismatch responses and each of the right channel mismatch responses.

[0090] In one optional embodiment, the sentiment bias determination unit is specifically used for: For each emotion type, the contralateral mismatch response is selected from the left and right tract mismatch responses corresponding to the emotion type, and features are extracted from the contralateral mismatch responses to obtain the contralateral processing features corresponding to the emotion type. Based on the aforementioned contralateral processing characteristics, the emotional bias of the target user is determined; The contralateral mismatch response includes the single-channel mismatch response corresponding to the right electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the left electrode channel in the right channel mismatch response.

[0091] In an optional embodiment, the device further includes: The lateralization result determination module is used to classify the left tract mismatch response and right tract mismatch response corresponding to the emotional bias, and obtain ipsilateral mismatch response and contralateral mismatch response. Based on the ipsilateral mismatch response and the contralateral mismatch response, the lateralization result of the target user's emotional bias is determined; The ipsilateral mismatch response includes the single-channel mismatch response corresponding to the left electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the right electrode channel in the right channel mismatch response.

[0092] In an optional embodiment, the electrode group corresponding to the original EEG signal includes a temporal T7 electrode and a temporal T8 electrode, wherein the temporal T7 electrode is mainly used to collect the EEG response corresponding to the right vocal tract stimulation signal, and the temporal T8 electrode is mainly used to collect the EEG response corresponding to the left vocal tract stimulation signal.

[0093] In an optional embodiment, the electrode group further includes a frontal electrode pair and / or a central electrode pair, wherein the frontal electrode pair includes an F3 electrode and an F4 electrode, and the central electrode pair includes a C3 electrode and a C4 electrode; The frontal electrode pair is used to collect EEG responses related to emotion processing, and the central electrode pair is used to collect EEG responses related to attention allocation.

[0094] The emotion bias identification device provided in this disclosure can execute the emotion bias identification method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method execution.

[0095] Figure 7 This is a schematic diagram illustrating the structure of an emotion bias recognition system provided in one embodiment of this disclosure. Figure 7 As shown, the system includes: a terminal device 410, a sound output device 420 communicatively connected to the terminal device 410, and an electroencephalogram (EEG) acquisition device 430 communicatively connected to the terminal device 410.

[0096] The sound output device 420 is used to play a dual-channel stimulation signal to the target user. The dual-channel stimulation signal includes a left channel stimulation signal and a right channel stimulation signal. Both channel stimulation signals are composed of multiple emotional sounds with a neutral sound distribution at intervals. The emotional sounds in the two channel stimulation signals are aligned in time, and the two time-aligned emotional sounds have different emotional types. The EEG acquisition device 430 is used to synchronously acquire the target user's original EEG signals.

[0097] Specifically, the EEG acquisition device 430 includes an electrode assembly and an EEG transceiver. The electrode assembly is used to acquire EEG signals from the scalp surface of the target user. The EEG transceiver is used to amplify, filter, and digitize the EEG signals acquired by the electrode assembly and transmit them to the terminal device 410 wirelessly or via wired means.

[0098] In an optional embodiment, the electrode group includes a temporal T7 electrode and a temporal T8 electrode, wherein the temporal T7 electrode is mainly used to collect the EEG response corresponding to the right vocal tract stimulation signal, and the temporal T8 electrode is mainly used to collect the EEG response corresponding to the left vocal tract stimulation signal.

[0099] Based on the above embodiments, optionally, the electrode group further includes a frontal electrode pair and / or a central electrode pair, wherein the frontal electrode pair includes an F3 electrode and an F4 electrode, and the central electrode pair includes a C3 electrode and a C4 electrode; wherein the frontal electrode pair is used to collect EEG responses related to emotion processing, and the central electrode pair is used to collect EEG responses related to attention allocation.

[0100] Figure 8 This is a schematic diagram illustrating a specific example of an emotion bias recognition system provided in one embodiment of this disclosure, such as... Figure 8 As shown, in practical deployment, this system can be integrated into a portable EEG acquisition device. The simplified electrode set in the portable EEG acquisition device consists of temporal T7 and temporal T8 electrodes, or may be covered with a small number of other auxiliary electrodes to meet the needs of home monitoring and daily monitoring scenarios for device comfort and ease of operation. The terminal device 410 connects to stereo headphones via a standard audio interface and establishes a communication connection with the EEG transceiver in the portable EEG acquisition device via wireless transmission methods such as Bluetooth and lightweight wireless communication modules. This allows the EEG transceiver in the portable EEG acquisition device to perform real-time preprocessing of the EEG waves acquired by the simplified electrode set and transmit the preprocessed EEG signals wirelessly to the terminal device 410, enabling the function of playing dual-channel stimulation signals to the target user and simultaneously acquiring the raw EEG signals.

[0101] Figure 9 This is a schematic diagram of the structure of a terminal device provided according to one embodiment of the present disclosure. Terminal device 410 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, and other suitable computers. Terminal device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0102] like Figure 9As shown, the terminal device 410 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the terminal device 410. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0103] Multiple components in terminal device 410 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows terminal device 410 to exchange information or data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0104] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the sentiment bias recognition method provided in the above embodiments.

[0105] In some embodiments, the sentiment bias identification method provided in the above embodiments can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on terminal device 410 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the sentiment bias identification method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the sentiment bias identification method by any other suitable means (e.g., by means of firmware).

[0106] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of embodiments of this disclosure.

[0107] Various embodiments of the systems and techniques described above can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] Computer programs used to implement the sentiment bias identification method of this disclosure can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable storage medium. Examples of machine-readable storage media include, based on an electrical connection of at least one wire, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on a terminal device having: a display device for displaying information to the user (e.g., a cathode-ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the terminal device. Other types of devices can also provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including audio input or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0112] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0113] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0114] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying emotional bias, characterized in that, include: A dual-channel stimulation signal is played to the target user, and the target user's original EEG signal is collected simultaneously; wherein, the dual-channel stimulation signal includes a left channel stimulation signal and a right channel stimulation signal, both channels are composed of multiple emotional sounds with a neutral sound distribution at intervals, the emotional sounds in the two channels are aligned in time, and the two time-aligned emotional sounds have different emotional types. The neutral EEG signal corresponding to the neutral sound is extracted from the original EEG signal, and the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel are extracted from the original EEG signal. The emotional bias of the target user is determined based on the neutral EEG signal, the left duct EEG signal, and the right duct EEG signal.

2. The method according to claim 1, characterized in that, In the same audible stimulation signal, the distribution interval between two adjacent emotional sounds is a random value that meets the preset interval range; The total number of occurrences of the emotional sound corresponding to each emotion type is the same in the binaural stimulation signal, and the number of occurrences of the emotional sound is the same in both vocal tract stimulation signals.

3. The method according to claim 1, characterized in that, Playing the dual-channel stimulation signal to the target user includes: The loudness consistency of the two audio stimulation signals is processed to obtain the processed binaural stimulation signal, and the processed binaural stimulation signal is played to the target user.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the target user's emotional bias based on the neutral EEG signal, each of the left vocal tract EEG signals, and each of the right vocal tract EEG signals includes: The reference feature signal is obtained by averaging each neutral EEG segment in the neutral EEG signal, the left channel feature signal is obtained by averaging each emotional EEG segment in each left channel EEG signal, and the right channel feature signal is obtained by averaging each emotional EEG segment in each right channel EEG signal. Each left channel feature signal is subtracted from the reference feature signal channel by channel to obtain the left channel mismatch response, and each right channel feature signal is subtracted from the reference feature signal channel by channel to obtain the right channel mismatch response. The emotional bias of the target user is determined based on the left channel mismatch response and the right channel mismatch response.

5. The method according to claim 4, characterized in that, The step of determining the target user's emotional bias based on each of the left channel mismatch responses and each of the right channel mismatch responses includes: For each emotion type, the contralateral mismatch response is selected from the left and right tract mismatch responses corresponding to the emotion type, and features are extracted from the contralateral mismatch responses to obtain the contralateral processing features corresponding to the emotion type. Based on the aforementioned contralateral processing characteristics, the emotional bias of the target user is determined; The contralateral mismatch response includes the single-channel mismatch response corresponding to the right electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the left electrode channel in the right channel mismatch response.

6. The method according to claim 5, characterized in that, The method further includes: The left and right tract mismatch responses corresponding to the emotional biases are categorized to obtain ipsilateral mismatch responses and contralateral mismatch responses. Based on the ipsilateral mismatch response and the contralateral mismatch response, the lateralization result of the target user's emotional bias is determined; The ipsilateral mismatch response includes the single-channel mismatch response corresponding to the left electrode channel in the left channel mismatch response, and the single-channel mismatch response corresponding to the right electrode channel in the right channel mismatch response.

7. The method according to claim 4, characterized in that, The electrode group corresponding to the original EEG signal includes a temporal T7 electrode and a temporal T8 electrode. The temporal T7 electrode is mainly used to collect the EEG response corresponding to the right vocal tract stimulation signal, and the temporal T8 electrode is mainly used to collect the EEG response corresponding to the left vocal tract stimulation signal.

8. The method according to claim 7, characterized in that, The electrode group further includes a frontal electrode pair and / or a central electrode pair, wherein the frontal electrode pair includes an F3 electrode and an F4 electrode, and the central electrode pair includes a C3 electrode and a C4 electrode; The frontal electrode pair is used to collect EEG responses related to emotion processing, and the central electrode pair is used to collect EEG responses related to attention allocation.

9. A device for recognizing emotional bias, characterized in that, include: A dual-channel stimulation signal playback module is used to play dual-channel stimulation signals to a target user and simultaneously acquire the target user's original electroencephalogram (EEG) signals; wherein, the dual-channel stimulation signals include a left channel stimulation signal and a right channel stimulation signal, both channel stimulation signals are composed of multiple emotional sounds with a neutral sound distribution at intervals, the emotional sounds in the two channel stimulation signals are time-aligned, and the two time-aligned emotional sound segments have different emotional types. The raw EEG signal extraction module is used to extract the neutral EEG signal corresponding to the neutral sound from the raw EEG signal, and to extract the left channel EEG signal corresponding to each emotion type in the left channel and the right channel EEG signal corresponding to each emotion type in the right channel from the raw EEG signal. The emotion bias determination module is used to determine the emotion bias of the target user based on the neutral EEG signal, the left channel EEG signals, and the right channel EEG signals.

10. A system for recognizing emotional bias, characterized in that, include: A terminal device, a sound output device communicatively connected to the terminal device, and an electroencephalogram (EEG) acquisition device communicatively connected to the terminal device; The sound output device is used to play a dual-channel stimulus signal to a target user. The dual-channel stimulus signal includes a left channel stimulus signal and a right channel stimulus signal. Both channel stimulus signals are composed of multiple emotional sounds distributed with neutral intervals. The emotional sounds in the two channel stimulus signals are aligned in time, and the two time-aligned emotional sounds have different emotional types. The EEG acquisition device is used to synchronously acquire the raw EEG signals of the target user; The terminal device includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the emotion bias identification method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for identifying emotional bias as described in any one of claims 1-8.

12. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method for identifying emotional bias as described in any one of claims 1-8.

Images