A prompt processing method, apparatus, terminal device, and program product

Abstract

This application relates to the field of health monitoring technology, providing a prompt processing method, device, terminal equipment, and program product. The method is applied to fatigue detection scenarios, acquiring the user's current neck information at the current moment, and acquiring the user's historical neck information over a historical time period prior to the current moment; calculating the user's current electromyographic fatigue parameters based on current neck muscle signals, and calculating the user's current postural load parameters based on current neck posture signals; calculating the user's current load time parameters based on the user's historical neck information, current electromyographic fatigue parameters, and current postural load parameters over a historical time period; determining the user's current neck muscle fatigue level based on the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters; and outputting prompt information. This method considers the crucial role of time in the fatigue formation process, greatly improving the accuracy and reliability of the output prompt information.

Description

Technical Field

[0001] This application belongs to the field of health monitoring technology, and in particular relates to a prompt processing method, device, terminal equipment and program product. Background Technology

[0002] With the widespread use of mobile electronic devices and computer terminals, prolonged periods of working with the head down, hunching over desks, and maintaining a fixed posture have become common behavioral patterns for modern people, especially office workers, students, and users of smart devices for extended periods. In these scenarios, the head is constantly in a forward-flexed position, causing the neck muscles to endure abnormal mechanical loads, potentially leading to chronic strain, myofascial pain syndrome, and degenerative changes in the cervical spine. Therefore, accurate and continuous monitoring of neck muscle fatigue is crucial for preventing related diseases and for early intervention.

[0003] However, neck muscle fatigue depends not only on the current load level but also on the duration of the load, belonging to a cumulative effect over time. However, most existing technologies rely on instantaneous signal characteristics for fatigue assessment, neglecting the crucial role of time in the fatigue formation process and reducing the reliability of fatigue evaluation results. Summary of the Invention

[0004] This application provides a prompt processing method, apparatus, terminal device, and program product that takes into account the key role of time in the fatigue formation process, greatly improving the accuracy and reliability of the output prompt information.

[0005] In a first aspect, embodiments of this application provide a prompting processing method applied to fatigue detection scenarios, including: Obtain the user's current neck information at the current moment, as well as the user's historical neck information during the historical time period before the current moment. The current neck information includes the current neck muscle signals and the current neck posture signals. The user's current electromyographic fatigue parameters are calculated based on the current neck muscle signals, and the user's current posture load parameters are calculated based on the current neck posture signals. Based on the user's historical neck information, current electromyographic fatigue parameters, and current postural load parameters within a historical time period, the user's current load time parameters are calculated. Based on the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters, determine the current fatigue level of the user's neck muscles; Output a prompt message associated with the current fatigue level. The prompt message indicates the current fatigue level and provides corresponding suggestions.

[0006] In one possible implementation of the first aspect, calculating the user's current electromyographic fatigue parameters based on the current neck muscle signals includes: The current neck muscle signal is subjected to feature extraction processing to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal; Based on the time-domain feature parameters and the frequency-domain feature parameters, the electromyographic fatigue parameters of the user are calculated.

[0007] In one possible implementation of the first aspect, the step of performing feature extraction processing on the current neck muscle signal to obtain time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal includes: The current neck muscle signal is filtered and rectified to obtain the processed electromyographic signal. The processed electromyographic signal is subjected to feature extraction processing to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal.

[0008] In one possible implementation of the first aspect, the current neck posture signal includes current neck flexion data and current neck lateral flexion data, and the calculation of the user's current posture load parameters based on the current neck posture signal includes: Feature extraction processing is performed on the current cervical flexion data and the current cervical lateral flexion data to obtain the user's posture deviation feature parameters, which are used to characterize the user's posture deviation from the reference angle. Based on the posture deviation feature parameters, the user's current posture load parameters are calculated.

[0009] In one possible implementation of the first aspect, calculating the user's current load time parameter based on the user's historical neck information within the historical time period, the current electromyographic fatigue parameter, and the current postural load parameter includes: Based on the user’s historical neck information at each historical time point within the historical time period, calculate the user’s historical posture load parameters and historical posture load parameters at each historical time point. The current load time parameter of the user is calculated based on the user's historical posture load parameter, the current electromyographic fatigue parameter, and the current posture load parameter at each historical time point.

[0010] In one possible implementation of the first aspect, determining the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current postural load parameters, and the current load time parameters includes: Calculate the user's comprehensive fatigue index parameters based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters; Based on the comprehensive fatigue index parameters, the current fatigue level of the user's neck muscles is determined.

[0011] In one possible implementation of the first aspect, determining the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current postural load parameters, and the current load time parameters includes: Detect whether at least one of the current electromyographic fatigue parameter, the current posture load parameter, and the current load time parameter has reached the set fatigue condition; If the electromyographic fatigue parameter is detected to reach the set fatigue condition, then the current fatigue level of the user is determined to be moderate fatigue level. If the posture load parameter or the fatigue time accumulation parameter is detected to meet the set fatigue condition, then the current fatigue level of the user is determined to be severe fatigue level.

[0012] Secondly, embodiments of this application provide a prompting processing device configured in a fatigue detection scenario, including: The acquisition module is used to acquire the user's current neck information at the current moment, and to acquire the user's historical neck information during a historical time period before the current moment. The current neck information includes current neck muscle signals and current neck posture signals. The first calculation module is used to calculate the user's current electromyographic fatigue parameters based on the current neck muscle signals, and to calculate the user's current posture load parameters based on the current neck posture signals. The second calculation module is used to calculate the user's current load time parameter based on the user's historical neck information, current electromyographic fatigue parameters, and current posture load parameters within the historical time period; The determination module is used to determine the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters. The output module is used to output prompt information associated with the current fatigue level. The prompt information is used to indicate the current fatigue level and the corresponding suggestion information.

[0013] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any of the first aspects.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any of the first aspects.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute any of the methods described in the first aspect above.

[0016] This application provides a prompting processing method, apparatus, terminal device, and program product. The method is applied to a fatigue detection scenario and includes: acquiring the user's current neck information at the current moment, and acquiring the user's historical neck information within a historical time period prior to the current moment. The current neck information includes current neck muscle signals and current neck posture signals. Based on the current neck muscle signals, the method calculates the user's current electromyographic fatigue parameters, and based on the current neck posture signals, the method calculates the user's current posture load parameters. Based on the user's historical neck information within the historical time period, the current electromyographic fatigue parameters, and the current posture load parameters, the method calculates the user's current load time parameters. Based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters, the method determines the user's current neck muscle fatigue level. The prompt information is used to indicate the current fatigue level, and also includes suggested information corresponding to the current fatigue level. By using the above technical solution, and determining the user's current neck muscle fatigue level based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters, the method considers the crucial role of time in the fatigue formation process, greatly improving the accuracy and reliability of the output prompt information. Attached Figure Description

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

[0018] Figure 1 This is a flowchart illustrating a prompt processing method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a prompt processing method provided in another embodiment of this application; Figure 3 This is a structural block diagram of a prompt processing device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0021] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this application 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 detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0023] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0025] It can be assumed that existing methods for monitoring neck status mainly focus on the analysis of a single signal source. One type of method is based on inertial measurement units or flexible posture sensors to obtain changes in neck angle and determine whether there is an undesirable posture by setting a threshold. Another type of method is based on surface electromyography signals to analyze muscle activity levels in order to assess muscle load.

[0026] However, all of the above methods have significant limitations. While posture-based monitoring methods can reflect the mechanical state of the neck, they cannot distinguish whether muscles are fatigued. Similarly, methods based solely on electromyography (EMG) signals, while reflecting muscle activity characteristics, struggle to identify external causes of fatigue, especially persistent loads resulting from poor posture, in the absence of postural information. Furthermore, most existing technologies rely on instantaneous signal characteristics for fatigue assessment, neglecting the crucial role of time in the fatigue formation process.

[0027] In reality, neck muscle fatigue depends not only on the current load level but also on the duration of the load, exhibiting a cumulative effect over time. Existing cue processing methods lack modeling of duration, making it difficult to accurately describe the development of fatigue and thus reducing the reliability of assessment results. Furthermore, existing cue processing methods primarily rely on "state cues," such as simple posture reminders or sedentary reminders, failing to provide targeted intervention strategies based on different types of fatigue. This hinders effective behavioral guidance and health management, limiting the intervention effectiveness of these methods in practical applications.

[0028] To address the issues of insufficient utilization of multi-source information, lack of time-cumulative modeling in fatigue assessment, and imperfect intervention mechanisms in existing technologies, this application provides a prompting processing method that can assess and guide behavior in neck muscle fatigue based on multimodal signal fusion, achieving non-invasive, continuous, and intelligent monitoring throughout the entire process from signal acquisition to fatigue assessment and feedback.

[0029] Figure 1 This is a flowchart illustrating a prompting method according to an embodiment of this application, applied to a fatigue detection scenario. It is provided as an example and not a limitation; this method can be applied to terminal devices, such as... Figure 1 As shown, the method includes: S101. Obtain the user's current neck information at the current moment, and obtain the user's historical neck information during the historical time period before the current moment.

[0030] The current neck information refers to user neck-related data collected at a specific monitoring moment (i.e., the current moment), used to assess the user's immediate neck state. In this embodiment, the current neck information may include current neck muscle signals and current neck posture signals. The current neck muscle signals may refer to bioelectrical signals collected from the user's neck muscles at the current moment, such as surface electromyography (sEMG), which can reflect the intensity of muscle activity, contraction pattern, and degree of fatigue. The current neck posture signals may refer to posture-related data collected from the user's neck or head at the current moment, used to characterize the spatial position and force state of the user's neck.

[0031] Historical neck information refers to user neck-related data collected continuously or periodically over a historical period prior to the current moment. It can be used to analyze the cumulative effect and trend of user neck load.

[0032] For example, current neck muscle signals can be acquired by attaching electrode pads to the skin of the user's neck and connecting them to a terminal device that can record the potential changes generated by muscle activity in real time. Alternatively, current neck muscle signals can be non-invasively acquired by integrating wearable electromyography (EMG) sensors into clothing or patches. Current neck posture signals can be acquired by an inertial measurement unit (IMU) sensor worn on the user's head or neck, which can provide real-time posture data such as pitch, yaw, and roll angles. Alternatively, current neck posture signals can be acquired using image recognition-based posture estimation techniques, capturing images of the user's neck or head with a camera and analyzing posture changes using algorithms.

[0033] In a specific implementation, this embodiment utilizes a flexible sensing unit for acquiring multimodal signals from the neck. This unit integrates surface electromyography (EMG) electrodes and a flexible strain sensor to achieve simultaneous monitoring of muscle electrical activity and neck posture changes. The EMG electrodes are constructed based on a low-modulus polymer substrate with a conductive layer formed on the substrate surface. This allows them to possess good conductivity while having mechanical properties that match those of the skin, enabling stable adhesion during neck movement and achieving high-quality signal acquisition. The strain sensor is also constructed based on a flexible substrate, utilizing the resistance change characteristics of the conductive layer on the substrate surface to continuously sense neck bending and posture changes, and outputting stable electrical signals during deformation.

[0034] Specifically, the electromyography electrode can use a low-modulus elastomer material (preferably SEBS) as the substrate, with an elastic modulus of 0.9-2 MPa. A flexible substrate film with a thickness of 50-200 µm is prepared by spin coating. A metal conductive layer (preferably silver or gold) with a thickness of 60-200 nm is deposited on the substrate surface using physical vapor deposition. The electrode pattern is designed using a mask. A conductive gel layer or microstructure is set on the electrode surface to reduce the skin-electrode interface impedance.

[0035] The strain sensor can use SEBS, which is different from the electromyographic electrode model, as a flexible substrate to construct a resistive strain sensing layer based on crack structure or conductive network. The sensor sensitivity is in the range of 20-200, maintains good linear response in the range of 0-100% strain, and has a response time of <600ms, which meets the requirements of dynamic attitude monitoring.

[0036] Furthermore, electromyographic electrodes and strain sensors can be modularly combined and deployed in the neck to achieve simultaneous acquisition of multimodal signals, providing a data foundation for subsequent fatigue assessment. The electromyographic electrodes can be arranged symmetrically, attached to the upper trapezius, sternocleidomastoid, and levator scapulae muscles respectively. The upper trapezius electrode is placed near the midpoint of the line connecting the seventh cervical vertebra to the acromion; the sternocleidomastoid electrode is placed in the middle of the line connecting the mastoid process behind the ear to the medial aspect of the clavicle; and the levator scapulae electrode is placed in the upper-middle section of the line connecting the superior angle of the scapula to the upper cervical vertebrae (C1-C4), approximately 1-2 cm medial to the superior angle of the scapula, and placed parallel to the muscle fiber direction to improve signal acquisition quality and reduce crosstalk from adjacent muscle groups. Reference electrodes are placed in the bony regions of the posterior neck (such as the spinous process) or the clavicle region. Strain sensors are placed in the midline of the posterior neck to monitor flexion / extension movements, and in the lateral neck region to monitor lateral flexion and rotation movements, thereby achieving a synergistic characterization of multi-degree-of-freedom neck movements and muscle fatigue status.

[0037] Furthermore, the electromyographic electrodes can acquire the current neck muscle signal at a sampling frequency of 1000Hz and an acquisition bandwidth of 20-450Hz. The current neck muscle signal is amplified and common-mode interference is suppressed by a high input impedance amplifier circuit (input impedance ≥100MΩ) and a high common-mode rejection ratio differential amplifier (CMRR ≥100dB). The sampling frequency of the strain sensor is preferably 50-200Hz, and the corresponding resistance change signal is obtained by measuring the bridge circuit. Based on the pre-calibrated resistance-strain-angle mapping relationship, the real-time acquired resistance change signal is converted into the current neck posture signal.

[0038] The acquisition of historical neck information can be similar to that of current neck information, but the collection is continuous. For example, data can be sampled and stored in real time or at certain time intervals (such as 1 minute or 5 minutes) to build a historical record of neck activity over a period of time.

[0039] Furthermore, this embodiment can also include an inertial sensor to correct the current neck posture signal corresponding to the strain sensor. For example, the inertial sensor can measure the user's posture signal in real time. By comparing the difference between the posture signal measured by the inertial sensor in real time and the current neck posture signal corresponding to the strain sensor, the current neck posture signal corresponding to the strain sensor can be corrected to obtain the corrected current neck posture signal. Based on this, the accuracy of the current neck posture signal can be ensured, providing more precise data for subsequently determining the fatigue level of the neck muscles.

[0040] The number of inertial sensors can be one or more. For example, one inertial sensor can be placed on the top of the head and another inertial sensor can be placed on the neck to jointly correct the current neck posture signal corresponding to the strain sensor.

[0041] S102. Calculate the user's current electromyographic fatigue parameters based on the current neck muscle signals, and calculate the user's current posture load parameters based on the current neck posture signals.

[0042] Current electromyographic fatigue parameters can refer to indicators obtained by analyzing current neck muscle signals, used to quantify the degree of muscle fatigue, and to reflect the fatigue performance of muscles at the physiological level.

[0043] Current posture load parameters can refer to indicators obtained by analyzing current neck posture signals, used to quantify the degree of load on muscles caused by neck posture, and to reflect the mechanical load effect of neck posture.

[0044] Specifically, the current electromyographic fatigue parameters and current postural load parameters can be directly obtained by pre-setting a large model. For example, a neck biomechanical model can be established, and the torque or pressure borne by the neck muscles can be estimated by combining the current neck posture signal, thereby quantifying the current postural load parameters. Alternatively, the corresponding current electromyographic fatigue parameters and current postural load parameters can be obtained by performing a series of calculations on the current electromyographic fatigue parameters and current postural load parameters respectively.

[0045] In some embodiments, calculating the user's current electromyographic fatigue parameters based on current neck muscle signals includes: Feature extraction processing is performed on the current neck muscle signal to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal; Based on time-domain and frequency-domain characteristic parameters, the user's electromyographic fatigue parameters are calculated.

[0046] To more accurately calculate a user's current electromyographic fatigue parameters, embodiments of this application can first perform feature extraction processing after acquiring the current neck muscle signal. This processing aims to extract time-domain and frequency-domain feature parameters closely related to muscle fatigue from the raw, complex bioelectrical signal. Time-domain feature parameters reflect the intensity and duration of muscle contraction; for example, the amplitude of muscle contraction may change as muscle fatigue intensifies. Simultaneously, frequency-domain feature parameters reveal changes in muscle fiber conduction velocity; for example, in a fatigued state, the power spectrum of the muscle signal shifts towards lower frequencies.

[0047] In a specific implementation, feature extraction can be performed directly on the current neck muscle signal to obtain the corresponding time-domain and frequency-domain feature parameters. For example, statistical analysis methods or transform domain analysis methods can be used to process the current neck muscle signal to obtain the time-domain and frequency-domain feature parameters. Alternatively, considering that the current neck muscle signal may contain noise interference, such as power frequency interference, motion artifacts, or baseline drift, direct feature extraction would affect the accuracy and reliability of the calculation of electromyographic fatigue parameters, thus leading to deviations in fatigue level judgment. Therefore, this embodiment can first preprocess the current neck muscle signal and then perform feature extraction on the preprocessed data to obtain the time-domain and frequency-domain feature parameters.

[0048] For example, the current neck muscle signal can first be filtered and rectified to obtain a processed electromyography (EMG) signal. Then, feature extraction processing can be performed on the processed EMG signal to obtain the time-domain and frequency-domain feature parameters corresponding to the current neck muscle signal. For instance, the current neck muscle signal can be bandpass filtered (20–450 Hz), power frequency notch filtered (50 Hz or 60 Hz), and rectified. Subsequently, a sliding window method can be used to segment the signal for analysis, with a window length of 200–500 ms and a window overlap rate of 50%–75%. Time-domain and frequency-domain feature parameters are extracted within each window. The time-domain feature parameters can include the root mean square (RMS) value and integrated electromyography (iEMG). The frequency-domain feature parameters can be obtained by fast Fourier transform to obtain the power spectrum and then calculating the median frequency (MF) and average power frequency (MPF) to characterize the frequency spectrum shift to lower frequencies during muscle fatigue.

[0049] Furthermore, this embodiment can calculate the user's electromyographic fatigue parameters based on the obtained time-domain and frequency-domain feature parameters. For example, the root mean square (RMS) value can be selected from the time-domain feature parameters, and the median frequency (MF) can be selected from the frequency-domain feature parameters, denoted as RMS(t) and MF(t) respectively. Their respective baseline values ​​are denoted as RMS base and MF base. Then, the electromyographic fatigue parameters are calculated. , where α and β are weighting coefficients used to balance the contributions of amplitude features and frequency domain features.

[0050] Based on this, by simultaneously extracting and comprehensively utilizing time-domain and frequency-domain feature parameters, the fatigue physiological manifestations of neck muscles can be captured from different dimensions, making the analysis of current neck muscle signals more comprehensive and in-depth. This provides a richer and more reliable data foundation for the subsequent calculation of electromyographic fatigue parameters, effectively overcoming the noise interference and instability problems that may exist when directly extracting fatigue information from the original signal, and significantly improving the accuracy of fatigue assessment.

[0051] In some embodiments, the current neck posture signal includes current neck flexion data and current neck lateral flexion data. Calculating the user's current posture load parameters based on the current neck posture signal includes: performing feature extraction processing on the current neck flexion data and current neck lateral flexion data to obtain the user's posture deviation feature parameters, which are used to characterize the user's posture deviation from the reference angle; and calculating the user's current posture load parameters based on the posture deviation feature parameters.

[0052] Understandably, the current neck posture signal is a set of data used to describe the spatial position and orientation of the user's neck at the current moment. For more refined analysis of neck posture, this signal can specifically include current neck flexion data and current neck lateral flexion data. Current neck flexion data can be used to characterize the degree of neck curvature in the sagittal plane, such as the angle or distance at which the head tilts forward, while current neck lateral flexion data can be used to characterize the degree of neck tilt in the coronal plane, such as the angle at which the head tilts to the left or right.

[0053] The posture deviation feature parameters can be used to characterize the user's posture deviation from the reference angle. These parameters may include the magnitude, duration, and rate of change of the posture deviation from the reference angle. The duration is obtained by accumulating the time period during which the angle exceeds a preset threshold.

[0054] In specific implementations, feature extraction processing can be performed on the current cervical flexion data and the current cervical lateral flexion data using specific algorithms or models to extract key values ​​or vectors that can effectively characterize the degree of cervical posture deviation, thereby obtaining the user's posture deviation feature parameters. Further, a weighted summation method can be used, multiplying different posture deviation feature parameters (such as flexion deviation angle and lateral flexion deviation angle) by corresponding weight coefficients and then accumulating them to obtain the current posture load parameter. Alternatively, a pre-trained regression model can be used, taking the posture deviation feature parameters as input and outputting the current posture load parameter. This model can consider that the impact of different degrees of deviation on the load is non-linear.

[0055] For example, the angle of neck deviation from neutral position can be selected from the posture deviation feature parameters. (i.e., the magnitude of the attitude deviation from the reference angle), and set the reference angle. and attitude threshold So, what are the current attitude load parameters? Where I is an indicator function, which is triggered when the magnitude of the attitude deviation from the reference angle exceeds a threshold. If the value is 1, then the value is 0; otherwise, the value is 0.

[0056] Based on this, by refining the abstract current neck posture signal into measurable current neck flexion data and current neck lateral flexion data, and based on these quantified posture deviation feature parameters, the user's current posture load parameters are calculated. This allows for the precise quantification of the actual load on muscles caused by neck posture, avoiding fuzzy judgments based solely on the original posture signal, and thus providing a more accurate and reliable input for subsequent fatigue level determination.

[0057] In some embodiments, after obtaining time-domain feature parameters, frequency-domain feature parameters, and posture deviation feature parameters through the above feature extraction process, the obtained parameters can be time-synchronized and aligned to construct a multi-dimensional feature vector containing information such as "electromyographic intensity, spectral characteristics, posture deviation, and duration". This vector is used to characterize the physiological and mechanical properties of neck muscles under different load conditions, providing a data input basis for subsequent fatigue assessment models.

[0058] S103. Calculate the user's current load time parameters based on the user's historical neck information, current electromyographic fatigue parameters, and current posture load parameters within the historical time period.

[0059] The current load time parameter can be an index calculated by comprehensively considering the user's neck information, current electromyographic fatigue parameters and current postural load parameters within a historical time period, which is used to characterize the duration or cumulative effect of neck muscle load and reflects the cumulative effect of neck muscle load.

[0060] The specific process for calculating the current load time parameter is not limited. For example, a load threshold can be set, and when the electromyographic fatigue parameter or postural load parameter exceeds this threshold, the cumulative timing begins. This load time parameter can be the total duration of continuous high load, or it can be the weighted integral of the electromyographic fatigue parameter and postural load parameter under high load. Alternatively, the calculation of the current load time parameter can employ a machine learning model, taking historical neck information (including historical electromyographic signals and historical postural signals), current electromyographic fatigue parameters, and current postural load parameters as input, and outputting a value reflecting the cumulative load through a trained model. This model can be trained based on individual user data to adapt to the physiological characteristics and behavioral patterns of different users.

[0061] S104. Based on the current electromyographic fatigue parameters, current posture load parameters, and current load time parameters, determine the current fatigue level of the user's neck muscles.

[0062] The current fatigue level can be understood as a classification or grading of the user's neck muscle fatigue state. For example, it can be divided into no fatigue, mild fatigue, moderate fatigue, and severe fatigue.

[0063] This embodiment does not limit the specific method for determining the current fatigue level. One implementation approach is to preset a series of rules or thresholds. When one or more of the electromyographic fatigue parameters, postural load parameters, and load time parameters reach a specific condition, the fatigue level is divided into different levels, such as "no fatigue," "mild fatigue," "moderate fatigue," or "severe fatigue." Another implementation approach is to determine the fatigue level by constructing a multi-parameter fusion model. For example, based on algorithms such as fuzzy logic, neural networks, or support vector machines, the three parameters are taken as input, and a comprehensive fatigue level is output. The multi-parameter fusion model can handle the nonlinear relationships and uncertainties between parameters, thereby providing an assessment.

[0064] In some embodiments, determining the current fatigue level of a user's neck muscles based on current electromyographic fatigue parameters, current postural load parameters, and current load time parameters includes: calculating the user's comprehensive fatigue index parameters based on the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters; and determining the user's current fatigue level of neck muscles based on the comprehensive fatigue index parameters.

[0065] The calculation of the user's comprehensive fatigue index parameter aims to integrate multiple independent fatigue-related parameters (current electromyographic fatigue parameter, current postural load parameter, and current load time parameter) into a single, comprehensive quantitative indicator that reflects the user's neck muscle fatigue level. This integration avoids misjudgments caused by fluctuations or limitations of a single parameter, providing a more stable and representative basis for fatigue assessment. Implementation methods may include, but are not limited to: assigning a weight to each fatigue parameter and then summing the weighted parameter values ​​to obtain the comprehensive fatigue index parameter; or constructing a fuzzy inference system, using each fatigue parameter as fuzzy input, and through fuzzy rules and fuzzy inference mechanisms, outputting a fuzzy value representing the comprehensive fatigue level, and then defuzzifying it into the comprehensive fatigue index parameter.

[0066] Furthermore, by presetting thresholds for one or more comprehensive fatigue index parameters, when a comprehensive fatigue index parameter exceeds a certain threshold, it is classified into the corresponding fatigue level; alternatively, a correspondence table between comprehensive fatigue index parameters and fatigue levels can be established, and the corresponding fatigue level can be found in the table based on the calculated comprehensive fatigue index parameter, and so on. Based on this, by effectively integrating multi-source heterogeneous fatigue-related parameters (including current electromyographic fatigue parameters, current posture load parameters, and current load time parameters) into a unified comprehensive fatigue index parameter, the potential bias and inaccuracy of individually evaluating each parameter is avoided. This makes the assessment of the user's neck muscle fatigue state more comprehensive, objective, and accurate, thereby enabling the output of more targeted and effective prompts and suggestions, significantly improving the accuracy of fatigue detection and user experience.

[0067] For example, a comprehensive fatigue index can be constructed. Where w1, w2, and w3 represent the weighting coefficients of the current electromyographic fatigue parameter, the current postural load parameter, and the current load time parameter, respectively. Preferably, in this embodiment, w1=0.5, w2=0.3, and w3=0.2 are initially set. Then, the fatigue level is determined according to the value of the comprehensive fatigue index FI(t): when FI<0.3, it is determined to be mild fatigue; when 0.3≤FI<0.6, it is determined to be moderate fatigue; when FI≥0.6, it is determined to be severe fatigue.

[0068] In some embodiments, determining the current fatigue level of the user's neck muscles based on current electromyographic fatigue parameters, current postural load parameters, and current load time parameters includes: Detect whether at least one of the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters has reached the set fatigue condition; If the electromyographic fatigue parameters are detected to reach the set fatigue condition, the user's current fatigue level is determined to be moderate fatigue level. If the posture load parameter or fatigue time accumulation parameter is detected to meet the set fatigue conditions, then the user's current fatigue level is determined to be severe fatigue level.

[0069] In this embodiment, specific fatigue conditions can be set for the current electromyographic fatigue parameters, current posture load parameters, and current load time parameters. For example, if electromyographic fatigue parameters are detected... When the electromyographic fatigue parameter increases significantly and is accompanied by a shift in spectral characteristics to lower frequencies, it indicates that the electromyographic fatigue parameter has reached the corresponding set fatigue condition. If the current posture load parameter is detected to exceed the preset threshold and the duration exceeds the set time, it indicates that the current posture load parameter has reached the corresponding set fatigue condition. If the current load time parameter is detected to continuously increase and exceed the threshold, it indicates that the current load time parameter has reached the corresponding set fatigue condition.

[0070] S105. Output a prompt message associated with the current fatigue level. The prompt message is used to indicate the current fatigue level and provide suggestions corresponding to the current fatigue level.

[0071] Based on the current fatigue level, this embodiment can further construct a behavior guidance mechanism and an individualized adjustment strategy module to achieve closed-loop control from "state recognition" to "intervention feedback," generating targeted intervention strategy outputs. For example, different intervention strategies can be output in stages according to the fatigue level, providing mild reminders in moderate fatigue states and enhanced prompts or continuous interventions in high fatigue states, thereby improving the effectiveness of interventions and user compliance.

[0072] For example, when the posture load parameter or fatigue time accumulation parameter is detected to meet the set fatigue condition, that is, when the user's current fatigue level is moderate fatigue level, a posture abnormality prompt can be triggered, reminding the user to adjust their posture through a visual interface, sound, or vibration (such as prompting the user to raise their head, straighten their neck, or reduce the flexion angle due to excessive neck flexion). When the posture load parameter or fatigue time accumulation parameter is detected to meet the set fatigue condition, that is, when the user's current fatigue level is severe fatigue level, a high-priority intervention can be triggered, prompting the user to take intermittent rest to avoid further fatigue accumulation, such as outputting a strong prompt: "Neck muscles are severely fatigued, please take intermittent rest and stretch muscles immediately."

[0073] This embodiment provides a prompting processing method that determines the current fatigue level of the user's neck muscles based on current electromyographic fatigue parameters, current posture load parameters, and current load time parameters. It takes into account the key role of time factors in the fatigue formation process, which greatly improves the accuracy and reliability of the output prompting information.

[0074] Figure 2 This is a flowchart illustrating a prompting method according to another embodiment of this application. This embodiment further optimizes the calculation of the user's current load time parameter based on the user's historical neck information, current electromyographic fatigue parameters, and current postural load parameters within a historical time period. The optimization is as follows: Based on the user's historical neck information at each historical time point within the historical time period, calculate the user's historical postural load parameters and historical postural load parameters at each historical time point; calculate the user's current load time parameter based on the user's historical postural load parameters, historical postural load parameters, current electromyographic fatigue parameters, and current postural load parameters at each historical time point. For example... Figure 2 As shown, the method includes: S201. Obtain the user's current neck information at the current moment, and obtain the user's historical neck information during the historical time period before the current moment.

[0075] S202. Calculate the user's current electromyographic fatigue parameters based on the current neck muscle signals, and calculate the user's current posture load parameters based on the current neck posture signals.

[0076] S203. Based on the user's historical neck information at each historical time point within a historical time period, calculate the user's historical posture load parameters and historical posture load parameters at each historical time point.

[0077] In a specific implementation, the steps for calculating the current electromyographic fatigue parameters and current postural load parameters described above can be followed to similarly calculate the user's historical postural load parameters and historical postural load parameters at each historical time point. Alternatively, the user's historical postural load parameters and historical postural load parameters at each historical time point can be directly obtained from the database.

[0078] S204. Calculate the user's current load time parameters based on the user's historical posture load parameters, current electromyographic fatigue parameters, and current posture load parameters at each historical time point.

[0079] For example, weighted average, time integration, or machine learning model-based methods can be used to fuse historical posture load parameters with current load parameters to obtain a current load time parameter that can reflect the long-term stress on neck muscles and the fatigue accumulation trend.

[0080] For example, the current load time parameter , where γ1 and γ2 are the weighting coefficients of each component during the time accumulation process, used to characterize the dynamic accumulation effect of fatigue over time.

[0081] In some embodiments, this embodiment also includes a feature standardization process, which normalizes each feature based on individual baseline data to improve comparability and evaluation stability among different users. Specifically, to improve the model's individual adaptability, an individualized adaptive adjustment mechanism can be introduced to dynamically optimize system parameters by constructing a user baseline model. For example, by collecting multimodal data of subjects under different fatigue states and combining it with subjective fatigue scores, a training dataset is constructed. The least squares method is used to fit and optimize the aforementioned weight parameters (w1, w2, w3) to obtain the individualized optimal parameter configuration. More specifically, in the initial use phase, electromyography and posture data of users in resting and low-load states can be collected to establish an individual baseline feature library, and the initial threshold and feature weights can be determined accordingly. During long-term use, user historical data can be continuously recorded, and the fatigue judgment threshold, feature weights, and intervention triggering conditions can be adaptively adjusted through sliding time windows or periodic updates, thereby eliminating evaluation errors caused by individual physiological differences, adapting to physiological differences and changes in behavioral habits among different users, and achieving increasingly accurate intelligent neck health management over time. In implementation, the adaptive process can be based on statistical update methods or machine learning models, for example, by iteratively optimizing the model parameters by minimizing the deviation between historical fatigue determination results and user feedback.

[0082] S205. Based on the current electromyographic fatigue parameters, current posture load parameters, and current load time parameters, determine the current fatigue level of the user's neck muscles.

[0083] S206. Output a prompt message associated with the current fatigue level.

[0084] The prompting method provided in this embodiment no longer relies solely on the instantaneous state at the current moment when calculating the current load time parameter, but incorporates the cumulative load information of the user's neck muscles over a period of time. This allows for a more accurate assessment of the actual fatigue level of the user's neck muscles, avoiding misjudgments that may result from relying solely on current data. Especially in scenarios where the user is under low-intensity load for a long time but the cumulative effect is significant, it can effectively identify potential fatigue risks.

[0085] As can be seen from the above description, the prompting processing method provided in this embodiment adopts a flexible wearable sensing structure to realize the synchronous acquisition of multimodal information of the neck at the signal acquisition level. The electrodes have good flexibility and skin fit, and do not affect the natural movement of the neck during dynamic use. At the same time, they can stably acquire high-quality electromyographic signals, thereby ensuring signal reliability and long-term wearing comfort.

[0086] Secondly, at the signal analysis level, a built-in multimodal fusion evaluation algorithm is used to jointly model the acquired electromyographic (EMG) and posture signals. By extracting key parameters such as EMG amplitude and frequency domain features, posture angle, and duration, a three-dimensional fusion evaluation framework of "EMG features—posture features—time factors" is constructed. By introducing duration as a key variable, the cumulative effect of fatigue is modeled. Considering the different contributions of various features to fatigue characterization, a weighting mechanism is introduced to weight and fuse changes in EMG features, the degree of posture deviation, and duration, thereby obtaining a comprehensive fatigue index. Based on this index, a multi-level fatigue assessment system is established to achieve continuous quantitative characterization from low to high fatigue states, improving the ability to distinguish and the sensitivity of different fatigue stages, and demonstrating good engineering feasibility and individual adaptability.

[0087] Furthermore, at the application level, this embodiment supports the wireless transmission of signal processing and evaluation results to mobile terminals. Users can obtain fatigue status and trends in real time through a visual interface, and perform posture adjustments or muscle relaxation training based on the output behavioral guidance suggestions, thereby achieving proactive intervention. It can also provide differentiated intervention plans based on user characteristics, thereby improving the accuracy, practicality, and long-term effectiveness of the method in practical applications, achieving intelligent neck health management tailored to individuals.

[0088] In summary, this embodiment provides a prompting processing method that constructs a multimodal quantitative assessment and behavioral guidance method for neck muscle fatigue targeting daily office workers and those at risk of neck strain. By synchronously acquiring surface electromyographic signals from key neck muscle groups and combining this with information on neck posture changes, a joint characterization of physiological and mechanical muscle load is achieved. Based on this, a multi-dimensional assessment index system incorporating factors such as electromyographic characteristics, degree of posture deviation, and duration is introduced to establish an objective quantitative fatigue assessment method that reflects the fatigue accumulation process, thereby enabling continuous and dynamic monitoring of neck muscle fatigue. The entire system requires no complex external equipment, is easy to operate, and provides timely feedback. It is suitable for health management in daily office and life scenarios, as well as for continuous monitoring and assessment during rehabilitation training, providing an efficient and reliable technical solution for intelligent monitoring and individualized intervention of neck muscle fatigue.

[0089] Corresponding to the prompt processing method in the above embodiments, Figure 3 This is a structural block diagram of a prompting processing device provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0090] Reference Figure 3 The device includes: The acquisition module 301 is used to acquire the user's current neck information at the current moment, and to acquire the user's historical neck information during the historical time period before the current moment. The current neck information includes the current neck muscle signal and the current neck posture signal. The first calculation module 302 is used to calculate the user's current electromyographic fatigue parameters based on the current neck muscle signals, and to calculate the user's current posture load parameters based on the current neck posture signals. The second calculation module 303 is used to calculate the user's current load time parameters based on the user's historical neck information, current electromyographic fatigue parameters, and current posture load parameters within a historical time period. The determination module 304 is used to determine the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters. The output module 305 is used to output prompt information associated with the current fatigue level. The prompt information is used to indicate the current fatigue level and the corresponding suggestion information.

[0091] This embodiment provides a prompting processing device that acquires the user's current neck information at the current moment and historical neck information from a previous time period through an acquisition module. The current neck information includes current neck muscle signals and current neck posture signals. A first calculation module calculates the user's current electromyographic fatigue parameters based on the current neck muscle signals and current posture load parameters based on the current neck posture signals. A second calculation module calculates the user's current load time parameters based on the historical neck information, current electromyographic fatigue parameters, and current posture load parameters. A determination module determines the user's current neck muscle fatigue level based on the current electromyographic fatigue parameters, current posture load parameters, and current load time parameters. An output module outputs prompting information associated with the current fatigue level, indicating the current fatigue level and providing corresponding suggestions. This device, by determining the user's current neck muscle fatigue level based on the current electromyographic fatigue parameters, current posture load parameters, and current load time parameters, considers the crucial role of time in the fatigue formation process, significantly improving the accuracy and reliability of the output prompting information.

[0092] Optionally, the first computing module includes: The feature extraction processing unit is used to perform feature extraction processing on the current neck muscle signal to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal. The calculation unit is used to calculate the user's electromyographic fatigue parameters based on time-domain and frequency-domain characteristic parameters.

[0093] Optionally, the feature extraction processing unit is specifically used for: The current neck muscle signal is filtered and rectified to obtain the processed electromyographic signal. Feature extraction is performed on the processed electromyographic signal to obtain the time-domain and frequency-domain feature parameters corresponding to the current neck muscle signal.

[0094] Optionally, the current neck posture signal includes current neck flexion data and current neck lateral flexion data, and the first calculation module is specifically used for: Feature extraction processing is performed on the current cervical flexion data and the current cervical lateral flexion data to obtain the user's posture deviation feature parameters. The posture deviation feature parameters are used to characterize the user's posture deviation from the reference angle. Based on the attitude deviation characteristic parameters, the user's current attitude load parameters are calculated.

[0095] Optionally, the second calculation module is specifically used for: Based on the user’s historical neck information at each historical time point within a historical time period, calculate the user’s historical posture load parameters and historical posture load parameters at each historical time point. Based on the user's historical posture load parameters, current electromyographic fatigue parameters, and current posture load parameters at each historical time point, calculate the user's current load time parameters.

[0096] Optionally, the module is specifically used for: Calculate the user's comprehensive fatigue index parameters based on the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters; Based on comprehensive fatigue index parameters, the current fatigue level of the user's neck muscles is determined.

[0097] Optionally, the module is specifically used for: Detect whether at least one of the current electromyographic fatigue parameters, current postural load parameters, and current load time parameters has reached the set fatigue condition; If the electromyographic fatigue parameters are detected to reach the set fatigue condition, the user's current fatigue level is determined to be moderate fatigue level. If the posture load parameter or fatigue time accumulation parameter is detected to meet the set fatigue conditions, then the user's current fatigue level is determined to be severe fatigue level.

[0098] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] Figure 4 This is a schematic diagram of the structure of a terminal device provided in one embodiment of this application, as shown below. Figure 4 As shown, the terminal device 500 of this embodiment includes: at least one processor 502 ( Figure 4 (Only one is shown) a processor, a memory 501, and a computer program 503 stored in the memory 501 and executable on at least one processor 502. When the processor 502 executes the computer program 503, it implements the steps in the control method embodiments of any of the above-described application programs.

[0101] Terminal device 500 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud terminal device. This terminal device may include, but is not limited to, a processor 502 and a memory 501. Those skilled in the art will understand that... Figure 4 This is merely an example of terminal device 500 and does not constitute a limitation on terminal device 500. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0102] 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0103] In some embodiments, memory 501 may be an internal storage unit of terminal device 500, such as a hard disk or memory of terminal device 500. In other embodiments, memory 501 may be an external storage device of terminal device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on terminal device 500. Furthermore, memory 501 may include both internal and external storage units of terminal device 500. Memory 501 is used to store operating system, applications, boot loader, data, and other programs, such as program code for computer programs. Memory 501 can also be used to temporarily store data that has been output or will be output.

[0104] This application also provides a computer-readable storage medium storing a computer program, which, when executed by processor 502, can implement the steps in the above-described method embodiments.

[0105] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments.

[0106] 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 computer-readable storage medium. Based on this understanding, 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 can be stored in a computer-readable storage medium, and when executed by the processor 502, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include at least: any entity or device capable of carrying computer program code to a device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0107] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0108] 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, or a combination of computer software and electronic hardware. 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 implementation should not be considered beyond the scope of this application.

[0109] In the embodiments provided in this application, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A prompt processing method, characterized in that, Applications include fatigue detection scenarios, including: Obtain the user's current neck information at the current moment, and obtain the user's historical neck information during a historical time period prior to the current moment. The current neck information includes current neck muscle signals and current neck posture signals. The user's current electromyographic fatigue parameters are calculated based on the current neck muscle signals, and the user's current postural load parameters are calculated based on the current neck posture signals. Based on the user's historical neck information, current electromyographic fatigue parameters, and current posture load parameters within the historical time period, calculate the user's current load time parameters; Based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters, the current fatigue level of the user's neck muscles is determined; Output a prompt message associated with the current fatigue level, the prompt message being used to indicate the current fatigue level, and suggestive information corresponding to the current fatigue level.

2. The prompt processing method as described in claim 1, characterized in that, The calculation of the user's current electromyographic fatigue parameters based on the current neck muscle signals includes: The current neck muscle signal is subjected to feature extraction processing to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal; Based on the time-domain feature parameters and the frequency-domain feature parameters, the electromyographic fatigue parameters of the user are calculated.

3. The prompt processing method as described in claim 2, characterized in that, The step of performing feature extraction processing on the current neck muscle signal to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal includes: The current neck muscle signal is filtered and rectified to obtain the processed electromyographic signal. The processed electromyographic signal is subjected to feature extraction processing to obtain the time-domain feature parameters and frequency-domain feature parameters corresponding to the current neck muscle signal.

4. The prompt processing method as described in claim 1, characterized in that, The current neck posture signal includes current neck flexion data and current neck lateral flexion data. The calculation of the user's current posture load parameters based on the current neck posture signal includes: Feature extraction processing is performed on the current cervical flexion data and the current cervical lateral flexion data to obtain the user's posture deviation feature parameters, which are used to characterize the user's posture deviation from the reference angle. Based on the posture deviation feature parameters, the user's current posture load parameters are calculated.

5. The prompt processing method as described in claim 1, characterized in that, The step of calculating the user's current load time parameter based on the user's historical neck information, current electromyographic fatigue parameters, and current postural load parameters within the historical time period includes: Based on the user’s historical neck information at each historical time point within the historical time period, calculate the user’s historical posture load parameters and historical posture load parameters at each historical time point. The current load time parameter of the user is calculated based on the user's historical posture load parameter, the current electromyographic fatigue parameter, and the current posture load parameter at each historical time point.

6. The prompt processing method according to any one of claims 1-5, characterized in that, Determining the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current postural load parameters, and the current load time parameters includes: Calculate the user's comprehensive fatigue index parameters based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters; Based on the comprehensive fatigue index parameters, the current fatigue level of the user's neck muscles is determined.

7. The prompt processing method according to any one of claims 1-5, characterized in that, Determining the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current postural load parameters, and the current load time parameters includes: Detect whether at least one of the current electromyographic fatigue parameter, the current posture load parameter, and the current load time parameter has reached the set fatigue condition; If the electromyographic fatigue parameter is detected to reach the set fatigue condition, then the current fatigue level of the user is determined to be moderate fatigue level. If the posture load parameter or the fatigue time accumulation parameter is detected to meet the set fatigue condition, then the current fatigue level of the user is determined to be severe fatigue level.

8. A notification processing device, characterized in that, Configuration for fatigue detection scenarios, including: The acquisition module is used to acquire the user's current neck information at the current moment, and to acquire the user's historical neck information during a historical time period before the current moment. The current neck information includes current neck muscle signals and current neck posture signals. The first calculation module is used to calculate the user's current electromyographic fatigue parameters based on the current neck muscle signals, and to calculate the user's current posture load parameters based on the current neck posture signals. The second calculation module is used to calculate the user's current load time parameter based on the user's historical neck information, current electromyographic fatigue parameters, and current posture load parameters within the historical time period; The determination module is used to determine the current fatigue level of the user's neck muscles based on the current electromyographic fatigue parameters, the current posture load parameters, and the current load time parameters. The output module is used to output prompt information associated with the current fatigue level. The prompt information is used to indicate the current fatigue level and the corresponding suggestion information.

9. A terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the terminal device to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on a terminal device, it causes the terminal device to perform the method as described in any one of claims 1-7.

Images