An audio AI playback method and system based on music therapy

Abstract

The present invention discloses an audio AI playback method and system based on music therapy, which relates to the technical field of music therapy. The system uses a first physiological data detection module and a second physiological data detection module to collect the user's physiological data before and after music therapy in real time through a physiological monitoring bracelet, and constructs a first and a second physiological data set. This measure realizes the transformation of music therapy from subjective experience to objective data, so that the treatment process can be carried out according to the user's real physiological response. By carefully analyzing the music attribute index Yyz of each piece of music in the music library and associating it with the user's second physiological index SLz2, the system can intelligently evaluate the actual effect of music therapy. The calculation of the therapeutic effect value lxz not only provides direct evidence of the presence or absence of therapeutic effect, but also can distinguish the efficiency of different music in improving the user's physiological state. The system automatically pushes effective music to improve user satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of music therapy, and in particular to an audio AI playback method and system based on music therapy. Background Art

[0002] As an important part of non-drug intervention, music therapy has shown broad application prospects in the fields of psychology and physical and mental health. However, traditional music therapy often relies on the professional judgment and personal experience of therapists, coupled with the consideration of individual differences among patients, which makes the entire treatment process subjective and uncertain. Specifically, the lack of precise quantitative data support means that the formulation of treatment plans and the evaluation of their effects are mostly based on qualitative perceptions and feedback rather than objective physiological indicators. This limitation not only limits the consistency and repeatability of treatment plans, but also affects the reliability and verifiability of the therapeutic effect, thus posing a challenge to the effectiveness of music therapy.

[0003] On the other hand, individuals' responses to music are highly specific, which means that the same piece of music may produce completely different physiological and psychological effects on different people. Traditional music therapy fails to fully consider the personalized needs at this level, and often adopts a one-size-fits-all model, making it difficult to make timely and accurate adjustments to the music content based on the specific conditions of each patient. This universal treatment strategy ignores individual differences and cannot effectively stimulate the maximum potential of music therapy, which may weaken the effectiveness of treatment and reduce patient satisfaction with the treatment process. In addition, the subjectivity of therapists in selecting and fine-tuning music, as well as their reliance on patients' self-reports and intuitive observations when evaluating treatment effects, have limited the scientific and refined development of music therapy and hindered the continuous optimization and innovation of treatment plans. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an audio AI playback method and system based on music therapy to solve the problems mentioned in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an audio AI playback method and system based on music therapy, including a first physiological data detection module, a music preset analysis module, a second physiological data detection module, a therapeutic effect prediction module and a push module; the first physiological data detection module is used to collect the user's physiological data before the music therapy process through a physiological monitoring bracelet, construct a first physiological data set, and calculate and analyze the first physiological data set to obtain the first physiological index SLz1 of each user; the music preset analysis module is used to detect and analyze each piece of music in the preset music library to obtain the music attribute index Yyz of each piece of music: the second physiological data detection module is used to collect the user's physiological data during the music therapy process through a physiological monitoring bracelet Processing data, construct a second physiological data set, and associate the music attribute index Yyz of each piece of music according to the processed second physiological data set to construct a second physiological index SLz2; the efficacy prediction module is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1, and obtain the efficacy value lxz. If the efficacy value lxz is positive, it means that the music therapy is effective. If the efficacy value lxz is zero or a negative number, it means that the music therapy is ineffective; when the efficacy value lxz is positive, the current music is classified into the first priority efficacy list; the push module compares and evaluates the efficacy value lxz in the first priority efficacy list with the step threshold, generates the corresponding first priority playlist, second priority playlist and third priority playlist, and pushes them to the user.

[0008] Preferably, the first physiological data detection module includes a first acquisition unit and a first calculation unit;

[0009] The first collection unit is used to collect physiological data of the user before listening to music through a physiological monitoring bracelet to construct a first physiological data set, the first physiological data set including: a first blood pressure xy1, a first skin conductivity pf1, a first average sleeping time rs1 and a first meditation index Ms1;

[0010] The first meditation index Ms1 is calculated by the following formula:

[0011]

[0012] In the formula, represents the number of breathing samples before music therapy, represents the respiratory frequency value of the i+1th sample, Represents the respiratory frequency value of the i-th sample; It represents the difference between the breathing frequency of the i+1th sample and the breathing frequency of the ith sample. represents the preset breathing frequency interval difference; M represents the number of heart rate samples before music therapy, represents the i+1th sample heart rate, represents the heart rate value of the i-th sample, represents the heart rate of the i+1th sample and the heart rate increment of the ith sample, Indicates the preset heart rate increment difference; and Respectively represent weight values, which are adjusted by the user, and , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet.

[0013] Preferably, the first calculation unit is used to calculate and obtain the first physiological index SLz1. The first physiological index SLz1 is obtained by extracting the first blood pressure xy1, the first skin conductivity pf1, the first average sleep time rs1 and the first meditation index Ms1 in the first physiological data set, and after dimensionless processing, the first physiological index SLz1 is calculated by the following formula:

[0014]

[0015] In the formula, and They respectively represent the weight values ​​of the first blood pressure xy1, the first skin conductivity pf1, the first average sleeping time rs1 and the first meditation index Ms1, which are adjusted and set by the user. , , , , , It is represented as the first corrected normal value; the first blood pressure xy1 and the first skin conductivity pf1 are measured and obtained by the pressure sensor and the skin conductivity sensor built into the physiological monitoring bracelet respectively.

[0016] Preferably, the music preset analysis module also includes a feature extraction unit and an analysis unit, the feature extraction unit is used to perform digital signal processing on each piece of music in the music library to extract music parameter features, including: average volume yl, average rhythm jz, average frequency spectrum pl, average number of beats jp, average white noise bz and average instantaneous loudness ss;

[0017] The average volume yl is measured and obtained by the built-in DSP digital signal processor of the physiological monitoring bracelet;

[0018] The average rhythm jz is measured and obtained through the smart audio device built into the physiological monitoring bracelet;

[0019] The average frequency spectrum pl is measured and obtained by the built-in spectrum analyzer of the physiological monitoring bracelet;

[0020] The average white noise bz is measured and obtained by the noise analyzer built into the physiological monitoring bracelet;

[0021] The average instantaneous loudness ss is measured and obtained by the loudness analyzer built into the physiological monitoring bracelet;

[0022] The analysis unit is used to construct a music attribute index Yyz based on the music parameter characteristics: the music attribute index Yyz is obtained by extracting the average volume yl, average rhythm jz, average frequency spectrum pl, average number of beats jp, average white noise bz and average instantaneous loudness ss, and after dimensionless processing, constructing a music therapy attribute database, and calculating the music attribute index Yyz by the following formula:

[0023]

[0024] In the formula, , , , They represent the weight values ​​of average volume yl, average rhythm jz, average frequency spectrum pl, average white noise bz and average instantaneous loudness ss, respectively, and are adjusted by the user. , , , , , 2 3 4 5=1, Indicates the third normal value.

[0025] Preferably, the second physiological data detection module includes a second acquisition unit and a second calculation unit;

[0026] The second acquisition unit is used to collect physiological data of the user during the music therapy process through a physiological monitoring bracelet to construct a second physiological data set, where the second physiological data set includes: a second blood pressure xy2, a second skin conductivity pf2, a second average sleeping time rs2, and a second meditation index Ms2;

[0027] The physiological data of the user during the music therapy is collected through the physiological monitoring bracelet to construct a second physiological data set, and the processed second physiological data set is associated with the music attribute index Yyz of each song to generate the second physiological index SLz2 through the following formula;

[0028] The second meditation index Ms2 is calculated by the following formula:

[0029]

[0030] In the formula, Represents the number of breathing samples after music therapy, represents the breathing frequency value of the j+1th sample after music therapy, represents the respiratory frequency value of the jth sample; It represents the difference between the breathing frequency of the j+1th sample and the breathing frequency of the jth sample after music therapy. 2 represents the preset breathing frequency interval difference; R represents the number of heart rate samples after music therapy. represents the j+1th sample heart rate after music therapy, represents the jth sample heart rate value after music therapy, represents the j+1th sample heart rate and the jth sample heart rate increment after music therapy, 2 indicates the preset heart rate increment difference; , and Respectively represent weight values, which are adjusted by the user, and , , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet;

[0031] The second calculation unit is used to calculate and obtain the second physiological index SLz2. The second physiological index SLz2 is obtained by extracting the second blood pressure xy2, the second skin conductivity pf2, the second average sleep time rs2 and the second meditation index Ms2 in the second physiological data set, and after dimensionless processing, the second physiological index SLz2 is calculated by the following formula:

[0032]

[0033] In the formula, represents the difference between the second blood pressure and the first blood pressure, represents the difference between the second skin conductivity and the first skin conductivity, represents the difference between the second average sleep onset time and the first average sleep onset time, It represents the difference between the second meditation index and the first meditation index. , , and The weight values ​​respectively represent the difference between the second blood pressure and the first blood pressure, the difference between the second skin conductivity and the first skin conductivity, the difference between the second average sleep time and the first average sleep time, and the difference between the second meditation index and the first meditation index, which are adjusted and set by the user. , , , , , Indicates the second corrected normal value.

[0034] Preferably, the efficacy estimation module includes a difference calculation unit and an efficacy evaluation unit;

[0035] The difference calculation unit is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1, and obtain the therapeutic effect value lxz by the following formula:

[0036] .

[0037] Preferably, the efficacy evaluation unit is used to evaluate the efficacy value lxz to obtain a first evaluation result, including:

[0038] If the calculated lxz>0, it means that the music therapy has produced a positive physiological effect, that is, the music therapy is effective;

[0039] On the contrary, if lxz is equal to zero or less than zero, i.e., lxz ≤ 0, it means that music therapy fails to induce significant positive physiological changes and can be regarded as ineffective or unsatisfactory.

[0040] When lxz is confirmed to be a positive value, the system will automatically classify the currently playing music into the first priority therapeutic effect list and recommend the most effective music therapy option for each user.

[0041] First, the operation process of the push module is as follows:

[0042] The push module performs a graded evaluation based on the calculated positive efficacy value lxz, including:

[0043] The step threshold includes a first level threshold X1 and a second level threshold X2, and the first level threshold X1> the second level threshold X2; and the positive therapeutic effect value lxz is compared with the first level threshold X1 and the second level threshold X2 respectively, including:

[0044] The therapeutic effect value lxz<the second level threshold value X2, indicating that the music therapeutic effect belongs to the low level category, and a third priority playlist is generated;

[0045] The second level threshold value X2≤the therapeutic effect value lxz≤the first level threshold value X1, indicating that the music therapeutic effect belongs to the intermediate category, and a second priority playlist is generated;

[0046] The therapeutic effect value lxz> the first level threshold value X1, the music therapeutic effect belongs to the advanced category, and the first priority playlist is generated;

[0047] The first priority playlist, the second priority playlist, and the third priority playlist are pushed according to the order of priority.

[0048] The preferred steps include:

[0049] Step 1, collecting physiological data before music therapy: before the user is treated, the user is equipped with a unique physiological monitoring bracelet, and the physiological data of the user before listening to music is collected through the physiological monitoring bracelet to construct a first physiological data set, and the first physiological index SLz1 of each user is obtained by calculation and analysis based on the first physiological data set;

[0050] Step 2: Score the music attribute of each piece of music: Used to detect and analyze each piece of music in the preset music library to obtain the music attribute index Yyz of each piece of music:

[0051] Step 3: Collect physiological data after music therapy: collect the physiological data of the user during music therapy through the physiological monitoring bracelet, construct a second physiological data set, and associate the music attribute index Yyz of each piece of music based on the processed second physiological data set to construct a second physiological index SLz2;

[0052] Step 4: Preliminary evaluation of whether each music therapy produces therapeutic effect: Calculate the difference between the second physiological index SLz2 and the first physiological index SLz1 to obtain the therapeutic effect value lxz. If the therapeutic effect value lxz is positive, it means that the music therapy is effective. If the therapeutic effect value lxz is zero or negative, it means that the music therapy is ineffective. When the therapeutic effect value lxz is positive, classify the current music into the first priority therapeutic effect list.

[0053] Step 5: Multi-level evaluation and push: Compare and grade the efficacy value lxz in the first priority efficacy list with the step threshold, generate the corresponding first priority playlist, second priority playlist and third priority playlist, and push them to the user.

[0054] (III) Beneficial effects

[0055] The present invention provides an audio AI playback method and system based on music therapy, which has the following beneficial effects:

[0056] (1) First, the system introduces music therapy driven by physiological data. By using the first physiological data detection module and the second physiological data detection module, the system collects the user's physiological data before and after music therapy in real time through the physiological monitoring bracelet, and constructs the first physiological data set and the second physiological data set. This measure realizes the transformation of music therapy from subjective experience to objective data, so that the treatment process can be carried out based on the user's real physiological reactions, rather than just intuition or experience. This data-based therapy greatly improves the targetedness and personalization of the treatment, ensuring that music can more accurately touch the unique physiological and psychological needs of each user.

[0057] (2) Secondly, the combination of the music preset analysis module and the efficacy prediction module has created a new path for efficacy prediction and verification; by carefully analyzing the music attribute index Yyz of each piece of music in the music library and associating it with the user's second physiological index SLz2, the system can intelligently evaluate the actual effect of music therapy. The calculation of the efficacy value lxz not only provides direct evidence of the efficacy, but also distinguishes the efficiency of different music in improving the user's physiological state, providing a scientific basis for subsequent music selection. This music recommendation mechanism based on efficacy value classification ensures that each music playback is the optimal choice based on the user's individual response, thereby significantly improving the treatment effect and user satisfaction.

[0058] (3) Finally, the design of the push module further optimizes the user experience. By comparing the therapeutic value lxz with the step threshold, the system automatically creates the first priority playlist, the second priority playlist, and the third priority playlist. This hierarchical recommendation mechanism not only improves the efficiency of music therapy, but also enhances the user's sense of participation and autonomy. Users can flexibly adjust the order of music playback according to their own preferences and actual efficacy feedback, and enjoy a more personalized and efficient music therapy experience. At the same time, this dynamically updated playlist can also promote the continuous optimization of the music library, ensuring that the music therapy plan keeps pace with the times, constantly adapting to the changing needs of users, and achieving long-term health management goals.

[0059] In summary, this technical solution comprehensively improves the scientificity, effectiveness and personalization of music therapy and increases user satisfaction through physiological data collection, music attribute analysis, quantitative evaluation of therapeutic effects and intelligent playlist generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a block diagram flow chart of an audio AI playback system based on music therapy of the present invention;

[0061] Figure 2 The present invention is a schematic diagram of the steps of an audio AI playing method based on music therapy. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] See also Figure 1, the present invention provides an audio AI playback system based on music therapy, including a first physiological data detection module, a music preset analysis module, a second physiological data detection module, a therapeutic effect prediction module and a push module;

[0065] The first physiological data detection module is used to collect the physiological data of the user before the music therapy process through the physiological monitoring bracelet, construct a first physiological data set, and calculate and analyze the first physiological data set to obtain a first physiological index SLz1 of each user;

[0066] The music preset analysis module is used to detect and analyze each piece of music in the preset music library to obtain the music attribute index Yyz of each piece of music:

[0067] The second physiological data detection module is used to collect the physiological data of the user during the music therapy process through the physiological monitoring bracelet, construct a second physiological data set, and associate the music attribute index Yyz of each piece of music according to the processed second physiological data set to construct a second physiological index SLz2;

[0068] The therapeutic effect estimation module is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1 to obtain the therapeutic effect value lxz. If the therapeutic effect value lxz is positive, it means that the music therapy is effective. If the therapeutic effect value lxz is zero or negative, it means that the music therapy is ineffective. When the therapeutic effect value lxz is positive, the current music is classified into the first priority therapeutic effect list;

[0069] The push module compares and grades the efficacy value lxz in the first priority efficacy list with the step threshold, generates the corresponding first priority playlist, second priority playlist and third priority playlist, and pushes them to the user.

[0070] In this embodiment, the purpose is to achieve personalized music therapy by intelligently analyzing the relationship between the user's physiological reactions and music attributes. The core components of the system include a physiological data detection module, a music preset analysis module, an efficacy prediction module and an intelligent push module, which work together to provide users with a customized music therapy experience.

[0071] First, the physiological monitoring bracelet collects the user's heart rate, blood pressure, skin conductivity and other physiological indicators before and after music playing, and constructs the first and second physiological data sets. These data are converted into the first physiological index SLz1 and the second physiological index SLz2 after calculation, representing the physiological state before and after treatment respectively. At the same time, the music preset analysis module conducts an in-depth analysis of each track in the music library, extracts music attributes such as volume, rhythm, and frequency, and forms a music attribute index Yyz, laying the foundation for subsequent efficacy evaluation.

[0072] Secondly, the efficacy prediction module evaluates the effectiveness of music therapy by comparing the physiological indexes before and after music therapy, that is, calculating the difference lxz between SLz2 and SLz1. If lxz is positive, it means that music therapy has a positive effect on improving physiological status, otherwise the effect is not obvious. All music with significant efficacy will be classified into the first priority efficacy list.

[0073] Finally, the push module uses a step threshold to classify the therapeutic effect value lxz, and divides the music therapy effect into three levels: high, medium, and low, corresponding to the first priority playlist, the second priority playlist, and the third priority playlist respectively; this classification mechanism ensures that users can receive the music that best suits their physiological needs first, thereby improving the overall effect of music therapy. The entire system continuously optimizes music selection through closed-loop feedback, realizes the personalization and intelligence of music therapy, and brings users more accurate and efficient means of health promotion.

[0074] Example 2

[0075] For details, please refer to Figure 1 , the first physiological data detection module includes a first acquisition unit and a first calculation unit;

[0076] The first collection unit is used to collect physiological data of the user before listening to music through a physiological monitoring bracelet to construct a first physiological data set, the first physiological data set including: a first blood pressure xy1, a first skin conductivity pf1, a first average sleeping time rs1 and a first meditation index Ms1;

[0077] The first meditation index Ms1 is calculated by the following formula:

[0078]

[0079] In the formula, represents the number of breathing samples before music therapy, represents the respiratory frequency value of the i+1th sample, Represents the respiratory frequency value of the i-th sample; It represents the difference between the breathing frequency of the i+1th sample and the breathing frequency of the ith sample. represents the preset breathing frequency interval difference; M represents the number of heart rate samples before music therapy, represents the i+1th sample heart rate, represents the heart rate value of the i-th sample, represents the heart rate of the i+1th sample and the heart rate increment of the ith sample, Indicates the preset heart rate increment difference; and Respectively represent weight values, which are adjusted by the user, and , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet.

[0080] In this embodiment, the core is to accurately measure and quantify the user's physiological response to provide a scientific basis for subsequent music therapy. The solution is mainly executed by the first physiological data detection module, which is specifically divided into two parts: the first acquisition unit and the first calculation unit, aiming to construct a comprehensive first physiological data set to reflect the user's physical condition before listening to music.

[0081] The first collection unit uses a physiological monitoring bracelet to non-sensibly collect a series of key physiological parameters, including the first blood pressure xy1, the first skin conductivity pf1, the first average sleep time rs1, and a unique indicator - the meditation index Ms1; among them, the meditation index is calculated by analyzing the changes in breathing frequency and heart rate, involving the number of breathing and heart rate samples and their changing patterns, supplemented by user-adjustable weight values ​​to ensure personalized considerations.

[0082] Specifically, the calculation of the first meditation index Ms1 covers the dynamic monitoring of breathing rate and heart rate. It not only records the differences between consecutive samples, but also considers the comparison with preset standards, such as the difference in breathing rate intervals and the difference in heart rate increments. These data are captured in real time by built-in sensors and then processed by the first calculation unit using complex algorithms to finally obtain a comprehensive index reflecting the individual's level of psychological and physiological calmness.

[0083] This technical solution provides a solid foundation for personalized recommendations for music therapy through precise data collection and analysis. It can objectively evaluate the physiological state before music therapy, ensure that subsequent music selection can more accurately meet the user's health needs, and thus improve the effectiveness and satisfaction of music therapy. Through continuous monitoring and feedback, the system can gradually optimize the music library so that each music therapy can achieve the best state of physical and mental balance.

[0084] Example 3

[0085] For details, please refer to Figure 1 The first calculation unit is used to calculate and obtain the first physiological index SLz1. The first physiological index SLz1 is obtained by extracting the first blood pressure xy1, the first skin conductivity pf1, the first average sleep time rs1 and the first meditation index Ms1 in the first physiological data set, and after dimensionless processing, the first physiological index SLz1 is calculated by the following formula:

[0086]

[0087] In the formula, and They respectively represent the weight values ​​of the first blood pressure xy1, the first skin conductivity pf1, the first average sleeping time rs1 and the first meditation index Ms1, which are adjusted and set by the user. , , , , , It is represented as the first corrected normal value; the first blood pressure xy1 and the first skin conductivity pf1 are measured and obtained by the pressure sensor and the skin conductivity sensor built into the physiological monitoring bracelet respectively.

[0088] In this embodiment, a quantitative assessment of the user's physiological state before music therapy is achieved through precise physiological data collection and analysis. The first computing unit plays a vital role. It is responsible for processing the original physiological data collected by the first acquisition unit and converting it into a comparable physiological index SLz1 for evaluating the potential impact of music therapy.

[0089] During this process, the first calculation unit first extracts four key parameters from the first physiological data set: the first blood pressure xy1, the first skin conductivity pf1, the first average sleep onset time rs1, and the first meditation index Ms1. These parameters respectively reflect the user's cardiovascular health, emotional state, sleep quality and psychological relaxation level, and are important indicators for evaluating the physiological baseline before music therapy.

[0090] Next, in order to eliminate the impact of the dimensional differences between different physiological parameters, the system performs dimensionless processing on these data to ensure that when calculating the first physiological index SLz1, each parameter can be fairly compared at the same scale. This processing step is crucial, as it ensures that the final calculated index has high interpretability and accuracy;

[0091] The calculation formula cleverly incorporates user-adjustable weight values, allowing users to adjust the importance of various physiological parameters according to their personal health goals and preferences. In this way, the first physiological index SLz1 is not only an objective indicator of physiological status, but also a part of personalized physiological assessment, which can more accurately reflect the user's specific physiological needs.

[0092] Finally, the first physiological index SLz1 is obtained by weighted averaging, in which the contribution of each parameter is reflected by its corresponding weight value. The calculation of this index not only reflects the powerful data capture capability of the built-in sensor of the physiological monitoring bracelet, but also demonstrates the algorithm's superb skills in processing and analyzing complex physiological signals. Through such a design, the system can provide users with a comprehensive and personalized snapshot of their physiological state, laying a solid foundation for the formulation of subsequent music therapy plans and efficacy evaluation.

[0093] Example 4

[0094] For details, please refer to Figure 1 The music preset analysis module also includes a feature extraction unit and an analysis unit. The feature extraction unit is used to perform digital signal processing on each piece of music in the music library and extract music parameter features, including: average volume yl, average rhythm jz, average frequency spectrum pl, average number of beats jp, average white noise bz and average instantaneous loudness ss;

[0095] The average volume yl is measured and obtained by the built-in DSP digital signal processor of the physiological monitoring bracelet;

[0096] The average rhythm jz is measured and obtained through the smart audio device built into the physiological monitoring bracelet;

[0097] The average frequency spectrum pl is measured and obtained by the built-in spectrum analyzer of the physiological monitoring bracelet;

[0098] The average white noise bz is measured and obtained by the noise analyzer built into the physiological monitoring bracelet;

[0099] The average instantaneous loudness ss is measured and obtained by the loudness analyzer built into the physiological monitoring bracelet;

[0100] The analysis unit is used to construct a music attribute index Yyz based on the music parameter characteristics: the music attribute index Yyz is obtained by extracting the average volume yl, average rhythm jz, average frequency spectrum pl, average number of beats jp, average white noise bz and average instantaneous loudness ss, and after dimensionless processing, constructing a music therapy attribute database, and calculating the music attribute index Yyz by the following formula:

[0101]

[0102] In the formula, , , , They represent the weight values ​​of average volume yl, average rhythm jz, average frequency spectrum pl, average white noise bz and average instantaneous loudness ss, respectively, and are adjusted by the user. , , , , , 2 3 4 5=1, Indicates the third normal value.

[0103] In this embodiment, the music preset analysis module is one of the key components in this technical solution. Through advanced digital signal processing technology, it deeply explores the intrinsic properties of music and provides data support for subsequent personalized music therapy. The module consists of a feature extraction unit and an analysis unit, which are jointly committed to the accurate capture and quantitative analysis of music parameter features to construct a music attribute index Yyz. The music attribute index Yyz is a bridge connecting music characteristics and physiological reactions, which is crucial for the effectiveness evaluation of music therapy. The feature extraction unit uses various sensors and processors built into the physiological monitoring bracelet to perform multi-dimensional analysis on each piece of music in the music library. It not only considers traditional musicology parameters such as volume, rhythm and frequency spectrum, but also innovatively incorporates white noise and instantaneous loudness considerations, which makes the characteristic description of music more comprehensive and delicate. Through DSP digital signal processors, intelligent audio devices, spectrum analyzers, noise analyzers and loudness analyzers, the module can capture the dynamic changes of music and reveal the intrinsic structure and energy distribution of music from multiple angles.

[0104] The analysis unit is responsible for converting these music parameter characteristics into comparable music attribute index Yyz. It first performs dimensionless processing on the collected music parameters to eliminate unit differences and ensure fair comparison between different parameters. Then, through the user-adjustable weight value, the analysis unit weights the importance of each music feature to reflect the different effects that music may have on individuals. Finally, the music attribute index Yyz is calculated through a formula. It not only summarizes the physical properties of music, but also incorporates user preferences, becoming an important basis for the design of music therapy programs and the prediction of efficacy. This technical solution enriches the scientificity and personalization of music therapy. By accurately extracting and quantifying the intrinsic properties of music, the system can match each user with the music that best suits their physiological and psychological needs, thereby improving the pertinence and effectiveness of music therapy. In addition, the construction of the music attribute index Yyz also provides a solid data foundation for the standardization and repeatability research of music therapy, which helps to promote the further development and popularization of the field of music therapy. In short, this technical solution brings music therapy into a more scientific, precise and personalized era through technological innovation.

[0105] Example 5

[0106] For details, please refer to Figure 1 , the second physiological data detection module includes a second acquisition unit and a second calculation unit;

[0107] The second acquisition unit is used to collect physiological data of the user during the music therapy process through a physiological monitoring bracelet to construct a second physiological data set, where the second physiological data set includes: a second blood pressure xy2, a second skin conductivity pf2, a second average sleeping time rs2, and a second meditation index Ms2;

[0108] The physiological data of the user during the music therapy is collected through the physiological monitoring bracelet to construct a second physiological data set, and the processed second physiological data set is associated with the music attribute index Yyz of each song to generate the second physiological index SLz2 through the following formula;

[0109] The second meditation index Ms2 is calculated by the following formula:

[0110]

[0111] In the formula, Represents the number of breathing samples after music therapy, represents the breathing frequency value of the j+1th sample after music therapy, represents the respiratory frequency value of the jth sample; It represents the difference between the breathing frequency of the j+1th sample and the breathing frequency of the jth sample after music therapy. 2 represents the preset breathing frequency interval difference; R represents the number of heart rate samples after music therapy. represents the j+1th sample heart rate after music therapy, represents the jth sample heart rate value after music therapy, represents the j+1th sample heart rate and the jth sample heart rate increment after music therapy, 2 indicates the preset heart rate increment difference; , and Respectively represent weight values, which are adjusted by the user, and , , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet;

[0112] The second calculation unit is used to calculate and obtain the second physiological index SLz2. The second physiological index SLz2 is obtained by extracting the second blood pressure xy2, the second skin conductivity pf2, the second average sleep time rs2 and the second meditation index Ms2 in the second physiological data set, and after dimensionless processing, the second physiological index SLz2 is calculated by the following formula:

[0113]

[0114] In the formula, The difference between the second blood pressure and the first blood pressure, represents the difference between the second skin conductivity and the first skin conductivity, represents the difference between the second average sleep onset time and the first average sleep onset time, It represents the difference between the second meditation index and the first meditation index. , , and The weight values ​​respectively represent the difference between the second blood pressure and the first blood pressure, the difference between the second skin conductivity and the first skin conductivity, the difference between the second average sleep time and the first average sleep time, and the difference between the second meditation index and the first meditation index, which are adjusted and set by the user. , , , , , Indicates the second corrected normal value.

[0115] In this embodiment, physiological monitoring and music therapy are integrated to quantify the effect of music on individual physiological states. Specifically, the second physiological data detection module uses a physiological monitoring bracelet to collect physiological data such as blood pressure, skin conductivity, sleep time, and meditation index of the user when listening to different music in real time, and construct a second physiological data set. These data are then dimensionally processed to eliminate unit differences, and are fused through a specific algorithm to generate a second physiological index SLz2, which reflects the comprehensive impact of music on the user's physiological effects.

[0116] Among them, the calculation of the second meditation index Ms2 involves the statistical analysis of the changes in breathing frequency and heart rate before and after music therapy, combined with the user-defined weight value, to evaluate the regulatory effect of music on breathing and heart rate. The generation of the second physiological index SLz2 further integrates the difference in changes in blood pressure, skin conductivity, sleep time and meditation index, and accurately measures the positive effect of music on physiological state through weighted summation. It provides objective physiological data support for music therapy, making music selection and adjustment more personalized and scientific. Through continuous monitoring and analysis, it can not only evaluate the specific contribution of music to personal health, but also guide users to find the type of music that best suits their own physiological rhythm, thereby enhancing the pertinence and effectiveness of music therapy and promoting physical and mental health.

[0117] Example 6

[0118] For details, please refer to Figure 1 ,The efficacy estimation module includes a difference calculation unit and a efficacy evaluation unit;

[0119] The difference calculation unit is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1, and obtain the therapeutic effect value lxz by the following formula:

[0120] .

[0121] In this embodiment, the core function of the efficacy prediction module is to compare and analyze the changes in physiological state before and after the two music interventions. First, the difference calculation unit quantifies this change, that is, by calculating the difference between the second physiological index SLz2 after the music intervention and the first physiological index SLz1 before the music intervention, the direct impact of music on physiological indicators is intuitively displayed. Subsequently, the efficacy evaluation unit uses a specific formula based on the above difference to obtain the efficacy value lxz, and objectively evaluates the effect of music therapy.

[0122] The advantage of this program is that it provides a standardized method for evaluating the effectiveness of music therapy, making the treatment process quantifiable and the results visual, which helps to optimize music selection, improve the accuracy and individual adaptability of treatment, and promote the physical and mental health of users.

[0123] Example 7

[0124] For details, please refer to Figure 1 The efficacy evaluation unit is used to evaluate the efficacy value lxz to obtain a first evaluation result, including:

[0125] If the calculated lxz>0, it means that the music therapy has produced a positive physiological effect, that is, the music therapy is effective;

[0126] On the contrary, if lxz is equal to zero or less than zero, i.e., lxz ≤ 0, it means that music therapy fails to induce significant positive physiological changes and can be regarded as ineffective or unsatisfactory.

[0127] When lxz is confirmed to be a positive value, the system will automatically classify the currently playing music into the first priority therapeutic effect list and recommend the most effective music therapy option for each user.

[0128] In this embodiment, the core function of the efficacy evaluation unit is to determine the specific impact of music therapy on the individual's physiological state through quantitative analysis. When the efficacy value lxz is greater than zero, the system determines that the music therapy is effective, indicating that the music has successfully triggered a positive physiological response and improved the user's physical condition. On the contrary, if lxz is zero or a negative value, it means that the music therapy has failed to produce the expected positive effect, or even has a negative impact.

[0129] This mechanism ensures the scientific and personalized music selection. By automatically classifying effective music into the first priority efficacy list, the system can accurately recommend the most appropriate music therapy plan for each user, maximize the treatment effect, and exclude ineffective or negative music, thereby improving the overall treatment quality and user satisfaction. This dynamic adjustment strategy based on efficacy value not only improves the targeted nature of music therapy, but also promotes the continuous optimization of treatment plans, thus achieving the personalization and efficiency of music therapy.

[0130] Example 8

[0131] For details, please refer to Figure 1 The operation process of the push module is as follows:

[0132] The push module performs a graded evaluation based on the calculated positive efficacy value lxz, including:

[0133] The step threshold includes a first level threshold X1 and a second level threshold X2, and the first level threshold X1> the second level threshold X2; and the positive therapeutic effect value lxz is compared with the first level threshold X1 and the second level threshold X2 respectively, including:

[0134] The therapeutic effect value lxz<the second level threshold value X2, indicating that the music therapeutic effect belongs to the low level category, and a third priority playlist is generated;

[0135] The second level threshold value X2≤the therapeutic effect value lxz≤the first level threshold value X1, indicating that the music therapeutic effect belongs to the intermediate category, and a second priority playlist is generated;

[0136] The therapeutic effect value lxz> the first level threshold value X1, the music therapeutic effect belongs to the advanced category, and the first priority playlist is generated;

[0137] The first priority playlist, the second priority playlist, and the third priority playlist are pushed according to the order of priority.

[0138] In this embodiment, the push module combines the quantitative evaluation of the therapeutic effect value lxz with the intelligent push of personalized music therapy. Its core mechanism is to classify the physiological feedback effect of music therapy by setting two step thresholds X1 and X2. When lxz is lower than X2, the music is considered to have a lower therapeutic effect and is included in the third priority playlist; when it is between X2 and X1, the therapeutic effect is considered to be moderate and enters the second priority playlist; and lxz higher than X1 indicates a significant therapeutic effect and is classified in the first priority playlist.

[0139] Such a grading strategy enables the system to automatically screen and recommend the most effective music resources based on the actual physiological effects of music on individuals. By placing highly therapeutic music at the top of the priority list, it ensures that users are first exposed to music that is most likely to bring about positive changes, thereby improving the overall efficiency and personalized experience of music therapy. In addition, this mechanism also promotes dynamic adjustment of the treatment process, making the selection of music more scientific and refined, and ultimately achieving the goal of enhancing the effectiveness of music therapy and improving user satisfaction. By continuously monitoring and responding to changes in efficacy values, the system continuously optimizes the playlist to achieve personalized customization of music therapy and maximize its effects.

[0140] Example 9

[0141] See also Figure 2The present invention provides an audio playing method based on music therapy, comprising the following steps:

[0142] Step 1, collecting physiological data before music therapy: before the user is treated, the user is equipped with a unique physiological monitoring bracelet, and the physiological data of the user before listening to music is collected through the physiological monitoring bracelet to construct a first physiological data set, and the first physiological index SLz1 of each user is obtained by calculation and analysis based on the first physiological data set;

[0143] Step 2: Score the music attribute of each piece of music: Used to detect and analyze each piece of music in the preset music library to obtain the music attribute index Yyz of each piece of music:

[0144] Step 3: Collect physiological data after music therapy: collect the physiological data of the user during music therapy through the physiological monitoring bracelet, construct a second physiological data set, and associate the music attribute index Yyz of each piece of music based on the processed second physiological data set to construct a second physiological index SLz2;

[0145] Step 4: Preliminary evaluation of whether each music therapy produces therapeutic effect: Calculate the difference between the second physiological index SLz2 and the first physiological index SLz1 to obtain the therapeutic effect value lxz. If the therapeutic effect value lxz is positive, it means that the music therapy is effective. If the therapeutic effect value lxz is zero or negative, it means that the music therapy is ineffective. When the therapeutic effect value lxz is positive, classify the current music into the first priority therapeutic effect list.

[0146] Step 5: Multi-level evaluation and push: Compare and grade the efficacy value lxz in the first priority efficacy list with the step threshold, generate the corresponding first priority playlist, second priority playlist and third priority playlist, and push them to the user.

[0147] In this embodiment, physiological monitoring and music attribute analysis are integrated to achieve the personalization and intelligence of music therapy. First, the physiological data of users before and after treatment are collected through the physiological monitoring bracelet to form a comparative data set, and the changes in physiological indexes are accurately calculated to quantify the effect of music therapy. Secondly, the attributes of each track in the music library are scored, and a music attribute index is established to provide a basis for subsequent efficacy association. Subsequently, the physiological indexes before and after treatment are compared, the efficacy value is calculated, and the effectiveness of music therapy is clarified. The positive efficacy value indicates that the music is effective and is immediately included in the priority efficacy list. Finally, a multi-level threshold is used to evaluate the efficacy value, and a playlist of different priorities is intelligently generated to ensure that users receive the most effective music therapy resources first. This solution not only improves the pertinence and effectiveness of music therapy, but also enhances the user experience by dynamically adjusting the playlist, realizes the personalization and efficiency of music therapy, and promotes scientific and technological progress in the field of music therapy.

[0148] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An audio AI playback system based on music therapy, characterized by: It includes a first physiological data detection module, a music preset analysis module, a second physiological data detection module, a therapeutic effect estimation module and a push module; The first physiological data detection module is used to collect the physiological data of the user before the music therapy process through the physiological monitoring bracelet, construct a first physiological data set, and calculate and analyze the first physiological data set to obtain a first physiological index SLz1 of each user; The first physiological data detection module includes a first acquisition unit and a first calculation unit; The first acquisition unit is used to collect physiological data of the user before listening to music through a physiological monitoring bracelet to construct a first physiological data set, the first physiological data set including: a first blood pressure xy1, a first skin conductivity pf1, a first average sleeping time rs1 and a first meditation index Ms1; The first meditation index Ms1 is calculated by the following formula: ； In the formula, represents the number of breathing samples before music therapy, represents the respiratory frequency value of the i+1th sample, Represents the respiratory frequency value of the i-th sample; It represents the difference between the breathing frequency of the i+1th sample and the breathing frequency of the ith sample. represents the preset breathing frequency interval difference; M represents the number of heart rate samples before music therapy, represents the i+1th sample heart rate, represents the heart rate value of the i-th sample, represents the heart rate of the i+1th sample and the heart rate increment of the ith sample, Indicates the preset heart rate increment difference; and Respectively represent weight values, which are adjusted by the user, and , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet; The first calculation unit is used to calculate and obtain the first physiological index SLz1. The first physiological index SLz1 is obtained by extracting the first blood pressure xy1, the first skin conductivity pf1, the first average sleep time rs1 and the first meditation index Ms1 in the first physiological data set, and after dimensionless processing, the first physiological index SLz1 is calculated by the following formula: ； In the formula, and They respectively represent the weight values ​​of the first blood pressure xy1, the first skin conductivity pf1, the first average sleeping time rs1 and the first meditation index Ms1, which are adjusted and set by the user. , , , , , It is represented as the first corrected normal value; the first blood pressure xy1 and the first skin conductivity pf1 are measured and obtained by the pressure sensor and the skin conductivity sensor built into the physiological monitoring bracelet respectively; The music preset analysis module is used to detect and analyze each piece of music in the preset music library to obtain the music attribute index Yyz of each piece of music: The music preset analysis module also includes a feature extraction unit and an analysis unit, wherein the feature extraction unit is used to perform digital signal processing on each piece of music in the music library to extract music parameter features, including: average volume yl, average rhythm jz, average frequency spectrum pl, average number of beats jp, average white noise bz and average instantaneous loudness ss; The average volume yl is measured and obtained by the built-in DSP digital signal processor of the physiological monitoring bracelet; The average rhythm jz is measured and obtained through the smart audio device built into the physiological monitoring bracelet; The average frequency spectrum pl is measured and obtained by the built-in spectrum analyzer of the physiological monitoring bracelet; The average white noise bz is measured and obtained by the noise analyzer built into the physiological monitoring bracelet; The average instantaneous loudness ss is measured and obtained by the loudness analyzer built into the physiological monitoring bracelet; The analysis unit is used to construct a music attribute index Yyz according to the music parameter characteristics: the music attribute index Yyz is obtained by extracting the average volume yl, the average rhythm jz, the average frequency spectrum pl, the average number of beats jp, the average white noise bz and the average instantaneous loudness ss, and after dimensionless processing, constructing a music therapy attribute database, and calculating the music attribute index Yyz by the following formula: ； In the formula, , , , They represent the weight values ​​of average volume yl, average rhythm jz, average frequency spectrum pl, average white noise bz and average instantaneous loudness ss, respectively, and are adjusted by the user. , , , , , 2 3 4 5=1, It is expressed as the third normal value; The second physiological data detection module is used to collect the physiological data of the user during the music therapy process through the physiological monitoring bracelet, construct a second physiological data set, and associate the music attribute index Yyz of each piece of music according to the processed second physiological data set to construct a second physiological index SLz2; The second physiological data detection module includes a second acquisition unit and a second calculation unit; The second acquisition unit is used to collect physiological data of the user during the music therapy process through a physiological monitoring bracelet to construct a second physiological data set, and the second physiological data set includes: a second blood pressure xy2, a second skin conductivity pf2, a second average sleeping time rs2 and a second meditation index Ms2; The physiological data of the user during the music therapy is collected through the physiological monitoring bracelet to construct a second physiological data set, and the processed second physiological data set is associated with the music attribute index Yyz of each song to generate the second physiological index SLz2 through the following formula; The second meditation index Ms2 is calculated by the following formula: ； In the formula, Represents the number of breathing samples after music therapy, represents the breathing frequency value of the j+1th sample after music therapy, Represents the respiratory frequency value of the jth sample; It represents the difference between the breathing frequency of the j+1th sample and the breathing frequency of the jth sample after music therapy. 2 represents the preset breathing frequency interval difference; R represents the number of heart rate samples after music therapy. represents the j+1th sample heart rate after music therapy, represents the jth sample heart rate value after music therapy, represents the j+1th sample heart rate and the jth sample heart rate increment after music therapy, 2 indicates the preset heart rate increment difference; , and Respectively represent weight values, which are adjusted by the user, and , , , ; The breathing sample data and heart rate sample data are obtained through the built-in breathing sensor and heart rate sensor of the physiological monitoring bracelet; The second calculation unit is used to calculate and obtain the second physiological index SLz2. The second physiological index SLz2 is obtained by extracting the second blood pressure xy2, the second skin conductivity pf2, the second average sleep time rs2 and the second meditation index Ms2 in the second physiological data set, and after dimensionless processing, the second physiological index SLz2 is calculated by the following formula: ； In the formula, represents the difference between the second blood pressure and the first blood pressure, represents the difference between the second skin conductivity and the first skin conductivity, represents the difference between the second average sleep onset time and the first average sleep onset time, It represents the difference between the second meditation index and the first meditation index. , , and The weight values ​​respectively represent the difference between the second blood pressure and the first blood pressure, the difference between the second skin conductivity and the first skin conductivity, the difference between the second average sleep time and the first average sleep time, and the difference between the second meditation index and the first meditation index, which are adjusted and set by the user. , , , , , It is expressed as the second normal value; The therapeutic effect estimation module is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1 to obtain a therapeutic effect value lxz. If the therapeutic effect value lxz is positive, it means that the music therapy is effective. If the therapeutic effect value lxz is zero or a negative number, it means that the music therapy is ineffective. When the therapeutic effect value lxz is positive, the current music is classified into the first priority therapeutic effect list; The efficacy estimation module includes a difference calculation unit and an efficacy evaluation unit; The difference calculation unit is used to calculate the difference between the second physiological index SLz2 and the first physiological index SLz1, and obtain the therapeutic effect value lxz by the following formula: ； The efficacy evaluation unit is used to evaluate the efficacy value lxz to obtain a first evaluation result, including: If the calculated lxz>0, it means that the music therapy has produced a positive physiological effect, that is, the music therapy is effective; On the contrary, if lxz is equal to zero or less than zero, i.e., lxz ≤ 0, it means that music therapy fails to induce significant positive physiological changes and can be regarded as ineffective or unsatisfactory. When lxz is confirmed to be positive, the system will automatically classify the currently playing music into the first priority efficacy list and recommend the most effective music therapy option for each user; The push module compares and grades the efficacy value lxz in the first priority efficacy list with the step threshold, generates the corresponding first priority play list, second priority play list and third priority play list, and pushes them to the user; The operation process of the push module is specifically as follows: The push module performs a graded evaluation based on the calculated positive efficacy value lxz, including: The step threshold includes a first level threshold X1 and a second level threshold X2, and the first level threshold X1> the second level threshold X2; and the positive therapeutic effect value lxz is compared with the first level threshold X1 and the second level threshold X2 respectively, including: The therapeutic effect value lxz<the second level threshold value X2, indicating that the music therapeutic effect belongs to the low level category, and a third priority playlist is generated; The second level threshold value X2≤the therapeutic effect value lxz≤the first level threshold value X1, indicating that the music therapeutic effect belongs to the intermediate category, and a second priority playlist is generated; The therapeutic effect value lxz> the first level threshold value X1, the music therapeutic effect belongs to the advanced category, and the first priority playlist is generated; The first priority playlist, the second priority playlist, and the third priority playlist are pushed according to the order of priority.

Images