Music feedback training interface interaction method and system based on electroencephalogram data

Abstract

The invention relates to the technical field of music feedback, in particular to a music feedback training interface interaction method and system based on electroencephalogram data, and the method comprises the following steps: collecting electroencephalogram data of a user based on an electroencephalogram collection device, and removing environmental noise and non-target signals through signal amplification and filtering processing to obtain a user electroencephalogram data set. According to the method, the emotion recognition accuracy and time sensitivity are improved by analyzing the brain wave frequency band intensity, judging the emotion state of the user and recording the emotion change time point, and the emotion recognition accuracy and time sensitivity are improved by matching music tracks of the emotion state, combining real-time monitoring of electroencephalogram reaction and adjusting the rhythm, volume and spatial sound effect setting of music. Dynamic adjustment of music output parameters is achieved, the emotion intervention requirement is optimized, emotion improvement and user satisfaction are evaluated according to brain wave changes of the user, and the improvement effect of music intervention on the psychological state of the user can be measured.

Description

Technical Field

[0001] The present invention relates to the field of music feedback technology, and in particular to a music feedback training interface interaction method and system based on electroencephalogram data. Background Art

[0002] The field of music feedback technology includes various physiological and psychological feedback technologies combined with music. The core content of this field is to use music to have a positive impact on people's behavior and emotional state, and to adjust the individual's psychological state and physiological response through the melody, rhythm and tonality of music. The systematic introduction of the technical field includes the selection of music, the dynamic adjustment of music, and how music is combined with the user's physiological data to achieve the best therapeutic effect. This technical field covers multiple sub-fields such as music therapy, psychotherapy and physiological data monitoring. By integrating various sensor data and using the natural influence of music on the brain and body, it promotes mental health and physiological rehabilitation.

[0003] Among them, the music feedback training interface interaction method is a technology that automatically adjusts the music output to adapt to the user's current emotional and physiological state based on the user's physiological data. The technical matters targeted by the patent subject include real-time collection and analysis of user emotional status data and dynamic adjustment of music output. By collecting the user's emotional status data, data analysis is used to select or adjust music parameters such as rhythm, volume and tone to match the user's psychological needs.

[0004] Traditional interactive methods rely on a single physiological signal when identifying emotional states, and fail to fully combine the activity characteristics of users' multi-band brain waves, which may lead to misjudgment or omissions in complex emotional states. In terms of music output, traditional methods have relatively fixed adjustments to playback parameters, and fail to dynamically optimize playback rhythm, sound effects, and spatial sound effect distribution based on real-time feedback from users, resulting in emotional intervention effects that are difficult to meet individual needs. In the evaluation of emotional intervention effects, existing technologies mostly stay at simple satisfaction statistics based on user feedback questionnaires, lacking in-depth analysis of changes in user brain wave data before and after music adjustment, resulting in insufficient quantitative evaluation of intervention effects. As a result, the application of existing technologies in complex emotional regulation scenarios is limited, making it difficult to provide effective and efficient emotional intervention support. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a music feedback training interface interaction method and system based on EEG data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a music feedback training interface interaction method based on EEG data, comprising the following steps:

[0007] S1: Based on the EEG acquisition device, the user's EEG data is collected, and the environmental noise and non-target signals are removed through signal amplification and filtering to obtain the user's EEG data set;

[0008] S2: Based on the user's brain wave data set, analyze the activities of the differentiated frequency bands, identify and quantify the intensity of each band, and judge the user's current emotional state by comparing it with a preset threshold, and record the time point of emotional changes to obtain emotional analysis results;

[0009] S3: Based on the emotion analysis result, the preset music database is searched to retrieve music tracks that match the emotional state, the music is played, and the brain wave data and the music playing status are synchronously displayed through the display interaction interface, the user's adjustment of the music playing is received, and real-time music feedback interaction information is obtained;

[0010] S4: Based on the real-time music feedback display information, the user's brain wave response is monitored in real time, the music parameters are adjusted, and according to the instant feedback of the user's brain waves, the spatial sound effect settings of the music are adjusted to generate music feedback adjustment information;

[0011] S5: Based on the music feedback adjustment information, according to the changes in brain waves before and after music playing and adjustment, analyze the impact of music playing adjustment on user emotions, evaluate the degree of emotion improvement and user satisfaction index, and obtain user experience evaluation results.

[0012] As a further solution of the present invention, the user brain wave data set includes the frequency distribution of α, β and γ waves, the amplitude information of each band and the total power spectrum of the brain waves; the emotion analysis result includes the user emotional state label, the timestamp corresponding to the emotional state and the emotion intensity index; the real-time music feedback interaction information includes the music track ID that meets the emotional needs, the playback order of the tracks and the scheduled playback time of each track; the music feedback adjustment information includes the volume adjustment value, the rhythm adjustment frequency, the user's EEG response change data and the instant playback status of the adjusted music; the user experience evaluation result includes the comparison of emotional states before and after music intervention, the percentage of emotional improvement and the user satisfaction score.

[0013] As a further solution of the present invention, based on the brain wave acquisition device, the steps of collecting the user's brain wave data, removing environmental noise and non-target signals through signal amplification and filtering processing, and obtaining the user's brain wave data set are specifically as follows:

[0014] S101: Based on the brain wave acquisition device, the brain wave sensor connected to the user's head records the user's brain wave activity in real time, including the frequency, amplitude and spatial distribution of the brain wave, to obtain raw brain wave data;

[0015] S102: Based on the raw brain wave data, high-pass and low-pass filters are applied to process the brain wave data, signal amplification parameters and filtering frequency range are set, low-frequency environmental noise and high-frequency non-target signals are removed, clarity and usability of the data are optimized, and filtered brain wave data are obtained;

[0016] S103: Based on the filtered brain wave data, the brain wave data is timestamped, and the brain wave data is stored and backed up to obtain a user brain wave data set.

[0017] As a further solution of the present invention, based on the user's brain wave data set, the differentiated frequency band activities are analyzed, the intensity of each band is identified and quantified, and the current emotional state of the user is judged by comparing with a preset threshold, and the time point of emotional change is recorded. The steps of obtaining the emotional analysis result are specifically as follows:

[0018] S201: Based on the user's brain wave data set, separate each brain wave frequency band through frequency band analysis, analyze the energy peak and average power of each frequency band, evaluate the activity intensity of each frequency band, and obtain a frequency band intensity analysis result;

[0019] S202: Based on the frequency band intensity analysis result, the frequency band intensity is compared with a preset threshold value related to the emotional state, the emotional state of the current user is identified through logical judgment, and the emotional intensity is evaluated according to the frequency band activity intensity to obtain an emotional state determination result;

[0020] S203: Based on the emotion state determination result, the time point of emotion change is recorded by time stamp, and the emotion state at the differentiated time point is analyzed to monitor the emotion fluctuation and trend to obtain the emotion analysis result.

[0021] As a further solution of the present invention, the formula for evaluating the intensity of emotion according to the intensity of frequency band activity is:

[0022]

[0023] Among them, Q is the emotional intensity index, w i represents the weight coefficient of the ith frequency band, p i represents the activity intensity of the current user in the ith frequency band, t i represents the preset threshold of the emotional state associated with the ith frequency band, and n represents the total number of frequency bands.

[0024] As a further solution of the present invention, based on the emotion analysis result, by searching a preset music database, searching for music tracks matching the emotional state, implementing music playback, and synchronously displaying brain wave data and music playback status through a display interaction interface, receiving user adjustments to music playback, and obtaining real-time music feedback interaction information, the specific steps are:

[0025] S301: Based on the emotion analysis result, access a preset music database, filter music tracks that match the current user's emotional state by emotion tags and emotion intensity, and obtain a music track list;

[0026] S302: Based on the music track list, adjusting the playing start point and end point of each piece of music, and adjusting the playing order, optimizing the fluency of music playing, and obtaining an adjusted playing queue;

[0027] S303: Based on the adjusted play queue, brain wave data and music play status are synchronously displayed on the display interaction interface, and the play adjustment made by the user through the interface is received, including volume adjustment and track switching, to obtain real-time music feedback interaction information.

[0028] As a further solution of the present invention, based on the real-time music feedback display information, the user's brain wave response is monitored in real time, the music parameters are adjusted, and the spatial sound effect settings of the music are adjusted according to the instant feedback of the user's brain waves. The steps of generating the music feedback adjustment information are specifically as follows:

[0029] S401: Based on the real-time music feedback display information, the user's EEG response to the music being played is captured in real time, the corresponding EEG response time and response intensity are recorded, the influence of music playing on the user's EEG activity is analyzed, the changes in emotions and physiological responses are recorded, and the EEG data of music affecting the user is obtained;

[0030] S402: Based on the music-induced EEG data, adjust the parameters of music playback, including volume and tempo, to match the user's instant feedback and obtain a music playback parameter adjustment record;

[0031] S403: Based on the music playback parameter adjustment record, adjust the music space effect, including stereo positioning and channel distribution, according to the user's EEG response, to optimize the overall auditory experience, and record the adjusted music playback settings, including the time point of each adjustment and the corresponding parameter value, to obtain music feedback adjustment information.

[0032] As a further solution of the present invention, based on the music feedback adjustment information, according to the changes in brain waves before and after music playing and adjustment, the influence of music playing adjustment on user emotions is analyzed, and the degree of emotion improvement and user satisfaction index are evaluated. The specific steps of obtaining the user experience evaluation result are as follows:

[0033] S501: Based on the music feedback adjustment information, collect brain wave data before and after the music is played, record changes in key parameters, including brain wave frequency and amplitude, analyze the impact of music before and after playing on brain electrical activity, and generate brain wave change analysis results;

[0034] S502: Based on the brain wave change analysis result, compare the changes in emotional state through quantitative analysis, evaluate the degree of emotional improvement, and obtain an emotional improvement evaluation result;

[0035] S503: Based on the emotion improvement evaluation result and in combination with the user feedback survey data, the user satisfaction index is evaluated to obtain a user experience evaluation result.

[0036] As a further embodiment of the present invention, the formula for evaluating the degree of mood improvement is:

[0037]

[0038] Among them, E is the mood improvement index, μ A Represents the average amplitude of brain waves before music is played, μ B represents the average amplitude of brain waves after music is played, σ A represents the standard deviation of the EEG amplitude before music playing, σ B represents the standard deviation of the brain wave amplitude after music playing, and C is the correction coefficient.

[0039] A music feedback training interface interaction system based on EEG data, the music feedback training interface interaction system based on EEG data is used to execute the above-mentioned music feedback training interface interaction method based on EEG data, the system comprises:

[0040] The brain wave processing module collects the user's brain wave data based on the brain wave acquisition device, removes environmental noise and non-target signals through signal amplification and filtering, and stores the processed brain wave data to obtain the user's brain wave data set;

[0041] The emotion judgment module analyzes the differentiated frequency band activities based on the user's brain wave data set, judges the user's current emotional state, and records the time point of emotional changes to obtain the emotion analysis result;

[0042] The music matching interaction module retrieves music tracks that match the emotional state by searching a preset music database based on the emotion analysis result, plays the music, and synchronously displays the brain wave data and the music playing status through a display interaction interface, receives the user's adjustment of the music playing, and obtains real-time music feedback interaction information;

[0043] The music feedback adjustment module monitors the user's brain wave response in real time based on the real-time music feedback display information, adjusts the music parameters, and adjusts the spatial sound effect settings of the music according to the instant feedback of the user's brain waves to generate music feedback adjustment information;

[0044] The emotion adjustment evaluation module evaluates the degree of emotion improvement and the user's satisfaction index based on the music feedback adjustment information and the changes in brain waves before and after music playing and adjustment to obtain a user experience evaluation result.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, by analyzing the intensity of brain wave frequency bands, quantifying and identifying the differentiated characteristics of the bands, comparing with preset thresholds, judging the user's emotional state, and recording the time points of emotional changes, the accuracy and time sensitivity of emotion recognition are improved. By matching the music tracks with the emotional state, combining the display interaction interface and the user's feedback operation, the real-time linkage between music and the user's current emotion is realized, and the user's emotion regulation effect is effectively optimized. Combined with real-time monitoring of EEG reactions, the rhythm, volume and spatial sound effect settings of the music are adjusted to achieve dynamic adjustment of music output parameters, optimize the demand for emotional intervention, and evaluate emotional improvement and user satisfaction based on the changes in the user's brain waves. It is possible to measure the improvement effect of music intervention on the user's psychological state, ensure the effectiveness of the feedback closed loop, and provide users with a more efficient, accurate and psychologically satisfying music feedback training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0049] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0050] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0051] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0052] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0053] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0054] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] See also Figure 1 The present invention provides a technical solution: a music feedback training interface interaction method based on EEG data, comprising the following steps:

[0061] S1: Based on the brain wave acquisition device, the user's brain wave data is collected, including the frequency, amplitude and spatial distribution of the brain waves. Through signal amplification and filtering, environmental noise and non-target signals are removed, and the processed brain wave data is stored to obtain the user's brain wave data set;

[0062] S2: Based on the user's EEG data set, analyze the activities of differentiated frequency bands, identify and quantify the intensity of each band, and judge the user's current emotional state by comparing it with the preset threshold, and record the time point of emotional changes to obtain the emotional analysis results;

[0063] S3: Based on the emotion analysis results, the preset music database is searched to retrieve music tracks that match the emotional state, and the playback parameters of the tracks are adjusted to create a playback queue, implement music playback, and synchronously display brain wave data and music playback status through the display interaction interface. The user's adjustment of music playback is received through the interactive interface to obtain real-time music feedback interaction information;

[0064] S4: Based on the real-time music feedback display information, the user's EEG response is monitored in real time, and the music parameters are adjusted, including the rhythm speed and volume of the music. According to the instant feedback of the user's EEG, the spatial sound effect settings of the music are adjusted, including stereo positioning and channel distribution, to optimize the spatial effect of the music, and the playback parameters are recorded to generate music feedback adjustment information;

[0065] S5: Based on the music feedback adjustment information, according to the changes in brain waves before and after music playback and adjustment, analyze the impact of music playback adjustment on user emotions, evaluate the degree of emotion improvement and user satisfaction index, and obtain user experience evaluation results.

[0066] The user's EEG data set includes the frequency distribution of α, β and γ waves, the amplitude information of each band and the total power spectrum of the EEG. The emotion analysis results include the user's emotional state label, the timestamp corresponding to the emotional state and the emotion intensity index. The real-time music feedback interaction information includes the music track ID that meets the emotional needs, the playback order of the tracks and the scheduled playback time of each track. The music feedback adjustment information includes the volume adjustment value, the rhythm adjustment frequency, the user's EEG response change data and the instant playback status of the adjusted music. The user experience evaluation results include the comparison of emotional states before and after music intervention, the percentage of emotional improvement and the user satisfaction score.

[0067] See also Figure 2 , based on the brain wave acquisition device, collect the user's brain wave data, including the frequency, amplitude and spatial distribution of the brain wave, remove environmental noise and non-target signals through signal amplification and filtering, store the processed brain wave data, and obtain the user's brain wave data set in the following steps:

[0068] S101: Based on the brain wave acquisition device, the brain wave sensor connected to the user's head records the user's brain wave activity in real time, including the frequency, amplitude and spatial distribution of the brain wave, to obtain raw brain wave data;

[0069] Based on the brain wave acquisition device, the device is calibrated and connected to the user's head through multiple electrodes to collect the original data of brain wave frequency, amplitude and spatial distribution. The data is directly obtained from the brain wave sensor. The device first collects data and transmits the data to the host via cable or wirelessly for subsequent analysis. During the transmission process, the data is encrypted to maintain data security, ensuring that the data is not tampered with or leaked during transmission, and obtaining the original brain wave data.

[0070] S102: Based on the original brain wave data, high-pass and low-pass filters are applied to process the brain wave data, signal amplification parameters and filtering frequency range are set, low-frequency environmental noise and high-frequency non-target signals are removed, the clarity and usability of the data are optimized, and filtered brain wave data are obtained;

[0071] Based on the raw EEG data, high-pass and low-pass filters are used to process the EEG data. By setting specific parameters of the filters, such as setting the cutoff frequency of the high-pass filter to 1 Hz and the cutoff frequency of the low-pass filter to 50 Hz, the parameters are set based on the best practices and laboratory standards determined in previous studies. Signal amplification technology is used to enhance the signal amplitude after the noise is filtered out to maintain the availability of the signal. At the same time, by dynamically monitoring the environmental noise and adjusting the filter settings to adapt to different test conditions, including using real-time signal processing software to evaluate signal interference and instantly adjusting the filter parameters to optimize data capture, the process ensures the high quality and high availability of EEG data, providing a reliable foundation for subsequent data analysis.

[0072] S103: Based on the filtered brain wave data, the brain wave data is timestamped, and the brain wave data is stored and backed up to obtain a user brain wave data set;

[0073] Based on the filtered EEG data, the timestamp technology is used to accurately mark the specific time of collection for each data point, so that specific events or state changes can be tracked in subsequent data analysis. In addition, data backup strategies, such as real-time synchronous storage, are adopted to ensure the security and integrity of data during the collection process. The demand for storage space is reduced by setting data compression parameters. In terms of data management and use, data management software, such as EEG database management software, is used to organize and index data to ensure rapid retrieval and efficient use of data, thereby achieving effective management and efficient use of data.

[0074] See also Figure 3 , based on the user's brain wave data set, analyze the activities of differentiated frequency bands, identify and quantify the intensity of each band, and judge the user's current emotional state by comparing it with the preset threshold, and record the time point of emotional changes. The specific steps to obtain the emotional analysis results are:

[0075] S201: Based on the user's brain wave data set, separate each brain wave frequency band through frequency band analysis, analyze the energy peak and average power of each frequency band, evaluate the activity intensity of each frequency band, and obtain the frequency band intensity analysis result;

[0076] Based on the user's EEG data set, frequency band analysis technology is applied to separate each frequency band in the EEG data. Professional data analysis software such as the signal processing toolbox in MATLAB is used to perform fast Fourier transform to separate each frequency band, and the frequency band data is converted into frequency domain representation in order to identify and analyze the characteristics of each frequency band. For example, the low frequency range is set to 0.5-4Hz, the medium frequency range is 4-8Hz, and the high frequency range is 8-12Hz. The energy peak and average power are calculated for each frequency band. Statistical methods are used to calculate the peak and average power. For example, the energy peak is determined by the square integral of the signal, and the average power of each frequency band is calculated by the average power formula. The numerical value is calculated by an automated algorithm. Finally, the activity intensity of each frequency band is evaluated, and the calculation results are displayed in a chart to provide intuitive data for subsequent analysis.

[0077] S202: Based on the frequency band intensity analysis result, the frequency band intensity is compared with a preset threshold value related to the emotional state, the emotional state of the current user is identified through logical judgment, and the emotional intensity is evaluated according to the frequency band activity intensity to obtain an emotional state determination result;

[0078] The formula for evaluating the intensity of emotion based on the intensity of frequency band activity is:

[0079]

[0080] Among them, Q is the emotional intensity index, w i represents the weight coefficient of the ith frequency band, p i represents the activity intensity of the current user in the ith frequency band, t i represents the preset threshold of the emotional state associated with the ith frequency band, and n represents the total number of frequency bands.

[0081] formula:

[0082]

[0083] The meaning and acquisition method of parameters:

[0084] w i : The weight coefficient of the ith frequency band, representing the importance of the ith frequency band on emotions. This parameter is usually obtained through historical data analysis, analyzing the contribution of the frequency band to different emotional states in history, and using statistical methods such as linear regression analysis to determine the weight of each frequency band.

[0085] p i : The activity intensity of the current user in the i-th frequency band, usually measured directly by EEG detection equipment, expressed as the voltage value or power density of a specific frequency band.

[0086] t i: The preset threshold of the emotional state associated with the ith frequency band. Based on research in psychology and neuroscience, the preset threshold is usually set by professional psychologists or neuroscientists based on large-scale experimental data.

[0087] n: The total number of frequency bands involved in the analysis. It is a fixed value that is pre-set based on the equipment and analysis method used. For example, a common setting is to use the five main EEG frequency bands: δ, θ, α, β, and γ.

[0088] Calculation example:

[0089] Data for three frequency bands are set, and the parameters are set as follows: w1=0.5, w2=0.3, w3=0.2, p1=10, p2=15, p3=5, t1=8, t2=15, t3=3, n=3.

[0090] Calculate the |p for each frequency band i -t i |:

[0091] |p1-t1|=|10-8|=2;

[0092] |p2-t2|=|15-15|=0;

[0093] |p3-t3|=|5-3|=2;

[0094] Compute the weighted sum:

[0095] w1×|p1-t1|=0.5×2=1.0;

[0096] w2×|p2-t2|=0.3×0=0.0;

[0097] w3×|p3-t3|=0.2×2=0.4;

[0098] Sum = 1.0 + 0.0 + 0.4 = 1.4;

[0099] Calculate Q:

[0100]

[0101] The calculation result Q represents the emotional intensity index. The larger the index is, the greater the difference between the user's emotional state and the preset threshold, reflecting the possible abnormal or significant changes in the current user's emotions. In this example, the Q value is 0.808, indicating that there is a certain emotional fluctuation, but not an extreme change.

[0102] S203: Based on the emotion state determination result, the time point of emotion change is recorded by timestamp marking, and the emotion state at the differentiated time point is analyzed to monitor the emotion fluctuation and trend, and obtain the emotion analysis result;

[0103] Based on the results of emotional state determination, the time points of emotional changes are recorded by timestamps, and timestamps are added to each identified emotional state event to ensure the accuracy and timeliness of emotional change records. The generation of timestamps depends on system time and is synchronized with data collection. Every change in emotional state is accurately recorded. Subsequently, by analyzing the emotional state at different time points, monitoring emotional fluctuations and trends, and using trend analysis tools such as time series analysis or sliding average method to analyze emotional change patterns, the main trends and cycles of emotional fluctuations are determined, providing strong data support for mental health experts and obtaining emotional analysis results.

[0104] See also Figure 4 , based on the emotion analysis results, by searching the preset music database, searching for music tracks that match the emotion state, adjusting the playback parameters of the tracks, creating a playback queue, implementing music playback, and synchronously displaying brain wave data and music playback status through the interactive interface, receiving the user's adjustment of music playback through the interactive interface, and obtaining real-time music feedback interaction information. The specific steps are:

[0105] S301: Based on the emotion analysis result, access a preset music database, filter music tracks that match the current user's emotional state by emotion tags and emotion intensity, and obtain a music track list;

[0106] Based on the results of sentiment analysis, the preset music database is connected. By matching the sentiment label and sentiment intensity with the track information in the database, the database uses SQL or NoSQL technology to store a large amount of track information. Each track is marked with sentiment classification such as "happy", "sad" and sentiment intensity indicators. During the matching process, the user's emotional state is read to query all music tracks in the database that match this emotion. Database query languages ​​such as SQL's SELECT and WHERE clauses are used for precise screening. The screening conditions are optimized based on sentiment similarity and user historical preference algorithms. For example, if the user's sentiment label is "happy", music with fast tempo or positive lyrics is given priority. The sentiment intensity is used to adjust the range of song selection to ensure that the selected music best matches the user's current emotional state. Finally, a personalized music track list is obtained to provide users with a music experience that supports emotion regulation.

[0107] S302: Based on the music track list, adjusting the start point and end point of each piece of music, and adjusting the play order, optimizing the smoothness of music play, and obtaining an adjusted play queue;

[0108] Based on the generated music track list, the start and end points of each piece of music are adjusted. During the adjustment process, music editing software or special algorithms are used to analyze the structure of each song and identify appropriate entry and end points. For example, the beat and energy high points of the song are detected through automatic music analysis technology, and the best start and end points are set for each song to ensure that the song can quickly resonate with the user when it is played. At the same time, the playback order is adjusted according to the user's emotional change pattern, and a machine learning model is used to predict the changing trend of the user's emotions. The order of the playlist is adjusted according to the prediction results to make the track flow more natural and in line with the user's emotional fluctuations, and generate an adjusted playback queue.

[0109] S303: Based on the adjusted play queue, the brain wave data and the music play status are synchronously displayed on the display interaction interface, and the play adjustment made by the user through the interface is received, including volume adjustment and track switching, to obtain real-time music feedback interaction information;

[0110] Based on the adjusted playback queue, brain wave graphics and music playback controls are displayed simultaneously on the interactive interface, allowing users to intuitively see the impact of music on their emotions. The interface design uses modern UI / UX design principles to ensure easy operation for users, such as adjusting the volume through a slider and clicking a button to switch tracks. These interactive operations are implemented by front-end technologies such as JavaScript and HTML5, and communicate with the back-end server through WebAPI to ensure real-time response of operations. All user interactive operations are recorded in the server, and real-time music feedback interactive information is obtained.

[0111] See also Figure 5 Based on the real-time music feedback display information, the user's EEG response is monitored in real time, and the music parameters are adjusted, including the rhythm speed and volume of the music. According to the instant feedback of the user's EEG, the spatial sound effect settings of the music are adjusted, including stereo positioning and channel distribution, to optimize the spatial effect of the music, and the playback parameters are recorded. The specific steps of generating music feedback adjustment information are as follows:

[0112] S401: Based on the real-time music feedback display information, the user's EEG response to the music being played is captured in real time, the corresponding EEG response time and response intensity are recorded, the impact of music playing on the user's EEG activity is analyzed, the changes in emotions and physiological responses are recorded, and the EEG data of music impact is obtained;

[0113] Based on real-time music feedback display information, real-time captured EEG response data is collected through EEG equipment. The collected data includes but is not limited to the frequency and amplitude of brain waves. Real-time analysis is performed through software to identify and parse specific patterns in brain waves. The patterns are closely related to emotional changes caused by music. For example, happy emotions may be manifested as increased beta wave activity, and sad emotions may lead to an increase in alpha waves. In addition, the system also records the response intensity, that is, the change in brain wave amplitude, in real time to quantify the impact of music on user emotions. The data are synchronized through high-precision timestamps to ensure accurate matching of data and accuracy of subsequent analysis.

[0114] S402: Based on the EEG data of music affecting music, the parameters of music playing, including volume and rhythm speed, are adjusted to match the user's instant feedback, and a music playing parameter adjustment record is obtained;

[0115] Based on the fact that music affects EEG data, the adjustment of music playback parameters is based on the results of real-time EEG data analysis. For example, if the analysis results show that the user's EEG activity shows signs of relaxation under a certain musical rhythm, the rhythm of the music will be automatically slowed down and the volume may be increased to enhance the relaxation effect. Conversely, if the user shows excitement or pleasure, the rhythm will be adjusted faster and the volume will be louder accordingly. The adjustment is achieved through dynamic feedback, and it will continuously learn and adapt to user feedback according to preset feedback rules and algorithms to optimize the user's auditory experience. All adjustments are recorded in the log, including the time point and parameter value of the adjustment, for easy tracking and analysis.

[0116] S403: Based on the music playback parameter adjustment record, according to the user's EEG response, adjust the music space effect, including stereo positioning and channel distribution, to optimize the overall auditory experience, and record the adjusted music playback settings, including the time point and corresponding parameter value of each adjustment, to obtain music feedback adjustment information;

[0117] Based on the adjustment records of music playback parameters, audio processing technology is used to optimize the stereo effect. The direction and distribution of the sound are adjusted according to the user's EEG response. For example, if the user shows a more positive response to a specific channel configuration, the output of this channel will be enhanced and the output of other channels will be reduced. Such adjustments are intended to enhance the user's emotional experience by changing the spatial distribution of sound. The specific parameters of each adjustment, such as channel strength and direction, are also recorded to ensure that the adjustment can be reproduced in subsequent playback, thereby providing users with a consistent auditory experience. All adjustments are fed back to the user through the user interface to ensure transparency and controllability.

[0118] See also Figure 6Based on the music feedback adjustment information, according to the changes in brain waves before and after music playing and adjustment, the impact of music playing adjustment on user emotions is analyzed, and the degree of emotion improvement and user satisfaction index are evaluated. The specific steps to obtain the user experience evaluation results are as follows:

[0119] S501: Based on the music feedback adjustment information, collect brain wave data before and after the music is played, record the changes in key parameters, including the frequency and amplitude of the brain waves, analyze the impact of the music before and after the music is played on the brain electrical activity, and generate brain wave change analysis results;

[0120] Based on the music feedback adjustment information, the baseline EEG data before music playing is recorded in real time through high-precision EEG acquisition equipment. The data includes the activity of specific brain wave frequency bands such as α wave, β wave, θ wave and δ wave. The changes in the frequency bands continue to be monitored during the music playing, with special attention to the amplitude changes and frequency adjustments caused by music. The data is processed and analyzed by EEG analysis software. The software can automatically identify and record the key moments and degree of brain wave changes. The analysis results highlight the specific areas and degrees of the impact of music on EEG activity, so as to evaluate the influence of music and provide data support for mood improvement research.

[0121] S502: Based on the results of the brain wave change analysis, compare the changes in the emotional state through quantitative analysis, evaluate the degree of emotional improvement, and obtain an emotional improvement evaluation result;

[0122] The formula for assessing the degree of mood improvement is:

[0123]

[0124] Among them, E is the mood improvement index, μ A Represents the average amplitude of brain waves before music is played, μ B represents the average amplitude of brain waves after music is played, σ A represents the standard deviation of the EEG amplitude before music playing, σ B represents the standard deviation of the brain wave amplitude after music playing, and C is the correction coefficient.

[0125] formula:

[0126]

[0127] The meaning and acquisition method of parameters:

[0128] μ A and μ B : The parameter represents the average amplitude of brain waves before and after music is played. It is usually measured by brain wave detection equipment and is calculated as the arithmetic mean of all amplitude values ​​within a specified time.

[0129] σ Aand σ B : The parameter represents the standard deviation of the EEG amplitude before and after the music is played, which is used to measure the variability or dispersion of the amplitude values. The standard deviation is calculated by taking the square root of the mean of the sum of the squares of the deviations of the amplitude values ​​from their mean.

[0130] C: Correction factor is an empirical parameter used to adjust the sensitivity of the final mood improvement assessment. This factor can be determined based on a pre-conducted validation study to ensure that the calculated results match the actual mood improvement.

[0131] Calculation example:

[0132] Setting data: Data before music playback: μ A =50μV,σ A =5μV; Data after music playing: μ B =60μV,σ B =4μV; correction coefficient: C=10.

[0133] Calculate the absolute value of the mean amplitude difference: |μ A -μ B |=|50-60|=10μV;

[0134] Calculate the sum of standard deviations: σ A +σ B =5+4=9μV;

[0135] Plug in the correction factor and calculate the final mood improvement percentage:

[0136]

[0137] The calculation result E=11.11 represents the change in brain wave amplitude before and after music playing relative to the standardized value of its variability, multiplied by the correction coefficient, to obtain the degree of mood improvement. The larger this value is, the more significant the positive impact of music on the user's mood is. The mood improvement degree of 11.11 indicates that music playing has a significant positive impact on brain wave activity and has significantly improved the user's emotional state.

[0138] S503: Based on the emotion improvement evaluation result and in combination with the user feedback survey data, the user satisfaction index is evaluated to obtain the user experience evaluation result;

[0139] Based on the results of the emotion improvement evaluation, the evaluation includes quantitative measurement of user satisfaction after music therapy, and the use of structured questionnaires to collect user feedback. The questionnaire design covers user evaluations of music selection, volume setting, and satisfaction with the impact of music on emotions. The questionnaire data is processed through data analysis software to calculate the user satisfaction index, which comprehensively considers the user's evaluation of music playback effects, emotional changes, and overall experience. The results will directly reflect the overall effect of music therapy and user acceptance, and provide important indicators for optimizing music therapy programs.

[0140] See also Figure 7 , a music feedback training interface interaction system based on EEG data, a music feedback training interface interaction system based on EEG data is used to execute the above-mentioned music feedback training interface interaction method based on EEG data, and the system includes:

[0141] The brain wave processing module collects the user's brain wave data based on the brain wave acquisition device, removes environmental noise and non-target signals through signal amplification and filtering, and stores the processed brain wave data to obtain the user's brain wave data set;

[0142] The emotion judgment module analyzes the activities of differentiated frequency bands based on the user's brain wave data set, determines the user's current emotional state, and records the time point of emotional changes to obtain the emotion analysis results;

[0143] The music matching interaction module searches the preset music database based on the emotion analysis results, retrieves the music tracks that match the emotion state, plays the music, and synchronously displays the brain wave data and the music playing status through the display interaction interface, receives the user's adjustment of the music playing, and obtains real-time music feedback interaction information;

[0144] The music feedback adjustment module monitors the user's EEG response in real time based on the real-time music feedback display information, adjusts the music parameters, and adjusts the spatial sound effect settings of the music according to the instant feedback of the user's brain waves to generate music feedback adjustment information;

[0145] The emotion adjustment evaluation module is based on the music feedback adjustment information and the changes in brain waves before and after music playing and adjustment to evaluate the degree of emotion improvement and the user's satisfaction index to obtain the user experience evaluation results.

[0146] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0147] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0148] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0149] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0151] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0154] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0155] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A music feedback training interface interaction method based on EEG data, characterized in that: The following steps are involved: S1: Based on the EEG acquisition device, the user's EEG data is collected, and the environmental noise and non-target signals are removed through signal amplification and filtering to obtain the user's EEG data set; S2: Based on the user's brain wave data set, analyze the activities of the differentiated frequency bands, identify and quantify the intensity of each band, and judge the user's current emotional state by comparing it with a preset threshold, and record the time point of emotional changes to obtain emotional analysis results; S3: Based on the emotion analysis result, the preset music database is searched to retrieve music tracks that match the emotional state, the music is played, and the brain wave data and the music playing status are synchronously displayed through the display interaction interface, the user's adjustment of the music playing is received, and real-time music feedback interaction information is obtained; S4: Based on the real-time music feedback display information, the user's brain wave response is monitored in real time, the music parameters are adjusted, and according to the instant feedback of the user's brain waves, the spatial sound effect settings of the music are adjusted to generate music feedback adjustment information; S5: Based on the music feedback adjustment information, according to the changes in brain waves before and after music playing and adjustment, analyze the impact of music playing adjustment on user emotions, evaluate the degree of emotion improvement and user satisfaction index, and obtain user experience evaluation results.

2. The music feedback training interface interaction method based on EEG data according to claim 1 is characterized in that: The user's brain wave data set includes the frequency distribution of α, β and γ waves, the amplitude information of each band and the total power spectrum of the brain waves. The emotion analysis result includes the user's emotional state label, the timestamp corresponding to the emotional state and the emotion intensity index. The real-time music feedback interaction information includes the music track ID that meets the emotional needs, the playback order of the tracks and the scheduled playback time of each track. The music feedback adjustment information includes the volume adjustment value, the rhythm adjustment frequency, the user's brain wave response change data and the instant playback status of the adjusted music. The user experience evaluation result includes the comparison of emotional states before and after music intervention, the percentage of emotional improvement and the user satisfaction score.

3. The music feedback training interface interaction method based on EEG data according to claim 1 is characterized in that: Based on the brain wave acquisition device, the user's brain wave data is collected, and the environmental noise and non-target signals are removed through signal amplification and filtering. The specific steps to obtain the user's brain wave data set are as follows: S101: Based on the brain wave acquisition device, the brain wave sensor connected to the user's head records the user's brain wave activity in real time, including the frequency, amplitude and spatial distribution of the brain wave, to obtain raw brain wave data; S102: Based on the raw brain wave data, high-pass and low-pass filters are applied to process the brain wave data, signal amplification parameters and filtering frequency range are set, low-frequency environmental noise and high-frequency non-target signals are removed, clarity and usability of the data are optimized, and filtered brain wave data are obtained; S103: Based on the filtered brain wave data, the brain wave data is timestamped, and the brain wave data is stored and backed up to obtain a user brain wave data set.

4. The music feedback training interface interaction method based on EEG data according to claim 1, characterized in that: Based on the user's brain wave data set, the differentiated frequency band activities are analyzed, the intensity of each band is identified and quantified, and the current emotional state of the user is judged by comparing with the preset threshold, and the time point of emotional change is recorded. The steps for obtaining the emotional analysis result are specifically as follows: S201: Based on the user's brain wave data set, separate each brain wave frequency band through frequency band analysis, analyze the energy peak and average power of each frequency band, evaluate the activity intensity of each frequency band, and obtain a frequency band intensity analysis result; S202: Based on the frequency band intensity analysis result, the frequency band intensity is compared with a preset threshold value related to the emotional state, the emotional state of the current user is identified through logical judgment, and the emotional intensity is evaluated according to the frequency band activity intensity to obtain an emotional state determination result; S203: Based on the emotion state determination result, the time point of emotion change is recorded by time stamp, and the emotion state at the differentiated time point is analyzed to monitor the emotion fluctuation and trend to obtain the emotion analysis result.

5. The music feedback training interface interaction method based on EEG data according to claim 4 is characterized in that: The formula for evaluating the intensity of emotion based on the intensity of frequency band activity is: Among them, Q is the emotional intensity index, w i represents the weight coefficient of the ith frequency band, p i represents the activity intensity of the current user in the ith frequency band, t i represents the preset threshold of the emotional state associated with the ith frequency band, and n represents the total number of frequency bands.

6. The music feedback training interface interaction method based on EEG data according to claim 1, characterized in that: Based on the emotion analysis result, the steps of searching a preset music database, retrieving music tracks matching the emotion state, playing music, synchronously displaying brain wave data and music playing status through a display interaction interface, receiving user adjustments to music playing, and obtaining real-time music feedback interaction information are as follows: S301: Based on the emotion analysis result, access a preset music database, filter music tracks that match the current user's emotional state by emotion tags and emotion intensity, and obtain a music track list; S302: Based on the music track list, adjusting the playing start point and end point of each piece of music, and adjusting the playing order, optimizing the fluency of music playing, and obtaining an adjusted playing queue; S303: Based on the adjusted play queue, brain wave data and music play status are synchronously displayed on the display interaction interface, and the play adjustment made by the user through the interface is received, including volume adjustment and track switching, to obtain real-time music feedback interaction information.

7. The music feedback training interface interaction method based on EEG data according to claim 1, characterized in that: Based on the real-time music feedback display information, the user's brain wave response is monitored in real time, the music parameters are adjusted, and the spatial sound effect settings of the music are adjusted according to the instant feedback of the user's brain waves. The steps of generating the music feedback adjustment information are specifically as follows: S401: Based on the real-time music feedback display information, the user's EEG response to the music being played is captured in real time, the corresponding EEG response time and response intensity are recorded, the influence of music playing on the user's EEG activity is analyzed, the changes in emotions and physiological responses are recorded, and the EEG data of music affecting the user is obtained; S402: Based on the music-induced EEG data, adjust the parameters of music playback, including volume and tempo, to match the user's instant feedback and obtain a music playback parameter adjustment record; S403: Based on the music playback parameter adjustment record, adjust the music space effect, including stereo positioning and channel distribution, according to the user's EEG response, to optimize the overall auditory experience, and record the adjusted music playback settings, including the time point of each adjustment and the corresponding parameter value, to obtain music feedback adjustment information.

8. The music feedback training interface interaction method based on EEG data according to claim 1, characterized in that: Based on the music feedback adjustment information, according to the brain wave changes before and after the music playing and adjustment, the influence of the music playing adjustment on the user's emotions is analyzed, and the degree of emotion improvement and the user's satisfaction index are evaluated. The steps of obtaining the user experience evaluation result are specifically as follows: S501: Based on the music feedback adjustment information, collect brain wave data before and after the music is played, record changes in key parameters, including brain wave frequency and amplitude, analyze the impact of music before and after playing on brain electrical activity, and generate brain wave change analysis results; S502: Based on the brain wave change analysis result, compare the changes in emotional state through quantitative analysis, evaluate the degree of emotional improvement, and obtain an emotional improvement evaluation result; S503: Based on the emotion improvement evaluation result and in combination with the user feedback survey data, the user satisfaction index is evaluated to obtain a user experience evaluation result.

9. The music feedback training interface interaction method based on EEG data according to claim 8, characterized in that: The formula for evaluating the degree of mood improvement is: Among them, E is the mood improvement index, μ A Represents the average amplitude of brain waves before music is played, μ B represents the average amplitude of brain waves after music is played, σ A represents the standard deviation of the EEG amplitude before music playing, σ B represents the standard deviation of the brain wave amplitude after music playing, and C is the correction coefficient.

10. Music feedback training interface interaction system based on EEG data, characterized in that: According to any one of claims 1 to 9, the music feedback training interface interaction method based on EEG data comprises: The brain wave processing module collects the user's brain wave data based on the brain wave acquisition device, removes environmental noise and non-target signals through signal amplification and filtering, and stores the processed brain wave data to obtain the user's brain wave data set; The emotion judgment module analyzes the differentiated frequency band activities based on the user's brain wave data set, judges the user's current emotional state, and records the time point of emotional changes to obtain the emotion analysis result; The music matching interaction module retrieves music tracks that match the emotional state by searching a preset music database based on the emotion analysis result, plays the music, and synchronously displays the brain wave data and the music playing status through a display interaction interface, receives the user's adjustment of the music playing, and obtains real-time music feedback interaction information; The music feedback adjustment module monitors the user's brain wave response in real time based on the real-time music feedback display information, adjusts the music parameters, and adjusts the spatial sound effect settings of the music according to the instant feedback of the user's brain waves to generate music feedback adjustment information; The emotion adjustment evaluation module evaluates the degree of emotion improvement and the user's satisfaction index based on the music feedback adjustment information and the changes in brain waves before and after music playing and adjustment to obtain a user experience evaluation result.

Images