Respiratory training control method, device and equipment based on AI and medium

Abstract

The invention discloses a breathing training control method, device and equipment based on AI and a medium, and relates to the field of artificial intelligence. The breathing training control method comprises the steps that the breathing state of a user is monitored, and a corresponding breathing state signal is generated; generating a corresponding sound control signal according to the breathing state signal; controlling a preset audio output device to make corresponding sound according to the sound control signal; wherein the sound control signal is at least used for controlling the volume and / or tone of the sound, and when the breathing state signal indicates that expiration is unstable, the volume and / or tone of the sound is controlled to fluctuate. By establishing the real-time interaction relation between respiration and sound, the interestingness and the user participation degree of the training process are remarkably improved. A closed-loop feedback mechanism guides a user to actively adjust a breathing mode, and boring physiological training is converted into vivid music creation experience, so that the training effect can be maintained for a long time.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an AI-based breathing training control method, device, equipment, and medium. Background Technology

[0002] Breathing training plays a positive role in improving lung function and regulating breathing rhythm; with the increasing health awareness of people, the application of breathing training in the health field is becoming more and more widespread. Currently, common training methods mainly include guiding users to perform repetitive deep breathing, abdominal breathing, and other actions, or passive training using simple equipment.

[0003] This type of method has significant shortcomings in implementation: the training content is monotonous and dull, lacking effective interactive mechanisms and immediate feedback, making it difficult to stimulate users' active participation. Prolonged use of this type of training can easily lead to user fatigue, resulting in decreased training adherence and ultimately affecting the training outcome.

[0004] Therefore, existing breathing training methods generally suffer from technical problems such as insufficient user participation and difficulty in maintaining training effects due to the monotonous training process. Summary of the Invention

[0005] This invention provides an AI-based breathing training control method, device, equipment, and medium, aiming to solve the problems of insufficient user participation and difficulty in maintaining training effects caused by the monotonous training process in existing breathing training methods.

[0006] In a first aspect, embodiments of the present invention provide an AI-based breathing training control method, comprising: Monitor the user's breathing status and generate corresponding breathing status signals; Based on the breathing state signal, a corresponding sound control signal is generated; According to the sound control signal, the preset audio output device is controlled to emit a corresponding sound; The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate.

[0007] A further technical solution is that generating a corresponding sound control signal based on the breathing state signal includes: Extract respiratory feature parameters from the respiratory state signal, wherein the respiratory feature parameters include at least one of expiratory flow rate, expiratory rhythm and expiratory stability; The breathing feature parameters are mapped to corresponding music feature control instructions, which are used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

[0008] A further technical solution is that mapping the breathing feature parameters to corresponding music feature control commands includes: Map the exhalation rhythm to instructions that control the rhythm of the sound; And / or, map the expiratory flow rate to instructions that control the harmonic richness of the sound; And / or, map the expiratory stability to instructions that control the timbre effects of the sound.

[0009] A further technical solution is that mapping the breathing feature parameters to corresponding music feature control commands includes: The respiratory characteristic parameters are preprocessed to obtain input data; The input data is fed into a pre-trained AI music generation model, which then generates matching music feature data based on the input data. Based on the music feature data, a corresponding music feature control instruction is generated.

[0010] A further technical solution is that the method further includes: It receives the user's touch operation and generates the corresponding finger position signal; The pitch of the sound to be generated is determined based on the finger position signal. The step of controlling a preset audio output device to emit a corresponding sound according to the sound control signal includes: The scale sound determined by the finger position signal is used as the main melody sound; The sound generated under the control of the sound control signal is used as background music; The main melody is mixed with the background music in real time and then output.

[0011] A further technical solution is that the method further includes: Preset respiratory state thresholds corresponding to the breathing training goals; When the user's breathing state is detected to reach the breathing state threshold, a positive feedback signal is generated; Based on the positive feedback signal, the audio output device is controlled to output a preset reward audio.

[0012] A further technical solution is that, when the respiratory state signal indicates unstable exhalation, controlling the volume and / or pitch of the sound to fluctuate includes: Based on the parameter values ​​reflecting expiratory stability in the respiratory state signal, a corresponding fluctuation control signal is calculated and applied to the audio output in real time; The fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a tone fluctuation signal for modulating the frequency.

[0013] Secondly, embodiments of the present invention also provide an AI-based breathing training control device, which includes a unit for performing the above-described method.

[0014] Thirdly, embodiments of the present invention also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0016] This invention provides an AI-based breathing training control method, device, equipment, and medium. The method includes: monitoring a user's breathing state and generating a corresponding breathing state signal; generating a corresponding sound control signal based on the breathing state signal; and controlling a preset audio output device to emit a corresponding sound based on the sound control signal. The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate. This invention monitors the user's breathing state and generates a corresponding signal, thereby controlling the audio device to output sound that changes with breathing. When exhalation is unstable, the volume and pitch of the sound fluctuate accordingly, transforming abstract breathing training into intuitive auditory feedback. This technical solution effectively solves the core problem of the monotony and boredom of traditional breathing training. By establishing a real-time interactive relationship between breathing and sound, it significantly improves the fun and user participation of the training process. Its closed-loop feedback mechanism guides users to actively adjust their breathing patterns, transforming tedious physiological training into a vivid musical creation experience, thereby ensuring that the training effect can be maintained in the long term. Attached Figure Description

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

[0018] Figure 1A flowchart illustrating an AI-based breathing training control method provided in an embodiment of the present invention; Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

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

[0020] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0021] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0023] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0024] Please see Figure 1 This invention provides an AI-based breathing training control method. By constructing a complete real-time mapping system from breathing state to sound output, it effectively solves the technical problems of insufficient user participation and unsustainable training effects caused by the monotonous training process in existing breathing training methods. Specifically, the method includes the following steps: S1 monitors the user's breathing status and generates corresponding breathing status signals.

[0025] In practice, by continuously monitoring the user's breathing state and generating corresponding breathing state signals, the system achieves accurate capture of the user's physiological state, which lays a data foundation for subsequent interactive feedback. For example, during training, the user's inhalation depth, exhalation duration, and the stability of exhalation airflow are quantified in real time, making the originally subjective breathing experience objective and measurable.

[0026] In one embodiment, a respiratory sensing module is provided, which includes at least one physical sensor configured to sense the user's breathing behavior and output raw sensing signals. The physical sensor is preferably a pressure sensor, an airflow sensor, or a microphone. Specifically, the pressure sensor is positioned near the user's lips to detect pressure changes caused by exhalation; the airflow sensor is positioned along the user's exhalation path to detect the dynamic characteristics of the exhaled airflow; and the microphone is configured to collect sound characteristics generated during the user's breathing.

[0027] The raw sensor signal is transmitted to a signal processing unit, which preprocesses the received raw sensor signal. The preprocessing operations include signal amplification, noise filtering, and analog-to-digital conversion to convert the raw sensor signal into a digital respiratory signal suitable for analysis.

[0028] Feature extraction and analysis are performed on the digitized respiratory signal to identify respiratory characteristic parameters. These parameters include, but are not limited to, expiratory flow rate, expiratory rhythm (expiratory duration, expiratory interval, etc.), and expiratory stability index. The expiratory stability index is obtained by calculating the variance of the digitized respiratory signal in the time domain or the energy distribution characteristics in the frequency domain.

[0029] Based on the respiratory characteristic parameters, a standardized respiratory state signal is generated. This respiratory state signal is configured to contain quantized data of the respiratory characteristic parameters and can be directly called and processed by the subsequent sound control signal generation module.

[0030] S2, Generate a corresponding sound control signal based on the breathing state signal.

[0031] In practice, corresponding sound control signals are generated based on respiratory status signals, achieving a creative transformation from physiological parameters to artistic expression. This transformation process is not a simple signal triggering, but rather establishes a dynamic correlation model between respiratory quality and sound characteristics. For example, when the respiratory status signal indicates unstable exhalation, the system does not simply issue a warning sound, but rather generates corresponding artistic fluctuations by controlling the volume and pitch of the sound. This approach transforms imperfect performance during training into musically expressive sound variations. In principle, this design fully utilizes the sensitivity of the human auditory system to sound changes, reflecting continuous changes in respiratory quality through continuous sound variations, allowing users to obtain rich information about their own respiratory state through the auditory channel. This real-time feedback forms a closed-loop training system, allowing users to adjust their breathing patterns by listening to changes in sound. For instance, when they hear unwanted fluctuations in sound, they will naturally try to adjust their breathing to restore a stable sound output.

[0032] In some preferred embodiments, the above step "generating a corresponding sound control signal based on the breathing state signal" specifically includes the following steps: extracting breathing feature parameters from the breathing state signal, the breathing feature parameters including at least one of expiratory flow rate, expiratory rhythm, and expiratory stability; mapping the breathing feature parameters to corresponding music feature control instructions, the music feature control instructions being used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

[0033] In practice, by systematically decomposing key parameters in the respiratory state signal, including expiratory flow, expiratory rhythm, and expiratory stability, and mapping them to different dimensions of music, such as rhythm, harmonic richness, and timbre effects, a deep conversion from physiological signals to musical expression is achieved.

[0034] For example, when a user performs deep breathing training, the volume of their exhaled air can control the complexity of the harmonics in the background music: deep breathing produces rich and full harmonies, while shallow breathing produces simple and pure harmonies; the speed of exhalation can be mapped to the tempo of the music; and the stability of exhalation can be expressed through sound effects such as reverb and vibrato. This multi-dimensional mapping creates a highly immersive training environment where each breath the user takes shapes a unique musical scene. In principle, this design fully utilizes the multi-element characteristics of music, breaking down a single breathing training goal into multiple independently controllable sound dimensions, allowing users to simultaneously train multiple aspects of breathing, such as depth, rhythm, and stability.

[0035] Furthermore, this refined mapping makes the feedback information more specific and meaningful. Users can not only perceive whether their breathing is "good" or "bad," but also precisely understand which aspect of their breathing ability needs improvement. For example, when a user hears a disordered musical rhythm, they realize they need to adjust their breathing rhythm; when the harmony becomes thin, it motivates them to take deeper breaths. This targeted feedback greatly improves the scientific rigor and effectiveness of the training, while maintaining the richness and creativity of artistic expression, transforming breathing training from mechanical repetitive exercises into an expressive musical creation experience.

[0036] In some preferred embodiments, the above step "mapping the breathing feature parameters to corresponding music feature control instructions" specifically includes the following steps: mapping the exhalation rhythm to an instruction to control the rhythm of the sound; and / or mapping the exhalation flow rate to an instruction to control the harmonic richness of the sound; and / or mapping the exhalation stability to an instruction to control the timbre effects of the sound.

[0037] In practice, by mapping the exhalation rhythm to instructions for controlling the rhythm of the voice, the exhalation flow to instructions for controlling the harmony richness, and the exhalation stability to instructions for controlling the timbre effects, this scheme establishes a highly structured feedback system that conforms to cognitive intuition.

[0038] For example, when users perform rhythmic breathing training, the ratio of their inhalation to exhalation time directly determines the tempo of the background music. This intuitive correspondence allows users to master complex rhythmic control skills through bodily perception. Simultaneously, the correlation between expiratory flow and harmonic richness motivates users to exhale more deeply and continuously, as only sufficient expiratory flow can trigger rich and full harmonic effects, directly promoting improvements in lung capacity and expiratory control. Particularly innovative is the design that links expiratory stability with timbre effects. When a user's exhalation is unstable, the system doesn't simply issue a warning sound; instead, it adds artistic sound effects such as chorus or ethereal quality to transform imperfect breathing into unique musical expression. This approach significantly reduces frustration during training.

[0039] Furthermore, this precise mapping relationship aligns with the divide-and-conquer design principle, breaking down complex breathing training tasks into relatively independent sub-goals, allowing users to focus on improving specific breathing abilities. Simultaneously, this design also conforms to the cognitive principles of multimedia learning theory, avoiding cognitive overload by mapping different types of breathing information to different musical dimensions, making it easier for users to understand and respond to feedback information.

[0040] In one embodiment, a mapping model between respiratory characteristic parameters and music control parameters is established. This model includes a parameter receiving module, a feature analysis module, and an instruction generation module. The parameter receiving module is configured to receive expiratory rhythm parameters, expiratory flow rate parameters, and expiratory stability parameters from the respiratory state signal.

[0041] For the mapping from exhalation rhythm to sound rhythm, the feature analysis module first calculates the periodic characteristics of the exhalation action per unit time, including the ratio of the duration of the inhalation phase to the exhalation phase. Based on the periodic characteristics, a corresponding rhythm control command is generated through a preset rhythm mapping algorithm. Specifically, when the exhalation rhythm is detected to be accelerating, the beat speed of the sound is increased accordingly, and vice versa; when the exhalation rhythm is detected to be stabilizing, the sound rhythm is locked at a constant beat.

[0042] For the mapping from expiratory flow rate to harmonic richness, the feature analysis module analyzes the amplitude characteristics of the expiratory flow rate signal in real time and normalizes it to a standard flow rate level. Through a preset harmonic richness control algorithm, the standard flow rate level is mapped to instructions for harmonic complexity parameters, wherein the harmonic complexity parameters include at least one of the number of simultaneously vocalized notes, harmonic progression complexity, and the number of voice parts. When the expiratory flow rate increases, the harmonic complexity parameter increases accordingly; when the expiratory flow rate decreases, the harmonic complexity parameter decreases accordingly.

[0043] For the mapping from expiratory stability to timbre effects, the feature analysis module quantifies the stability index by calculating the variance characteristics of the expiratory flow signal. Based on the stability index, a corresponding timbre modulation instruction is generated through a preset timbre effect control algorithm. Specifically, when expiratory stability is lower than a preset threshold, the timbre modulation instruction controls the audio synthesis unit to load timbre effect processing, including at least one of vibrato depth, reverberation intensity, or chorus effect; when expiratory stability is higher than the preset threshold, the timbre modulation instruction controls the audio synthesis unit to use a pure base timbre.

[0044] The instruction generation module integrates the rhythm control instructions, harmonic complexity parameter instructions, and tone modulation instructions into standardized music feature control instructions, and outputs them to the audio synthesis system for execution.

[0045] In some preferred embodiments, the above step of "mapping the breathing feature parameters to corresponding music feature control instructions" specifically includes the following steps: preprocessing the breathing feature parameters to obtain input data; inputting the input data into a pre-trained AI music generation model so that the AI ​​music generation model generates matching music feature data based on the input data; and generating corresponding music feature control instructions based on the music feature data.

[0046] In practice, the breathing feature parameters are preprocessed and converted into an input data format acceptable to the model. This data is then input into the AI ​​music generation model to generate matching musical feature data, ultimately producing music feature control commands. This complete technological chain delivers highly intelligent, personalized, and creative technical effects. Specifically, the AI ​​music generation model can learn the deep correlation between complex music composition rules and breathing patterns, thereby generating richer musical expressions far exceeding simple rule mappings. For example, when the system detects a user's specific breathing pattern, the AI ​​model can generate melodic variations, harmonic progressions, or rhythmic patterns that resonate with the user's emotions in real time, ensuring that each training session produces a unique musical work. In principle, this AI-based method overcomes the limitations of preset rule systems, processing complex and non-linear features in breathing signals and generating sound outputs with artistic coherence and musicality. The preprocessing step ensures the standardization and validity of the input data, providing a foundation for the model's stable operation. The core role of the AI ​​model lies in its powerful pattern recognition and generation capabilities, dynamically adjusting musical parameters based on real-time breathing data to achieve truly intelligent accompaniment. This allows the system to adapt to different users' breathing characteristics and musical preferences, providing a highly personalized training experience. For example, for users who enjoy classical music, the AI ​​model can generate corresponding Baroque-style music; for users who prefer modern music, it can generate electronic music-style accompaniment. This adaptability greatly enhances the system's universality and user engagement. At the same time, the introduction of the AI ​​model also significantly expands the system's creative boundaries, enabling breathing training to go beyond simple pitch and volume changes and create musical works with complex structures and emotional depth, thereby further enhancing the artistry and appeal of breathing training.

[0047] It should be noted that the AI ​​music generation model refers to a computational model built on artificial intelligence technology that can automatically generate audio content that conforms to music theory and aesthetic rules based on input data. It can employ a sequence generation model based on recurrent neural networks, particularly long short-term memory networks or gated recurrent units; this invention is not specifically limited to these. The AI ​​music generation model achieves its function through the following technical features: First, the AI ​​music generation model includes a pre-trained parameterized network structure, which is obtained through training on a large music dataset and is capable of understanding the inherent correlations and creative rules between musical elements. The AI ​​music generation model receives pre-processed respiratory feature parameters as input data, including but not limited to expiratory rhythm, expiratory flow rate, and expiratory stability indicators. Internally, the AI ​​music generation model uses a multi-layered neural network to perform feature parsing and semantic understanding of the input data, mapping physiological parameter features to corresponding musical creation dimensions. Specifically, the AI ​​music generation model includes a temporal feature extraction module for analyzing the dynamic changes in respiratory parameters; a music element generation module for generating corresponding musical components based on the feature extraction results; and a music logic constraint module to ensure that the generated music content conforms to music theory rules and auditory aesthetics. The AI ​​music generation model utilizes an encoder-decoder architecture to transform the input domain into the output domain. The encoder understands the musical semantics of breathing features, while the decoder generates corresponding musical feature data based on this understanding. During generation, the AI ​​music generation model employs an attention mechanism to capture the complex correspondence between breathing parameters and musical elements, and uses an adversarial training strategy to ensure the quality and diversity of the generated music. Ultimately, the AI ​​music generation model outputs musical feature control commands, including rhythm control instructions, harmonic richness parameters, and timbre effect commands. These commands are configured to directly drive a sound library or audio synthesis engine to produce corresponding musical effects.

[0048] S3, according to the sound control signal, control the preset audio output device to emit a corresponding sound; wherein, the sound control signal is at least used to control the volume and / or pitch of the sound, and when the breathing state signal indicates that the exhalation is unstable, control the volume and / or pitch of the sound to fluctuate.

[0049] In practice, the step of controlling a preset audio output device to emit corresponding sounds based on sound control signals transforms the aforementioned signal processing results into an auditory experience that the user can directly perceive. The technical effect of this step is to create a highly intuitive training interface. Users do not need to understand complex physiological parameters or view instrument readings; they can understand their breathing state simply by listening to the sounds. This design is particularly in line with the principle of attention allocation, allowing users to focus their primary attention on breathing control while subconsciously perceiving sound feedback, thereby reducing cognitive load. More importantly, transforming breathing training into a sound creation process significantly enhances intrinsic motivation. Users are no longer training for the sake of training, but actively adjusting their breathing to create beautiful sounds. This shift in motivation plays a crucial role in maintaining long-term training adherence.

[0050] The technical advantage of this invention lies in establishing a complete system that artistically and gamifies the breathing training process through the synergistic effect of respiratory state monitoring, sound control signal generation, and audio output. This system not only provides precise physiological feedback but, more importantly, transforms the essential nature of training through creative sound expression, turning what was originally a tedious repetitive exercise into an engaging artistic creation process. This fundamental shift allows users to maintain high levels of engagement, ensuring the long-term sustainability of training effects and ultimately effectively solving the technical problems of insufficient engagement and unsustainable results caused by monotony in traditional breathing training methods.

[0051] In some preferred embodiments, the method further includes: receiving a user's touch operation and generating a corresponding finger position signal; determining the pitch of the sound to be generated based on the finger position signal. The step "controlling a preset audio output device to emit a corresponding sound according to the sound control signal" specifically includes the following steps: using the pitch determined by the finger position signal as the main melody sound; using the sound generated by the sound control signal as background music; and mixing the main melody sound and the background music in real time before outputting.

[0052] In practice, touch operation is introduced to generate finger position signals, and the scale sound determined by these signals is used as the main melody sound. This melody is then mixed and output in real time with background music generated by sound control signals. The finger position signals are generated based on the user's finger pressure on the input device, with each position corresponding to a specific scale, allowing users to customize the main melody. This design enables users to simultaneously perform breathing exercises and musical performance, elevating traditional single-function breathing practice into a comprehensive musical performance experience. For example, users can play familiar melodies through touch operation, while their breathing state controls various aspects of the background music in real time: the depth of breathing affects the richness of the accompanying instruments, the rhythm of breathing determines the speed of the drumbeats, and the stability of breathing affects the timbre of the harmonics. This separation of the main melody and background music design yields significant technological advantages: users gain a sense of control and dominance in music creation through touch operation, while breathing training naturally integrates into the shaping of the background music, avoiding the monotony of purely breathing exercises.

[0053] Furthermore, this design aligns with the multi-resource theory of attention allocation. Users can focus their conscious attention on melodic performance, while breath control relies to some extent on trained, automated skills. This allocation makes breath training more natural and sustainable. Simultaneously, the harmonious unity of the main melody and background music creates a strong sense of artistic wholeness. Through the coordination of their breathing and finger placement, users truly become creators and performers of the music—a sense of accomplishment that traditional breath training cannot provide. Particularly noteworthy is that this design also offers training modes at different difficulty levels: beginners can focus on the impact of breath on the background music to play simple melodies, while advanced users can challenge complex finger sequences while maintaining stable breathing, achieving a gradual progression in skill training.

[0054] In some preferred embodiments, the above step "when the breathing state signal indicates unstable exhalation, control the volume and / or pitch of the sound to fluctuate" specifically includes the following steps: calculating and applying a corresponding fluctuation control signal to the audio output in real time based on the parameter value reflecting the exhalation stability in the breathing state signal; wherein, the fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a pitch fluctuation signal for modulating the frequency.

[0055] In practical implementation, when the respiratory status signal indicates expiratory instability, the audio modulation module calculates and applies a fluctuation control signal, including amplitude and pitch fluctuation signals, to the audio output in real time, resulting in a highly sensitive and artistic feedback effect. This scheme transforms the abstract physiological parameter of respiratory instability into a concrete and operable audio modulation parameter, achieving a fine correlation between respiratory quality and sound characteristics through professional signal processing technology. Expiratory stability can be characterized by expiratory stability indices, such as time-domain fluctuation variance, which is not specifically limited in this invention.

[0056] For example, when the system detects a subtle tremor during exhalation, the audio modulation module generates a corresponding amplitude fluctuation signal in real time, resulting in natural volume fluctuations in the output sound. When there are fluctuations in exhalation flow, a pitch fluctuation signal is generated, causing subtle changes in the pitch of the sound. This technology differs from simple on / off feedback; it provides a continuous response proportional to breathing instability, making the feedback information richer and more precise. From the perspective of audio processing principles, amplitude modulation simulates changes in sound intensity by changing the envelope shape of the signal, while frequency modulation produces pitch fluctuations by changing the fundamental frequency. The combination of these two basic modulation methods can create a rich variety of sound effects. It is particularly worth emphasizing that this technology allows even minute instabilities in breathing to be appropriately represented in the sound, providing users with extremely sensitive feedback information and helping to cultivate fine breathing control. At the same time, through carefully designed modulation parameters, the system can transform unstable breathing into an artistic musical expression, such as portraying a slight exhalation tremor as an elegant vibrato effect, rather than a simple erroneous indication. This artistic approach fundamentally changes the negative experience brought about by "false prompts" in traditional biofeedback, transforming the imperfections in breathing training into distinctive elements of musical expression, and greatly reducing psychological pressure during the training process.

[0057] In some preferred embodiments, the method further includes the following steps: preset a breathing state threshold corresponding to the breathing training target; when the user's breathing state is detected to reach the breathing state threshold, generate a positive feedback signal; and control the audio output device to output a preset reward audio based on the positive feedback signal.

[0058] In practice, by preset breathing state thresholds and generating positive feedback signals when the user reaches these thresholds, the audio output device is controlled to output rewarding audio. This technical feature significantly enhances the training motivation system and long-term effects. Based on basic real-time audio feedback, this solution introduces a goal-oriented incentive mechanism. By setting clear training goals and rewards for achieving them, it effectively solves the key challenge of maintaining motivation in breathing training. For example, the system can set a threshold for maintaining stable exhalation for a specific duration. When the user successfully reaches this goal, the system plays a congratulatory audio clip, such as enthusiastic applause, a victory horn, or a specially unlocked beautiful timbre. This positive reinforcement mechanism is based on the classic theory of behavioral psychology: timely positive feedback can reinforce the frequency of desired behaviors. From a technical implementation perspective, the preset breathing state thresholds provide an objective performance evaluation standard, making training progress quantifiable and trackable; while the output of rewarding audio creates emotional satisfaction and a sense of accomplishment. This design is particularly suitable for progressive training plans, allowing users to start with simple thresholds and gradually challenge themselves with more difficult goals, continuously gaining a sense of success at each stage. Unlike simple completion prompts, carefully designed rewarding audio, such as a pleasant melody, a fun sound effect, or an encouraging voice, can trigger positive emotional responses in users, thus establishing a psychological association between breathing exercises and feelings of pleasure. This positive emotional connection is a key factor in maintaining long-term training adherence. At the same time, threshold settings can be personalized to suit different user ability levels, ensuring that each user experiences success with an appropriate challenge, avoiding frustration from overly high goals or boredom from overly low goals.

[0059] This invention proposes an AI-based breathing training control method, comprising: monitoring the user's breathing state and generating a corresponding breathing state signal; generating a corresponding sound control signal based on the breathing state signal; and controlling a preset audio output device to emit a corresponding sound based on the sound control signal. The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate. This invention monitors the user's breathing state and generates a corresponding signal, thereby controlling the audio device to output sound that changes with breathing. When exhalation is unstable, the volume and pitch of the sound fluctuate accordingly, transforming abstract breathing training into intuitive auditory feedback. This technical solution effectively solves the core problem of the monotony and boredom of traditional breathing training. By establishing a real-time interactive relationship between breathing and sound, it significantly improves the fun and user participation of the training process. Its closed-loop feedback mechanism guides users to actively adjust their breathing patterns, transforming tedious physiological training into a vivid musical creation experience, thereby ensuring that the training effect can be maintained in the long term.

[0060] Corresponding to the above-described AI-based breathing training control method, this invention also provides an AI-based breathing training control device. This AI-based breathing training control device includes a unit for executing the aforementioned AI-based breathing training control method, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal. Specifically, the AI-based breathing training control device includes: The monitoring unit is used to monitor the user's breathing status and generate corresponding breathing status signals; The generation unit is used to generate a corresponding sound control signal based on the breathing state signal; A sound-generating unit is used to control a preset audio output device to emit corresponding sounds according to the sound control signal; The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate.

[0061] In some preferred embodiments, generating a corresponding sound control signal based on the breathing state signal includes: Extract respiratory feature parameters from the respiratory state signal, wherein the respiratory feature parameters include at least one of expiratory flow rate, expiratory rhythm and expiratory stability; The breathing feature parameters are mapped to corresponding music feature control instructions, which are used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

[0062] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: Map the exhalation rhythm to instructions that control the rhythm of the sound; And / or, map the expiratory flow rate to instructions that control the harmonic richness of the sound; And / or, map the expiratory stability to instructions that control the timbre effects of the sound.

[0063] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: The respiratory characteristic parameters are preprocessed to obtain input data; The input data is fed into a pre-trained AI music generation model, which then generates matching music feature data based on the input data. Based on the music feature data, a corresponding music feature control instruction is generated.

[0064] In some preferred embodiments, it further includes: The receiving unit is used to receive the user's touch operation and generate corresponding finger position signals; The determining unit is used to determine the pitch of the sound to be generated based on the finger position signal; The step of controlling a preset audio output device to emit a corresponding sound according to the sound control signal includes: The scale sound determined by the finger position signal is used as the main melody sound; The sound generated under the control of the sound control signal is used as background music; The main melody is mixed with the background music in real time and then output.

[0065] In some preferred embodiments, it further includes: A setting unit is used to preset the respiratory state threshold corresponding to the respiratory training target; The generation unit generates a positive feedback signal when it detects that the user's breathing state has reached the breathing state threshold. The output unit is used to control the audio output device to output a preset reward audio based on the positive feedback signal.

[0066] In some preferred embodiments, controlling the volume and / or pitch of the sound to fluctuate when the respiratory state signal indicates unstable exhalation includes: Based on the parameter values ​​reflecting expiratory stability in the respiratory state signal, a corresponding fluctuation control signal is calculated and applied to the audio output in real time; The fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a tone fluctuation signal for modulating the frequency.

[0067] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned AI-based breathing training control device and its various units can be referred to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity, these details will not be repeated here.

[0068] The aforementioned AI-based breathing training control device can be implemented as a computer program, which can, for example... Figure 2 It runs on the computer device shown.

[0069] Please see Figure 2 , Figure 2This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0070] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0071] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute an AI-based breathing training control method.

[0072] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0073] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an AI-based breathing training control method.

[0074] The network interface 505 is used for network communication with other devices. Those skilled in the art will understand that the above structure is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0075] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps: Monitor the user's breathing status and generate corresponding breathing status signals; Based on the breathing state signal, a corresponding sound control signal is generated; According to the sound control signal, the preset audio output device is controlled to emit a corresponding sound; The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate.

[0076] In some preferred embodiments, generating a corresponding sound control signal based on the breathing state signal includes: Extract respiratory feature parameters from the respiratory state signal, wherein the respiratory feature parameters include at least one of expiratory flow rate, expiratory rhythm and expiratory stability; The breathing feature parameters are mapped to corresponding music feature control instructions, which are used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

[0077] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: Map the exhalation rhythm to instructions that control the rhythm of the sound; And / or, map the expiratory flow rate to instructions that control the harmonic richness of the sound; And / or, map the expiratory stability to instructions that control the timbre effects of the sound.

[0078] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: The respiratory characteristic parameters are preprocessed to obtain input data; The input data is fed into a pre-trained AI music generation model, which then generates matching music feature data based on the input data. Based on the music feature data, a corresponding music feature control instruction is generated.

[0079] In some preferred embodiments, the method further includes: It receives the user's touch operation and generates the corresponding finger position signal; The pitch of the sound to be generated is determined based on the finger position signal. The step of controlling a preset audio output device to emit a corresponding sound according to the sound control signal includes: The scale sound determined by the finger position signal is used as the main melody sound; The sound generated under the control of the sound control signal is used as background music; The main melody is mixed with the background music in real time and then output.

[0080] In some preferred embodiments, the method further includes: Preset respiratory state thresholds corresponding to the breathing training goals; When the user's breathing state is detected to reach the breathing state threshold, a positive feedback signal is generated; Based on the positive feedback signal, the audio output device is controlled to output a preset reward audio.

[0081] In some preferred embodiments, controlling the volume and / or pitch of the sound to fluctuate when the respiratory state signal indicates unstable exhalation includes: Based on the parameter values ​​reflecting expiratory stability in the respiratory state signal, a corresponding fluctuation control signal is calculated and applied to the audio output in real time; The fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a tone fluctuation signal for modulating the frequency.

[0082] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0083] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0084] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform the following steps: Monitor the user's breathing status and generate corresponding breathing status signals; Based on the breathing state signal, a corresponding sound control signal is generated; According to the sound control signal, the preset audio output device is controlled to emit a corresponding sound; The sound control signal is used at least to control the volume and / or pitch of the sound, and when the breathing state signal indicates unstable exhalation, it controls the volume and / or pitch of the sound to fluctuate.

[0085] In some preferred embodiments, generating a corresponding sound control signal based on the breathing state signal includes: Extract respiratory feature parameters from the respiratory state signal, wherein the respiratory feature parameters include at least one of expiratory flow rate, expiratory rhythm and expiratory stability; The breathing feature parameters are mapped to corresponding music feature control instructions, which are used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

[0086] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: Map the exhalation rhythm to instructions that control the rhythm of the sound; And / or, map the expiratory flow rate to instructions that control the harmonic richness of the sound; And / or, map the expiratory stability to instructions that control the timbre effects of the sound.

[0087] In some preferred embodiments, mapping the breathing feature parameters to corresponding music feature control commands includes: The respiratory characteristic parameters are preprocessed to obtain input data; The input data is fed into a pre-trained AI music generation model, which then generates matching music feature data based on the input data. Based on the music feature data, a corresponding music feature control instruction is generated.

[0088] In some preferred embodiments, the method further includes: It receives the user's touch operation and generates the corresponding finger position signal; The pitch of the sound to be generated is determined based on the finger position signal. The step of controlling a preset audio output device to emit a corresponding sound according to the sound control signal includes: The scale sound determined by the finger position signal is used as the main melody sound; The sound generated under the control of the sound control signal is used as background music; The main melody is mixed with the background music in real time and then output.

[0089] In some preferred embodiments, the method further includes: Preset respiratory state thresholds corresponding to the breathing training goals; When the user's breathing state is detected to reach the breathing state threshold, a positive feedback signal is generated; Based on the positive feedback signal, the audio output device is controlled to output a preset reward audio.

[0090] In some preferred embodiments, controlling the volume and / or pitch of the sound to fluctuate when the respiratory state signal indicates unstable exhalation includes: Based on the parameter values ​​reflecting expiratory stability in the respiratory state signal, a corresponding fluctuation control signal is calculated and applied to the audio output in real time; The fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a tone fluctuation signal for modulating the frequency.

[0091] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0092] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0093] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0094] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0095] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0096] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0097] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0098] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An AI-based breathing training control method, characterized in that, include: Monitor the user's breathing status and generate corresponding breathing status signals; Based on the breathing state signal, a corresponding sound control signal is generated; According to the sound control signal, a preset audio output device is controlled to emit a corresponding sound; wherein, the sound control signal is at least used to control the volume and / or pitch of the sound, and when the breathing state signal indicates that the exhalation is unstable, the volume and / or pitch of the sound is controlled to fluctuate.

2. The AI-based breathing training control method according to claim 1, characterized in that, The step of generating a corresponding sound control signal based on the breathing state signal includes: Extract respiratory feature parameters from the respiratory state signal, wherein the respiratory feature parameters include at least one of expiratory flow rate, expiratory rhythm and expiratory stability; The breathing feature parameters are mapped to corresponding music feature control instructions, which are used to control at least one of the rhythm, harmonic richness, or timbre effects of the sound.

3. The AI-based breathing training control method according to claim 2, characterized in that, The step of mapping the breathing feature parameters to corresponding music feature control commands includes: Map the exhalation rhythm to instructions that control the rhythm of the sound; And / or, map the expiratory flow rate to instructions controlling the harmonic richness of the sound; And / or, map the expiratory stability to instructions that control the timbre effects of the sound.

4. The AI-based breathing training control method according to claim 2, characterized in that, The step of mapping the breathing feature parameters to corresponding music feature control commands includes: The respiratory characteristic parameters are preprocessed to obtain input data; The input data is fed into a pre-trained AI music generation model, which then generates matching music feature data based on the input data. Based on the music feature data, a corresponding music feature control instruction is generated.

5. The AI-based breathing training control method according to claim 1, characterized in that, The method further includes: It receives the user's touch operation and generates the corresponding finger position signal; The pitch of the sound to be generated is determined based on the finger position signal. The step of controlling a preset audio output device to emit a corresponding sound according to the sound control signal includes: The scale sound determined by the finger position signal is used as the main melody sound; The sound generated under the control of the sound control signal is used as background music; The main melody is mixed with the background music in real time and then output.

6. The AI-based breathing training control method according to claim 1, characterized in that, The method further includes: Preset respiratory state thresholds corresponding to the breathing training goals; When the user's breathing state is detected to reach the breathing state threshold, a positive feedback signal is generated; Based on the positive feedback signal, the audio output device is controlled to output a preset reward audio.

7. The AI-based breathing training control method according to claim 1, characterized in that, When the respiratory state signal indicates unstable exhalation, controlling the volume and / or pitch of the sound to fluctuate includes: Based on the parameter values ​​reflecting expiratory stability in the respiratory state signal, a corresponding fluctuation control signal is calculated and applied to the audio output in real time; The fluctuation control signal includes an amplitude fluctuation signal for modulating the amplitude and / or a tone fluctuation signal for modulating the frequency.

8. An AI-based breathing training control device, characterized in that, Includes a unit for performing the method as described in any one of claims 1-7.

9. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1-7.

Images