Intelligent sofa control method based on user habits and intelligent sofa

Abstract

The invention provides an intelligent sofa control method based on user habits and an intelligent sofa, and relates to the technical field of sofa control, and the method comprises the following steps: collecting the maximum sinking amount of a sofa seat cushion in a use state of a user; establishing a sofa parameter recommendation model taking the maximum sinking amount of the sofa seat cushion as a state vector and the sofa parameters as control variables; collecting the maximum sinking amount of the sofa seat cushion with the maintaining duration longer than the preset maintaining duration and the corresponding sofa parameters; training the support vector regression model by using the training set to obtain an optimal hyperplane which enables a prediction error to be smaller than a preset prediction error; the real-time maximum sinking amount of the sofa seat cushion is collected; inputting the real-time maximum sinking amount of the sofa seat cushion into the trained support vector regression model, and outputting predicted sofa parameters; and controlling the sofa according to the predicted sofa parameters. The method can recommend the sofa parameters which ensure the healthy sitting posture of the user and meet the comfort level, and can control the sofa.

Description

Technical Field

[0001] The present invention relates to the technical field of sofa control, and in particular to an intelligent sofa control method based on user habits and an intelligent sofa. Background Art

[0002] Smart sofas are high-tech sofas that combine sensors and control systems. They use intelligent algorithms to monitor the user's weight distribution, seat cushion pressure, backrest angle and other data, and automatically adjust various parameters to optimize the user's sitting comfort. This type of sofa can achieve personalized sitting posture adjustment, providing higher comfort and health protection.

[0003] The smart sofa control method based on user habits usually involves the use of sensors to monitor data such as user sitting posture, usage time and frequency. The system analyzes this data, learns the user's habits and preferences, and then automatically adjusts the hardness, angle and other settings of the sofa to suit the user's comfort needs. It is very necessary to carry out smart sofa control based on user habits because it can improve personal comfort and health. Intelligent adjustments that adapt to user habits can help reduce back and neck pain and improve sitting posture quality, thereby enhancing quality of life and work efficiency.

[0004] However, in the initial use stage of the sofa, the existing intelligent sofa control method needs to obtain the prior knowledge of user habits in advance, and then learn how to adjust the sofa to the user's habitual posture based on the prior knowledge. However, when the user uses the sofa for the first time, he is not sure under which sofa parameter setting can achieve the best comfort. Some users only set the parameters by themselves, and will not waste time to adjust them when they feel the comfort is appropriate. In this state, the sofa parameter settings may not be the ones that allow users to achieve the best comfort. If the data collected in this way is used as user habits for learning and automatic adjustment, it will not only increase the user's usage burden, but also cannot ensure the accuracy of sofa adjustment based on user habits. The adjustment method is too single and cannot improve the user experience of the sofa. It is not practical enough and cannot give full play to the adjustable performance of the sofa. Summary of the invention

[0005] In order to solve the technical problems that the smart sofa control method existing in the prior art increases the user's usage burden, and cannot ensure the accuracy of sofa adjustment only according to user habits, the adjustment method is too single and cannot improve the usage experience of the sofa, the practicality is insufficient, and the adjustable performance of the sofa cannot be fully utilized, the present invention provides a smart sofa control method based on user habits and a smart sofa.

[0006] The technical solution provided by the embodiment of the present invention is as follows: First aspect An embodiment of the present invention provides a method for controlling a smart sofa based on user habits, comprising: S1: Collect the maximum sinking amount of the sofa cushion when the user is using it; S2: Taking the ergonomic standard as the adjustment constraint condition of the sofa H point, a sofa parameter recommendation model is established with the maximum sinking amount of the sofa cushion as the state vector and the sofa parameters as the control variables. The sofa parameters include the sofa backrest angle, sofa cushion height, sofa cushion depth and sofa cushion inclination. S3: collecting the maximum sinking amount of the sofa cushion whose maintenance time is longer than the preset maintenance time and the corresponding sofa parameters, wherein the collected maximum sinking amount of the sofa cushion and the sofa parameters constitute a training set; S4: combining the radial basis kernel function with adaptive width adjustment parameters and the weight that is proportional to the maintenance time, using the training set to train the support vector regression model, and obtaining the optimal hyperplane that makes the prediction error less than the preset prediction error, wherein the prediction error is the difference between the predicted sofa parameters and the actual sofa parameters; S5: Collect the maximum sinking amount of the sofa cushion in real time; S6: input the maximum sinking amount of the real-time sofa cushion into the trained support vector regression model, and output the predicted sofa parameters; S7: Control the sofa according to the predicted sofa parameters.

[0007] Second aspect A smart sofa provided in an embodiment of the present invention is applied to the smart sofa control method based on user habits as described in the first aspect.

[0008] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, the maximum lower limit of the sofa cushion that can reflect the user's use status is first collected, and then the ergonomic standard is combined as the constraint of the sofa H point to determine the sofa parameter recommendation model. Under the state of obtaining the maximum lower limit of the sofa cushion, the sofa parameter range that meets the healthy sitting posture of the human body and enables the user to reach the H point of sufficient comfort, namely the sofa backrest angle, sofa cushion height, sofa cushion depth and sofa cushion inclination, can be recommended, and a group of sofa parameters are randomly selected to adjust the seat. After that, user feedback is obtained, and the sofa parameters that meet the requirements of the maintenance time are retained to form a training set, and the support vector regression model is trained using the training set. By adaptively adjusting the width of the kernel function, the model can adapt to the characteristics of the data more flexibly, and the introduction of the time weight ensures that the data used for a long time has a greater impact on the model training, thereby more truly reflecting the impact of the use conditions on the performance of the sofa cushion, not only improving the generalization ability of the model, but also making the sofa design more in line with actual use needs. The model can learn the complex and invisible correlation between the maximum sinkage of the sofa cushion and the sofa parameters, improve the prediction accuracy and adaptability of the model, and dig out more reasonable sofa parameters that meet health and comfort requirements, avoiding the user burden caused by self-adjustment during the initial use process. It can also make reasonable recommendations considering the user's health and comfort and deeply dig out more reasonable sofa parameters, thereby improving the user experience and increasing product competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic flow chart of a method for controlling a smart sofa based on user habits provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0012] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0013] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0014] Reference Manual Attached Figure 1 , showing a flow chart of a smart sofa control method based on user habits provided by an embodiment of the present invention.

[0015] The embodiment of the present invention provides a method for controlling a smart sofa based on user habits, which can be implemented by an attack bypass blocking device based on network abnormal behavior analysis, and the attack bypass blocking device based on network abnormal behavior analysis can be a terminal or a server. The processing flow of the method for controlling a smart sofa based on user habits can include the following steps: S1: Collect the maximum sinking amount of the sofa cushion when the user is using it.

[0016] The maximum sinkage of a sofa seat cushion refers to the depth of the seat cushion sinking from the unpressed state to the maximum pressure when the user sits on the sofa. This measurement reflects the softness, load-bearing capacity and elasticity of the sofa seat cushion. Measuring the maximum sinkage is extremely important for evaluating the comfort and functionality of a sofa, as it affects the sitting support and comfort during long-term use.

[0017] S2: Taking the ergonomic standard as the adjustment constraint condition of the sofa H point, a sofa parameter recommendation model is established with the maximum sinking amount of the sofa cushion as the state vector and the sofa parameters as the control variables.

[0018] Among them, sofa parameters include sofa back angle, sofa seat cushion height, sofa seat cushion depth and sofa seat cushion inclination.

[0019] Specifically, the ergonomics standard can be GB / T 14755-1993 Ergonomic Requirements for Chairs. The self-recommendation of parameters in the initial stage can help users quickly find sofa parameters that are more comfortable and meet the healthy sitting posture standards. Even if the user is not clear about the specific parameter settings, the system can still give appropriate recommendations to ensure comfort for the first use.

[0020] The H-point of the sofa refers to the point in the sofa that contacts the human hip. This point is a key position to determine how the seat supports the user's body, especially in ergonomics, because it is related to the comfort and health impact of the sitting posture. Ergonomic standards are used as constraints for adjusting the H-point of the sofa to create an intelligent sofa parameter recommendation model. The model uses the maximum sinkage of the sofa cushion as the state vector and sofa parameters (such as backrest angle, cushion height, cushion depth, and cushion inclination) as control variables. In this way, the model is able to recommend sofa parameter settings based on the user's actual usage status to optimize the sitting posture and increase comfort. The core goal of the model is to ensure that the design and configuration of the sofa meet the requirements of ergonomics, and use the H-point to ensure the user's comfort during the adjustment process, improving the user's seating experience and physical health.

[0021] In a possible implementation manner, the sofa parameter recommendation model established by the state variables and the control variables is specifically:

[0022] in, Indicates the sofa backrest angle, Indicates the height of the sofa cushion. d Indicates the depth of the sofa cushion. Sofa seat cushion tilt, z Indicates the maximum sinking amount of the sofa cushion. They respectively represent the horizontal coordinate, vertical coordinate and vertical coordinate of point H of the sofa in the user's use state in the coordinate system with the midpoint of the rear edge of the sofa cushion as the coordinate origin, wherein the horizontal coordinate is the coordinate of point H of the sofa in the width direction of the seat cushion, the vertical coordinate is the coordinate of point H of the sofa in the depth direction of the seat cushion, and the vertical coordinate is the coordinate of point H of the sofa perpendicular to the plane of the seat cushion.

[0023] It should be noted that the model will randomly select a set of parameter outputs from the calculated sofa parameter set that meets the adjustment constraints and obtain user feedback. The sofa parameter recommendation model calculates the position of the sofa H point in three dimensions by combining the maximum sinking amount of the sofa cushion in the actual user's use status and other related sofa parameters (sofa back angle, sofa cushion height, sofa cushion depth, sofa cushion inclination). The model uses these calculated coordinate values ​​to ensure that the recommended sofa parameters not only meet ergonomic requirements, but also improve user comfort. By randomly selecting from the qualified parameter set and obtaining user feedback to optimize and adjust the recommendation algorithm, this method can dynamically adjust the sofa settings to adapt to the specific needs of different users, thereby improving user experience and satisfaction.

[0024] In a possible implementation manner, the adjustment constraint conditions of the sofa parameter recommendation model are specifically:

[0025] in, W Indicates the total width of the sofa cushion. D Indicates the total depth of the sofa cushion. a =3cm represents the height adjustment factor based on ergonomic standards.

[0026] It should be noted that this adjustment constraint ensures that the sofa design meets specific ergonomic standards to improve user comfort and support. The constraints include that the location of the sofa's H point must be within the central tenth of the seat cushion width, the depth must be between half and three-quarters of the seat cushion depth, and the vertical position of the H point must be within the allowable range of the seat cushion height. In addition, the sofa backrest angle should be maintained between 95 and 105 degrees. The range of these parameters is selected to provide adequate support while maintaining overall comfort and functionality.

[0027] S3: Collect the maximum sinking amount of the sofa cushion and the corresponding sofa parameters when the maintenance time is longer than the preset maintenance time.

[0028] Among them, the collected maximum sinkage of the sofa cushion and sofa parameters constitute the training set.

[0029] Among them, the maintenance time refers to the length of time that the user maintains a certain sitting posture on the sofa. The system collects data by monitoring the usage status that is maintained for more than the preset time. Only when the user's sitting posture on the sofa lasts longer than the set threshold, the maximum sinking amount of the seat cushion and the corresponding sofa parameters in this state will be recorded and added to the training set. This data collection method helps to filter out data that may cause a short sitting posture maintenance time due to discomfort, thereby ensuring that the data in the training set reflects the state of high user satisfaction. In this way, the established training set can more accurately reflect the sofa parameters with good comfort and ergonomic design, and provide high-quality basic data for subsequent model training and parameter optimization. Not only can user preferences be recorded, but also the initial parameter setting recommendation can be completed based on ergonomic standards, which can make up for the problem that customers cannot determine which set of sofa parameters is most suitable, reduce the impact of abnormal sitting posture on user health, and ensure the comfort of user use.

[0030] It should be noted that those skilled in the art can set the preset maintenance time length according to actual needs, and the present invention is not limited thereto.

[0031] In a possible implementation, S3 specifically includes: S301: Initialize sofa parameters.

[0032] S302: Collect the maximum sinking amount of the sofa cushion.

[0033] S303: Inputting the maximum sinking amount of the sofa cushion into the sofa parameter recommendation model, and randomly outputting the recommended sofa parameters that meet the adjustment constraint conditions.

[0034] S304: Determine whether the maintenance time under the recommended sofa parameters is greater than the preset maintenance time. If so, retain the recommended sofa parameters whose maintenance time is greater than the preset maintenance time and the corresponding maximum sinking amount of the sofa cushion as a data pair. Otherwise, return to step S303.

[0035] It should be noted that those skilled in the art can set the preset maintenance time length according to actual needs, and the present invention is not limited thereto.

[0036] S305: Determine whether the number of data pairs is greater than the preset number of data pairs. If so, terminate the iteration and proceed to step S306; otherwise, return to step S303.

[0037] It should be noted that those skilled in the art can set the size of the number of preset data pairs according to actual needs, and the present invention is not limited thereto.

[0038] S306: Outputting the retained recommended sofa parameters and the corresponding maximum sinking amount of the sofa cushion as a training set.

[0039] Specifically, first, the sofa parameters are initialized. Subsequently, the system collects the maximum sinking amount of the sofa cushion when in use, and inputs this data into the sofa parameter recommendation model, which randomly outputs sofa parameters that meet the adjustment constraints. Next, the system checks whether the user's maintenance time under these parameters exceeds the preset value. If so, this set of parameters and the corresponding sinking amount data are saved. If not, a new parameter combination is searched again. This process is repeated until a sufficient number of data pairs are collected. Finally, these data pairs are output as training sets for further optimization and adjustment of the recommendation model. This iterative process ensures that the recommended sofa parameters can actually improve the user's comfort, and the collected data will support future model training and refinement.

[0040] S4: Combined with the radial basis kernel function with adaptive width adjustment parameters and the weight that is proportional to the maintenance duration, the support vector regression model is trained using the training set to obtain the optimal hyperplane that makes the prediction error less than the preset prediction error.

[0041] Among them, the prediction error is the difference between the predicted sofa parameters and the actual sofa parameters.

[0042] Among them, the adaptive width adjustment parameter is a parameter in the radial basis kernel function, which is used to adjust the width of the function, thereby controlling the sensitivity of the kernel function to neighboring data points. According to different data distributions, automatically adjusting this parameter can improve the fitting effect and generalization ability of the model. The radial basis kernel function is a kernel function commonly used in support vector machines, especially suitable for feature space mapping of nonlinear data. The support vector regression model is a regression analysis method based on the principle of support vector machines. It tries to find a function that minimizes the difference between the actual output value and the predicted output value while keeping the complexity of the model as low as possible. In the support vector machine, the optimal hyperplane refers to the decision interface that can maximize the margin (that is, the minimum distance from the data point to the separation plane), which is as close as possible to all data points (within a certain error tolerance).

[0043] The system uses the support vector regression model of the radial basis kernel function, combined with the adaptive width adjustment parameters, to predict the sofa parameters. The goal of the model training is to find an optimal hyperplane that minimizes the prediction error between the predicted sofa parameters and the actual parameters. By using weights proportional to the maintenance time, the model increases the importance of data points that maintain a comfortable sitting posture for a long time, thereby improving the accuracy of the model's prediction of comfortable sitting posture parameters. This method ensures that each parameter recommendation is as consistent as possible with the user's actual usage experience, thereby improving user satisfaction and comfort experience. Moreover, in the recommendation process, this model determines the random recommendation method as an accurate recommendation method, ensuring that each recommendation can maintain a maintenance time greater than the preset maintenance time.

[0044] It should be noted that those skilled in the art can set the size of the preset prediction error according to actual needs, and the present invention is not limited here.

[0045] In a possible implementation, S4 specifically includes: S401: Use a radial basis kernel function with an adaptive width adjustment parameter to map the maximum sinking amount of the sofa cushion to a high-dimensional space for linear separation:

[0046] in, represents the radial basis kernel function value representing the similarity between the maximum sinking amount of the first sofa cushion and the maximum sinking amount of the second sofa cushion, exp represents the exponential function, represents the width adjustment parameter that controls the radial basis kernel function, Indicates the calculation of the square of the Euclidean distance, represents the input data set including the maximum sinkage of all sofa cushions in the training set, n represents the total number of samples in the training set, Indicates the training set iMaximum sinking amount of a sofa seat cushion, α and β Represent local adjustment parameters and global adjustment parameters respectively, represents the mean maximum sinking amount of the sofa cushion in the training set, Indicates the calculation of Euclidean distance, log indicates the logarithmic function, represents the standard deviation of the maximum sinkage of the sofa cushion in the training set, Represents a constant that prevents the denominator from being zero.

[0047] Optionally, the constant Specifically .

[0048] It should be noted that in the calculation process of the width adjustment parameter, the Euclidean distance from each data point to the mean is calculated to capture the discreteness of the data, and the exponential term in the Taylor series expansion, i.e., the numerator, is used to deal with the nonlinear characteristics of the distance, so that the close-distance data has a greater impact on the width parameter. The introduction of the logarithmic term ensures the robustness of the model to outliers while avoiding overfitting. Combining the squared distance term of each point with the logarithmic function can better capture the local structure of the data and the impact of outliers on the parameters.

[0049] The system uses a radial basis kernel function with an adaptive width adjustment parameter to map the maximum sinkage of the sofa cushion to a high-dimensional space. This mapping allows the model to perform linear separation in high-dimensional space, thereby effectively capturing the complex nonlinear relationship between the maximum sinkage of the sofa cushion and the sofa adjustment parameters (such as the seat cushion tilt angle, backrest angle, and seat height). By mapping the data to a high-dimensional space, the model can find a hyperplane in this space that can clearly express the relationship between the sinkage and different sofa adjustment parameters, thereby achieving accurate prediction and adjustment of these relationships. The linear inseparable problem that cannot be solved in the original space is solved by increasing the dimension.

[0050] In a possible implementation, the local adjustment parameter and the global adjustment parameter are solved based on the maximum entropy principle, and the solving process specifically includes: According to the maximum entropy principle, the selection of local adjustment parameters and global adjustment parameters can allow the model to maximize entropy while capturing global and local information, so that these two parameters can enable the model to achieve the best balance in capturing global and local features. Estimation through the maximum entropy principle ensures that the formula is sufficiently sensitive to both the global and local characteristics of the data.

[0051] The objective function for solving local adjustment parameters and global adjustment parameters is determined based on the maximum entropy principle. The specific objective function is:

[0052] in,H represents the information entropy of the training set, It represents the local adjustment parameters and global adjustment parameters that maximize the information entropy. Represents the first i The probability density of a sample.

[0053] The partial derivatives of information entropy with respect to local adjustment parameters and global adjustment parameters are calculated respectively to obtain the conversion objective function:

[0054] in, It means partial derivative.

[0055] The transformation objective function is iteratively solved by Newton's method to obtain local adjustment parameters and global adjustment parameters.

[0056] It should be noted that partial derivative optimization can find the best value based on the rate of change of entropy. α and β The value enables the model to retain the maximum amount of information in the data during training, which is in line with the maximum entropy principle. By maximizing the information entropy, the model can better capture the diversity and uncertainty of data distribution, thereby improving generalization ability and avoiding overfitting. By solving their partial derivatives, the model can more accurately adjust the performance of the kernel function in different regions, making it more sensitive to similar data points, thereby better capturing the nonlinear relationship between the input features and the target variable.

[0057] S402: According to the maximum sinking amount of the sofa cushion after high-dimensional mapping and its corresponding sofa parameters, an optimization function for hyperplane parameters is established with the goal of minimizing the prediction error, wherein the hyperplane parameters include a weight vector and a bias vector:

[0058] in, W represents the weight vector, b represents the bias vector, C represents the penalty parameter, max represents the maximum value, Indicates the training set i The first j The actual sofa parameter values, , n represents the total number of samples in the training set, , , , Respectively represent i The real sofa back angle, real sofa cushion height, real sofa cushion depth and real sofa cushion inclination in the samples. Indicatesi The maximum sinking amount of the sofa cushion in the sample corresponds to the j Predicted sofa parameter values, represents the tolerance error, It means taking the function to the minimum value W and b , Indicates the training set i The weight of the samples, Indicates the training set i The duration of the sample, Indicates the maintenance time of the training set samples T The maximum duration of maintenance.

[0059] It should be noted that the introduction of weight The weighted sum of makes the model automatically biased towards samples with longer maintenance time during the training process, ensuring that the model is more in line with the user's sitting habits when recommending sofa parameters, improving the comfort of user experience. During the training process, the weights of different training data are assigned according to the size of the maintenance time, so that the determined hyperplane can recommend sofa parameters in the most optimal way to the greatest extent, in line with the user's sitting habits. The weight solution method of the exponential function can increase the weight difference of high maintenance time, and the weight of high maintenance time samples will be higher, which meets the recommendation requirements.

[0060] Specifically, the loss function combines the squared loss with the penalty term, and the regularization term used here is It helps prevent the model from overfitting, that is, overfitting to the noise in the training data rather than the underlying data patterns. This can improve the model's ability to generalize to unseen data. By introducing a penalty term, the model is penalized if the difference between the predicted value and the true value is less than or equal to This method reduces excessive punishment on the model and allows a certain amount of error, making the model more robust, especially when dealing with small fluctuations in real-world data. By setting the weight of each sample to an exponential function of the ratio of its maintenance time to the maximum maintenance time, the model automatically favors samples that users can maintain for a long time. This weighting method ensures that during model training and prediction, parameter settings that are more in line with users' long-term usage habits are given higher priority, so as to be more in line with users' actual usage preferences and comfort. The optimization function combines the adjustment of the weight vector and the bias vector to find the best hyperplane by adjusting these parameters. This hyperplane can minimize the overall prediction error and meet the above-mentioned regularization and error tolerance conditions. Such a setting helps to find a model that can both accurately predict and widely adapt to various user needs. The adaptability of the model to the time users maintain a comfortable sitting posture is improved, while maintaining the accuracy of the prediction and the generalization ability of the model.

[0061] In a possible implementation manner, after S402, the method further includes: S402A: Adjust the hyperparameters of the support vector regression model by using a gradient descent method with a momentum term, where the hyperparameters include a penalty parameter and a tolerance error.

[0062] It should be noted that by introducing the gradient descent method with momentum term, the hyperparameters of the support vector regression model are adjusted, including penalty parameters and tolerance errors. The addition of momentum term helps to accelerate the convergence process in gradient descent and helps to avoid falling into local minimum. This method enables the model to find a better parameter combination more quickly, thereby improving the prediction performance and stability of the model, ensuring that the final model can more accurately reflect and predict the user's usage habits and comfort requirements.

[0063] In a possible implementation manner, S402A specifically includes: S402A1: Calculate the partial derivatives of the objective function value with respect to the penalty parameter and the tolerance error respectively:

[0064] in, J represents the objective function value, Indicates the use for judgment The sign function of the difference direction, represents the indicator function, when The indicator function takes 1 when , otherwise, the indicator function takes 0.

[0065] S402A2: Update the penalty parameter and tolerance error according to the obtained partial derivatives until the update amplitude of each hyperparameter is less than the preset update amplitude:

[0066] in, represents the learning rate, Indicates assignment, and Both represent the momentum term of the stored gradient, represents the momentum parameter.

[0067] The update amplitude refers to the amount by which the hyperparameters are updated in each iteration during the optimization process. Specifically, this measure reflects the magnitude of the change in the penalty parameter and tolerance error from one iteration to the next. If the update amplitude is less than a preset threshold, it means that the hyperparameters are already close to their optimal values ​​and further adjustments will have little effect, so the iteration process can be stopped.

[0068] Optionally, the momentum parameter can be set to 0.9.

[0069] It should be noted that those skilled in the art can set the size of the preset update amplitude according to actual needs, and the present invention is not limited here.

[0070] It should be noted that the momentum term can accelerate convergence and reduce oscillations by introducing the gradient accumulation of the previous steps in the hyperparameter update. It is especially suitable for dealing with narrow and long optimization areas and jumping out of local optimality, thereby improving optimization efficiency and stabilizing the parameter search process. Specifically, first, by calculating the partial derivatives of the objective function with respect to the penalty parameter and the tolerance error, it is determined how these parameters should be adjusted to minimize the objective function. Then, the hyperparameters are updated using the gradient descent method with momentum terms based on these partial derivatives. The introduction of the momentum term can be regarded as an acceleration technique, which speeds up convergence and reduces oscillations by considering the influence of previous gradients, making the parameter update process more efficient and stable. This method is particularly effective in guiding the global optimal solution, especially in complex optimization landscapes, helping to avoid falling into local minima.

[0071] S403: Solve the optimization function and establish the optimal hyperplane of the support vector regression model based on the hyperplane parameters obtained by the solution:

[0072] in, Represents input data x That is, the function value of the maximum sinking amount of the sofa cushion.

[0073] Specifically, the maximum sinking amount of the sofa cushion is first mapped to a high-dimensional space using a radial basis kernel function, which helps reveal the complex nonlinear relationship between the sinking amount and the sofa adjustment parameters. Then, in S402, an optimization problem is set to minimize the prediction error, and the weight vector and the bias vector are adjusted to find the best hyperplane. Finally, in S403, this optimization problem is solved to determine the hyperplane parameters, and the optimal hyperplane of the support vector regression model is established to ensure that the model can accurately predict and adjust the sofa parameters, thereby improving the user experience and meeting personalized needs.

[0074] S5: Collect the maximum sinking amount of the sofa cushion in real time.

[0075] S6: Input the real-time maximum sinking amount of the sofa cushion into the trained support vector regression model and output the predicted sofa parameters.

[0076] S7: Control the sofa according to the predicted sofa parameters.

[0077] In a possible implementation manner, after S7, the method further includes: Retrain the support vector regression model at preset intervals.

[0078] It should be noted that those skilled in the art can set the preset duration according to actual needs, and the present invention is not limited thereto.

[0079] It can be understood that the implementation method of retraining the support vector regression model at preset intervals is to ensure that the model is continuously updated and improved.

[0080] In the actual application process, the whole scheme describes a complete intelligent sofa parameter adjustment system. From data collection to model training to real-time application, the whole process is closely linked to form a closed-loop feedback system. First, a sofa parameter recommendation model was established to recommend sofa parameters based on the maximum sinking amount of the sofa cushion. Then, the support vector regression model was established based on these data to recommend parameters based on ergonomics and the sofa H point as the basis and adjustment target to ensure that the healthy sitting posture standards and comfort requirements are met. Finally, the trained model is used to dynamically adjust the sofa settings according to the user's immediate use to provide continuous comfort and support. It can automatically learn and optimize, adapt to individual differences, improve user experience, ensure comfort, and reduce health problems caused by long-term improper sitting posture.

[0081] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, the maximum lower limit of the sofa cushion that can reflect the user's use status is first collected, and then the ergonomic standard is combined as the constraint of the sofa H point to determine the sofa parameter recommendation model. Under the state of obtaining the maximum lower limit of the sofa cushion, the sofa parameter range that meets the human body's healthy sitting posture and enables the user to reach the H point of sufficient comfort, namely the sofa backrest angle, sofa cushion height, sofa cushion depth and sofa cushion inclination, can be recommended, and a group of sofa parameters are randomly selected to adjust the seat. Afterwards, user feedback is obtained, and the sofa parameters that meet the requirements of the maintenance time are retained to form a training set, and the support vector regression model is trained using the training set. By adaptively adjusting the width of the kernel function, the model can adapt to the characteristics of the data more flexibly, and the introduction of the time weight ensures that the data used for a long time has a greater impact on the model training, thereby more truly reflecting the impact of the use conditions on the performance of the sofa cushion, not only improving the generalization ability of the model, but also making the sofa design more in line with actual use needs. The model can learn the complex and invisible correlation between the maximum sinkage of the sofa cushion and the sofa parameters, improve the prediction accuracy and adaptability of the model, and dig out more reasonable sofa parameters that meet health and comfort requirements, avoiding the user burden caused by self-adjustment during the initial use process. It can also make reasonable recommendations considering the user's health and comfort and deeply dig out more reasonable sofa parameters, thereby improving the user experience and increasing product competitiveness.

[0082] An embodiment of the present invention provides a smart sofa, which is applied to the smart sofa control method based on user habits as described in the method embodiment.

[0083] A computer-readable storage medium provided by the present invention can implement the steps and effects of the smart sofa control method based on user habits of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0084] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, the maximum lower limit of the sofa cushion that can reflect the user's use status is first collected, and then the ergonomic standard is combined as the constraint of the sofa H point to determine the sofa parameter recommendation model. Under the state of obtaining the maximum lower limit of the sofa cushion, the sofa parameter range that meets the healthy sitting posture of the human body and enables the user to reach the H point of sufficient comfort, namely the sofa backrest angle, sofa cushion height, sofa cushion depth and sofa cushion inclination, can be recommended, and a group of sofa parameters are randomly selected to adjust the seat. After that, user feedback is obtained, and the sofa parameters that meet the requirements of the maintenance time are retained to form a training set, and the support vector regression model is trained using the training set. By adaptively adjusting the width of the kernel function, the model can adapt to the characteristics of the data more flexibly, and the introduction of the time weight ensures that the data used for a long time has a greater impact on the model training, thereby more truly reflecting the impact of the use conditions on the performance of the sofa cushion, not only improving the generalization ability of the model, but also making the sofa design more in line with actual use needs. The model can learn the complex and invisible correlation between the maximum sinkage of the sofa cushion and the sofa parameters, improve the prediction accuracy and adaptability of the model, and dig out more reasonable sofa parameters that meet health and comfort requirements, avoiding the user burden caused by self-adjustment during the initial use process. It can also make reasonable recommendations considering the user's health and comfort and deeply dig out more reasonable sofa parameters, thereby improving the user experience and increasing product competitiveness.

[0085] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0086] There are a few points to note: (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0087] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0088] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0089] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A smart sofa control method based on user habits, characterized in that: include: S1: Collect the maximum sinking amount of the sofa cushion when the user is using it; S2: Taking the ergonomic standard as the adjustment constraint condition of the sofa H point, a sofa parameter recommendation model is established with the maximum sinking amount of the sofa cushion as the state vector and the sofa parameters as the control variables, wherein the sofa parameters include the sofa backrest angle, sofa cushion height, sofa cushion depth and sofa cushion inclination; S3: collecting the maximum sinking amount of the sofa cushion whose maintenance time is longer than the preset maintenance time and the corresponding sofa parameters, wherein the collected maximum sinking amount of the sofa cushion and the sofa parameters constitute a training set; S4: combining a radial basis kernel function with an adaptive width adjustment parameter and a weight that is proportional to the maintenance time, using the training set to train a support vector regression model, and obtaining an optimal hyperplane that makes the prediction error less than a preset prediction error, wherein the prediction error is the difference between the predicted sofa parameter and the actual sofa parameter; S5: Collect the maximum sinking amount of the sofa cushion in real time; S6: inputting the real-time maximum sinking amount of the sofa cushion into the trained support vector regression model, and outputting predicted sofa parameters; S7: Controlling the sofa according to the predicted sofa parameters.

2. The method for controlling a smart sofa based on user habits according to claim 1, characterized in that: The sofa parameter recommendation model established by the state variables and the control variables is specifically: in, Indicates the sofa backrest angle, Indicates the height of the sofa cushion. d Indicates the depth of the sofa cushion. Sofa seat cushion tilt, z Indicates the maximum sinking amount of the sofa cushion. They respectively represent the horizontal coordinate, vertical coordinate and vertical coordinate of point H of the sofa in the user's use state in the coordinate system with the midpoint of the rear edge of the sofa cushion as the coordinate origin, wherein the horizontal coordinate is the coordinate of point H of the sofa in the width direction of the seat cushion, the vertical coordinate is the coordinate of point H of the sofa in the depth direction of the seat cushion, and the vertical coordinate is the coordinate of point H of the sofa perpendicular to the plane of the seat cushion.

3. The method for controlling a smart sofa based on user habits according to claim 2, characterized in that: The adjustment constraints of the sofa parameter recommendation model are specifically: in, W Indicates the total width of the sofa cushion. D Indicates the total depth of the sofa cushion. a =3cm represents the height adjustment factor based on ergonomic standards.

4. The method for controlling a smart sofa based on user habits according to claim 1, characterized in that: The S3 specifically includes: S301: Initializing the sofa parameters; S302: collecting the maximum sinking amount of the sofa cushion; S303: inputting the maximum sinking amount of the sofa cushion into the sofa parameter recommendation model, and randomly outputting the recommended sofa parameters that meet the adjustment constraint conditions; S304: Determine whether the maintenance time under the recommended sofa parameter is greater than the preset maintenance time, if so, retain the recommended sofa parameter whose maintenance time is greater than the preset maintenance time and the corresponding maximum sinking amount of the sofa cushion as a data pair, otherwise, return to step S303; S305: Determine whether the number of data pairs is greater than a preset number of data pairs. If so, terminate the iteration and proceed to step S306. Otherwise, return to step S303. S306: Outputting the retained recommended sofa parameters and the corresponding maximum sinking amount of the sofa cushion as a training set.

5. The method for controlling a smart sofa based on user habits according to claim 1, characterized in that: The S4 specifically includes: S401: Mapping the maximum sinking amount of the sofa cushion to a high-dimensional space using a radial basis kernel function with an adaptive width adjustment parameter for linear separation: in, represents the radial basis kernel function value representing the similarity between the maximum sinking amount of the first sofa cushion and the maximum sinking amount of the second sofa cushion, exp represents the exponential function, represents the width adjustment parameter that controls the radial basis kernel function, Indicates the calculation of the square of the Euclidean distance, represents the input data set including the maximum sinkage of all sofa cushions in the training set, n represents the total number of samples in the training set, Indicates the training set i Maximum sinking amount of a sofa seat cushion, α and β Represent local adjustment parameters and global adjustment parameters respectively, represents the mean maximum sinking amount of the sofa cushion in the training set, Indicates the calculation of Euclidean distance, log indicates the logarithmic function, represents the standard deviation of the maximum sinkage of the sofa cushion in the training set, represents a constant that avoids zero denominator; S402: According to the maximum sinking amount of the sofa cushion after high-dimensional mapping and its corresponding sofa parameters, an optimization function for hyperplane parameters is established with the goal of minimizing the prediction error, wherein the hyperplane parameters include a weight vector and a bias vector: in, W represents the weight vector, b represents the bias vector, C represents the penalty parameter, max represents the maximum value, Indicates the training set i The first j The actual sofa parameter values, , n represents the total number of samples in the training set, , , , Respectively represent i The real sofa back angle, real sofa cushion height, real sofa cushion depth and real sofa cushion inclination in the samples. Indicates i The maximum sinking amount of the sofa cushion in the sample corresponds to the j Predicted sofa parameter values, represents the tolerance error, It means taking the function when it takes the minimum value W and b , Indicates the training set i The weight of the samples, Indicates the training set i The duration of the sample, Indicates the maintenance time of the training set samples T The maximum duration of maintenance in S403: Solving the optimization function, and establishing the optimal hyperplane of the support vector regression model based on the hyperplane parameters obtained by the solution: in, Represents input data x That is, the function value of the maximum sinking amount of the sofa cushion.

6. The intelligent sofa control method based on user habits according to claim 5 is characterized in that: The local adjustment parameter and the global adjustment parameter are solved based on the maximum entropy principle, and the solving process specifically includes: The objective function for solving the local adjustment parameter and the global adjustment parameter is determined based on the maximum entropy principle. The objective function is specifically: in, H represents the information entropy of the training set, It represents the local adjustment parameters and global adjustment parameters that maximize the information entropy. Represents the first i The probability density of samples; The partial derivatives of the information entropy with respect to the local adjustment parameter and the global adjustment parameter are calculated respectively to obtain the conversion objective function: in, It means to find partial derivative; The conversion objective function is iteratively solved by Newton's method to obtain the local adjustment parameter and the global adjustment parameter.

7. The method for controlling a smart sofa based on user habits according to claim 5, characterized in that: After S402, the method further includes: S402A: Adjusting the hyperparameters of the support vector regression model by using a gradient descent method with a momentum term, wherein the hyperparameters include the penalty parameter and the tolerance error.

8. The method for controlling a smart sofa based on user habits according to claim 7, characterized in that: The S402A specifically includes: S402A1: Calculate the partial derivatives of the objective function value with respect to the penalty parameter and the tolerance error respectively: in, J represents the objective function value, Indicates the use for judgment The sign function of the difference direction, represents the indicator function, when When the indicator function takes 1, otherwise, the indicator function takes 0; S402A2: The penalty parameter and the tolerance error are updated according to the obtained partial derivatives until the update amplitude of each hyperparameter is less than the preset update amplitude: in, represents the learning rate, Indicates assignment, and Both represent the momentum term of the stored gradient, represents the momentum parameter.

9. The method for controlling a smart sofa based on user habits according to claim 1, characterized in that: After S7, the method further includes: The support vector regression model is retrained at preset time intervals.

10. A smart sofa, characterized in that: Applicable to the smart sofa control method based on user habits as described in any one of claims 1 to 9.

Images