Intelligent adjustment method and system for shared massage chair based on big data

Abstract

The invention relates to the technical field of intelligent health equipment, and discloses an intelligent adjustment method and system for a shared massage armchair based on big data, and the method comprises the steps: collecting sleep-related physiological indexes of a user, and generating a preliminary sleep state feature vector; a personalized spine curve digital model is constructed, and spine biomechanical feature vectors are generated; using a hidden Markov model to identify the sleep state of the user in real time, and generating a complete sleep state vector; establishing a sleep spine collaborative optimization model, and constructing a state conversion function, a spine mechanical response function and a sleep quality evaluation function; real-time optimization and dynamic adjustment of massage parameters are achieved, and a closed-loop control system is formed; the state machine and the self-adaptive trajectory planning algorithm are introduced, the optimal massage mode is automatically switched, the strategy is continuously optimized through the sleep quality feedback mechanism, and the comfortable experience and the health management level of the user are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent health equipment, and more specifically, to an intelligent adjustment method and system for a shared massage chair based on big data. Background Art

[0002] With the accelerating pace of modern life, sleep disorders and spinal health issues are becoming increasingly prominent. More and more people are facing health issues such as poor sleep quality, spinal fatigue, and chronic pain in their daily lives and work. Massage chairs, as important devices to improve sleep and spinal health, have been widely used in various scenarios, including homes, public places, and medical rehabilitation. Traditional massage chairs rely primarily on mechanical structures and preset programs to provide basic massage and support functions, but they have significant shortcomings in addressing individual user differences and dynamic physiological needs.

[0003] In recent years, with the advancement of biosensor technology and artificial intelligence algorithms, smart health devices based on multimodal physiological signal acquisition and analysis have gradually emerged. By integrating multiple sensors, they can acquire real-time physiological parameters such as a user's breathing, heart rate, and body movement, providing a data foundation for health management and personalized services. However, existing massage chairs, in terms of sleep assistance and spinal regulation, have yet to achieve a deep integration and dynamic response between the user's sleep state and spinal biomechanical characteristics, making it difficult to meet the personalized needs of users at different sleep stages and spinal conditions.

[0004] In addition, existing technologies generally lack real-time evaluation and feedback mechanisms for sleep quality, and are unable to continuously optimize massage strategies based on user historical data and subjective experience, resulting in significant room for improvement in massage effects and user experience.

[0005] Therefore, there is a need for an intelligent massage chair system that can integrate multimodal physiological signals and spinal pressure distribution data and has adaptive control and closed-loop optimization capabilities to achieve coordinated optimization of sleep quality improvement and spinal health protection. Summary of the Invention

[0006] The present invention provides an intelligent adjustment method and system for a shared massage chair based on big data, which solves the technical problems in related technologies such as the inability to integrate multimodal physiological signals and spinal pressure distribution data, the lack of individualized dynamic regulation and sleep quality feedback closed-loop mechanism, and the difficulty in achieving coordinated optimization of sleep quality improvement and spinal health.

[0007] The present invention provides an intelligent adjustment method for a shared massage chair based on big data, comprising the following steps: Collect the user's sleep-related physiological indicators and generate a preliminary sleep state feature vector; Based on the preliminary sleep state feature vector, the pressure distribution data of the user's spine and the contact surface of the massage chair are collected to build a personalized spinal curve digital model and generate the spinal biomechanical feature vector; Based on the preliminary sleep state feature vector and spinal biomechanical feature vector, the hidden Markov model is applied to identify the user's sleep state in real time and generate a complete sleep state vector; Based on the complete sleep state vector and spinal biomechanical characteristic vector, a sleep-spine collaborative optimization model is established, and the state transition function, spinal mechanical response function and sleep quality evaluation function are constructed. Based on the sleep spine collaborative optimization model, real-time optimization and dynamic adjustment of massage parameters are achieved to form a closed-loop control system.

[0008] In a preferred embodiment, the step of collecting the user's sleep-related physiological indicators includes: A multimodal sensing system integrating millimeter-wave radar sensors, far-infrared sensors, and sound sensors collects sleep-related physiological indicators of users. Preprocessing of the collected raw biological signals, including noise filtering, signal separation and feature extraction; The processed multimodal physiological features are fused to generate a preliminary sleep state feature vector.

[0009] In a preferred embodiment, the step of collecting pressure distribution data on the contact surface between the user's spine and the massage chair includes: Deploy a high-density pressure sensor array in the backrest area of ​​the massage chair to collect pressure distribution data in the user's spine area; Based on the collected pressure distribution data, the thin plate spline interpolation algorithm is applied to reconstruct the user's spinal curve; Based on the reconstructed spinal curve and pressure distribution, the spinal biomechanical feature vector is constructed.

[0010] In a preferred embodiment, the step of applying a hidden Markov model to identify the user's sleep state in real time includes: Extract and fuse the temporal features of the preliminary sleep state feature vector; Build a sleep state classifier based on the Hidden Markov Model to determine the user's sleep stage in real time; Based on the identified sleep state sequence, sleep quality scores and characteristic indicators are calculated; The sleep state classification results are combined with other physiological features to form a complete sleep state vector.

[0011] In a preferred embodiment, the step of establishing a sleep spine collaborative optimization model includes: Construct a state transition function to predict the changing trend of the current sleep state under specific massage parameters; Construct a spinal mechanical response function to predict the effect of specific massage parameters on the biomechanical state of the spine; Improve the sleep quality evaluation function to achieve a comprehensive assessment of sleep status; Construct the overall objective function of sleep-spine collaborative optimization.

[0012] In a preferred embodiment, the overall objective function is formally expressed as: maximizing the effect of massage parameters on improving sleep quality while satisfying spinal safety constraints.

[0013] In a preferred embodiment, the step of achieving real-time optimization and dynamic adjustment of massage parameters includes: Build a sleep spinal state machine to define the ideal spinal support configuration for different sleep stages; Based on the current sleep state and spinal characteristics, an adaptive trajectory planning algorithm is used to dynamically optimize the massage trajectory; Realize multi-dimensional coordinated control of massage parameters to form a complete massage experience; Introduce a sleep quality feedback mechanism to continuously optimize the regulation strategy through sleep effect evaluation.

[0014] In a preferred embodiment, the sleep spine state machine comprises: defining a sleep spinal joint state space, which includes combinations of sleep stages and spinal support patterns; Based on knowledge of sleep physiology and biomechanics, a mapping relationship between sleep stages and ideal spinal support configuration is established; Define the trigger conditions and smooth transition mechanism for state transition to ensure comfort when switching between massage modes; According to the user's spinal characteristics and feedback history, the state machine parameters are optimized to achieve personalized support configuration.

[0015] In a preferred embodiment, the sleep quality feedback mechanism includes: Based on the changing trend of sleep status, the immediate effect of massage intervention can be evaluated in real time; After each use, the effectiveness of the massage program was evaluated based on the overall sleep quality score; Automatically adjust the massage strategy library and optimize algorithm parameters based on the evaluation results; Combining users' subjective feedback and objective sleep data, a comprehensive evaluation is formed to guide continuous optimization of the system.

[0016] In a preferred embodiment, a big data-based intelligent adjustment system for a shared massage chair is used to perform a big data-based intelligent adjustment method for a shared massage chair, comprising: A non-contact biological parameter monitoring unit is used to collect the user's sleep-related physiological indicators and generate a preliminary sleep state feature vector; The pressure distribution sensing unit collects pressure distribution data on the contact surface between the user's spine and the massage chair based on the preliminary sleep state feature vector, constructs a personalized digital model of the spinal curve, and generates a spinal biomechanical feature vector; The sleep state recognition unit uses a hidden Markov model to identify the user's sleep state in real time based on the preliminary sleep state feature vector and the spinal biomechanical feature vector, generating a complete sleep state vector. The collaborative optimization modeling unit establishes a sleep-spine collaborative optimization model based on the complete sleep state vector and spinal biomechanical characteristic vector, and constructs the state transition function, spinal mechanical response function, and sleep quality evaluation function; The adaptive trajectory planning unit, based on the sleeping spine collaborative optimization model, realizes real-time optimization and dynamic adjustment of massage parameters to form a closed-loop control system.

[0017] The beneficial effects of the present invention are: By integrating multimodal physiological signals with spinal pressure distribution data, the system accurately identifies the user's sleep state and spinal characteristics, dynamically adapting to individual differences and significantly enhancing the intelligence of the massage chair. The system automatically optimizes massage parameters based on the user's real-time sleep stage and spinal biomechanical state, providing personalized spinal support and sleep assistance, enhancing the user's comfort and sleep quality.

[0018] The sleep-spine collaborative optimization model breaks through the limitations of traditional massage chairs' single-objective optimization, achieving coordinated regulation of sleep quality improvement and spinal health protection. By incorporating a state machine and adaptive trajectory planning algorithm, the system automatically switches to the optimal massage mode for different sleep stages, meeting the user's dynamically changing physiological needs.

[0019] A closed-loop sleep quality feedback mechanism has been established, enabling continuous optimization of massage strategies based on historical user data and subjective feedback, enabling the system's self-learning and long-term evolution capabilities. This not only improves the effectiveness of massage interventions, but also provides users with a more scientific and reliable health management experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a method for intelligent adjustment of a shared massage chair based on big data according to the present invention; Figure 2 is a bar graph comparing sleep quality improvements of the present invention; Figure 3 It is a radar chart of the spinal health index improvement of the present invention; Figure 4is a line graph of the sleep state recognition accuracy of the present invention; Figure 5 is a Sankey diagram of spinal support configurations for different sleep stages of the present invention; Figure 6 is an area graph of the new user adaptability capability of the present invention; Figure 7 It is a bar chart comparing the system response times of the present invention. DETAILED DESCRIPTION

[0021] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. Furthermore, features described in some examples may be combined in other examples.

[0022] At least one embodiment of the present invention discloses a method for intelligently adjusting a shared massage chair based on big data, such as Figure 1 As shown, the following steps are included: Step 1: Collect the user's sleep-related physiological indicators and generate a preliminary sleep state feature vector; The specific steps include: Step 1.1, biological parameter collection; The multimodal sensing system, which integrates millimeter-wave radar sensors, far-infrared sensors, and sound sensors, collects sleep-related physiological indicators such as the user's breathing rate, heart rate variability, body movement frequency, and breathing sounds.

[0023] Millimeter-wave radar sensor: By transmitting 24GHz or 60GHz millimeter waves and receiving reflected waves, it uses the Doppler effect to detect tiny chest and abdominal movements and collect respiratory rate and amplitude data.

[0024] Far-infrared sensor: Captures changes in the user's body surface temperature and monitors the correlation between body temperature regulation and sleep cycles.

[0025] Sound sensor: collects breathing sound characteristics to assist in sleep state analysis.

[0026] The sensing system is configured on the headrest and backrest of the massage chair, maintaining an effective sensing distance of 20 to 50 cm, ensuring the acquisition of high-quality physiological signals without contacting the user's body.

[0027] Step 1.2, signal preprocessing; Preprocessing of the collected raw biological signals includes: Noise filtering: Apply adaptive filtering algorithms to eliminate environmental noise and motion artifacts, improving the signal-to-noise ratio.

[0028] Signal separation: Use independent component analysis technology to separate overlapping physiological signals, such as separating respiratory signals and heartbeat signals from composite signals.

[0029] Feature extraction: Calculate key time-domain and frequency-domain features such as respiratory rate, heart rate, heart rate variability indicators (SDNN, RMSSD, LF / HF ratio), and body movement frequency.

[0030] Step 1.3, generating preliminary sleep state feature vectors; The processed multimodal physiological features are fused to generate a preliminary sleep state feature vector. This vector contains the following dimensions: Respiratory feature subvector: contains parameters such as respiratory frequency, depth, and regularity.

[0031] Heart rate feature subvector: contains parameters such as heart rate mean and variability.

[0032] Body motion feature subvector: contains parameters such as body motion frequency and amplitude.

[0033] Temperature feature vector: contains body surface temperature and its changing trend.

[0034] By connecting and normalizing these sub-vectors, a preliminary sleep state feature vector is formed, providing a data basis for subsequent sleep state classification.

[0035] like Figure 2 As shown in the figure, the comparative data on sleep quality indicators of using this system and traditional massage chairs are displayed, which intuitively shows the sleep quality improvement effect brought by this system.

[0036] Step 2: Based on the preliminary sleep state feature vector, the pressure distribution data of the user's spine and the contact surface of the massage chair are collected to build a personalized spinal curve digital model and generate a spinal biomechanical feature vector; The specific steps include: Step 2.1, pressure distribution data acquisition; A high-density pressure sensor array is deployed in the backrest area of ​​the massage chair to collect pressure distribution data in the user's spine area: Sensor array configuration: A 12×24 flexible pressure sensor array is arranged longitudinally along the backrest, with a sensor unit spacing of 1.5 cm, covering the complete spinal area from the cervical vertebrae to the sacral vertebrae.

[0037] Pressure data sampling: The pressure distribution matrix data is collected at a frequency of 20Hz. The pressure value range of each sensing unit is 0-1000g / cm² with an accuracy of ±5g / cm².

[0038] Initial calibration: When the user uses it for the first time, the system guides the user to perform calibration collection in a standard posture and record the baseline pressure distribution.

[0039] Step 2.2, spine curve reconstruction; Based on the collected pressure distribution data, the thin plate spline interpolation algorithm is applied to reconstruct the user's spinal curve: Pressure centerline extraction: By analyzing the local maximum points of the pressure distribution matrix, the pressure centerline along the spine is extracted.

[0040] Spline curve fitting: The extracted pressure center points are used as control points, and the cubic spline interpolation algorithm is applied to generate a continuous spinal curve.

[0041] Curve parameterization: Convert the reconstructed spinal curve into a parametric representation, including the curvature radius and relative position of the cervical curve, thoracic curve, and lumbar curve.

[0042] Step 2.3, generation of spine biomechanical feature vectors; Based on the reconstructed spinal curve and pressure distribution, the spinal biomechanical eigenvector is constructed: Curve feature subvector: contains the curvature parameters and relative positions of the cervical, thoracic, lumbar, and sacral vertebrae.

[0043] Pressure distribution sub-vector: contains the pressure distribution characteristics of each spinal segment, such as peak pressure, pressure uniformity, etc.

[0044] Contact area quantum vector: describes the degree of match between the user's body shape and the massage chair backrest.

[0045] Muscle tension estimation subvector: Muscle tension distribution inferred from pressure variation patterns.

[0046] By combining the above sub-vectors and performing normalization processing, a complete spinal biomechanical feature vector is formed, which provides constraints for subsequent massage parameter optimization.

[0047] like Figure 3 As shown, the system demonstrates the improvement effect on multiple spinal health-related indicators, including reduced spinal pressure peak, improved muscle tension balance, and reduced spinal discomfort.

[0048] Step 3: Based on the preliminary sleep state feature vector and the spinal biomechanical feature vector, a hidden Markov model is applied to identify the user's sleep state in real time to generate a complete sleep state vector; The specific steps include: Step 3.1, sleep feature fusion; Extract and fuse the temporal features of the preliminary sleep state feature vector: Time series feature extraction: Sliding window technology (window length of 30 seconds, overlap rate of 50%) was used to calculate the statistical characteristics and trend characteristics of each physiological parameter.

[0049] Feature importance evaluation: Apply the feature importance evaluation algorithm based on XGBoost to adaptively adjust the weights of different features.

[0050] Multimodal feature fusion: The attention mechanism is used to fuse physiological features of different modalities, thereby increasing the weight of features that contribute most to sleep state judgment.

[0051] Step 3.2, sleep state classification model; Build a sleep state classifier based on the Hidden Markov Model to determine the user's sleep stage in real time: State space definition: The sleep state space is defined as five discrete states: {awake, transition to sleep, light sleep, deep sleep, REM sleep}.

[0052] Observation probability modeling: Based on the fused physiological characteristics, an observation probability distribution model for each sleep state is constructed.

[0053] State transition matrix: Initialize the state transition matrix based on the physiological laws of sleep and continuously optimize it based on user historical data.

[0054] Sequence decoding: Apply the Viterbi algorithm to decode the observed sequence and determine the most likely sleep state sequence.

[0055] Step 3.3, sleep quality assessment; Based on the identified sleep state sequence, calculate the sleep quality score and characteristic indicators: Sleep structure indicators: calculate the time proportion of each sleep stage, transition frequency and other indicators.

[0056] Sleep continuity indicators: Calculate indicators such as the number of sleep interruptions and the average interruption duration.

[0057] Comprehensive sleep quality score: ; in, represents the final comprehensive sleep quality score; Indicates the total number of sleep quality indicators included in the evaluation system; Indicates the Specific sleep quality indicators; Indicates the The weight coefficient corresponding to each sleep quality indicator is used to reflect the relative importance of the indicator in the comprehensive score. The sum of is 1, that is , to ensure the normalization of the score. This scoring method can comprehensively reflect the user's multi-dimensional sleep quality status.

[0058] Step 3.4, complete sleep state vector generation; The sleep state classification results are combined with other physiological features to form a complete sleep state vector: Sleep stage sub-vector: contains the current sleep stage, the time spent in that stage, the probability of stage transition, etc.

[0059] Sleep quality sub-vector: contains the current sleep quality score, sleep depth index, etc.

[0060] Physiological state sub-vector: includes muscle tension state, autonomic nervous system balance state, etc.

[0061] Sleep trend sub-vector: contains the predicted sleep stage development trend and transition time points.

[0062] The complete sleep state vector provides key input for subsequent massage parameter optimization.

[0063] like Figure 4 As shown in the figure, the recognition accuracy of the system in different sleep stages changes with usage time, reflecting the self-learning ability and adaptability of the system.

[0064] Step 4: Based on the complete sleep state vector and spinal biomechanical characteristic vector, a sleep-spine collaborative optimization model is established to construct the state transition function, spinal mechanical response function, and sleep quality evaluation function; The specific steps include: Step 4.1, state transition function is established; Construct a state transition function to predict the changing trend of the current sleep state under specific massage parameters: Function definition: Construct state transition function: ; in, Represents the state transition operator, which is used to describe the state transition given the current sleep state vector and massage parameter vector How will the user's sleep state change under different conditions? Represents the current sleep state vector; represents the massage parameter vector; Represents the expected sleep state vector. This function describes how the user's sleep state changes under specific massage parameters and is the core prediction tool for subsequent optimization models.

[0065] Model structure: A recurrent neural network structure is applied, with the sleep state vector and massage parameter vector as input to predict the sleep state at future time points.

[0066] Model training: Based on historical user data and knowledge of sleep physiology, the model is trained using a combination of supervised learning and reinforcement learning.

[0067] Model validation: The model prediction accuracy is evaluated through cross-validation methods, and the model parameters are continuously optimized through online learning.

[0068] Step 4.2, establishing the spinal mechanical response function; Construct a spinal mechanical response function to predict the effect of specific massage parameters on the biomechanical state of the spine: Function definition: Build the response function: ; in, Represents the spinal mechanical response function, which is used to describe the given massage parameter vector and the spinal biomechanical eigenvectors The mechanical distribution of the spine under certain conditions. is the biomechanical eigenvector of the spine, is the massage parameter vector, is the force distribution vector of the spine.

[0069] Model construction: Based on finite element analysis and biomechanics principles, a parametric spinal mechanics model is constructed to simulate the effects of different massage movements on the spine.

[0070] Fast computing optimization: Through model reduction technology and pre-calculated database, real-time response prediction can be achieved in milliseconds.

[0071] Safety constraint definition: Based on biomechanical safety standards and expert knowledge, define the set of spinal biomechanical safety constraints , ensuring that the massage parameters will not cause discomfort or damage to the spine.

[0072] Step 4.3, sleep quality evaluation function optimization; Improve the sleep quality evaluation function to achieve a comprehensive assessment of sleep status: Function improvement: optimize the sleep quality evaluation function and refine various sleep quality indicators The calculation method makes the scoring more comprehensive and reasonable: ; in, Represents the current sleep state vector The comprehensive sleep quality score, the higher the value, the better the sleep quality; Represents the current sleep state vector, which contains the user's multi-dimensional sleep physiological characteristics at the current moment (such as sleep stage, depth, muscle tension, etc.); Indicates the total number of sleep quality indicators included in the evaluation system; Indicates the The scoring function of the sleep quality index takes the current sleep state vector as input , the output is the score of the indicator (such as sleep depth, continuity, stability, etc.); Indicates the The weight coefficient corresponding to each sleep quality indicator reflects the relative importance of the indicator in the comprehensive score. All weight coefficients meet , to ensure the normalization of the scores.

[0073] Weight adaptation: Dynamically adjust the weight coefficient of each indicator based on user characteristics (such as age, gender, sleep habits) and usage scenarios (short break or full night sleep) .

[0074] Individualized parameters: Based on the user's historical data, the evaluation function parameters are adjusted to make them more in line with the user's personal sleep characteristics and needs.

[0075] Step 4.4, collaborative optimization objective function construction; Based on the above functions, the overall objective function of sleep-spine collaborative optimization is constructed: Optimization objective definition: The optimization problem can be formally expressed as , the constraints are , that is, the force distribution of the spine under the selected massage parameters must meet the safety constraints.

[0076] in, Represents the vector of all possible massage parameters In the above example, we look for the function that can make the objective function Get the maximum value of the parameter combination; Represents the massage parameter vector, including multiple dimensions such as massage intensity, frequency, mode, and action area; Represents the current sleep state vector, reflecting the user's current sleep stage, depth, muscle tension and other multi-dimensional physiological characteristics; Represents the state transition function, input current sleep state and massage parameters , output the predicted future sleep state vector ; It represents the sleep quality evaluation function, which comprehensively scores the input sleep state vector. The higher the value, the better the sleep quality. Represents the spinal biomechanical eigenvector, describing the current biomechanical state of the user's spine; Represents the spinal mechanical response function, input massage parameters and spinal features , output the spine force distribution vector ; Represents the set of biomechanical safety constraints of the spine, which stipulates the safety conditions that the spine must meet. The optimization goal is to ensure the distribution of spinal force. Satisfy safety constraints Under the premise of , so that the user's sleep quality score after state transition To maximize.

[0077] Multi-objective optimization: The two goals of improving sleep quality and ensuring spinal health are combined through weight coefficients to form a balanced optimization goal.

[0078] Constraint integration: Multiple constraints such as spinal safety constraints, massage equipment physical limitations, and user comfort requirements are incorporated into the optimization framework.

[0079] After completing the model construction, the system obtains a theoretical basis for calculating the optimal massage parameters based on the user's current sleep state and spinal characteristics, providing scientific guidance for subsequent adaptive adjustments.

[0080] like Figure 5 As shown, it shows how the system dynamically adjusts the spinal support configuration according to different sleep stages, and shows the mapping relationship between sleep state and spinal support mode.

[0081] Step 5: Based on the sleep spine collaborative optimization model, the massage parameters are optimized and adjusted dynamically in real time to form a closed-loop control system. The specific steps include: Step 5.1, sleep spine state machine construction; Build a sleeping spine state machine to define the ideal spinal support configuration for different sleep stages: State Definition: Defines the sleep spinal joint state space, which contains the combination of sleep stages and spinal support patterns.

[0082] State mapping: Based on knowledge of sleep physiology and biomechanics, a mapping relationship is established between sleep stages and ideal spinal support configurations, such as relaxed support during REM sleep and stable support during deep sleep.

[0083] Transition rules: Define the triggering conditions and smooth transition mechanism for state transition to ensure comfort when switching between massage modes.

[0084] Individualized adjustment: Based on the user's spinal characteristics and feedback history, the state machine parameters are optimized to achieve personalized support configuration.

[0085] like Figure 6 As shown in the figure, the system response time of the proposed system is compared with that of the traditional massage chair in different operation scenarios, demonstrating the advantages of the proposed system in terms of computing efficiency.

[0086] Step 5.2, adaptive trajectory planning algorithm; Based on the current sleep state and spinal characteristics, an adaptive trajectory planning algorithm is used to dynamically optimize the massage trajectory: Trajectory library initialization: pre-design a basic massage trajectory library for different sleep stages and spinal characteristics.

[0087] Real-time trajectory adjustment: Based on the optimization model, the parameters in the trajectory library are optimized and adjusted in real time.

[0088] Trajectory smoothing: The cubic spline interpolation algorithm is applied to smooth the optimized trajectory to ensure motion continuity.

[0089] Dynamic response mechanism: The dynamic response mechanism of the design trajectory enables the massage trajectory to quickly respond to sudden changes in sleep state.

[0090] Step 5.3, multi-parameter coordinated control; Achieve multi-dimensional coordinated control of massage parameters to form a complete massage experience: Parameter vector collaborative optimization: Simultaneously optimize multi-dimensional parameters such as force, frequency, trajectory, heat, vibration, etc. to achieve the overall optimal effect.

[0091] Parameter correlation modeling: Establish a correlation model between different massage parameters to avoid contradictions or conflicts in parameter combinations.

[0092] Hierarchical control strategy: A hierarchical control architecture is adopted to separate sleep cycle-scale strategy planning from millisecond-level motion control to improve system response speed.

[0093] Parameter constraint verification: Before executing specific control, the optimized parameters are checked for safety constraints to ensure that they do not exceed the equipment capabilities and biomechanical safety boundaries.

[0094] Step 5.4, sleep quality feedback closed loop; Introducing a sleep quality feedback mechanism to continuously optimize the control strategy through sleep effect evaluation: Real-time effect evaluation: Based on the changing trend of sleep status, the immediate effect of massage intervention is evaluated in real time.

[0095] Post-session evaluation: After each session, the effectiveness of the massage program was evaluated based on the overall sleep quality score.

[0096] Strategy adjustment: Based on the evaluation results, the massage strategy library and optimization algorithm parameters are automatically adjusted.

[0097] User feedback integration: Combines user subjective feedback and objective sleep data to form a comprehensive evaluation to guide continuous optimization of the system.

[0098] Through the above steps, the system forms a complete closed-loop control process, which can dynamically optimize massage parameters according to the user's real-time sleep status and spinal characteristics, and continuously improve through continuous feedback learning to achieve truly intelligent and personalized sleep assistance.

[0099] like Figure 7 As shown, the system's adaptation speed to new users is demonstrated, including the personalized model building time, parameter optimization completion, and user comfort score changes over usage time.

[0100] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make more forms of equivalent embodiments based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. An intelligent adjustment method for a shared massage chair based on big data, characterized in that: The following steps are involved: Collect the user's sleep-related physiological indicators and generate a preliminary sleep state feature vector; Based on the preliminary sleep state feature vector, the pressure distribution data of the user's spine and the contact surface of the massage chair are collected to build a personalized spinal curve digital model and generate the spinal biomechanical feature vector; Based on the preliminary sleep state feature vector and spinal biomechanical feature vector, the hidden Markov model is applied to identify the user's sleep state in real time and generate a complete sleep state vector; Based on the complete sleep state vector and spinal biomechanical characteristic vector, a sleep-spine collaborative optimization model is established, and the state transition function, spinal mechanical response function and sleep quality evaluation function are constructed. Based on the sleep spine collaborative optimization model, real-time optimization and dynamic adjustment of massage parameters are achieved to form a closed-loop control system.

2. The intelligent adjustment method for a shared massage chair based on big data according to claim 1, characterized in that: The step of collecting the user's sleep-related physiological indicators includes: A multimodal sensing system integrating millimeter-wave radar sensors, far-infrared sensors, and sound sensors collects sleep-related physiological indicators of users. Preprocessing of the collected raw biological signals, including noise filtering, signal separation and feature extraction; The processed multimodal physiological features are fused to generate a preliminary sleep state feature vector.

3. The intelligent adjustment method for a shared massage chair based on big data according to claim 1, characterized in that: The step of collecting pressure distribution data on the contact surface between the user's spine and the massage chair includes: Deploy a high-density pressure sensor array in the backrest area of ​​the massage chair to collect pressure distribution data in the user's spine area; Based on the collected pressure distribution data, the thin plate spline interpolation algorithm is applied to reconstruct the user's spinal curve; Based on the reconstructed spinal curve and pressure distribution, the spinal biomechanical feature vector is constructed.

4. The intelligent adjustment method for a shared massage chair based on big data according to claim 1, characterized in that: The step of applying the hidden Markov model to identify the user's sleep state in real time includes: Extract and fuse the temporal features of the preliminary sleep state feature vector; Build a sleep state classifier based on the Hidden Markov Model to determine the user's sleep stage in real time; Based on the identified sleep state sequence, sleep quality scores and characteristic indicators are calculated; The sleep state classification results are combined with other physiological features to form a complete sleep state vector.

5. The intelligent adjustment method for a shared massage chair based on big data according to claim 1, characterized in that: The steps of establishing the sleep spine collaborative optimization model include: Construct a state transition function to predict the changing trend of the current sleep state under specific massage parameters; Construct a spinal mechanical response function to predict the effect of specific massage parameters on the biomechanical state of the spine; Improve the sleep quality evaluation function to achieve a comprehensive assessment of sleep status; Construct the overall objective function of sleep-spine collaborative optimization.

6. The intelligent adjustment method for a shared massage chair based on big data according to claim 5, characterized in that: The overall objective function is formally expressed as: maximizing the effect of massage parameters on improving sleep quality while satisfying spinal safety constraints.

7. The intelligent adjustment method for a shared massage chair based on big data according to claim 1, characterized in that: The steps of achieving real-time optimization and dynamic adjustment of massage parameters include: Build a sleep spinal state machine to define the ideal spinal support configuration for different sleep stages; Based on the current sleep state and spinal characteristics, an adaptive trajectory planning algorithm is used to dynamically optimize the massage trajectory; Realize multi-dimensional coordinated control of massage parameters to form a complete massage experience; Introduce a sleep quality feedback mechanism to continuously optimize the regulation strategy through sleep effect evaluation.

8. The intelligent adjustment method for a shared massage chair based on big data according to claim 7, characterized in that: The sleep spine state machine includes: defining a sleep spinal joint state space, which includes combinations of sleep stages and spinal support patterns; Based on knowledge of sleep physiology and biomechanics, a mapping relationship between sleep stages and ideal spinal support configuration is established; Define the trigger conditions and smooth transition mechanism for state transition to ensure comfort when switching between massage modes; According to the user's spinal characteristics and feedback history, the state machine parameters are optimized to achieve personalized support configuration.

9. The intelligent adjustment method for a shared massage chair based on big data according to claim 7, characterized in that: Sleep quality feedback mechanisms include: Based on the changing trend of sleep status, the immediate effect of massage intervention can be evaluated in real time; After each use, the effectiveness of the massage program was evaluated based on the overall sleep quality score; Automatically adjust the massage strategy library and optimize algorithm parameters based on the evaluation results; Combining users' subjective feedback and objective sleep data, a comprehensive evaluation is formed to guide continuous optimization of the system.

10. An intelligent adjustment system for a shared massage chair based on big data, used to execute the intelligent adjustment method for a shared massage chair based on big data according to any one of claims 1 to 9, characterized in that: include: A non-contact biological parameter monitoring unit is used to collect the user's sleep-related physiological indicators and generate a preliminary sleep state feature vector; The pressure distribution sensing unit collects pressure distribution data on the contact surface between the user's spine and the massage chair based on the preliminary sleep state feature vector, constructs a personalized digital model of the spinal curve, and generates a spinal biomechanical feature vector; The sleep state recognition unit uses a hidden Markov model to identify the user's sleep state in real time based on the preliminary sleep state feature vector and the spinal biomechanical feature vector, generating a complete sleep state vector. The collaborative optimization modeling unit establishes a sleep-spine collaborative optimization model based on the complete sleep state vector and spinal biomechanical characteristic vector, and constructs the state transition function, spinal mechanical response function, and sleep quality evaluation function; The adaptive trajectory planning unit, based on the sleeping spine collaborative optimization model, realizes real-time optimization and dynamic adjustment of massage parameters to form a closed-loop control system.

Images