Data-driven massage bed function self-adaptive adjustment method

Abstract

The invention relates to the technical field of data processing, and provides a data-driven massage bed function adaptive adjustment method. The method comprises the following steps: extracting a first massage mode of the massage bed; acquiring a first experience feedback record of the user in the mode, wherein the first experience feedback record comprises first physiological feedback information and subjective feedback information; matching first physiological index data of the massage head data in the first physiological feedback information; performing correlation analysis on the massage head data and the physiological data to obtain a correlation coefficient, and combining subjective feedback information calibration to obtain fitness; judging whether the fitness is in a preset threshold or not; if yes, the massage head data are added to the self-adaptive list, and a self-adaptive massage mode is generated. The technical problem that a massage bed is difficult to provide personalized massage experience according to individual differences of users is solved, and the technical effect of dynamically adjusting the massage mode according to physiological feedback and subjective feedback information of the users to improve the comfort and satisfaction of the users is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a data-driven adaptive adjustment method for massage bed functions. Background Art

[0002] With the improvement of people's living standards and the enhancement of health awareness, massage equipment, especially smart massage beds, have gradually become popular among users. Traditional massage beds usually have a variety of massage modes, which can achieve massages with different techniques such as kneading, tapping, and massage to meet the basic comfort needs of users. However, current massage beds mainly rely on preset fixed modes and lack the ability to adaptively adjust to the individual differences of different users, resulting in the inability to provide the best personalized experience. For users of different physiques, ages, and health conditions, a single massage mode is often difficult to fully meet their actual needs, and may even cause discomfort or physical burden. Therefore, due to the lack of full consideration of individual differences among users, it is difficult to effectively switch and optimize between different modes, which makes the existing massage beds have obvious deficiencies in personalization and comfort, and it is difficult for the user experience to reach an ideal state. Summary of the invention

[0003] The present application provides a data-driven adaptive adjustment method for massage bed functions, aiming to solve the technical problem that massage beds are difficult to provide personalized massage experiences based on individual differences among users.

[0004] In view of the above problems, the present application provides a data-driven massage bed function adaptive adjustment method.

[0005] The present application provides a data-driven method for adaptively adjusting the functions of a massage bed, the method comprising: extracting a first massage mode from a plurality of massage modes of the massage bed; obtaining a first experience feedback record of a user in the first massage mode, the first experience feedback record comprising first physiological feedback information and first subjective feedback information; matching first physiological data of a first physiological indicator under first massage head data in the first physiological feedback information, the first massage head data referring to preset data of the first massage head under the first massage mode; performing a correlation analysis on the first massage head data and the first physiological data to obtain a first correlation coefficient, and calibrating the first correlation coefficient in combination with the first subjective feedback information to obtain a first correlation fitness; determining whether the first correlation fitness is within a predetermined fitness threshold; if so, adding the first massage head data to an adaptive list, and generating an adaptive massage mode for the user to use the massage bed according to the adaptive list.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The above data-driven adaptive adjustment method for massage bed functions first selects a mode from a plurality of massage modes of the massage bed as the first massage mode, and records the user's experience feedback information in this mode, including the user's physiological feedback and subjective feedback. In the collected physiological feedback, the preset parameters of the massage head in this mode are matched with the feedback data of the user's physiological indicators, and this matching ensures that the correlation analysis of the data is targeted. Subsequently, the preset parameters of the massage head and the user's physiological data are correlated, and the correlation coefficient between the two is calculated. The correlation coefficient is calibrated in combination with the user's subjective feedback to generate a correlation fitness, thereby reflecting the fitness of the massage mode with the user's needs. This process not only makes the analysis more accurate, but also more in line with the user's individual needs. Afterwards, it is evaluated whether the correlation fitness reaches the preset adaptation threshold to determine whether the current massage parameters are appropriate. If the adaptation threshold is reached, the massage head parameters are recorded in the adaptive list. Finally, a personalized massage mode is generated according to the adaptive list. In this way, the massage bed can automatically adjust to the massage mode that best suits the user's needs in future use, making the massage experience more personalized and comfortable.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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.

[0009] Figure 1 It is a flowchart of a data-driven massage bed function adaptive adjustment method in one embodiment; Figure 2 The figure is a flow chart of obtaining the first relevant fitness of a data-driven massage bed function adaptive adjustment method in one embodiment. DETAILED DESCRIPTION

[0010] The embodiment of the present application solves the technical problem that it is difficult for a massage bed to provide a personalized massage experience based on individual differences of users by providing a data-driven method for adaptively adjusting the functions of the massage bed.

[0011] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0012] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0013] Examples, such as Figure 1 As shown, the present application provides a data-driven massage bed function adaptive adjustment method, the method comprising: A first massage mode among a plurality of massage modes of the massage bed is extracted.

[0014] In the embodiment of the present application, the system terminal selects one of the multiple massage modes preset on the massage bed as the first massage mode. The massage bed usually has multiple modes, each of which includes different massage parts, techniques, intensities and rhythms, aiming to meet different massage needs of users.

[0015] A first experience feedback record of the user in the first massage mode is obtained, where the first experience feedback record includes first physiological feedback information and first subjective feedback information.

[0016] In one embodiment, during the user's experience of the first massage mode, the system terminal will record the user's feedback information, which is divided into physiological feedback information and subjective feedback information. Physiological feedback information includes the objective physiological reactions of the user's body during the massage, such as heart rate, muscle tension, skin temperature, etc., which can be monitored and recorded in real time through sensors. Subjective feedback information is the user's personal evaluation of the massage experience, such as whether the user feels the massage is comfortable, whether the strength is appropriate, etc. These are usually collected through active user input or feedback through an intelligent interface. The purpose of collecting these two types of feedback information is to have a more comprehensive understanding of the user's experience in the current massage mode, thereby providing a basis for subsequent personalized adjustments.

[0017] The first physiological data of the first physiological indicator under the first massage head data is matched in the first physiological feedback information, and the first massage head data refers to the preset data of the first massage head under the first massage mode.

[0018] In one embodiment, after obtaining the user's physiological feedback information, the system terminal searches for physiological indicator data related to the currently used massage head from the first physiological feedback information. Specifically, the massage head in the first massage mode has some preset data parameters, namely the first massage head data, including but not limited to strength, position, angle, frequency, etc. The system terminal will search for corresponding physiological indicator data in the user's physiological feedback by matching benchmark constraints set according to the first massage head data, such as muscle reaction, blood flow changes, local temperature, etc. at the contact part with the massage head. Subsequently, the physiological data of these users are matched with the preset parameters of the massage head. This matching is to confirm the specific physiological response of the user under the current massage head setting, thereby providing a basis for subsequent correlation analysis and mode optimization.

[0019] Further, matching the first physiological data of the first physiological index under the first massage head data in the first physiological feedback information includes: Acquire a set of massage heads of the massage bed, the set of massage heads including a plurality of massage heads with body part identifications; extract any massage head from the plurality of massage heads with body part identifications, the arbitrary massage head corresponding to any body part; form an arbitrary set of physiological indicators for the arbitrary body part; establish an arbitrary mapping relationship between the arbitrary massage head and the arbitrary set of physiological indicators, and use the arbitrary mapping relationship as a matching reference constraint for matching the first physiological indicator under the first massage head data in the first physiological feedback information.

[0020] Preferably, the system terminal obtains a set of all massage heads on the massage bed. Each massage head has an identifier corresponding to a body part, such as shoulders, waist, legs, etc., so that the system terminal knows which body area each massage head corresponds to. Subsequently, a massage head is randomly extracted from these massage heads marked with body parts for analysis, and this massage head corresponds to a specific body part, such as shoulders, back, etc. The purpose of this step is to focus on a specific massage head so as to more accurately monitor the physiological response of a specific part. Afterwards, a physiological indicator set is formed for this body part, that is, multiple physiological parameters of the part, such as muscle tension, blood flow, skin temperature, etc. This set includes possible physiological response indicators of the part, laying the foundation for subsequent analysis. Then, the system terminal establishes a mapping relationship between the massage head and the physiological indicator set. This mapping relationship enables the system terminal to find user physiological response data that matches the massage head data (such as strength, position, etc.) in the first physiological feedback information. These mapping relationships become the benchmark constraints for subsequent matching of physiological feedback, ensuring that accurate physiological data related to the massage head operation can be found during analysis. The purpose of this process is to establish a matching framework of physiological indicators for different massage heads and body parts, thereby providing a scientific data basis for subsequent personalized adjustments.

[0021] A correlation analysis is performed on the first massage head data and the first physiological data to obtain a first correlation coefficient, and the first correlation coefficient is calibrated in combination with the first subjective feedback information to obtain a first correlation fitness.

[0022] In one embodiment, the system terminal formats the first massage head data and the first physiological data, including time alignment, noise filtering, etc. Ensure that the data stream of the massage head and the user's physiological data stream have the same time reference, and eliminate interference factors. Then, the first massage head data and the first physiological data are standardized by the extreme difference standardization method, so that data of different dimensions have the same dimension, which is convenient for correlation analysis. Subsequently, according to the established mapping relationship between the set of physiological indicators and the massage head, the first massage head data is associated with the corresponding first physiological data, and then the associated first massage head data is used as the independent variable, and the first physiological data is used as the dependent variable to input into the correlation calculation formula for correlation calculation. The correlation calculation formula is as follows: ; Where r is the first correlation coefficient, and its value range is [−1,1]. When r>0, it means that there is a positive correlation between the first massage head data and the first physiological data, and the first massage parameter has a positive effect on physiological feedback. When r<0, it means that there is a negative correlation between the two, and the first massage parameter may have an adverse effect on physiological feedback. When r=0, it means that there is no correlation between the two. is the i-th parameter of the first massage parameter. is the i-th parameter of the first physiological data. and are the means of the first massage head data and the first physiological data, respectively. Through this correlation calculation formula, the system terminal calculates the first correlation coefficient between the first massage head data and the first physiological data. This first correlation coefficient reflects the degree of association between the first massage head parameters and the user's physiological response, that is, whether the setting of the massage head can effectively cause the expected physiological effect. After obtaining the first correlation coefficient, the system terminal will calibrate the correlation coefficient in combination with the user's subjective feedback information. The purpose of calibration is to incorporate the user's subjective feelings into the overall evaluation, because even if the physiological response is good, if the user's subjective feeling is not good, the massage mode needs to be adjusted. Through correlation analysis and subjective feedback calibration, a relevant fitness is finally obtained. This fitness combines the user's physiological and subjective responses, and can more comprehensively evaluate whether the current massage head parameters are suitable for user needs. The whole process ensures the scientificity and personalization of the massage mode adjustment, so that the massage bed can not only provide effective massage effects based on objective data, but also optimize the experience based on the user's subjective feelings.

[0023] Further, if Figure 2As shown, a first correlation coefficient is obtained by performing a correlation analysis on the first massage head data and the first physiological data, and the first correlation coefficient is calibrated in combination with the first subjective feedback information to obtain a first correlation fitness, including: Matching a first body part corresponding to the first massage head; screening first subjective comfort data corresponding to the first body part in the first subjective feedback information; calibrating the first correlation coefficient based on the first subjective comfort data to obtain the first correlation fitness.

[0024] Optionally, according to the body part identification configuration of the first massage head on the massage bed, the system terminal determines the specific position of the first massage head, that is, the corresponding first body part. For example, the first massage head may be located at the user's shoulder, waist or leg. This matching is completed through the hardware configuration or sensor information of the massage bed to ensure that the physical position of the first massage head and the identification of the body part correspond one by one. When the physical position of the first massage head and the identification of the body part are the same, the system terminal extracts data related to the body part from the user's first subjective feedback information, for example, the user's rating of the comfort of the shoulder in the feedback interface. The system terminal will filter out the first subjective comfort data related only to the first body part (such as the shoulder), and ignore information unrelated to other parts. Subsequently, the filtered first subjective comfort data of the first body part is combined with the calculated first correlation coefficient for calibration processing, that is, the first correlation coefficient is directly multiplied by the first subjective comfort data. After the calibration of the first correlation coefficient is completed, the system terminal outputs the calibrated first correlation coefficient as the first correlation fitness. The first correlation fitness combines the user's physiological data and subjective feedback information, and is a comprehensive evaluation of the adaptability of the massage mode. The result is used to determine whether the current massage parameters meet user needs and serves as the basis for subsequent optimization and adjustment.

[0025] Determine whether the first related fitness is within a predetermined fitness threshold; if so, add the first massage head data to an adaptive list, and generate an adaptive massage mode for the user to use the massage bed according to the adaptive list.

[0026] In one embodiment, the system terminal compares the calculated first relevant fitness with a predetermined fitness threshold, which is used to evaluate whether the current massage mode meets the user's needs, such as 0.6. If the first relevant fitness is less than the predetermined fitness threshold, it means that the current massage head parameters are insufficient to meet the user's needs and the massage mode needs to be switched. On the contrary, it means that the current massage head data and user feedback have a high degree of match and are suitable for the current user. At this time, the system terminal records the parameters of the first massage head (such as strength, frequency, position, etc.) into the adaptive list. The adaptive list is a dynamically updated data structure that stores the massage head parameters that the current user has a good experience with. The newly added data includes the massage head parameters and the associated fitness information, which are used to generate personalized massage modes later. The system terminal will filter and combine all the massage head data in the adaptive list, extract the parameters with the highest fitness, and generate a set of adaptive massage modes for the user. For example, the shoulder may use parameters with greater strength, while the waist may choose a mode with a faster frequency. In the above manner, it can be ensured that the massage bed can be dynamically adjusted according to the user's physiological and subjective feedback to improve the user's overall massage experience.

[0027] Further, the first massage head data is added to the adaptive list, which also includes: Obtain user information of the user; perform traversal analysis on the user information according to the read predetermined user indicators to obtain user indicator data; obtain a user feedback coefficient by weighted normalization of the user indicator data; adjust the first massage head data according to the user feedback coefficient; wherein the predetermined user indicators include at least age, gender, weight, height, occupation, and health status.

[0028] Preferably, the system terminal collects user information through a preset interactive method or sensor device. Including but not limited to basic information, health-related information, etc. Data can be obtained through user registration input, health device connection (such as wearable devices) or medical report upload. Subsequently, the predetermined user index is read, and the predetermined user index includes age, gender, weight, height, occupation and health status. The system terminal analyzes each index in the user information separately, extracts data that meets the predetermined user index, and forms user index data. After that, the data of each index is normalized to a standard range (such as 0 to 1). For numerical variables such as age and weight, normalization can be performed by the range standardization method. Taking age as an example, the difference between the current age and the minimum age can be calculated by the ratio of the difference between the maximum age and the minimum age. For categorical variables such as occupation and gender, normalization can be performed by combining Label Encoding and range standardization. Taking occupation as an example, the occupation is directly mapped to an integer value, such as 0 for sedentary offices, 1 for standing occupations, and 2 for manual laborers, and then the categorical values ​​are normalized by the range standardization method. Then, weights are assigned to different indicators, which are set based on professional experience in the fields of medicine, massage therapy, etc. A weighted calculation is then performed based on the weights and normalized values ​​to obtain the user feedback coefficient. After obtaining the user feedback coefficient, the calculated user feedback coefficient is used to adjust the parameters of the first massage head (such as strength, frequency, position, etc.). The adjustment method is to directly multiply the parameters of the first massage head by the user feedback coefficient. By obtaining user information, analyzing predetermined indicators, calculating feedback coefficients, and adjusting massage head parameters, the system terminal achieves optimization adjustments based on the personalized needs of users. This method can provide a more scientific and accurate massage mode based on personalized information such as the user's age and health status, thereby improving the user's comfort and satisfaction.

[0029] Further, determining whether the first related fitness is within a predetermined fitness threshold, then comprising: If not, extract a second massage mode from the multiple massage modes; analyze the user's second experience feedback record in the second massage mode to obtain a second relevant fitness of the second massage head data, wherein the second massage head data refers to the preset data of the first massage head in the second massage mode; determine whether the second relevant fitness is within the predetermined fitness threshold; if so, add the second massage head data to the adaptive list.

[0030] Preferably, if the first relevant fitness is not within the threshold value, that is, the first relevant fitness is less than the predetermined fitness threshold, the system terminal will consider that the current massage mode cannot effectively meet the user's needs and needs to be switched to another massage mode. At this time, the system terminal extracts a different massage mode from the first massage mode as the second massage mode from the multiple massage modes. After determining the second massage mode, the system terminal performs the same process as above, including obtaining the second experience feedback record under the second massage mode, matching the second physiological feedback information in the second experience feedback record with the second physiological data, and calculating the second relevant fitness of the second massage head data based on the second subjective feedback information and the second physiological data in the second experience feedback record. Among them, the second massage head data refers to the preset mode parameters of the first massage head under the second massage mode, such as strength, frequency, position, etc. Subsequently, the second relevant fitness is compared with the predetermined fitness threshold. If it is still not within the threshold range, the system terminal further switches to other massage modes. On the contrary, it means that the second massage mode is suitable for the user's needs. At this time, the data of the second massage head (such as strength, frequency, position, etc.) is recorded in the adaptive list as a basis for generating an adaptive massage mode.

[0031] Further, the present application provides generating an adaptive massage mode for the user to use the massage bed according to the adaptive list, and then further includes: Matching a target massage head set corresponding to a target body part in the massage head set; matching target adaptive data of the target massage head set in the adaptive massage mode; acquiring an adaptive massage log, wherein the adaptive massage log refers to massage record information of the user in the adaptive massage mode; extracting target subjective comfort data of the target body part in the adaptive massage log; constructing a target training data set based on the target adaptive data and the target subjective comfort data; performing machine learning test on the target training data set to obtain a target comfort prediction model; and optimizing the massage of the target body part according to the target comfort prediction model to obtain a target optimal massage plan for the target body part.

[0032] Optionally, the system terminal selects massage heads acting on the target body part from the massage head set to form a target massage head set. Then, the parameters corresponding to the target massage head set are extracted from the adaptive massage mode as target adaptive data. For example, the data of the target massage head set (shoulder) include force (20N), frequency (5Hz), and position (left shoulder area). These data will be used for subsequent training and optimization. The adaptive massage log is also selected from the massage log. This adaptive massage log refers to the detailed data of each massage recorded when the user uses the adaptive massage mode. The system terminal extracts the subjective comfort data related to the target body part from the adaptive massage log as the target subjective comfort data, which will be used as the label value (target variable) for subsequent model training. Subsequently, the target adaptive data is used as the input feature and the target subjective comfort data is used as the target variable to form a target training data set, and then the target training data set is used for machine learning verification. Specifically, the system terminal trains the target training data set through a multi-layer perceptron (MLP) neural network. The target adaptive data is used as an input feature, enters the neural network through the input layer, and propagates to the hidden layer and the output layer layer by layer. The hidden layer uses the ReLU activation function to enhance the nonlinear mapping capability, and the output layer generates predicted comfort data in the form of a single node. After each forward propagation, the difference between the predicted value and the target subjective comfort data is calculated, and the mean square error (MSE) is used as the loss function to quantify the difference. After calculating the loss, the weights and biases of the network are adjusted by the back-propagation algorithm, and the parameters are updated using the Adam optimizer to minimize the loss. During the training process, the system terminal will perform multiple rounds of iterations based on the training set data, and use the validation set data to monitor the generalization performance of the model. By recording the validation loss of each round, it is ensured that the model does not overfit. After the training is completed, the round with the lowest validation loss is selected as the final target comfort prediction model. After the model training is completed, the system terminal will randomly generate several massage parameter combinations and input them into the prediction model, calculate the predicted comfort data of these combinations, and select the parameter combination with the highest predicted comfort data as the target optimal massage plan for the target body part. Finally, this target optimal massage plan is updated to the adaptive massage mode to ensure that users can get a more accurate and comfortable massage experience in subsequent use.

[0033] Furthermore, the present application optimizes the massage of the target body part according to the target comfort prediction model to obtain the target optimal massage plan for the target body part, and then further includes: Randomly generate first test data of the target massage head set; use the first test data as input information of the target comfort prediction model to obtain a model output result, wherein the model output result includes first predicted comfort data; when the first predicted comfort data is greater than the target subjective comfort data, replace the target adaptive data with the first test data as the target optimal massage plan; update the target optimal massage plan to the adaptive massage mode.

[0034] Optionally, the system terminal randomly generates several groups of test data as the first test data according to the parameter range of the target massage head set. Each group of test data includes parameter values ​​such as the strength, frequency, and position of the target massage head. The generation of these test data will be based on a predetermined parameter range and distribution. For example, the strength range is 10N to 30N, the frequency range is 4Hz to 8Hz, and the position is optional parts such as shoulders and waist. The system terminal will generate test data in a uniform distribution or normal distribution manner to ensure that possible parameter combinations are covered. The generated first test data will be input into the target comfort prediction model one by one for evaluation. The model will output the predicted comfort data corresponding to each group of test data as the first predicted comfort data based on the relationship between the massage parameters and the comfort score learned during the training process. The system terminal compares the first predicted comfort data with the target subjective comfort data provided by the user in the adaptive massage log. When a group of first predicted comfort data is higher than the target subjective comfort data, the system terminal determines that this group of test data is more suitable for user needs than the current target adaptive data. For example, the target subjective comfort data is 85%, and the predicted comfort data of a group of test data is 92%. At this time, the test data will be selected to replace the current target adaptive data. The first selected test data will be regarded as the target optimal massage plan for the target body part. The system terminal updates this target optimal plan to the adaptive massage mode and records the relevant parameters for the user to use in subsequent massages. The updated adaptive massage mode can more accurately meet the user's personalized needs, thereby improving the overall massage experience.

[0035] Furthermore, the present application provides iterative prediction until a predetermined threshold of iteration times is reached, and outputs the target optimal massage plan.

[0036] Optionally, after the system terminal generates the first test data of the target massage head set and evaluates it through the target comfort prediction model, it will start the iterative optimization process. In each iteration, the range or parameter distribution of the test data will be adjusted according to the prediction results of the previous round to generate new test data. The newly generated test data will be input into the target comfort prediction model again to calculate the corresponding predicted comfort data. In each round of iteration, the system terminal will compare the predicted comfort data of the new test data with the highest comfort data currently recorded. If the predicted comfort score of the new test data is higher, it will be replaced with the current target optimal massage plan, and the corresponding strength, frequency and position parameters will be recorded. At the same time, the strategy for generating test data will be dynamically adjusted so that subsequent test data are more concentrated in the parameter range with high scores, thereby speeding up the optimization speed. This process will continue until the preset iteration number threshold is reached. For example, the number of iterations set by the system terminal is 100 rounds. After reaching 100 rounds, regardless of whether the comfort score continues to be improved, the massage parameters corresponding to the highest score currently recorded will be output as the final target optimal massage plan. The final output of the optimal massage plan will be updated to the adaptive massage mode to ensure that users can enjoy a more accurate and optimized massage experience in subsequent use. Through iterative optimization, the parameter space can be fully explored to improve the reliability and personalized adaptability of the optimal plan.

[0037] In summary, the embodiments of the present application have at least the following technical effects: The embodiment of the present application extracts the initial massage mode from the multiple massage modes of the massage bed and obtains the user's physiological feedback and subjective feedback information, establishes a matching relationship between the massage head data and the physiological index, performs a correlation analysis on the two, and generates relevant fitness in combination with subjective feedback calibration. When the fitness meets the predetermined threshold, the massage head data is added to the adaptive list, and the user's adaptive massage mode is generated according to the list; if it does not meet the threshold, it switches to other massage modes to reanalyze the fitness. Further, by constructing a mapping relationship between the massage head and the physiological index, the data related to the target body part is screened, the target comfort prediction model is generated using a machine learning method, and the optimal massage plan for the target body part is achieved through iterative optimization. Finally, the optimal plan is updated to the adaptive massage mode to provide users with a highly personalized massage experience. These technical effects jointly solve the technical problem that the massage bed is difficult to provide a personalized massage experience according to the individual differences of users, and realize the technical effect of dynamically adjusting the massage mode to improve the user's comfort and satisfaction according to the user's physiological feedback and subjective feedback information.

[0038] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0039] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0040] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A data-driven adaptive adjustment method for massage bed functions, characterized in that: include: Extracting a first massage mode from among a plurality of massage modes of the massage bed; Acquire a first experience feedback record of the user in the first massage mode, where the first experience feedback record includes first physiological feedback information and first subjective feedback information; Matching the first physiological data of the first physiological indicator under the first massage head data in the first physiological feedback information, wherein the first massage head data refers to the preset data of the first massage head under the first massage mode; Performing a correlation analysis on the first massage head data and the first physiological data to obtain a first correlation coefficient, and calibrating the first correlation coefficient in combination with the first subjective feedback information to obtain a first correlation fitness; Determining whether the first related fitness is within a predetermined fitness threshold; If yes, the first massage head data is added to an adaptive list, and an adaptive massage mode for the user to use the massage bed is generated according to the adaptive list.

2. The data-driven adaptive adjustment method for massage bed functions according to claim 1, characterized in that: Matching the first physiological data of the first physiological indicator under the first massage head data in the first physiological feedback information includes: Acquire a set of massage heads of the massage bed, wherein the set of massage heads includes a plurality of massage heads with marks of body parts; Extracting any massage head from the plurality of massage heads having identifications of body parts, wherein the any massage head corresponds to any body part; Establishing any set of physiological indicators of any body part; An arbitrary mapping relationship between the arbitrary massage head and the arbitrary set of physiological indicators is established, and the arbitrary mapping relationship is used as a matching reference constraint for matching the first physiological indicator under the first massage head data in the first physiological feedback information.

3. The data-driven adaptive adjustment method for massage bed functions according to claim 2, characterized in that: Performing a correlation analysis on the first massage head data and the first physiological data to obtain a first correlation coefficient, and calibrating the first correlation coefficient in combination with the first subjective feedback information to obtain a first correlation fitness, including: Matching the first body part corresponding to the first massage head; screening first subjective comfort data corresponding to the first body part from the first subjective feedback information; The first correlation coefficient is calibrated based on the first subjective comfort data to obtain the first correlation fitness.

4. The data-driven adaptive adjustment method for massage bed functions according to claim 1, characterized in that: Add the first massage head data to the adaptive list, which also includes: Obtaining user information of the user; The user information is traversed and analyzed according to the read predetermined user indicators to obtain user indicator data; The user index data after weighted normalization processing obtains the user feedback coefficient; Adjusting the first massage head data according to the user feedback coefficient; The predetermined user indicators include at least age, gender, weight, height, occupation, and health status.

5. The data-driven adaptive adjustment method for massage bed functions according to claim 1, characterized in that: Determining whether the first related fitness is within a predetermined fitness threshold, and then further comprising: If not, extracting a second massage mode from the plurality of massage modes; Analyzing a second experience feedback record of the user in the second massage mode to obtain a second relevant fitness of second massage head data, wherein the second massage head data refers to preset data of the first massage head in the second massage mode; Determining whether the second related fitness is within the predetermined fitness threshold; If yes, add the second massage head data to the adaptive list.

6. The data-driven adaptive adjustment method for massage bed functions according to claim 2, characterized in that: The method further comprises: generating an adaptive massage mode for the user to use the massage bed according to the adaptive list; and then: Matching a target massage head set corresponding to a target body part in the massage head set; matching the target adaptive data of the target massage head set in the adaptive massage mode; Acquire an adaptive massage log, wherein the adaptive massage log refers to massage record information of the user in the adaptive massage mode; extracting target subjective comfort data of the target body part in the adaptive massage log; Building a target training data set based on the target adaptive data and the target subjective comfort data; Performing machine learning test on the target training data set to obtain a target comfort prediction model; Massage optimization is performed on the target body part according to the target comfort prediction model to obtain a target optimal massage plan for the target body part.

7. The data-driven adaptive adjustment method for massage bed functions according to claim 6, characterized in that: Massage optimization is performed on the target body part according to the target comfort prediction model to obtain a target optimal massage plan for the target body part, and then the method further includes: Randomly generating first test data of the target massage head set; Using the first test data as input information of the target comfort prediction model to obtain a model output result, wherein the model output result includes first predicted comfort data; When the first predicted comfort data is greater than the target subjective comfort data, the target adaptive data is replaced by the first test data as the target optimal massage plan; The target optimal massage program is updated to the adaptive massage mode.

8. The data-driven adaptive adjustment method for massage bed functions according to claim 7, characterized in that: Iterate the prediction until a predetermined threshold of iteration times is reached, and output the target optimal massage plan.

Images