Shooting stability auxiliary system based on multi-mode physiological parameter feedback

Abstract

The invention provides a shooting stability auxiliary system based on multi-modal physiological parameter feedback, which comprises a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module and a prompt module, the physiological signal acquisition module is used for acquiring a first physiological parameter of the shooter in real time in the process that the shooter prepares to shoot; the first physiological parameters at least comprise a respiratory signal and an electrocardiogram; the signal processing and feature extraction module is used for preprocessing the first physiological parameter to obtain a second physiological parameter, and performing feature extraction on the second physiological parameter to obtain a first key feature; the prediction module is used for determining a target shooting moment according to the first key feature and a first machine learning model; and the prompting module is used for prompting the shooter to shoot at the target shooting moment, so that the accurate shooting moment can be provided for the shooter, and the shooting effect of the shooter is improved.

Description

Technical Field

[0001] This invention relates to the field of shooting training assistance technology, specifically to a shooting stability assistance system based on multimodal physiological parameter feedback, which is an intelligent assistance system that integrates physiological signal monitoring and real-time feedback. Background Technology

[0002] Shooting demands extremely high levels of accuracy and stability, especially stability, which significantly influences accuracy. Generally, stability encompasses both physiological and psychological stability. Physiological stability involves shooting stance, grip, center of gravity, aiming, firing, and breathing, requiring the shooter to possess good shoulder and arm stability, lower limb support, balance, and coordination. Psychological stability refers to the shooter's composure under intense and stressful conditions; significant emotional fluctuations can negatively impact shooting results.

[0003] Currently, shooting training mainly relies on coach experience, visual observation, or the use of simple target analysis systems. These methods cannot quantify the shooter's internal physiological state, such as tension, breathing disorders, and heart rate fluctuations, nor can they provide the shooter with precise shooting timing. Summary of the Invention

[0004] This application provides a shooting stability assistance system based on multimodal physiological parameter feedback. It can collect the shooter's physiological parameters and use these parameters to predict the corresponding shooting time. This shooting time can correspond to the shooter's optimal shooting state, thereby providing the shooter with a precise shooting time to improve the shooter's shooting effect.

[0005] This application provides a shooting stability assistance system based on multimodal physiological parameter feedback. The system includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The physiological signal acquisition module is used to acquire the shooter's first physiological parameters in real time during the shooter's preparation for shooting; the first physiological parameters include at least: respiratory signals and electrocardiogram; The signal processing and feature extraction module is used to preprocess the first physiological parameter to obtain the second physiological parameter, and to extract features from the second physiological parameter to obtain the first key feature; The prediction module is used to determine the target firing time based on the first key feature and the first machine learning model; The prompting module is used to prompt the shooter to fire at the moment the target is to be fired.

[0006] The embodiments of this application have the following beneficial effects: The shooting stability assistance system based on multimodal physiological parameter feedback, as described in this application embodiment, includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The physiological signal acquisition module acquires the shooter's first physiological parameters in real time during the shooter's preparation for firing. These first physiological parameters include at least respiratory signals and an electrocardiogram (ECG). The signal processing and feature extraction module preprocesses the first physiological parameters to obtain second physiological parameters and extracts features from the second physiological parameters to obtain first key features. The prediction module determines the target firing time based on the first key features and a first machine learning model. The prompting module prompts the shooter to fire at the target firing time. This system can acquire real-time physiological parameters from the shooter's respiratory and ECG modes, preprocess them to reduce noise interference, extract features to ensure feature saliency, and predict the firing time based on these features. This allows for accurate capture of the optimal firing time, which corresponds to the shooter's best firing state, thus providing the shooter with a precise firing time to improve shooting performance. Attached Figure Description

[0007] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 This is a first structural schematic diagram of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application; Figure 2 This is a schematic diagram of the second structure of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application; Figure 3 This is a schematic diagram of the third structure of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application; Figure 4 This is a schematic diagram of the fourth structure of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application; Figure 5 This is a schematic diagram of the fifth structure of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0009] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0010] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0011] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0012] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0013] In this embodiment of the application, heart rate variability (HRV) is a quantitative indicator of minute fluctuations in heart rate intervals, reflecting the autonomic nervous system's ability to regulate the heart.

[0014] Please see Figure 1 , Figure 1This is a first structural schematic diagram of a shooting stability assistance system based on multimodal physiological parameter feedback provided in an embodiment of this application. The shooting stability assistance system based on multimodal physiological parameter feedback includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module, wherein... The physiological signal acquisition module is used to acquire the shooter's first physiological parameters in real time during the shooter's preparation for shooting; the first physiological parameters include at least: respiratory signals and electrocardiogram; The signal processing and feature extraction module is used to preprocess the first physiological parameter to obtain the second physiological parameter, and to extract features from the second physiological parameter to obtain the first key feature; The prediction module is used to determine the target firing time based on the first key feature and the first machine learning model; The prompting module is used to prompt the shooter to fire at the moment the target is to be fired.

[0015] Among them, such as Figure 1 As shown, the shooting stability assistance system based on multimodal physiological parameter feedback includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The physiological signal acquisition module, signal processing and feature extraction module, prediction module, and prompting module can communicate with each other. The physiological signal acquisition module, signal processing and feature extraction module, prediction module, and prompting module can be hardware modules and / or software modules, respectively.

[0016] The physiological signal acquisition module may include at least one of the following: a respiratory sensor, an electrocardiogram sensor, a motion sensor, etc., without limitation.

[0017] Among these, respiratory sensors can be used to acquire respiratory waves and calculate respiratory rate, respiratory depth, inspiratory time, breath-holding time, and expiratory time. Electrocardiogram (ECG) sensors can acquire ECGs and extract heart rate (HR) and heart rate variability (HRV) indicators, such as SDNN, RMSSD, LF / HF, etc. Motion sensors can be used to detect microfibrillation, etc.

[0018] The physiological signal acquisition module can be embedded inside or on the shooter's body, or placed near the shooter. For example, it can be installed on a wearable device, which may include a shooting stability assistance system based on multimodal physiological parameter feedback. Specifically, the physiological signal acquisition module can collect the shooter's primary physiological parameters in real time during the shooter's preparation for firing. For example, it can acquire the shooter's physiological parameters at specified time intervals to obtain the primary physiological parameters, which at least include respiratory signals and an electrocardiogram. The specified time intervals can be preset or set by system default.

[0019] The signal processing and feature extraction module can preprocess the first physiological parameter, such as filtering, noise reduction, smoothing, etc., to obtain the second physiological parameter, and perform feature extraction on the second physiological parameter to obtain the first key feature. The first key feature may include respiratory-related features and / or electrocardiogram-related features.

[0020] Among them, ECG-related features may include at least one of the following: R wave peak value, RR interval sequence, HRV index, etc., without limitation.

[0021] Among them, respiratory wave-related features may include at least one of the following: peaks, troughs, inspiratory time, expiratory time, breath-holding time, respiratory rate, etc., without limitation.

[0022] The HRV index can include at least one of the following: time-domain indexes (e.g., standard deviation of all RR intervals (SDNN), root mean square of successive differences (RMSSD), percentage of adjacent NN intervals differing by more than 50ms (pNN50), etc.), frequency-domain indexes (e.g., performing fast Fourier transform analysis on the RR interval sequence to calculate VLF (ultra-low frequency power), LF (low frequency power), HL (high frequency power), low frequency / high frequency ratio, etc.), nonlinear indexes (e.g., scatter plots (SD1, SD2), sample entropy, fractal dimension, etc.), etc., without limitation.

[0023] For example, the signal processing and feature extraction module can filter, denoise, and segment the acquired raw signals, and extract key features. For instance, it can extract inspiratory / expiratory duration, respiratory interval, and amplitude stability from respiratory waves; and it can extract the RR interval sequence from electrocardiograms (ECGs) and calculate time-domain, frequency-domain, and nonlinear HRV features, etc. Other features include ECG signal preprocessing (filtering the raw ECG signal, such as bandpass filtering to remove baseline drift and power line interference) and denoising; R-wave peak detection (using differential thresholding and wavelet transform to accurately locate the R-wave peak in each heartbeat cycle); RR interval sequence extraction (calculating the time interval between adjacent R-wave peaks to form an RR interval sequence); and identification and interpolation correction of abnormal beats (such as premature beats and missed beats) to generate a normal sinus rhythm interval sequence for HRV analysis. For example, respiratory signal preprocessing: filtering and smoothing the raw respiratory signal; peak detection: identifying the peak point of the respiratory waveform, corresponding to the end of inspiration or the beginning of expiration; trough detection: identifying the trough point of the respiratory waveform, corresponding to the end of expiration or the beginning of inspiration; zero intersection or slope change point detection: used to more finely divide the inflection points of inspiration, expiration or breath-holding; respiratory indicators: inspiratory time, expiratory time, breath-holding time, respiratory rate.

[0024] The first machine learning model can be pre-set or a system default. For example, it can include neural network models, linear regression models, etc. The input to the first machine learning model can be relevant physiological characteristics, and the output can be the firing time or a stability evaluation value. The stability evaluation value is used to assess the shooter's stability; a higher stability evaluation value indicates better stability, and vice versa. The prediction module can be used to determine the target firing time based on the first key feature and the first machine learning model. For example, the first key feature can be input into the first machine learning model to obtain the target firing time.

[0025] The prompting module can prompt the shooter to fire at the target's firing time. The prompting module can be a display module, a voice module, etc.

[0026] Among them, such as Figure 2 As shown, the shooting stability assistance system based on multimodal physiological parameter feedback also includes a shooting critical event detection module. This shooting critical event detection module can be used to determine the firing moment. The shooting critical event detection module may include hardware modules and / or software modules. The shooting critical event detection module can communicate with other modules in the shooting stability assistance system based on multimodal physiological parameter feedback. For example, the firing moment can be determined by detecting the body tremor during shooting through a motion sensor. That is, the shooting speed of the shooter can be analyzed by using the deviation between the actual firing moment and the target firing moment.

[0027] Among them, such as Figure 3 As shown, the shooting stability assistance system based on multimodal physiological parameter feedback also includes a data analysis and state assessment module. This module can be used to establish correlation models. For example, it can correlate extracted physiological characteristics with key shooting events (a data window of N seconds before firing), where N can be preset or defaulted to by the system, and N is a positive integer. For example, it can analyze whether breathing is in a stable end-expiratory phase before firing, and whether HRV is in a relaxed state with high-frequency (HF) dominance. Another example is the definition of an 'ideal shooting physiological state template': based on a large amount of data from excellent shooters or theoretical models, it defines the optimal range of physiological parameters at the moment of firing (e.g., respiratory rate <10 breaths / min, stable heart rate, high HF power ratio). Furthermore, it can provide real-time state scoring / warning, such as comparing current physiological characteristics with the "ideal template" in real time to generate a stability score or risk warning (e.g., "tachypnea," "insufficient heart rate variability"), etc. The data analysis and state assessment module can include hardware modules and / or software modules, and can communicate with other modules in the shooting stability assistance system based on multimodal physiological parameter feedback. This allows for both quantification and personalization. Specifically, it enables the establishment of a quantitative relationship between physiological parameters and shooting performance, providing each shooter with a personalized "physiological baseline" and training goals.

[0028] The shooting stability assistance system based on multimodal physiological parameter feedback, as described in this application embodiment, includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The physiological signal acquisition module acquires the shooter's first physiological parameters in real time during the shooter's preparation for firing. These first physiological parameters include at least respiratory signals and an electrocardiogram (ECG). The signal processing and feature extraction module preprocesses the first physiological parameters to obtain second physiological parameters and extracts features from the second physiological parameters to obtain first key features. The prediction module determines the target firing time based on the first key features and a first machine learning model. The prompting module prompts the shooter to fire at the target firing time. This system can acquire real-time physiological parameters from the shooter's respiratory and ECG modes, preprocess them to reduce noise interference, extract features to ensure feature saliency, and predict the firing time based on these features. This allows for accurate capture of the optimal firing time, which corresponds to the shooter's best firing state, thus providing the shooter with a precise firing time to improve shooting performance.

[0029] Furthermore, related technologies cannot monitor and guide shooters to their optimal physiological state in real time before firing. They lack models that quantitatively correlate physiological parameters (such as respiratory waves and heart rate variability) with shooting stability. Feedback information is delayed and unintuitive, failing to form a closed-loop training process of "perception-adjustment." This application provides an auxiliary system capable of real-time, multi-parameter, and intelligent analysis of a shooter's physiological state, offering precise guidance. It visualizes the shooter's internal state, transforming invisible physiological states into visible and audible guidance signals. Furthermore, it enables real-time closed-loop training, forming a "monitoring-evaluation-feedback-adjustment" loop before firing, accelerating skill internalization.

[0030] Optionally, the first physiological parameter includes physiological parameter data over a preset time period; regarding the preprocessing of the first physiological parameter to obtain the second physiological parameter, the signal processing and feature extraction module is specifically used for: The physiological parameter data is filtered to obtain the filtered physiological parameter data. The filtered physiological parameter data is smoothed to obtain the smoothed physiological parameter data. The smoothed physiological parameter data is segmented to obtain the second physiological parameter, which includes multiple segments of physiological parameter data.

[0031] The first physiological parameter may include physiological parameter data for a preset time period. The preset time period may be a time period before the current time, and may or may not include the current time.

[0032] Specifically, the physiological parameter data can be filtered to obtain filtered physiological parameter data, which can reduce noise. Then, the filtered physiological parameter data can be smoothed to obtain smoothed physiological parameter data, ensuring data smoothness. Finally, the smoothed physiological parameter data can be segmented to obtain a second physiological parameter. The second physiological parameter includes multiple segments of physiological parameter data. Each segment of physiological parameter data can include a time period and at least one physiological parameter data. This can not only evaluate the shooter's shooting stability in segments, but also help to accurately predict the optimal shooting time.

[0033] Optionally, the multi-segment physiological parameter data includes: multi-segment respiratory data and multi-segment electrocardiogram data; the multi-segment respiratory data and the multi-segment electrocardiogram data correspond one-to-one; the first key feature includes multiple first feature sets and multiple second feature sets; In the process of extracting features from the second physiological parameter to obtain the first key feature, the signal processing and feature extraction module is specifically used for: Feature extraction is performed on the multiple respiratory data segments to obtain the multiple first feature sets; Feature extraction is performed on the multiple electrocardiogram data segments to obtain the multiple second feature sets.

[0034] In this context, multiple respiratory data segments correspond one-to-one with multiple first feature sets, meaning that a single respiratory data segment corresponds to a first feature set, and each first feature set may include at least one feature.

[0035] In this context, multiple electrocardiogram (ECG) data segments correspond one-to-one with multiple second feature sets, meaning that one ECG data segment corresponds to one second feature set, and each second feature set can include at least one feature.

[0036] Specifically, features can be extracted from multiple respiratory data segments to obtain multiple first feature sets. Correspondingly, features can be extracted from multiple electrocardiogram data segments to obtain multiple second feature sets. The multiple first feature sets correspond one-to-one with the multiple second feature sets, that is, each first feature set corresponds to one second feature set.

[0037] Optionally, in determining the target firing time based on the first key feature and the first machine learning model, the prediction module is specifically used for: The plurality of first feature sets and the plurality of second feature sets are input into the first machine learning model to obtain a plurality of first stability evaluation values; The target firing time is determined based on the intermediate time of the multiple first stability evaluation values ​​and the multiple physiological parameter data segments.

[0038] Specifically, the input to the first machine learning model is features, and the output is a stability evaluation value. Multiple first feature sets and multiple second feature sets can be input into the first machine learning model to obtain multiple first stability evaluation values. That is, the target shooting time can be determined based on multiple first stability evaluation values ​​and the intermediate time of multiple physiological parameter data. In other words, shooting time prediction is performed based on these features, which can accurately capture the best shooting time. This shooting time can correspond to the shooter's best shooting state, and thus can provide the shooter with a precise shooting time to improve the shooter's shooting effect.

[0039] For example, the first machine learning model could be a machine learning model trained using historical data (such as logistic regression) used for shooting state assessment. For instance, the input could be a physiological feature vector (heart rate, HRV, SDNN, RMSSD, HR, LF, exhalation time, inhalation time, breath-holding time, respiratory rate, respiratory depth, etc.) two seconds before firing, and the output could be a "high stability probability", which could correspond to a stability evaluation value.

[0040] Optionally, the first machine learning model includes a first model and a second model. Regarding inputting the plurality of first feature sets and the plurality of second feature sets into the first machine learning model to obtain a plurality of first stability evaluation values, the prediction module is specifically used for: The plurality of first feature sets are input into the first model to obtain a plurality of first reference stability evaluation values; The plurality of second feature sets are input into the second model to obtain a plurality of second reference stability evaluation values; The plurality of first stability evaluation values ​​are determined based on the plurality of first reference stability evaluation values ​​and the plurality of second reference stability evaluation values.

[0041] The first machine learning model includes a first model and a second model. Both the first and second models can be preset or set by the system default. For example, the first model can include a neural network model, a linear regression model, etc., and the second model can also include a neural network model, a linear regression model, etc. The input of the first model is a first feature set, and the output is a stability evaluation value. The input of the second model is a second feature set, and the output is a stability evaluation value. The first model and the second model can be the same or different.

[0042] Specifically, multiple first feature sets can be input into the first model to obtain multiple first reference stability evaluation values. Then, multiple second feature sets can be input into the second model to obtain multiple second reference stability evaluation values. Finally, weight pairs can be obtained, which include first weights and second weights, with the sum of the first weights and second weights being 1. That is, multiple first stability evaluation values ​​can be obtained by weighting multiple first reference stability evaluation values, multiple second reference stability evaluation values, and weight pairs. For example, for each segment, first reference stability evaluation value * first weight + second reference stability evaluation value * second weight = first stability evaluation value. This means that the shooter's stability can be evaluated from two dimensions: respiration and electrocardiogram, thereby accurately capturing the optimal shooting moment. This shooting moment corresponds to the shooter's best shooting state and can provide the shooter with a precise shooting moment to improve the shooter's shooting effect.

[0043] Optionally, in determining the target firing time based on the intermediate time of the plurality of first stability evaluation values ​​and the plurality of physiological parameter data, the prediction module is specifically used for: The first fitting line and the first fitting curve are obtained by fitting the multiple first stability evaluation values ​​and the midpoint of the multiple physiological parameter data; the horizontal axis of the first fitting line and the first fitting curve are both time, and the vertical axis is both stability evaluation value. The first moment corresponding to the preset stability evaluation value is determined based on the first fitted straight line; The second time point corresponding to the preset stability evaluation value is determined based on the first fitted curve; The target firing time is determined based on the first time and the second time.

[0044] In this system, multiple first stability evaluation values ​​correspond one-to-one with the intermediate times of multiple physiological parameter data segments. Therefore, multiple first stability evaluation values ​​and the intermediate times of multiple physiological parameter data segments can be associated as multiple coordinate points. Each coordinate point corresponds to a first stability evaluation value and its corresponding intermediate time. Then, a straight line is fitted based on these multiple coordinate points to obtain a first fitted straight line. The horizontal axis of the first fitted straight line is time, and the vertical axis is the stability evaluation value. Correspondingly, multiple coordinate points can be fitted with a curve to obtain a first fitted curve. The horizontal axis of the first fitted curve is time, and the vertical axis is the stability evaluation value.

[0045] Furthermore, the preset stability evaluation value can be set in advance or be the system default. For example, the first moment corresponding to the preset stability evaluation value can be determined based on the first fitted straight line, and the second moment corresponding to the preset stability evaluation value can be determined based on the first fitted curve. Finally, the target firing time can be determined based on the first moment and the second moment. The first fitted straight line and the first fitted curve reflect the shooting stability change trend of the shooter. Using this shooting stability change trend, the shooter's best firing time can be predicted, thereby ensuring the shooting effect.

[0046] Here, the first moment and the second moment can be a moment after the current moment, or the first moment and the second moment can be a moment before the current moment. There can be one or more second moments. For example, if there are multiple second moments, one can be selected, such as the moment most recent to the current moment.

[0047] Optionally, in determining the target firing time based on the first time and the second time, the prediction module is specifically used for: Detect whether the first time point and the second time point are later than the current time point; When the first moment is later than the current moment and the second moment is not later than the current moment, the first moment shall be taken as the moment of target firing; When the first moment is not later than the current moment and the second moment is later than the current moment, the second moment shall be taken as the moment of target firing; When the first moment is later than the current moment and the second moment is later than the current moment, the time difference between the first moment and the second moment and the current moment are determined respectively, and the smaller value among the time differences is selected as the time corresponding to the smaller value as the target firing moment; The step of real-time acquisition of the shooter's first physiological parameters is performed when the first moment is no later than the current moment and the second moment is no later than the current moment.

[0048] Specifically, it can detect whether the first moment and the second moment are later than the current moment. For example, if the first moment is later than the current moment and the second moment is not later than the current moment, the first moment can be taken as the target shooting moment. Or, if the first moment is not later than the current moment and the second moment is later than the current moment, the second moment can be taken as the target shooting moment. Or, if the first moment is later than the current moment and the second moment is later than the current moment, the time difference between the first moment and the second moment and the current moment is determined respectively, and the smaller value of the time difference is selected as the target shooting moment. Or, if the first moment is not later than the current moment and the second moment is not later than the current moment, it means that the shooter's posture or mindset is incorrect and needs to be prompted to readjust. In this case, the step of real-time collection of the shooter's first physiological parameters can be executed. In this way, the shooting stability change trend can be used to predict the shooter's optimal shooting moment, thereby ensuring the shooting effect.

[0049] Optionally, the prediction module is further specifically used for: Obtain the slope of the first fitted line to get the first slope; Detect whether the first slope is within a preset range; When the first slope is within the preset range, the step of determining the first moment corresponding to the preset stability evaluation value based on the first fitted straight line is executed.

[0050] The preset range can be set in advance or set by system default.

[0051] Specifically, the slope of the first fitted line can be obtained, and then it can be checked whether the first slope is within a preset range. If the first slope is within the preset range, it means that the shooter's breathing and electrocardiogram are fine and he is about to enter the best shooting state. Then the step of determining the first moment corresponding to the preset stability evaluation value based on the first fitted line can be executed. In this way, shooting efficiency and shooting effect can be guaranteed.

[0052] Optionally, the system further includes: a real-time feedback module; the real-time feedback module includes at least one of the following modules: a visual feedback module, an auditory feedback module, and a tactile feedback module; When the real-time feedback module includes the visual feedback module, it displays a respiratory wave guide curve and / or heart rate rhythm dots; And / or, When the real-time feedback module includes the auditory feedback module, a soothing breathing guide sound or rhythm is provided through the auditory feedback module; And / or, When the real-time feedback module includes the tactile feedback module, the tactile feedback module is used to vibrate and prompt the breathing rhythm.

[0053] Among them, such as Figure 4 As shown, the shooting stability assistance system based on multimodal physiological parameter feedback also includes a real-time feedback module. This module can be used to guide the shooter's adjustments in an intuitive way to quickly achieve a stable shooting state. For example, visual feedback: the AR glasses / display show a respiratory wave guidance curve, heart rate rhythm dots, and a "shrinking circle" progress bar representing stability. Another example is auditory feedback: soothing breathing guidance sounds or rhythms are provided through bone conduction headphones. Yet another example is tactile feedback: subtle vibrations from a smart wearable device provide feedback on breathing rhythm.

[0054] The real-time feedback module may include hardware modules and / or software modules. It can communicate with other modules in a shooting stability assistance system based on multimodal physiological parameter feedback. For example, the real-time feedback could use an interface simulating a scope, where the outer ring contracts with the breathing rhythm and the inner ring changes with heart rate stability; the optimal firing moment occurs when the two rings overlap and stabilize.

[0055] For example, when the real-time feedback module includes a visual feedback module (e.g., a display module), displaying a respiratory wave guidance curve and / or heart rate rhythm dots can guide the shooter to adjust their heart rate.

[0056] For example, when the real-time feedback module includes an auditory feedback module (e.g., bone conduction headphones), a soothing breathing guide sound or rhythm is provided through the auditory feedback module.

[0057] For example, when the real-time feedback module includes a haptic feedback module (e.g., a vibration module), the haptic feedback module can be used to provide vibration feedback to indicate the breathing rhythm.

[0058] Optionally, the system further includes: a data storage and review analysis module. The data storage and review analysis module is used to record physiological data, firing time, and bullet impact point for each shooting process.

[0059] Among them, such as Figure 5As shown, the shooting stability assistance system based on multimodal physiological parameter feedback also includes a data storage and review analysis module. This module can record physiological data, firing time, and bullet impact point for each shooting session. After training, a review can be performed to analyze the physiological state corresponding to "misses" or "excellent hits," providing personalized training suggestions. The data storage and review analysis module may include hardware and / or software modules, and can communicate with other modules in the shooting stability assistance system based on multimodal physiological parameter feedback. This enables scientific review, digitizes the training process, and facilitates precise analysis of the root causes of problems.

[0060] The following is combined with Figure 6 The electronic devices in the embodiments of this application will be described. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface through an internal communication bus. The electronic device includes a shooting stability assistance system based on multimodal physiological parameter feedback. The shooting stability assistance system based on multimodal physiological parameter feedback includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module.

[0061] It is understood that the electronic device may include more or fewer structural elements than those shown in the above block diagram. For example, the electronic device may also include at least one of the following modules, such as a Bluetooth module, a sensor, a Wi-Fi module, a power module, physical buttons, a speaker, a display module, etc., without limitation.

[0062] The processor can be used for: During the shooter's preparation for firing, the physiological signal acquisition module collects the shooter's first physiological parameters in real time; the first physiological parameters include at least: respiratory signals and electrocardiogram. The first physiological parameter is preprocessed by the signal processing and feature extraction module to obtain the second physiological parameter, and the second physiological parameter is then used to extract features to obtain the first key feature. The prediction module determines the target firing time based on the first key feature and the first machine learning model. The prompting module prompts the shooter to fire at the target firing time.

[0063] In this embodiment, the electronic device includes a shooting stability assistance system based on multimodal physiological parameter feedback. This system comprises a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The physiological signal acquisition module acquires the shooter's first physiological parameters in real time during the shooter's preparation for firing. These first physiological parameters include at least respiratory signals and an electrocardiogram (ECG). The signal processing and feature extraction module preprocesses the first physiological parameters to obtain second physiological parameters and extracts features from them to obtain first key features. The prediction module determines the target firing time based on the first key features and a first machine learning model. The prompting module prompts the shooter to fire at the target firing time. This system can acquire the shooter's real-time physiological parameters from multiple modalities (respiratory and ECG aspects), preprocess them to reduce noise interference, extract features to ensure feature saliency, and predict the firing time based on these features. This allows for accurate capture of the optimal firing time, which corresponds to the shooter's best firing state, thus providing the shooter with a precise firing time to improve shooting performance.

[0064] The processor can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a general-purpose processor, a digital signal processor (DSP), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0065] Furthermore, the processor can also implement or execute various exemplary logic blocks, units, and circuits described in conjunction with the disclosure of this application. Additionally, the processor can also be a combination of components implementing computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. Communication units can be communication interfaces, transceivers, transceiver circuits, etc., and storage units can be memory.

[0066] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0067] The memory can be volatile or non-volatile, or may include both. The non-volatile memory can be a programmable read-only memory (PROM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0068] The volatile memory can be random access memory (RAM), which serves as an external cache. The above description is by way of example and not limitation; many forms of random access memory (RAM) are available, such as double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), static RAM (SRAM), synchronous dynamic random access memory (SDRAM), dynamic random access memory (DRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0069] The electronic devices may include wearable devices or shooting stability assistance systems based on multimodal physiological parameter feedback.

[0070] This application also provides a shooting stability assistance method based on multimodal physiological parameter feedback. This method is applied to a shooting stability assistance system based on multimodal physiological parameter feedback. The shooting stability assistance system includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module. The method includes the following steps: During the shooter's preparation for firing, the physiological signal acquisition module collects the shooter's first physiological parameters in real time; the first physiological parameters include at least: respiratory signals and electrocardiogram. The first physiological parameter is preprocessed by the signal processing and feature extraction module to obtain the second physiological parameter, and the second physiological parameter is then used to extract features to obtain the first key feature. The prediction module determines the target firing time based on the first key feature and the first machine learning model. The prompting module prompts the shooter to fire at the target firing time. This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0071] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0072] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0073] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0074] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0075] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0076] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0077] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0078] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A shooting stability assistance system based on multimodal physiological parameter feedback, characterized in that, The shooting stability assistance system based on multimodal physiological parameter feedback includes: a physiological signal acquisition module, a signal processing and feature extraction module, a prediction module, and a prompting module, wherein... The physiological signal acquisition module is used to acquire the shooter's first physiological parameters in real time during the shooter's preparation for shooting; the first physiological parameters include at least: respiratory signals and electrocardiogram; The signal processing and feature extraction module is used to preprocess the first physiological parameter to obtain the second physiological parameter, and to extract features from the second physiological parameter to obtain the first key feature; The prediction module is used to determine the target firing time based on the first key feature and the first machine learning model; The prompting module is used to prompt the shooter to fire at the moment the target is to be fired.

2. The system as described in claim 1, characterized in that, The first physiological parameter includes physiological parameter data over a preset time period; regarding the preprocessing of the first physiological parameter to obtain the second physiological parameter, the signal processing and feature extraction module is specifically used for: The physiological parameter data is filtered to obtain the filtered physiological parameter data. The filtered physiological parameter data is smoothed to obtain the smoothed physiological parameter data. The smoothed physiological parameter data is segmented to obtain the second physiological parameter, which includes multiple segments of physiological parameter data.

3. The system as described in claim 2, characterized in that, The multi-segment physiological parameter data includes: multi-segment respiratory data and multi-segment electrocardiogram data; the multi-segment respiratory data and multi-segment electrocardiogram data correspond one-to-one; the first key feature includes multiple first feature sets and multiple second feature sets; In the process of extracting features from the second physiological parameter to obtain the first key feature, the signal processing and feature extraction module is specifically used for: Feature extraction is performed on the multiple respiratory data segments to obtain the multiple first feature sets; Feature extraction is performed on the multiple electrocardiogram data segments to obtain the multiple second feature sets.

4. The system as described in claim 3, characterized in that, In determining the target firing time based on the first key feature and the first machine learning model, the prediction module is specifically used for: The plurality of first feature sets and the plurality of second feature sets are input into the first machine learning model to obtain a plurality of first stability evaluation values; The target firing time is determined based on the intermediate time of the multiple first stability evaluation values ​​and the multiple physiological parameter data segments.

5. The system as described in claim 4, characterized in that, The first machine learning model includes a first model and a second model. Regarding inputting the plurality of first feature sets and the plurality of second feature sets into the first machine learning model to obtain a plurality of first stability evaluation values, the prediction module is specifically used for: The plurality of first feature sets are input into the first model to obtain a plurality of first reference stability evaluation values; The plurality of second feature sets are input into the second model to obtain a plurality of second reference stability evaluation values; The plurality of first stability evaluation values ​​are determined based on the plurality of first reference stability evaluation values ​​and the plurality of second reference stability evaluation values.

6. The system as described in claim 4 or 5, characterized in that, In determining the target firing time based on the intermediate time of the plurality of first stability evaluation values ​​and the plurality of physiological parameter data segments, the prediction module is specifically used for: The first fitting line and the first fitting curve are obtained by fitting the multiple first stability evaluation values ​​and the midpoint of the multiple physiological parameter data; the horizontal axis of the first fitting line and the first fitting curve are both time, and the vertical axis is both stability evaluation value. The first moment corresponding to the preset stability evaluation value is determined based on the first fitted straight line; The second time point corresponding to the preset stability evaluation value is determined based on the first fitted curve; The target firing time is determined based on the first time and the second time.

7. The system as described in claim 6, characterized in that, In determining the target firing time based on the first time and the second time, the prediction module is specifically used for: Detect whether the first time point and the second time point are later than the current time point; When the first moment is later than the current moment and the second moment is not later than the current moment, the first moment shall be taken as the moment of target firing; When the first moment is not later than the current moment and the second moment is later than the current moment, the second moment shall be taken as the moment of target firing; When the first moment is later than the current moment and the second moment is later than the current moment, the time difference between the first moment and the second moment and the current moment are determined respectively, and the smaller value among the time differences is selected as the time corresponding to the smaller value as the target firing moment; The step of real-time acquisition of the shooter's first physiological parameters is performed when the first moment is no later than the current moment and the second moment is no later than the current moment.

8. The system as described in claim 7, characterized in that, The prediction module is also specifically used for: Obtain the slope of the first fitted line to get the first slope; Detect whether the first slope is within a preset range; When the first slope is within the preset range, the step of determining the first moment corresponding to the preset stability evaluation value based on the first fitted straight line is executed.

9. The system according to any one of claims 1-5, characterized in that, The system further includes: a real-time feedback module; the real-time feedback module includes at least one of the following modules: a visual feedback module, an auditory feedback module, and a tactile feedback module; When the real-time feedback module includes the visual feedback module, it displays a respiratory wave guide curve and / or heart rate rhythm dots; And / or, When the real-time feedback module includes the auditory feedback module, a soothing breathing guide sound or rhythm is provided through the auditory feedback module; And / or, When the real-time feedback module includes the tactile feedback module, the tactile feedback module is used to vibrate and prompt the breathing rhythm.

10. The system according to any one of claims 1-5, characterized in that, The system also includes: a data storage and review analysis module; The data storage and review analysis module is used to record physiological data, firing time, and bullet impact point for each shooting process.

Images