Method for establishing intelligent adjustment model of male massager based on biofeedback monitoring

Abstract

The application discloses a male massager intelligent adjustment model establishment method based on biological feedback monitoring, relates to the male massager adjustment technical field, and comprises the following steps: installing a multi-modal sensor in the massager; real-time monitoring of the biological feedback of a user is carried out to obtain feedback data; feedback features of different feedback data are extracted; the feedback features of a test personnel are extracted as test features, and the adjustment expectation of the test personnel on the adjustment parameter is recorded; the adjustment correlation between different feedback features and the adjustment parameter is analyzed based on the test features and the adjustment expectation; and the adjustment parameter of the massager is intelligently adjusted based on the feedback features and the adjustment correlation; the application is used for solving the problem that the existing male massager adjustment technology is not intelligent enough in the adjustment of the massage parameter, the user needs to frequently set the massager, and the use experience of the user is reduced.

Description

Technical Field

[0001] This invention relates to the field of male massager adjustment technology, specifically a method for establishing an intelligent adjustment model for male massagers based on biofeedback monitoring. Background Technology

[0002] Male massager adjustment technology refers to a type of technology system that dynamically adjusts, programs, or intelligently controls the working parameters (such as massage frequency, intensity, rhythm, and mode) of male massager devices to achieve better personalized experience, safety, comfort, and effect control.

[0003] Existing male massager adjustment technology typically uses fixed parameter combinations to create different preset modes, which users then select or adjust themselves. This lacks intelligence and requires frequent user adjustments, making the process cumbersome and impacting the user's immersive experience, thus reducing the massager's comfort. Furthermore, current male massager adjustment technology suffers from insufficiently intelligent parameter adjustments and the need for frequent user intervention, further diminishing the user experience. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art. By installing a multimodal sensor within a massager, and then using this sensor to monitor the user's biofeedback in real time, feedback data is obtained. An intelligent adjustment model for regulating parameters is constructed, and feature extraction is performed on the feedback data to obtain feedback features for different feedback data. Simultaneously, a first number of testers are selected to test the massager, and their feedback features are extracted as test features. The testers' expectations for adjusting the parameters are recorded. These test features and expectations are then entered into the intelligent adjustment model, and values ​​are assigned to the expectations. The correlation effectiveness is analyzed based on the assigned test features and expectations. Based on the correlation effectiveness, the test features and expectations are grouped to obtain correlation groups, and analysis is performed on these correlation groups to obtain the regulatory correlation. Finally, biofeedback is monitored and feedback features are extracted every first adjustment cycle. Based on these feedback features and the regulatory correlation, the massager's adjustment parameters are intelligently adjusted. This addresses the problem that existing male massager adjustment technologies lack intelligent adjustment of massage parameters and require frequent user adjustments, thus reducing the user experience.

[0005] To achieve the above objectives, in a first aspect, this application provides a method for establishing an intelligent adjustment model for male massagers based on biofeedback monitoring, comprising the following steps:

[0006] Install multimodal sensors inside the massager;

[0007] The user's biofeedback is monitored in real time using multimodal sensors to obtain feedback data;

[0008] Construct an intelligent adjustment model for adjustment parameters, extract features from feedback data, and obtain feedback features for different feedback data;

[0009] The first number of testers were selected to test the massager, and the feedback characteristics of the testers were extracted as test characteristics. The testers' expectations for adjusting the adjustment parameters were also recorded.

[0010] The test features and adjustment expectations are entered into the intelligent adjustment model of the adjustment parameters, and the adjustment correlation between different feedback features and adjustment parameters is analyzed based on the test features and adjustment expectations.

[0011] The biofeedback is monitored and feedback features are extracted every first regulation cycle. Based on the feedback features and regulatory correlation, the regulation parameters of the massager are intelligently adjusted.

[0012] Furthermore, installing a multimodal sensor within the massager includes the following sub-steps:

[0013] The multimodal sensor includes a PPG photoplethysmography (PPG) sensor, an electrode patch sensor, a surface electromyography (SEM) sensor, and a thermal sensor.

[0014] The PPG photoplethysmography sensor and electrode patch sensor are located on the grip area of ​​the massager to monitor the user's palm.

[0015] Both the surface electromyography sensor and the thermal sensor are located inside the massager and are used to monitor the contact area.

[0016] Furthermore, real-time monitoring of the user's biofeedback using multimodal sensors yields feedback data through the following sub-steps:

[0017] The PPG photoplethysmography (PPG) sensor, electrode patch sensor, surface electromyography (EMG) sensor, and thermistor are used to monitor the user's heart rate, skin conductance, EMG of the contact area, and skin temperature of the contact area, respectively.

[0018] The heart rate, skin conductance, electromyography, and skin temperature are the feedback data.

[0019] Furthermore, an intelligent adjustment model for the adjustment parameters is constructed, and feature extraction is performed on the feedback data. The extraction of feedback features for different feedback data includes the following sub-steps:

[0020] A smart adjustment model for adjustment parameters is constructed, and feedback data is input into the smart adjustment model for adjustment parameters. The smart adjustment model for adjustment parameters is equipped with HRV algorithm, GSR rate of change algorithm, EMG activation amplitude algorithm and temperature change trend algorithm.

[0021] The HRV index is obtained by analyzing heart rate using the HRV algorithm.

[0022] The skin conductance response was analyzed using the GSR change rate algorithm to obtain the GRS change rate;

[0023] Electromyography was analyzed using an EMG activation amplitude algorithm to obtain the EMG activation amplitude.

[0024] Skin temperature is analyzed using a temperature change trend algorithm to obtain the slope of temperature change;

[0025] The HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope are collectively referred to as feedback characteristics.

[0026] Furthermore, a first number of testers are selected to test the massager, and the testers' feedback characteristics are extracted as test characteristics. The testers' expectations for adjusting the parameters are also recorded, including the following sub-steps:

[0027] The first number of testers were selected to test the massager;

[0028] During the test, the massager used a preset massage program to massage the tester for the first test duration.

[0029] Record the feedback characteristics of the testers last monitored before the end of the test, and name them as test characteristics;

[0030] The adjustment parameters include massage amplitude, massage frequency, massage rhythm, and cycle period;

[0031] After the test, record the testers' expectations for adjusting the parameters, including the expected amplitude, frequency, rhythm, and period.

[0032] Furthermore, the test features and adjustment expectations are input into the intelligent adjustment model of the adjustment parameters. Based on the test features and adjustment expectations, the adjustment correlation between different feedback features and adjustment parameters is analyzed, including the following sub-steps:

[0033] The test features and adjustment expectations are entered into the intelligent adjustment model of adjustment parameters, and values ​​are assigned to the adjustment expectations;

[0034] Analysis of correlation effectiveness based on post-assignment test features and adjustment expectations;

[0035] Based on the correlation validity, the test features and the moderation expectation are grouped to obtain the correlation group, and the moderation correlation is obtained by analysis based on the correlation group.

[0036] Furthermore, inputting the test features and adjustment expectations into the intelligent adjustment model of adjustment parameters, and assigning values ​​to the adjustment expectations, includes the following sub-steps:

[0037] Input the test features and adjustment expectations into the intelligent adjustment model of adjustment parameters;

[0038] Assign a value to the desired amplitude. If the tester wants to increase the massage amplitude by N1 levels, the desired amplitude is assigned the value +N1. If the tester wants to decrease the massage amplitude by N1 levels, the desired amplitude is assigned the value -N1. If the tester wants to maintain the current massage amplitude level, the desired amplitude is assigned the value 0.

[0039] Assign a value to the desired frequency. If the tester wants to increase the massage frequency by N2 levels, the desired frequency is assigned the value of +N2. If the tester wants to decrease the massage frequency by N2 levels, the desired frequency is assigned the value of -N2. If the tester wants to maintain the current massage frequency level, the desired frequency is assigned the value of 0.

[0040] Assign a value to the desired rhythm. If the tester wants to increase the massage level by N3 levels, the desired rhythm is assigned the value +N3. If the tester wants to decrease the massage level by N3 levels, the desired rhythm is assigned the value -N3. If the tester wants to maintain the current massage level, the desired rhythm is assigned the value 0.

[0041] Assign a value to the desired cycle. If the tester wants to increase the massage level by N4 cycles, the desired cycle is assigned the value of +N4. If the tester wants to decrease the massage level by N4 cycles, the desired cycle is assigned the value of -N4. If the tester wants to maintain the current massage level, the desired cycle is assigned the value of 0.

[0042] Furthermore, the analysis of correlation effectiveness based on the assigned test features and adjusted expectations includes the following sub-steps:

[0043] Using the expected adjustment as the Y-axis, and the HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope as the X-axis, a two-dimensional coordinate system was constructed. These systems were named the Heart Rate Correlation Chart, Electroreaction Correlation Chart, Electromyography Correlation Chart, and Temperature Correlation Chart, respectively. The expected adjustment was then entered into the corresponding two-dimensional coordinate system according to the test characteristics.

[0044] The coordinate points corresponding to the expected amplitude, expected frequency, expected rhythm, and expected period are named amplitude coordinates, frequency coordinates, rhythm coordinates, and period coordinates, respectively. Multinomial regression is performed on the amplitude coordinates, frequency coordinates, rhythm coordinates, and period coordinates in the heart rate correlation diagram, electroreaction correlation diagram, electromyography correlation diagram, and temperature correlation diagram to obtain amplitude correlation curves, frequency correlation curves, rhythm correlation curves, and period correlation curves, which are collectively referred to as correlation curves.

[0045] Obtain the fitting metric, Ri, for the amplitude correlation curve, frequency correlation curve, rhythm correlation curve, and period correlation curve. 2 They are labeled R1, R2, R3 and R4 respectively;

[0046] Obtain relevant thresholds. In the amplitude correlation curve, if R1 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the GRS change rate; if R3 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the temperature change slope.

[0047] In the frequency correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and temperature change slope.

[0048] In the rhythm correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the temperature change slope.

[0049] In the cycle correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the EMG activation amplitude; and if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the temperature change slope.

[0050] Furthermore, the test features and moderation expectations are grouped based on the association effectiveness to obtain association groups, and the moderation association is obtained through analysis based on the association groups, including the following sub-steps:

[0051] Test features that are statistically effectively correlated with massage amplitude are grouped into the same correlation group and named amplitude group; test features that are statistically effectively correlated with massage frequency are grouped into the same correlation group and named frequency group; test features that are statistically effectively correlated with massage rhythm are grouped into the same correlation group and named rhythm group; test features that are statistically effectively correlated with cycle period are grouped into the same correlation group and named cycle group.

[0052] Any associated group contains at most two types of test features. If there are more than two types, the two types of test features with the highest fit metric are retained.

[0053] When analyzing any associated group, mark it as the group to be analyzed. If there is only one type of test feature in the group to be analyzed, then the function of the association curve corresponding to the group to be analyzed is the modulated association.

[0054] If there are two types of test features in the group to be analyzed, then the test features are marked as the first feature and the second feature, respectively, and the corresponding adjustment expectations are marked as the expectations to be analyzed.

[0055] A three-dimensional coordinate system is established with the first feature as the X-axis, the second feature as the Y-axis, and the expected value to be analyzed as the Z-axis. This system is named the adjustment correlation coordinate system. The test features in the group to be analyzed are entered into the adjustment correlation coordinate system according to the corresponding adjustment expectations. The adjustment correlation coordinate system is the adjustment correlation.

[0056] Furthermore, monitoring biofeedback and extracting feedback features every first regulation cycle, and intelligently adjusting the regulation parameters of the massager based on feedback features and regulatory correlation, includes the following sub-steps:

[0057] Biofeedback is monitored once every first regulation cycle and feedback features are extracted and named real-time features; when performing regulation analysis on any regulation parameter, it is named the target parameter, and real-time features that have a valid correlation with the target parameter are marked as target features;

[0058] If there is only one type of real-time feature for the target feature, then the target adjustment value of the target parameter can be obtained by substituting the target feature into the adjustment correlation solution corresponding to the target parameter.

[0059] If there are two types of real-time features in the target features, then obtain a top view of the adjustment correlation corresponding to the target parameters, that is, only consider the X and Y axes of the adjustment correlation coordinate system, ignore the Z axis, and obtain a two-dimensional correlation diagram;

[0060] Name the coordinate points in the 2D correlation graph as the original points. Input the target features into the 2D correlation graph to obtain the target points. Find the original points in the 2D correlation graph that are closest to the target points and mark them as adjustment points. Obtain the value of the adjustment point on the Z-axis of the adjustment correlation coordinate system to obtain the target adjustment value. Adjust the target parameters, and the adjusted value is the target adjustment value.

[0061] The beneficial effects of this invention are as follows: This invention installs a multimodal sensor inside the massager and then monitors the user's biofeedback in real time through the multimodal sensor to obtain feedback data. An intelligent adjustment model for regulating parameters is then constructed, and features are extracted from the feedback data to obtain feedback features of different feedback data. Simultaneously, a first number of testers are selected to test the massager, and their feedback features are extracted as test features. The testers' expectations for adjusting the parameters are also recorded. These test features and expectations are then entered into the intelligent adjustment model for regulating parameters, and values ​​are assigned to the expectations. The correlation effectiveness is then analyzed based on the assigned test features and expectations. The advantage lies in testing the correlation between different massage parameters and feedback data based on user feedback data during use, finding effective feedback data that influences the massage parameters needed by the user, providing a valid data foundation for subsequent analysis, and improving the effectiveness and rationality of the massager's intelligent control.

[0062] This invention obtains correlation groups by grouping test features and regulatory expectations based on correlation effectiveness, and then analyzes these correlation groups to obtain regulatory correlation. Finally, it monitors biofeedback and extracts feedback features every first regulation cycle. Based on the feedback features and regulatory correlation, it intelligently adjusts the massager's regulation parameters. The advantage lies in analyzing the regulatory correlation between test features and regulatory expectations, thereby calculating the user's independent and precise adjustment of different massage parameters under different feedback features, automatically adapting to the user's current massage needs, and improving the accuracy and effectiveness of the massager's intelligent control. Attached Figure Description

[0063] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0064] Figure 2 This is a heart rate correlation graph of the present invention;

[0065] Figure 3 This is a schematic diagram of the correlation curve of the present invention;

[0066] Figure 4 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] Example 1, please refer to Figure 1 As shown, this application provides a method for establishing an intelligent adjustment model for male massagers based on biofeedback monitoring, including the following steps:

[0069] Step S1: Install a multimodal sensor inside the massager; Step S1 includes the following sub-steps:

[0070] Step S101: The multimodal sensor includes a PPG photoplethysmography (PPG) sensor, an electrode patch sensor, a surface electromyography (SEM) sensor, and a thermal sensor.

[0071] In step S102, the PPG photoplethysmography sensor and the electrode patch sensor are placed on the grip area of ​​the massager to monitor the user's palm.

[0072] In step S103, both the surface electromyography sensor and the thermal sensor are installed inside the massager to monitor the contact area.

[0073] In practice, the PPG photoplethysmography (PPG) sensor, electrode patch sensor, surface electromyography (SEMG) sensor, and thermal sensor are all existing sensors. The massager surface is provided with a grip area to restrict the user's grip and facilitate the collection of feedback data.

[0074] Step S2 involves real-time monitoring of the user's biofeedback using a multimodal sensor to obtain feedback data. Step S2 includes the following sub-steps:

[0075] In step S201, the PPG photoplethysmography (PPG) sensor, electrode patch sensor, surface electromyography (EMG) sensor, and thermal sensor are used to monitor the user's heart rate, skin conductance, EMG in the contact area, and skin temperature in the contact area, respectively.

[0076] In step S202, heart rate, skin conductance response, electromyography, and skin temperature are the feedback data;

[0077] In practice, the sampling frequencies of the PPG photoplethysmography (PPG) sensor, electrode patch sensor, surface electromyography (SEMG) sensor, and thermistor are kept consistent, and sampling is performed at the same time.

[0078] Step S3 involves constructing an intelligent adjustment model for the adjustment parameters, extracting features from the feedback data, and obtaining feedback features for different feedback data. Step S3 includes the following sub-steps:

[0079] Step S301: Construct an intelligent adjustment model for adjustment parameters, input feedback data into the intelligent adjustment model for adjustment parameters, which is equipped with HRV algorithm, GSR rate of change algorithm, EMG activation amplitude algorithm and temperature change trend algorithm;

[0080] Step S302: Analyze the heart rate using the HRV algorithm to obtain the HRV index;

[0081] Step S303: Analyze the skin conductance response using the GSR change rate algorithm to obtain the GRS change rate;

[0082] Step S304: Analyze electromyography using the EMG activation amplitude algorithm to obtain the EMG activation amplitude;

[0083] Step S305: Analyze skin temperature using a temperature change trend algorithm to obtain the temperature change slope;

[0084] Step S306: HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope are collectively referred to as feedback characteristics;

[0085] In specific implementation, the HRV algorithm, GSR rate of change algorithm, EMG activation amplitude algorithm, and temperature change trend algorithm are all existing algorithms, and the calculation process is relatively simple. They usually have preset processing models in various existing sensors, which can directly output the feedback features in this embodiment. This embodiment will not describe them in detail. For example, in the feedback features obtained from a certain monitoring, the HRV index is 15.65ms, the GRS rate of change is 0.076μS / s, the EMG activation amplitude is 0.0598mV, and the temperature change slope is -0.02.

[0086] Step S4 involves selecting a first number of testers to test the massager, extracting their feedback characteristics as test features, and recording their expectations for adjusting the parameters. Step S4 includes the following sub-steps:

[0087] Step S401: Select the first number of testers to test the massager;

[0088] Step S402: During the test, the massager uses a preset massage program to massage the tester for the first test duration.

[0089] Step S403: Record the feedback characteristics of the tester last monitored before the end of the test, and name them as test characteristics;

[0090] Step S404: Adjust parameters including massage amplitude, massage frequency, massage rhythm, and cycle period;

[0091] Step S405: After the test, record the tester's expectations for adjusting the parameters, including the expected amplitude, expected frequency, expected rhythm, and expected period.

[0092] In practice, testers can recruit volunteers or select company employees, and the testing process is anonymous to fully protect the privacy and security of each tester. The number of initial tests and the duration of the initial tests are set by the manufacturer. In this embodiment, the number of initial tests is set to 400, and the duration of the initial tests is set to 1 minute. Each adjustment parameter of the massager has 5 levels. The preset massage program in this embodiment is to adjust all adjustment parameters to the third level. This is because users usually do not directly increase the intensity from the lowest level to the highest level, or directly decrease it from the highest level to the lowest level when using the massager. The increase and decrease of the intensity level needs to follow a certain degree of gentleness, and because the intensity level has different... The massager is limited to a maximum of two intensity levels per cycle, with three possible scenarios: increase, decrease, and increase. Therefore, using the third intensity level as the preset massage mode allows for accurate determination of the massager's intensity level requirements. For example, in a certain test, the monitored test characteristics of the tester included an HRV index of 28.4 ms, a GRS change rate of 0.076 μS / s, an EMG activation amplitude of 0.0598 mV, and a temperature change slope of 0.02. The tester's desired intensity level was an increase of 2 massage amplitude levels, an increase of 1 massage frequency level, an increase of 1 massage rhythm level, and an increase of 1 cycle level.

[0093] Step S5 involves inputting the test features and adjustment expectations into the intelligent adjustment model for adjustment parameters, and analyzing the adjustment correlation between different feedback features and adjustment parameters based on the test features and adjustment expectations. Step S5 includes the following sub-steps:

[0094] Step S501: Input the test features and adjustment expectations into the intelligent adjustment model of adjustment parameters, and assign values ​​to the adjustment expectations;

[0095] Step S501 includes the following sub-steps:

[0096] Step S5011: Input the test features and adjustment expectations into the intelligent adjustment model of adjustment parameters;

[0097] Step S5012: Assign a value to the desired amplitude. If the tester wants to increase the massage amplitude by N1 levels, the desired amplitude is assigned the value +N1. If the tester wants to decrease the massage amplitude by N1 levels, the desired amplitude is assigned the value -N1. If the tester wants to maintain the current massage amplitude level, the desired amplitude is assigned the value 0.

[0098] Step S5013: Assign a value to the desired frequency. If the tester wants to increase the massage frequency by N2 levels, the desired frequency is assigned a value of +N2. If the tester wants to decrease the massage frequency by N2 levels, the desired frequency is assigned a value of -N2. If the tester wants to maintain the current massage frequency level, the desired frequency is assigned a value of 0.

[0099] Step S5014: Assign a value to the desired rhythm. If the tester wants to increase the massage rhythm level by N3 levels, the desired rhythm is assigned the value of +N3. If the tester wants to decrease the massage rhythm level by N3 levels, the desired rhythm is assigned the value of -N3. If the tester wants to maintain the current massage rhythm level, the desired rhythm is assigned the value of 0.

[0100] Step S5015: Assign a value to the desired cycle. If the tester wants to increase the level of N4 massage cycles, the desired cycle is assigned the value of +N4. If the tester wants to decrease the level of N4 massage cycles, the desired cycle is assigned the value of -N4. If the tester wants to maintain the current level of massage cycles, the desired cycle is assigned the value of 0.

[0101] In practice, since the process and principle of assigning values ​​to the desired amplitude, desired frequency, desired rhythm, and desired period are all the same, this embodiment will only use the assignment of the desired amplitude as an example for explanation. Taking the desired amplitude in step S4 as an example, the tester expects to increase the massage amplitude by 2 levels, so N1 is 2. At this time, the desired amplitude is assigned the value of +2, that is, positive 2. The plus sign only corresponds to the minus sign in negative 2, indicating positive, not indicating addition.

[0102] Step S502: Analyze the correlation effectiveness based on the assigned test features and adjustment expectations;

[0103] Step S502 includes the following sub-steps:

[0104] Step S5021: Using the expected adjustment as the Y-axis, construct a two-dimensional coordinate system with HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope as the X-axis, respectively named the heart rate correlation graph, electrical response correlation graph, electromyography correlation graph, and temperature correlation graph. Enter the expected adjustment into the corresponding two-dimensional coordinate system according to the test characteristics.

[0105] Please see Figures 2 to 3As shown, in step S5022, the coordinate points corresponding to the expected amplitude, expected frequency, expected rhythm and expected period are named amplitude coordinates, frequency coordinates, rhythm coordinates and period coordinates respectively. Multinomial regression is performed on the amplitude coordinates, frequency coordinates, rhythm coordinates and period coordinates in the heart rate correlation diagram, electrical response correlation diagram, electromyography correlation diagram and temperature correlation diagram respectively to obtain amplitude correlation curve, frequency correlation curve, rhythm correlation curve and period correlation curve, which are collectively referred to as correlation curves.

[0106] In practice, since the value range and meaning of the expected regulation after assignment are the same, the expected regulation can be uniformly used as the Y-axis, and the heart rate correlation graph, electrical response correlation graph, electromyography correlation graph and temperature correlation graph can be constructed using the HRV index, GRS rate of change, EMG activation amplitude and temperature change slope as the X-axis respectively. Since the analysis process and analysis principle of the heart rate correlation graph, electrical response correlation graph, electromyography correlation graph and temperature correlation graph are exactly the same in the subsequent analysis process, this embodiment only takes the analysis of the heart rate correlation graph as an example to explain the subsequent analysis process. Figure 2 This is a heart rate correlation plot, where different colored coordinate points represent amplitude, frequency, rhythm, and cycle coordinates, respectively. The correlation curve is obtained through regression, as shown below. Figure 3 As shown;

[0107] Step S5023: Obtain the fitting metric, Rfit, for the amplitude correlation curve, frequency correlation curve, rhythm correlation curve, and period correlation curve. 2 They are labeled R1, R2, R3 and R4 respectively;

[0108] Step S5024: Obtain relevant thresholds. In the amplitude correlation curve, if R1 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the GRS change rate; if R3 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the temperature change slope.

[0109] In step S5025, in the frequency correlation curve, if R1 is greater than or equal to the correlation threshold, then the massage frequency is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the correlation threshold, then the massage frequency is marked as having an effective correlation with the GRS change rate; if R3 is greater than or equal to the correlation threshold, then the massage frequency is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, then the massage frequency is marked as having an effective correlation with the temperature change slope.

[0110] In step S5026, in the rhythm correlation curve, if R1 is greater than or equal to the correlation threshold, then the massage rhythm is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the correlation threshold, then the massage rhythm is marked as having an effective correlation with the GRS change rate; if R3 is greater than or equal to the correlation threshold, then the massage rhythm is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, then the massage rhythm is marked as having an effective correlation with the temperature change slope.

[0111] Step S5027: In the periodic correlation curve, if R1 is greater than or equal to the correlation threshold, then the cycle period is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the correlation threshold, then the cycle period is marked as having an effective correlation with the GRS rate of change; if R3 is greater than or equal to the correlation threshold, then the cycle period is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, then the cycle period is marked as having an effective correlation with the temperature change slope.

[0112] In specific implementation, the acquisition Figure 3 The R1, R2, R3, and R4 values ​​were 0.939, 0.1304, 0.1778, and 0.0166, respectively, yielding a correlation threshold of 0.9. This correlation threshold was obtained from numerous correlation experiments across various fields. By selecting two data points with a generally accepted correlation in society for analysis, the results show that in different fields, as long as the data are generally considered to be correlated, their R... 2 The values ​​are usually above 0.9, so the relevant threshold is set to 0.9. By comparison, it is found that only R1 is greater than the relevant threshold. Therefore, the massage amplitude is only effectively correlated with the HRV index. Similarly, the analysis shows that the massage frequency is effectively correlated with the EMG activation amplitude and the slope of temperature change, the massage rhythm is effectively correlated with the GRS change rate and the HRV index, and the cycle period is effectively correlated with the HRV index and the EMG activation amplitude.

[0113] Step S503: Group the test features and moderation expectations based on the correlation validity to obtain the correlation groups, and analyze the correlation groups to obtain the moderation correlation.

[0114] Step S503 includes the following sub-steps:

[0115] Step S5031: Collect test features that are effectively correlated with massage amplitude and group them into the same correlation group, named amplitude group; collect test features that are effectively correlated with massage frequency and group them into the same correlation group, named frequency group; collect test features that are effectively correlated with massage rhythm and group them into the same correlation group, named rhythm group; collect test features that are effectively correlated with cycle period and group them into the same correlation group, named cycle group.

[0116] Step S5032: Any associated group contains at most two types of test features. If there are more than two types, the two types of test features with the largest fit metric are retained.

[0117] Step S5033: When analyzing any associated group, mark it as the group to be analyzed. If there is only one type of test feature in the group to be analyzed, then the function of the association curve corresponding to the group to be analyzed is the modulated association.

[0118] In practical implementation, taking amplitude grouping as an example, amplitude grouping only contains test features of the HRV indicator type, that is, there is only one type of test feature, which can be directly obtained. Figure 3 The function corresponding to the correlation curve in the figure yields the moderating correlation as Y1 = 0.0001 × X1. 2 -0.1057×X1+4.4992, where Y1 is the adjustment expectation and X1 is the HRV index;

[0119] Step S5034: If there are two types of test features in the group to be analyzed, then the test features are marked as the first feature and the second feature respectively, and the corresponding adjustment expectation is marked as the expectation to be analyzed;

[0120] Step S5035: Establish a three-dimensional coordinate system with the first feature as the X-axis, the second feature as the Y-axis, and the expected value to be analyzed as the Z-axis. Name it the adjustment correlation coordinate system. Enter the test features in the group to be analyzed into the adjustment correlation coordinate system according to the corresponding adjustment expectations. The adjustment correlation coordinate system is the adjustment correlation.

[0121] In practice, adjusting the associated coordinate system is actually... Figure 3 The Y-axis is replaced with another test feature, and the adjustment expectation is then transferred to the Z-axis dimension. Since the three-dimensional coordinate system is difficult to display on a two-dimensional plane, it will not be specifically shown in this embodiment.

[0122] Step S6 involves monitoring biofeedback and extracting feedback features every first regulation cycle, and intelligently adjusting the massager's regulation parameters based on these features and regulatory correlations. Step S6 includes the following sub-steps:

[0123] Step S601: Monitor the biofeedback once every first regulation cycle and extract the feedback features, which are named real-time features; when performing regulation analysis on any regulation parameter, name it as the target parameter, and mark the real-time features that have a valid correlation with the target parameter as the target features;

[0124] Step S602: If there is only one type of real-time feature in the target feature, then the target adjustment value of the target parameter can be obtained by substituting the target feature into the adjustment correlation solution corresponding to the target parameter.

[0125] Step S603: If there are two types of real-time features in the target features, then obtain a top view of the adjustment correlation corresponding to the target parameters, that is, only consider the X-axis and Y-axis of the adjustment correlation coordinate system, ignore the Z-axis, and obtain a two-dimensional correlation diagram.

[0126] Step S604: Name the coordinate points in the two-dimensional correlation graph as the original points, input the target features into the two-dimensional correlation graph to obtain the target points, find the original points in the two-dimensional correlation graph that are closest to the target points, mark them as adjustment points, obtain the value of the adjustment points on the Z-axis of the adjustment correlation coordinate system, and obtain the target adjustment value. Adjust the target parameters, and the adjusted value is the target adjustment value.

[0127] In practice, the first adjustment cycle is set by the manufacturer. In this embodiment, the first adjustment cycle is set to 30 seconds. For example, if the user's HRV index is monitored to be 28.4 ms, the GRS change rate is 0.076 μS / s, the EMG activation amplitude is 0.0572 mV, and the temperature change slope is 0.02 during a certain use, substituting X1=28.4 into Y1=0.0001×X1 2 The solution is -0.1057×X1+4.4992, which yields a target adjustment value of 2 for the massage amplitude. The result is rounded to the nearest integer, so the massage amplitude level of the massager is increased by 2. At this point, the HRV index is 28.4ms and the EMG activation amplitude is 0.0572mV, both affecting the cycle period. In the two-dimensional correlation diagram of the cycle period, the X-axis represents the HRV index and the Y-axis represents the EMG activation amplitude. Therefore, the coordinates (28.4, 0.0572) are entered into the two-dimensional correlation diagram. The coordinate α is found to be closest to (28.4, 0.0572), so the value of coordinate α on the Z-axis of the adjustment correlation coordinate system is read, yielding a target adjustment value of 1. Therefore, the cycle period level is increased by 1.

[0128] Example 2, please refer to Figure 4 As shown, Figure 4A schematic diagram of an electronic device is provided, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call these instructions. When the processor executes a computer-readable instruction, it performs steps such as those in the method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring, to achieve the following functions: installing multimodal sensors within the massager; real-time monitoring of the user's biofeedback to obtain feedback data; extracting feedback features from different feedback data; extracting the feedback features of the tester as test features and recording the tester's adjustment expectations for the adjustment parameters; analyzing the adjustment correlation between different feedback features and adjustment parameters based on the test features and adjustment expectations; and intelligently adjusting the adjustment parameters of the massager based on the feedback features and adjustment correlation.

[0129] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring provided by the above methods. This method includes: installing a multimodal sensor in the massager; monitoring the user's biofeedback in real time to obtain feedback data; extracting feedback features from different feedback data; extracting the feedback features of the tester as test features and recording the tester's adjustment expectations for the adjustment parameters; analyzing the adjustment correlation between different feedback features and adjustment parameters based on the test features and adjustment expectations; and intelligently adjusting the adjustment parameters of the massager based on the feedback features and adjustment correlation.

[0131] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps in the above-described method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring, to achieve the following functions: installing a multimodal sensor in the massager; monitoring the user's biofeedback in real time to obtain feedback data; extracting feedback features from different feedback data; extracting the feedback features of the tester as test features and recording the tester's adjustment expectations for the adjustment parameters; analyzing the adjustment correlation between different feedback features and adjustment parameters based on the test features and adjustment expectations; and intelligently adjusting the adjustment parameters of the massager based on the feedback features and adjustment correlation.

[0132] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0133] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for establishing an intelligent adjustment model for male massagers based on biofeedback monitoring, characterized in that, The steps include the following: Install multimodal sensors inside the massager; The user's biofeedback is monitored in real time using multimodal sensors to obtain feedback data; Construct an intelligent adjustment model for adjustment parameters, extract features from feedback data, and obtain feedback features for different feedback data; The first number of testers were selected to test the massager, and the feedback characteristics of the testers were extracted as test characteristics. The testers' expectations for adjusting the adjustment parameters were also recorded. The test features and adjustment expectations are entered into the intelligent adjustment model of the adjustment parameters, and the adjustment correlation between different feedback features and adjustment parameters is analyzed based on the test features and adjustment expectations. The biofeedback is monitored and feedback features are extracted once every first regulation cycle. The regulation parameters of the massager are intelligently adjusted based on the feedback features and regulation correlation. The process involves inputting test features and adjustment expectations into the intelligent adjustment model for adjustment parameters. Analyzing the adjustment correlation between different feedback features and adjustment parameters based on these features and expectations includes the following sub-steps: The test features and adjustment expectations are entered into the intelligent adjustment model of adjustment parameters, and values ​​are assigned to the adjustment expectations; Analysis of correlation effectiveness based on post-assignment test features and adjustment expectations; Based on the correlation validity, the test features and moderating expectations are grouped to obtain correlation groups, and the moderating correlation is obtained by analysis based on the correlation groups; The analysis of correlation effectiveness based on the assigned test features and adjusted expectations includes the following sub-steps: Using the expected adjustment as the Y-axis, and the HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope as the X-axis, a two-dimensional coordinate system was constructed. These systems were named the Heart Rate Correlation Chart, Electroreaction Correlation Chart, Electromyography Correlation Chart, and Temperature Correlation Chart, respectively. The expected adjustment was then entered into the corresponding two-dimensional coordinate system according to the test characteristics. The coordinate points corresponding to the expected amplitude, expected frequency, expected rhythm, and expected period are named amplitude coordinates, frequency coordinates, rhythm coordinates, and period coordinates, respectively. Multinomial regression is performed on the amplitude coordinates, frequency coordinates, rhythm coordinates, and period coordinates in the heart rate correlation diagram, electroreaction correlation diagram, electromyography correlation diagram, and temperature correlation diagram to obtain amplitude correlation curves, frequency correlation curves, rhythm correlation curves, and period correlation curves, which are collectively referred to as correlation curves. Obtain the fitting metric, Ri, for the amplitude correlation curve, frequency correlation curve, rhythm correlation curve, and period correlation curve. 2 They are labeled R1, R2, R3 and R4 respectively; Obtain relevant thresholds. In the amplitude correlation curve, if R1 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the HRV index; if R2 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the GRS change rate; if R3 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the EMG activation amplitude; if R4 is greater than or equal to the relevant threshold, then the massage amplitude is marked as having an effective correlation with the temperature change slope. In the frequency correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between massage frequency and temperature change slope. In the rhythm correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the massage rhythm and the temperature change slope. In the cycle correlation curve, if R1 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the HRV index; if R2 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the GRS change rate; if R3 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the EMG activation amplitude; if R4 is greater than or equal to the correlation threshold, it indicates that there is an effective correlation between the cycle period and the temperature change slope. Grouping test features and moderating expectations based on association effectiveness to obtain association groups, and then analyzing these association groups to obtain moderating association, includes the following sub-steps: Test features that are statistically effectively correlated with massage amplitude are grouped into the same correlation group and named amplitude group; test features that are statistically effectively correlated with massage frequency are grouped into the same correlation group and named frequency group; test features that are statistically effectively correlated with massage rhythm are grouped into the same correlation group and named rhythm group; test features that are statistically effectively correlated with cycle period are grouped into the same correlation group and named cycle group. Any associated group contains at most two types of test features. If there are more than two types, the two types of test features with the highest fit metric are retained. When analyzing any associated group, mark it as the group to be analyzed. If there is only one type of test feature in the group to be analyzed, then the function of the association curve corresponding to the group to be analyzed is the modulated association. If there are two types of test features in the group to be analyzed, then the test features are marked as the first feature and the second feature, respectively, and the corresponding adjustment expectations are marked as the expectations to be analyzed. A three-dimensional coordinate system is established with the first feature as the X-axis, the second feature as the Y-axis, and the expected value to be analyzed as the Z-axis. This system is named the adjustment correlation coordinate system. The test features in the group to be analyzed are entered into the adjustment correlation coordinate system according to the corresponding adjustment expectations. The adjustment correlation coordinate system is the adjustment correlation. The process of monitoring biofeedback and extracting feedback features every first regulation cycle, and then intelligently adjusting the regulation parameters of the massager based on these features and regulatory correlations, includes the following sub-steps: Biofeedback is monitored once every first regulation cycle and feedback features are extracted and named real-time features; when performing regulation analysis on any regulation parameter, it is named the target parameter, and real-time features that have a valid correlation with the target parameter are marked as target features; If there is only one type of real-time feature for the target feature, then the target adjustment value of the target parameter can be obtained by substituting the target feature into the adjustment correlation solution corresponding to the target parameter. If there are two types of real-time features in the target features, then obtain a top view of the adjustment correlation corresponding to the target parameters, that is, only consider the X and Y axes of the adjustment correlation coordinate system, ignore the Z axis, and obtain a two-dimensional correlation diagram; Name the coordinate points in the 2D correlation graph as the original points. Input the target features into the 2D correlation graph to obtain the target points. Find the original points in the 2D correlation graph that are closest to the target points and mark them as adjustment points. Obtain the value of the adjustment point on the Z-axis of the adjustment correlation coordinate system to obtain the target adjustment value. Adjust the target parameters, and the adjusted value is the target adjustment value.

2. The method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring according to claim 1, characterized in that, Installing a multimodal sensor within a massager includes the following sub-steps: The multimodal sensor includes a PPG photoplethysmography (PPG) sensor, an electrode patch sensor, a surface electromyography (SEM) sensor, and a thermal sensor. The PPG photoplethysmography sensor and electrode patch sensor are located on the grip area of ​​the massager to monitor the user's palm. Both the surface electromyography sensor and the thermal sensor are located inside the massager and are used to monitor the contact area.

3. The method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring according to claim 2, characterized in that, Real-time monitoring of user biofeedback using multimodal sensors yields feedback data through the following sub-steps: The PPG photoplethysmography (PPG) sensor, electrode patch sensor, surface electromyography (EMG) sensor, and thermistor are used to monitor the user's heart rate, skin conductance, EMG of the contact area, and skin temperature of the contact area, respectively. The heart rate, skin conductance, electromyography, and skin temperature are the feedback data.

4. The method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring according to claim 3, characterized in that, Constructing an intelligent adjustment model for adjustment parameters and extracting features from feedback data involves the following sub-steps: A smart adjustment model for adjustment parameters is constructed, and feedback data is input into the smart adjustment model for adjustment parameters. The smart adjustment model for adjustment parameters is equipped with HRV algorithm, GSR rate of change algorithm, EMG activation amplitude algorithm and temperature change trend algorithm. The HRV index is obtained by analyzing heart rate using the HRV algorithm. The skin conductance response was analyzed using the GSR change rate algorithm to obtain the GRS change rate; Electromyography was analyzed using an EMG activation amplitude algorithm to obtain the EMG activation amplitude. Skin temperature is analyzed using a temperature change trend algorithm to obtain the slope of temperature change; The HRV index, GRS rate of change, EMG activation amplitude, and temperature change slope are collectively referred to as feedback characteristics.

5. The method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring according to claim 4, characterized in that, The first batch of testers were selected to test the massager. Simultaneously, the testers' feedback characteristics were extracted as test features, and their expectations for adjusting the parameters were recorded. This process includes the following sub-steps: The first number of testers were selected to test the massager; During the test, the massager used a preset massage program to massage the tester for the first test duration. Record the feedback characteristics of the testers last monitored before the end of the test, and name them as test characteristics; The adjustment parameters include massage amplitude, massage frequency, massage rhythm, and cycle period; After the test, record the testers' expectations for adjusting the parameters, including the expected amplitude, expected frequency, expected rhythm, and expected period.

6. The method for establishing an intelligent adjustment model for a male massager based on biofeedback monitoring according to claim 5, characterized in that, The process of inputting test features and adjustment expectations into the intelligent adjustment model of adjustment parameters, and assigning values ​​to the adjustment expectations, includes the following sub-steps: Input the test features and adjustment expectations into the intelligent adjustment model of adjustment parameters; Assign a value to the desired amplitude. If the tester wants to increase the massage amplitude by N1 levels, the desired amplitude is assigned the value +N1. If the tester wants to decrease the massage amplitude by N1 levels, the desired amplitude is assigned the value -N1. If the tester wants to maintain the current massage amplitude level, the desired amplitude is assigned the value 0. Assign a value to the desired frequency. If the tester wants to increase the massage frequency by N2 levels, the desired frequency is assigned the value of +N2. If the tester wants to decrease the massage frequency by N2 levels, the desired frequency is assigned the value of -N2. If the tester wants to maintain the current massage frequency level, the desired frequency is assigned the value of 0. Assign a value to the desired rhythm. If the tester wants to increase the massage level by N3 levels, the desired rhythm is assigned the value +N3. If the tester wants to decrease the massage level by N3 levels, the desired rhythm is assigned the value -N3. If the tester wants to maintain the current massage level, the desired rhythm is assigned the value 0. Assign a value to the desired cycle. If the tester wants to increase the massage level by N4 cycles, the desired cycle is assigned the value of +N4. If the tester wants to decrease the massage level by N4 cycles, the desired cycle is assigned the value of -N4. If the tester wants to maintain the current massage level, the desired cycle is assigned the value of 0.

Images