Intelligent control method, device, equipment and medium for wearable massager

Abstract

The present invention relates to an intelligent control method, device, equipment and medium of a wearable massager, comprising obtaining massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager; according to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, using other types of sensors configured on the massage component where the sensor is located as attention target sensors, and determining the first target massage parameters of each massage component by cross-paying attention to the massage feedback data of the attention target sensor on the massage feedback data of the sensor; according to the first target massage parameters of the massage components adjacent to each massage component, correcting the first target massage parameters of each massage component to obtain the second target massage parameters of each massage component; according to the second target massage parameters of each massage component, controlling each massage component to perform massage.

Description

Technical Field

[0001] The present disclosure relates to the field of massage technology, and in particular to an intelligent control method, device, equipment and medium of a wearable massager. Background Art

[0002] Wearable massagers, as a portable and easy-to-use health device, have gradually gained favor among consumers. However, traditional wearable massagers have some shortcomings in terms of control, such as complex operation and inability to automatically adjust the massage mode according to the user's health status, which to some extent limits their use effect and user experience. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent control method, device, equipment and medium for a wearable massager, aiming to improve the massage effect and user experience.

[0004] In order to achieve the above-mentioned purpose, a first aspect of an embodiment of the present disclosure provides an intelligent control method of a wearable massager, the method comprising:

[0005] In response to a massage operation of the wearable massager, massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager are obtained;

[0006] According to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, the other types of sensors configured on the massage component where the sensor is located are used as attention target sensors, and the massage feedback data of the attention target sensors are cross-attended to determine the first target massage parameter of each massage component by cross-paying attention to the massage feedback data of the sensor;

[0007] According to the first target massage parameters of the plurality of massage components adjacent to each massage component, the first target massage parameter of each massage component is corrected to obtain a second target massage parameter of each massage component;

[0008] According to the second target massage parameter of each massage component, each massage component is controlled to perform massage.

[0009] In a possible implementation, according to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, the other types of sensors configured on the massage component where the sensor is located are used as attention target sensors, and the massage feedback data of the sensor is cross-attended to the massage feedback data of the attention target sensor to determine the first target massage parameter of each massage component, including:

[0010] According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend and a change amount of the massage feedback data collected by each sensor twice adjacently;

[0011] For each type of sensor on each massage component, determine a target sensor of attention from other types of sensors configured on the massage component where the sensor is located;

[0012] Taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor;

[0013] The first target massage parameter of each massage component is determined according to the cross-attention massage data of each type of the sensor on each massage component.

[0014] In a possible implementation, for each type of sensor on each massage component, determining the attention target sensor from other types of sensors configured on the massage component where the sensor is located includes:

[0015] According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend of the massage feedback data collected by each sensor twice adjacently;

[0016] For each type of the sensor on each of the massage components, a sensor having the same change trend as other types of sensors configured on the massage component where the sensor is located is used as an attention target sensor.

[0017] In a possible implementation, for each type of sensor on each massage component, determining the attention target sensor from other types of sensors configured on the massage component where the sensor is located includes:

[0018] For each type of sensor on each massage component, other types of sensors that are configured on the same massage component as the sensor and satisfy a preset cross-attention relationship are used as attention target sensors;

[0019] Among them, the preset cross-attention relationship of the pressure sensor is: the temperature sensor is used as the attention target sensor; the preset cross-attention relationship of the temperature sensor is: the bioelectric sensor is used as the attention target sensor; the preset cross-attention relationship of the bioelectric sensor is: the pressure sensor is used as the attention target sensor.

[0020] In a possible implementation, taking the massage feedback data of each type of the sensor on each of the massage components as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor includes:

[0021] Calculating a mean value of the change amount according to the change amount of the massage feedback data corresponding to each type of the sensor on each massage component and the change amount of the massage feedback data of the corresponding attention target sensor;

[0022] Taking the massage feedback data of each type of the sensor on each massage component as a query, performing a dot product operation with the mean of the corresponding change amount as a key, and obtaining an attention score of each type of the sensor on each massage component;

[0023] Using the square root of the dimension of the mean of the variation as a scaling factor, scaling the attention score corresponding to each type of the sensor on each massage component to obtain a corrected scaling score;

[0024] The cross-attention massage data of the sensor is determined according to the correction scaling scores corresponding to the multiple types of the sensors on each of the massage components.

[0025] In a possible implementation, the first target massage parameter of each massage component is corrected according to the first target massage parameters of the plurality of massage components adjacent to each massage component to obtain the second target massage parameter of each massage component, including:

[0026] Calculating an average value and a variance between the first target massage parameters of a plurality of massage components adjacent to each massage component and the first target massage parameter of the massage component;

[0027] Determine the Gaussian distribution parameter of the massage component according to the mean value and the variance corresponding to each massage component, the first target massage parameters of a plurality of massage components adjacent to the massage component, and the first target massage parameter of the massage component;

[0028] From the Gaussian distribution parameters corresponding to each of the massage components, a Gaussian distribution parameter within the preset variance range of the mean is taken as a target parameter, and the first target massage parameter corresponding to the target parameter and the first target massage parameter of the massage component are averaged to correct the first target massage parameter of the corresponding massage component to obtain the second target massage parameter of each of the massage components.

[0029] In a possible implementation, the second target massage parameter includes at least one of the following: a massage intensity parameter, a massage speed parameter, a massage heating temperature parameter, and a massage humidification parameter.

[0030] In a possible implementation, the wearable massager includes any one of the following: a head massager, a neck massager, and a lumbar massager.

[0031] According to a second aspect of the embodiments of the present disclosure, there is provided an intelligent control device for a wearable massager, comprising:

[0032] an acquisition module, configured to acquire massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager in response to a massage operation of the wearable massager;

[0033] a determination module configured to determine, according to the massage feedback data collected by the multiple types of sensors on each of the massage components, a first target massage parameter of the sensor by cross-paying attention to the massage feedback data of the sensor and taking other types of sensors configured on the massage component where the sensor is located as the attention target sensor for each type of the sensor on each of the massage components;

[0034] a correction module, configured to correct the first target massage parameter of the sensor on each massage component according to the first target massage parameter corresponding to the sensor of the same type on the adjacent massage components of each massage component, so as to obtain a second target massage parameter of the sensor on each massage component;

[0035] The control module is configured to determine the target control parameter of the massage component corresponding to the wearable massager according to the second target massage parameter of the sensor on each massage component, and control each massage component to perform massage according to the target control parameter.

[0036] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0037] According to a fourth aspect of the embodiments of the present disclosure, an electronic device is provided, including:

[0038] a memory having a computer program stored thereon;

[0039] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0040] The present invention provides an intelligent control method, device, equipment and medium for a wearable massager. Compared with the prior art, the present invention has the following beneficial effects:

[0041] By collecting massage feedback data through multiple types of sensors, various information in the massage process can be fully and accurately reflected. By using the cross-attention mechanism, for each type of sensor on each massage component, considering other types of sensors as attention targets, the massage effect can be analyzed more finely, thereby determining more accurate first-target massage parameters. Taking into account the physical differences and massage needs of different users, the massage parameters can be dynamically adjusted according to the collected massage feedback data. By correcting the massage parameters of adjacent massage components, the continuity and coordination of the massage process are ensured to avoid local over-massage or under-massage. Intelligent control of wearable massagers is realized, manual intervention is reduced, massage efficiency and comfort are improved, and massage strategies can be adjusted in real time to meet different massage needs of users.

[0042] In summary, by acquiring and analyzing massage feedback data from multiple types of sensors on multiple massage components, and using the cross-attention mechanism to determine and correct massage parameters, intelligent control of the wearable massager and personalized massage experience are achieved. This not only improves the efficiency and comfort of the massage, but also enhances the overall experience of the user. Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0044] Figure 1 It is a flow chart of an intelligent control method of a wearable massager shown in an embodiment of the specification.

[0045] Figure 2It is a block diagram of an intelligent control device for a wearable massager according to an embodiment of the specification.

[0046] Figure 3 It is a block diagram of another intelligent control device of a wearable massager according to an embodiment of the specification. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0049] The present invention provides an intelligent control method for a wearable massager. Figure 1 1 is a flow chart of an intelligent control method of a wearable massager according to an embodiment. The method comprises:

[0050] In step S11, in response to the massage operation of the wearable massager, massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager are obtained;

[0051] Among them, wearable massagers are small electronic devices that are worn on specific parts of the body and provide massage functions through built-in massage components. Massage components are the parts in wearable massagers that are responsible for producing massage effects, such as rollers, airbags, vibrators, etc. Sensors are devices used to detect and convert physical quantities (such as pressure, temperature, displacement, etc.) into measurable signals. Massage feedback data is collected by sensors on massage components, reflecting the changes in various physical quantities during the massage process.

[0052] In the disclosed embodiment, when the wearable massager starts the massage operation, the multiple massage components built into it start working. Each massage component is equipped with various types of sensors for monitoring various parameters during the massage process, such as pressure distribution, skin temperature, massage intensity, etc. These sensors transmit data to the control system in real time, and the control system obtains real-time feedback during the massage process by analyzing the data.

[0053] For example, suppose a pressure sensor and a temperature sensor are installed on the neck massage component of a wearable massager. When the massager is working, the pressure sensor monitors the pressure distribution of the massage head on the neck, and the temperature sensor monitors the temperature change of the neck skin. These data are collected in real time and transmitted to the control system as massage feedback data.

[0054] In step S12, according to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, the other types of sensors configured on the massage component where the sensor is located are used as attention target sensors, and the massage feedback data of the attention target sensor is cross-attended to determine the first target massage parameter of each massage component.

[0055] Among them, the attention target sensors are other sensors associated with the currently analyzed sensor data in the cross-attention mechanism, and their data are used as reference to optimize the parameter settings of the current sensor.

[0056] In the disclosed embodiment, after obtaining the massage feedback data, the control system cross-attends the data of each type of sensor on each massage component with the data of other types of sensors. This means that for each sensor, the control system will consider the correlation between it and other sensors (i.e., the attention target sensor) to optimize the parameter setting of the sensor. In this way, it can be ensured that the massage parameters are set more accurately and more in line with the actual needs of the user.

[0057] Continuing with the previous example, suppose the pressure sensor data on the neck massage component indicates that the current massage intensity is too strong, while the temperature sensor data shows that the neck skin temperature is slightly elevated. Under the cross-attention mechanism, the control system may reduce the target massage intensity of the pressure sensor to avoid excessive stimulation of the skin while maintaining a certain massage effect. In this way, the first target massage parameter of the pressure sensor will be adjusted to a lower massage intensity.

[0058] In step S13, the first target massage parameter of each massage component is corrected according to the first target massage parameters of a plurality of massage components adjacent to each massage component to obtain a second target massage parameter of each massage component;

[0059] In the disclosed embodiment, due to the mutual influence between different parts of the human body, the massage effect of a single massage component may be affected by adjacent massage components. Therefore, after determining the first target massage parameters of each massage component, the control system will further consider the parameter settings of the adjacent massage components and correct the parameters of the current massage component. This correction is intended to ensure coordination and consistency throughout the massage process.

[0060] For example, suppose a neck massager contains multiple massage components, each responsible for massaging different areas of the neck. After determining the first target massage parameters for each massage component, the control system may find that the massage intensity differences between some adjacent components are too large, which may cause discomfort to the user. Therefore, the control system will fine-tune the massage parameters of these components to ensure that the massage intensity of the entire neck area is more uniform and comfortable. In this way, the second target massage parameters of each massage component will be determined.

[0061] In step S14, each of the massage components is controlled to perform massage according to the second target massage parameter of each of the massage components.

[0062] In the disclosed embodiment, after determining the second target massage parameters of each massage component, the control system will control the massage component to perform corresponding massage operations according to these parameters, including adjusting massage intensity, frequency, rhythm and other parameters to ensure that the massage process meets the user's expectations and needs.

[0063] Continuing with the above example, assume that the control system of the neck massager has determined the second target massage parameters of each massage component. Next, the control system will send these parameters to the corresponding massage components and control them to perform massage according to the preset mode. In this way, the user can enjoy a more comfortable and effective massage experience.

[0064] The above technical solution collects massage feedback data through multiple types of sensors, which can comprehensively and accurately reflect various information in the massage process. By using the cross-attention mechanism, for each type of sensor on each massage component, considering other types of sensors as attention targets, the massage effect can be analyzed more finely, thereby determining more accurate first target massage parameters. Taking into account the physical differences and massage needs of different users, the massage parameters can be dynamically adjusted according to the collected massage feedback data. By correcting the massage parameters of adjacent massage components, the continuity and coordination of the massage process are ensured, and local over-massage or insufficient massage is avoided. Intelligent control of wearable massagers is realized, manual intervention is reduced, massage efficiency and comfort are improved, and massage strategies can be adjusted in real time to meet the different massage needs of users.

[0065] In summary, by acquiring and analyzing massage feedback data from multiple types of sensors on multiple massage components, and using the cross-attention mechanism to determine and correct massage parameters, the wearable massager can be intelligently controlled and personalized for massage experience. This not only improves the efficiency and comfort of massage, but also enhances the overall user experience.

[0066] Optionally, in step S12, according to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, with other types of sensors configured on the massage component where the sensor is located as attention target sensors, by cross-paying attention to the massage feedback data of the attention target sensor on the massage feedback data of the sensor, determining the first target massage parameter of each massage component, including:

[0067] In step S121, according to the massage feedback data collected by the multiple types of sensors on each massage component, the change trend and change amount of the massage feedback data collected by each sensor twice adjacently are determined;

[0068] Among them, change trend: the direction or trend of data change over time or other variables, such as increase, decrease, stability, etc. Change amount: the difference between data at two different time points or states, reflecting the magnitude of data change.

[0069] In the disclosed embodiment, massage feedback data collected twice in a row by multiple types of sensors on each massage component are first analyzed. By comparing these data, the system can calculate the change trend (increase or decrease) and specific change amount of each sensor data. This information is crucial for understanding the dynamic changes during the massage process.

[0070] For example: suppose there is a pressure sensor and a temperature sensor on a massage component. In two consecutive samplings, the pressure sensor reading increases from 50kPa to 55kPa, while the temperature sensor reading increases from 32°C to 33°C. The system can recognize that the pressure increased by 5kPa and the temperature increased by 1°C, which are their respective change trends and changes.

[0071] In step S122, for each type of the sensor on each massage component, determine an attention target sensor from other types of sensors configured on the massage component where the sensor is located;

[0072] In the disclosed embodiment, for each type of sensor on each massage component, one or more sensors of other types configured on the massage component are selected as the attention target sensors. The selection criteria may be based on the correlation between sensor types, physical meanings, or actual application requirements.

[0073] Continuing with the example above, the temperature sensor is selected as the target sensor for the pressure sensor’s attention because temperature and pressure are often correlated during a massage. Similarly, the system may also select other types of sensors (such as humidity sensors or muscle activity sensors) as the target of attention for a specific sensor, depending on the specific design and functionality of the massager.

[0074] In step S123, taking the massage feedback data of each type of the sensor on each massage component as a query, a cross-attention is performed according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor to determine the cross-attention massage data of the sensor;

[0075] In the disclosed embodiment, the massage feedback data of each sensor is used as a query, and the cross-attention keys are determined based on the change in the query and the change in the attention target sensor. The system then uses these keys to perform cross-attention operations to generate cross-attention massage data for each sensor. This process may involve complex algorithms, such as deep learning models, to accurately capture the correlation between different sensor data.

[0076] For example: Assume that a cross-attention relationship between a pressure sensor and a temperature sensor has been determined. During the cross-attention process, the system may consider the relationship between the amount of pressure increase and the amount of temperature increase. If the pressure increases significantly while the temperature increases only slightly, the system may adjust the data of the pressure sensor to reduce the risk of over-pressure. In this way, through the cross-attention mechanism, the system can generate more accurate and optimized massage data.

[0077] In step S124, the first target massage parameter of each massage component is determined according to the cross-attention massage data of each type of the sensor on each massage component.

[0078] In the disclosed embodiment, the first target massage parameters are determined based on the cross-attention massage data of each type of sensor on each massage component. These parameters may include massage intensity, frequency, duration, etc., aiming to provide the best massage effect. The system may use a preset algorithm or rule to convert these cross-attention massage data into specific massage parameters.

[0079] Continuing with the above example, assume that cross-attention massage data from the pressure sensor and the temperature sensor have been generated. Based on this data, the system may determine a more appropriate combination of massage intensity and frequency to ensure that the user can feel enough massage effect without feeling uncomfortable due to excessive pressure. These parameters will be used as the first target massage parameters to guide the actual operation of the massage component.

[0080] Optionally, in step S122, for each type of sensor on each massage component, determining an attention target sensor from other types of sensors configured on the massage component where the sensor is located includes:

[0081] In step S1221, according to the massage feedback data collected by the multiple types of sensors on each massage component, a change trend of the massage feedback data collected by each sensor twice adjacently is determined;

[0082] In the disclosed embodiment, massage feedback data collected two or more times by various types of sensors on each massage component are first analyzed. By comparing these data, the system can calculate the change trend of each sensor data. This trend reflects the dynamic changes of different physical quantities (such as pressure, temperature, humidity, etc.) during the massage process.

[0083] For example, suppose there is a pressure sensor and a temperature sensor on a massage component. In two consecutive samplings, the pressure sensor reading increases from 50kPa to 55kPa, and the temperature sensor reading also increases from 32°C to 33°C. The system can recognize that the data of these two sensors show an increasing trend.

[0084] In step S1222, for each type of sensor on each massage component, a sensor having the same change trend as other types of sensors configured on the massage component where the sensor is located is used as an attention target sensor.

[0085] In the disclosed embodiment, for each type of sensor on each massage component, one or more sensors with the same change trend are selected from other types of sensors configured on the massage component as the attention target sensors. The selection criterion is based on the consistency of the change trend of the sensor data, because sensors with the same change trend may reflect the same physiological or physical process, so there may be a strong correlation between their data.

[0086] Data Collection: First, the system collects massage feedback data continuously acquired by all types of sensors on each massage component.

[0087] Trend analysis: The system then analyzes the changing trends of these data to determine whether each sensor data is increasing, decreasing, or stable.

[0088] Target selection: Next, for each sensor, the system selects a sensor with the same change trend from other types of sensors configured on the massage component where the sensor is located as the attention target sensor.

[0089] Relationship Establishment: Finally, the system establishes the relationship between each sensor and its attention target sensor for use in subsequent cross-attention processes.

[0090] Continuing with the example above, suppose it has been determined that both the pressure sensor and the temperature sensor are showing an increasing trend. In this case, the system might select the temperature sensor as the attention target sensor for the pressure sensor because their trends are the same and may reflect the same physiological process (such as increased temperature and increased pressure due to muscle tension). Similarly, if there are other types of sensors on the massage component (such as humidity sensors or muscle activity sensors) and their data also shows an increasing trend, then these sensors may also be selected as one of the attention target sensors.

[0091] In this way, the correlations between different sensor data can be captured more accurately and utilized in the subsequent cross-attention process to optimize the settings of massage parameters.

[0092] Optionally, in step S122, for each type of sensor on each massage component, determining an attention target sensor from other types of sensors configured on the massage component where the sensor is located includes:

[0093] In step S12201, for each type of sensor on each massage component, other types of sensors that are configured on the same massage component as the sensor and satisfy a preset cross-attention relationship are used as attention target sensors;

[0094] Among them, the preset cross-attention relationship of the pressure sensor is: the temperature sensor is used as the attention target sensor; the preset cross-attention relationship of the temperature sensor is: the bioelectric sensor is used as the attention target sensor; the preset cross-attention relationship of the bioelectric sensor is: the pressure sensor is used as the attention target sensor.

[0095] In the disclosed embodiment, for each type of sensor on each massage component, it is checked whether there is another type of sensor configured on the same massage component and satisfying a preset cross-attention relationship. If such a sensor exists, it is selected as the attention target sensor.

[0096] For example, for the pressure sensor, the system presets a cross-attention relationship to associate it with the temperature sensor. This means that when processing the data of the pressure sensor, the system will use the temperature sensor as the attention target sensor and use the data of the temperature sensor to optimize or adjust the data processing results of the pressure sensor.

[0097] For the temperature sensor, the system presets a cross-attention relationship to associate it with the bioelectric sensor. This means that when processing the temperature sensor's data, the system will use the bioelectric sensor as the target sensor for attention, and use the bioelectric sensor's data to provide additional contextual information or adjust the temperature sensor's data processing strategy.

[0098] For the bioelectric sensor, the system presets a cross-attention relationship to associate it with the pressure sensor. This means that when processing the data from the bioelectric sensor, the system will use the pressure sensor as the target sensor for attention, using the data from the pressure sensor to understand the context of the bioelectric activity or adjust the way the bioelectric data is interpreted.

[0099] Preset relationship definition: During the system design phase, preset cross-attention relationships between different types of sensors are defined based on professional knowledge or experimental data.

[0100] Sensor configuration check: For each type of sensor on each massage component, check whether there are other types of sensors configured on the same massage component and satisfying the preset cross-attention relationship.

[0101] Target sensor selection: If there is a sensor that meets the conditions, it will be selected as the current sensor's attention target sensor.

[0102] Relationship Recording: Record the relationship between each sensor and its attention target sensor for use in subsequent cross-attention processes.

[0103] In this way, the preset cross-attention relationship can be used to more intelligently select the attention target sensor, thereby capturing and utilizing the correlation between different types of sensor data during the cross-attention process. This helps to improve the accuracy and effectiveness of massage parameter settings.

[0104] Optionally, in step S123, taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor, comprises:

[0105] In step S1231, according to the change amount of the massage feedback data corresponding to each type of the sensor on each massage component and the change amount of the massage feedback data of the corresponding attention target sensor, a mean value of the change amount is calculated;

[0106] Among them, the mean of the change refers to the average value of the change in massage feedback data of a certain type of sensor and its corresponding attention target sensor in continuous sampling, which is used to measure the consistency of the change trends of the two.

[0107] In the disclosed embodiment, the mean value of the change in massage feedback data between each type of sensor on each massage component and its attention target sensor is calculated. This mean value reflects the average consistency of data changes between the two during the massage process, which is the basis for subsequent cross-attention calculation.

[0108] For example: suppose a massage component has a pressure sensor and a temperature sensor as its attention target sensor. In two consecutive samplings, the data of the pressure sensor increases from 50kPa to 55kPa, a change of 5kPa; the data of the temperature sensor increases from 32°C to 33°C, and the change is also 1°C (assuming that it is standardized or converted to an order of magnitude comparable to the pressure change in some way). Then, the average of the changes of these two sensors is (5kPa + 1°C equivalent value) / 2. It should be noted that since the data units of different sensors may be different, the data may need to be standardized or converted in actual calculations.

[0109] In step S1232, the massage feedback data of each type of the sensor on each massage component is used as a query, and the mean of the corresponding change amount is used as a key to perform a dot product operation to obtain the attention score of each type of the sensor on each massage component;

[0110] In the disclosed embodiment, the massage feedback data of each type of sensor on each massage component is used as a query, and the mean value of its change is used as a key to perform a dot product operation. The result of this operation is an attention score, which reflects the degree of correlation between the sensor data and its mean value of change. The higher the attention score, the stronger the correlation between the sensor data and its mean value of change.

[0111] For example: Continuing with the above example, assume that we have calculated the mean of the pressure sensor and temperature sensor changes. Now, we perform a dot product operation on the massage feedback data of the pressure sensor (e.g., a vector containing multiple sampling points) and the mean of its changes to obtain an attention score. Similarly, we can also perform the same operation on the temperature sensor data.

[0112] In step S1233, the attention score corresponding to each type of the sensor on each massage component is scaled by taking the square root of the dimension of the mean value of the variation as a scaling factor to obtain a corrected scaling score;

[0113] In the disclosed embodiment, the square root of the dimension of the mean value of the variation is used as a scaling factor to scale the attention score of each type of sensor on each massage component. This scaling operation is to eliminate the influence of different sensor data dimensions on the attention score, so that the attention scores between different sensors are comparable.

[0114] For example: Assume that we have obtained the attention scores of the pressure sensor and the temperature sensor. Now, we will scale these scores using the square root of the dimension of the mean of their respective changes as the scaling factor. In this way, we get the corrected scaled scores, which more accurately reflect the correlation between the sensor data and its mean of change.

[0115] In step S1234, the cross-attention massage data of the sensor is determined according to the correction scaling scores corresponding to the multiple types of sensors on each of the massage components.

[0116] In the disclosed embodiment, the cross-attention massage data of the sensor is comprehensively determined according to the correction scaling scores of multiple types of sensors on each massage component. This data is obtained by weighted averaging or other suitable aggregation operations on the correction scaling scores of different sensors, which reflects the comprehensive impact of different sensor data on the final massage parameter setting under the cross-attention mechanism.

[0117] For example: Assume that we have obtained the corrected scaled scores of the pressure sensor, temperature sensor, and bioelectric sensor. Now, we will use these scores as weights to perform weighted average or other suitable aggregation operations on their respective massage feedback data to obtain the final cross-attention massage data. This data will be used to guide the subsequent operations or parameter adjustments of the massage components.

[0118] Optionally, in step S13, the first target massage parameter of each massage component is corrected according to the first target massage parameters of the plurality of massage components adjacent to each massage component to obtain the second target massage parameter of each massage component, including:

[0119] In step S131, the average value and variance between the first target massage parameters of the plurality of massage components adjacent to each massage component and the first target massage parameter of the massage component are calculated;

[0120] In the disclosed embodiment, the mean and variance of the first target massage parameters of each massage component and its adjacent massage components are calculated. The mean reflects the average level of the target massage parameters of the adjacent massage components, while the variance reflects the degree of dispersion of these parameters. This information will be used to determine the Gaussian distribution parameters in the subsequent steps.

[0121] For example: suppose there is a massage component A, and its adjacent massage components are B and C. The first target massage parameters of massage components A, B and C are X_A, X_B and X_C respectively. Then, the system first calculates the average value ((X_A +X_B + X_C) / 3) and variance ([(X_A - average value)^2 + (X_B - average value)^2 + (X_C - average value)^2] / 3) of these three parameters.

[0122] In step S132, according to the mean value and the variance corresponding to each massage component, and the first target massage parameters of a plurality of massage components adjacent to the massage component and the first target massage parameter of the massage component, the Gaussian distribution parameter of the massage component is determined;

[0123] In the disclosed embodiments, Gaussian distribution is a continuous probability distribution, also known as normal distribution, whose shape is determined by two parameters: mean (μ) and standard deviation (σ). Mean (μ): The center point of the Gaussian distribution, i.e., the location of the maximum value of the probability density function. Standard deviation (σ): A parameter that describes the width of the data distribution. The larger the standard deviation, the more dispersed the data distribution.

[0124] In the disclosed embodiment, the Gaussian distribution parameters (mean and standard deviation) of each massage component are determined by using the mean and variance of the first target massage parameters of each massage component and its adjacent massage components, as well as these parameters themselves. This Gaussian distribution reflects the distribution of the target massage parameters of the adjacent massage components.

[0125] Continuing with the above example, the system can use the calculated average as the mean (μ) of the Gaussian distribution, and the square root of the variance as the standard deviation (σ). In this way, the Gaussian distribution parameters of massage component A can be expressed as N(μ, σ^2), where μ is the average of X_A, X_B, and X_C, and σ is the square root of the variance.

[0126] In step S133, from the Gaussian distribution parameters corresponding to each of the massage components, a Gaussian distribution parameter within the preset variance range of the mean is taken as a target parameter, and the first target massage parameter corresponding to the target parameter and the first target massage parameter of the massage component are averaged to correct the first target massage parameter of the corresponding massage component to obtain the second target massage parameter of each of the massage components.

[0127] In the disclosed embodiment, from the Gaussian distribution parameters corresponding to each massage component, a Gaussian distribution parameter within a preset variance range of the mean is selected as the target parameter. Then, the first target massage parameter corresponding to these target parameters is averaged with the first target massage parameter of the massage component to correct the first target massage parameter of the massage component. This process takes into account the distribution characteristics of the target massage parameters of adjacent massage components, so that the corrected second target massage parameter is more reasonable and consistent.

[0128] For example: Assume that a preset variance range is set (for example, mean ± one standard deviation). Then, for massage component A, the system will check whether the Gaussian distribution parameters of its adjacent massage components B and C fall within the preset variance range. If they fall within the range, the first target massage parameters corresponding to these parameters (X_B and X_C, if their Gaussian distribution parameters meet the conditions) and X_A are averaged to obtain the modified second target massage parameters. If the Gaussian distribution parameters of B and C do not meet the conditions, other factors or strategies may need to be considered to determine the second target massage parameters.

[0129] Optionally, the second target massage parameter includes at least one of the following: a massage intensity parameter, a massage speed parameter, a massage heating temperature parameter, and a massage humidification parameter.

[0130] The massage force parameter refers to the amount of force or intensity used by the massage device when applying massage movements. This parameter can usually be adjusted according to the user's preferences and needs to suit different massage needs and body parts. For example, a higher massage force may be required for muscle areas that require deep relaxation, while a lower massage force may be required for more sensitive or delicate body parts.

[0131] The massage speed parameter refers to the speed of the massage device when performing massage movements. This parameter can also be adjusted according to the user's preferences and massage needs. A faster massage speed may be more suitable for situations where you need to quickly relieve muscle tension or promote blood circulation; while a slower massage speed may be more suitable for users who need to relax and enjoy a soothing massage experience.

[0132] The massage heating temperature parameter refers to the temperature reached by the heating element of the massage device when providing massage services. The setting of this parameter is crucial to providing a comfortable massage experience. The appropriate heating temperature can help relax muscles, promote blood circulation, and enhance the massage effect. However, too high a temperature may cause discomfort or skin burns to the user, so it needs to be set reasonably according to the user's heat tolerance and massage needs.

[0133] The massage humidification parameter refers to the humidity level achieved by the humidification function of the massage equipment when providing massage services. This parameter is more common in some high-end massage equipment. Especially in areas or seasons with dry climates, proper humidification can help maintain the moisture balance of the skin and reduce skin discomfort caused by dryness. At the same time, humidification can also be combined with massage movements to provide a more comfortable and relaxing massage experience.

[0134] Optionally, the wearable massager includes any one of the following: a head massager, a neck massager, a lumbar massager.

[0135] The present disclosure also provides an intelligent control device for a wearable massager, see Figure 2 As shown, including:

[0136] An acquisition module 210 is configured to acquire massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager in response to a massage operation of the wearable massager;

[0137] The determination module 220 is configured to determine, according to the massage feedback data collected by the multiple types of sensors on each of the massage components, a first target massage parameter of the sensor by cross-paying attention to the massage feedback data of the sensor and taking other types of sensors configured on the massage component where the sensor is located as the attention target sensor for each type of the sensor on each of the massage components;

[0138] The correction module 230 is configured to correct the first target massage parameter of the sensor on each massage component according to the first target massage parameter corresponding to the sensor of the same type on the adjacent massage components of each massage component, so as to obtain a second target massage parameter of the sensor on each massage component;

[0139] The control module 240 is configured to determine the target control parameter of the massage component corresponding to the wearable massager according to the second target massage parameter of the sensor on each massage component, and control each massage component to perform massage according to the target control parameter.

[0140] Optionally, the determining module 220 is configured to:

[0141] According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend and a change amount of the massage feedback data collected by each sensor twice adjacently;

[0142] For each type of sensor on each massage component, determine a target sensor of attention from other types of sensors configured on the massage component where the sensor is located;

[0143] Taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor;

[0144] The first target massage parameter of each massage component is determined according to the cross-attention massage data of each type of the sensor on each massage component.

[0145] Optionally, the determining module 220 is configured to:

[0146] According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend of the massage feedback data collected by each sensor twice adjacently;

[0147] For each type of the sensor on each of the massage components, a sensor having the same change trend as other types of sensors configured on the massage component where the sensor is located is used as an attention target sensor.

[0148] Optionally, the determining module 220 is configured to:

[0149] For each type of sensor on each massage component, other types of sensors that are configured on the same massage component as the sensor and satisfy a preset cross-attention relationship are used as attention target sensors;

[0150] Among them, the preset cross-attention relationship of the pressure sensor is: the temperature sensor is used as the attention target sensor; the preset cross-attention relationship of the temperature sensor is: the bioelectric sensor is used as the attention target sensor; the preset cross-attention relationship of the bioelectric sensor is: the pressure sensor is used as the attention target sensor.

[0151] Optionally, the determining module 220 is configured to:

[0152] Calculating a mean value of the change amount according to the change amount of the massage feedback data corresponding to each type of the sensor on each massage component and the change amount of the massage feedback data of the corresponding attention target sensor;

[0153] Taking the massage feedback data of each type of the sensor on each massage component as a query, performing a dot product operation with the mean of the corresponding change amount as a key, and obtaining an attention score of each type of the sensor on each massage component;

[0154] Using the square root of the dimension of the mean of the variation as a scaling factor, scaling the attention score corresponding to each type of the sensor on each massage component to obtain a corrected scaling score;

[0155] The cross-attention massage data of the sensor is determined according to the correction scaling scores corresponding to the multiple types of the sensors on each of the massage components.

[0156] Optionally, the correction module 230 is configured to:

[0157] Calculating an average value and a variance between the first target massage parameters of a plurality of massage components adjacent to each massage component and the first target massage parameter of the massage component;

[0158] Determine the Gaussian distribution parameter of the massage component according to the mean value and the variance corresponding to each massage component, the first target massage parameters of a plurality of massage components adjacent to the massage component, and the first target massage parameter of the massage component;

[0159] From the Gaussian distribution parameters corresponding to each of the massage components, a Gaussian distribution parameter within the preset variance range of the mean is taken as a target parameter, and the first target massage parameter corresponding to the target parameter and the first target massage parameter of the massage component are averaged to correct the first target massage parameter of the corresponding massage component to obtain the second target massage parameter of each of the massage components.

[0160] Optionally, the second target massage parameter includes at least one of the following: a massage intensity parameter, a massage speed parameter, a massage heating temperature parameter, and a massage humidification parameter.

[0161] Optionally, the wearable massager includes any one of the following: a head massager, a neck massager, a lumbar massager.

[0162] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in any one of the aforementioned embodiments are implemented.

[0163] The present disclosure also provides an electronic device, including:

[0164] a memory having a computer program stored thereon;

[0165] A processor is used to execute the computer program in the memory to implement the steps of the method in any one of the aforementioned embodiments.

[0166] Figure 3 The intelligent control device 100 of the wearable massager shown includes: a processor 1001 and a memory 1003. The processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the intelligent control device 100 of the wearable massager may also include a communication component 1004, which may be used for data interaction between the device 100 and other devices, such as data transmission and / or data reception. It should be noted that in actual scheduling, the communication component 1004 is not limited to one, and the structure of the intelligent control device 100 of the wearable massager does not constitute a limitation on the embodiments of the present application.

[0167] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0168] The bus 1002 may include a path to transmit information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0169] The memory 1003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, without limitation herein.

[0170] The memory 1003 is used to store program codes for executing the embodiments of the present disclosure, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the program codes stored in the memory 1003 to implement the steps shown in the embodiment of the intelligent control method of the wearable massager.

[0171] The embodiment of the present disclosure also provides a computer-readable storage medium, on which program codes are stored. When the program codes are executed by a processor, the steps and corresponding contents of the embodiment of the intelligent control method of the aforementioned wearable massager can be implemented.

[0172] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments; within the technical concept of the present disclosure, various changes, modifications, substitutions and variations may be made to these embodiments, and these changes, modifications, substitutions and variations all fall within the protection scope of the present disclosure.

[0173] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction, and they should also be regarded as the contents disclosed in this disclosure. In order to avoid unnecessary repetition, this disclosure will not further describe various possible combinations. The technical scope of this application is not limited to the contents in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An intelligent control method for a wearable massager, characterized in that: The method comprises: In response to a massage operation of the wearable massager, massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager are obtained; According to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, the other types of sensors configured on the massage component where the sensor is located are used as attention target sensors, and the massage feedback data of the attention target sensors are cross-attended to determine the first target massage parameter of each massage component by cross-paying attention to the massage feedback data of the sensor; According to the first target massage parameters of the plurality of massage components adjacent to each massage component, the first target massage parameter of each massage component is corrected to obtain a second target massage parameter of each massage component; Controlling each of the massage components to perform massage according to the second target massage parameter of each of the massage components; Wherein, according to the massage feedback data collected by the multiple types of sensors on each massage component, for each type of sensor on each massage component, the other types of sensors configured on the massage component where the sensor is located are used as attention target sensors, and the massage feedback data of the attention target sensor is cross-attended to determine the first target massage parameter of each massage component by cross-paying attention to the massage feedback data of the sensor, including: According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend and a change amount of the massage feedback data collected by each sensor twice adjacently; For each type of sensor on each massage component, determine a target sensor of attention from other types of sensors configured on the massage component where the sensor is located; Taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor; The first target massage parameter of each massage component is determined according to the cross-attention massage data of each type of the sensor on each massage component.

2. The intelligent control method of the wearable massager according to claim 1, characterized in that: For each type of sensor on each massage component, determining the attention target sensor from other types of sensors configured on the massage component where the sensor is located includes: According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend of the massage feedback data collected by each sensor twice adjacently; For each type of the sensor on each of the massage components, a sensor having the same change trend as other types of sensors configured on the massage component where the sensor is located is used as an attention target sensor.

3. The intelligent control method of the wearable massager according to claim 1, characterized in that: For each type of sensor on each massage component, determining the attention target sensor from other types of sensors configured on the massage component where the sensor is located includes: For each type of sensor on each massage component, other types of sensors that are configured on the same massage component as the sensor and satisfy a preset cross-attention relationship are used as attention target sensors; Among them, the preset cross-attention relationship of the pressure sensor is: the temperature sensor is used as the attention target sensor; the preset cross-attention relationship of the temperature sensor is: the bioelectric sensor is used as the attention target sensor; the preset cross-attention relationship of the bioelectric sensor is: the pressure sensor is used as the attention target sensor.

4. The intelligent control method of the wearable massager according to claim 1, characterized in that: The method of taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor includes: Calculating a mean value of the change amount according to the change amount of the massage feedback data corresponding to each type of the sensor on each massage component and the change amount of the massage feedback data of the corresponding attention target sensor; Taking the massage feedback data of each type of the sensor on each massage component as a query, performing a dot product operation with the mean of the corresponding change amount as a key, and obtaining an attention score of each type of the sensor on each massage component; Using the square root of the dimension of the mean of the variation as a scaling factor, scaling the attention score corresponding to each type of the sensor on each massage component to obtain a corrected scaling score; The cross-attention massage data of the sensor is determined according to the corrected scaling scores corresponding to the multiple types of the sensors on each of the massage components.

5. The intelligent control method of the wearable massager according to claim 1, characterized in that: The method of correcting the first target massage parameter of each massage component according to the first target massage parameters of the plurality of massage components adjacent to each massage component to obtain the second target massage parameter of each massage component comprises: Calculating an average value and a variance between the first target massage parameters of a plurality of adjacent massage components of each massage component and the first target massage parameter of the massage component; Determine the Gaussian distribution parameter of the massage component according to the mean value and the variance corresponding to each massage component, the first target massage parameters of a plurality of massage components adjacent to the massage component, and the first target massage parameter of the massage component; From the Gaussian distribution parameters corresponding to each of the massage components, a Gaussian distribution parameter within the preset variance range of the mean is taken as a target parameter, and the first target massage parameter corresponding to the target parameter and the first target massage parameter of the massage component are averaged to correct the first target massage parameter of the corresponding massage component to obtain the second target massage parameter of each of the massage components.

6. The intelligent control method of the wearable massager according to any one of claims 1 to 5, characterized in that: The second target massage parameter includes at least one of the following: a massage intensity parameter, a massage speed parameter, a massage heating temperature parameter, and a massage humidification parameter.

7. The intelligent control method of a wearable massager according to any one of claims 1 to 5, characterized in that: The wearable massager includes any one of the following: a head massager, a neck massager, and a lumbar massager.

8. An intelligent control device for a wearable massager, characterized in that: include: an acquisition module, configured to acquire massage feedback data collected by multiple types of sensors on multiple massage components for massage included in the wearable massager in response to a massage operation of the wearable massager; a determination module configured to determine, according to the massage feedback data collected by the multiple types of sensors on each of the massage components, a first target massage parameter of the sensor by cross-paying attention to the massage feedback data of the sensor and taking other types of sensors configured on the massage component where the sensor is located as the attention target sensor for each type of the sensor on each of the massage components; a correction module, configured to correct the first target massage parameter of the sensor on each massage component according to the first target massage parameter corresponding to the sensor of the same type on the adjacent massage components of each massage component, so as to obtain a second target massage parameter of the sensor on each massage component; a control module configured to determine a target control parameter of the massage component corresponding to the wearable massager according to the second target massage parameter of the sensor on each massage component, and control each massage component to perform massage according to the target control parameter; Wherein, the determination module is configured as follows: According to the massage feedback data collected by the multiple types of sensors on each massage component, determining a change trend and a change amount of the massage feedback data collected by each sensor twice adjacently; For each type of sensor on each massage component, determine a target sensor of attention from other types of sensors configured on the massage component where the sensor is located; Taking the massage feedback data of each type of the sensor on each massage component as a query, determining a key for cross-attention according to the change amount of the corresponding massage feedback data and the change amount of the massage feedback data of the corresponding attention target sensor, and determining the cross-attention massage data of the sensor; The first target massage parameter of each massage component is determined according to the cross-attention massage data of each type of the sensor on each massage component.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images