Personal care device characteristic prediction

Abstract

Schemes, solutions, concepts, designs, methods, and systems are presented relating to predicting characteristics of a personal care device that vibrates due to an actuator in use. In particular, the actuator is controlled such that an amplitude and / or duty cycle of vibration of the actuator causes varying vibration of the personal care device. As the vibration of the personal care device varies, a data set describing operating parameters of the personal care device is obtained. The dataset may include features that describe characteristics of the personal care device (e.g., a condition, type or assembly status of replaceable components of the personal care device, a user or user type of the personal care device, etc. Accordingly, the data set is processed to determine a predicted characteristic.

Description

Technical Field

[0001] This invention relates to predicting the characteristics of personal care devices. Background Technology

[0002] Identifying certain characteristics of personal care devices (e.g., toothbrushes, electric shavers, skin scrubbers, etc.) may be important for improving the effectiveness, safety, and user experience of these devices.

[0003] For example, understanding the condition, type, or assembly status of replaceable parts of a personal care device (e.g., brush heads, shaving heads, etc.) allows for appropriate adjustment of motor settings. Furthermore, identifying the user or user type of the personal care device can also be used to appropriately adjust motor settings to take the user's habits into account.

[0004] This characteristic information can also be used to provide feedback to users of personal care devices. For example, if it is determined that a component in a replaceable part is incorrectly assembled or damaged, it can be indicated to the user so that they can take corrective action. Furthermore, if the user is identified, the information collected by the personal care device can be stored for future reference by the appropriate user.

[0005] Therefore, there is a need for a device for automatically predicting the characteristics of personal care devices. Summary of the Invention

[0006] According to an example of one aspect of the invention, a method for predicting characteristics of a personal care device is provided. The personal care device includes an actuator that vibrates the personal care device during use. The method includes:

[0007] The actuator is controlled to induce varying vibrations in the personal care device by changing the amplitude and / or duty cycle of the actuator's vibration.

[0008] In response to the control actuator, a dataset describing the operating parameters of the personal care device during vibration of the personal care device is obtained; and

[0009] Process at least a portion of the dataset to determine predictive characteristics of personal care devices.

[0010] A method for predicting the characteristics of personal care devices due to actuator vibration during use is proposed. Specifically, the actuator is controlled such that the amplitude and / or duty cycle of the actuator's vibration causes changes in the vibration of the personal care device. As the vibration of the personal care device changes, a dataset describing the operating parameters of the personal care device is obtained. Therefore, the dataset includes features describing the characteristics of the personal care device (e.g., the condition, type, or assembly state of replaceable parts of the personal care device, the user of the personal care device, or the user type, etc.). The dataset is then processed to predict the characteristics of the personal care device.

[0011] Personal care devices include actuators that cause the personal care device to vibrate during use. An actuator can be a component of the personal care device configured to affect the functions of the personal care device (e.g., an electric motor driving the movement of the brush head of a toothbrush), or it can simply be a component configured to perform a different function but incidentally cause vibration of the personal care device. That is, an actuator can be any component that affects mechanical movement during use, thereby causing vibration of the personal care device.

[0012] Furthermore, the dataset is obtained in response to the vibration of the personal care device. In other words, the dataset is acquired / obtained / generated when the personal care device vibrates due to the controlled movement of the actuator. Therefore, features indicative of the vibration response of the personal care device can exist in the dataset.

[0013] The dataset for personal care devices describes the operating parameters of the personal care device during vibration. Specifically, the dataset contains values ​​indicating the system vibration response of the personal care device, measured in terms of, for example, acceleration (in one or more dimensions), motor current, and sound / noise, while the device is in operating mode (i.e., when the actuator is moving and thus causing vibration of the personal care device). The vibration response included in the dataset reflects the characteristics of the personal care device, as changes in certain characteristics of the personal care device will lead to changes in the vibration response of the personal care device (in response to the movement of the actuator).

[0014] In contrast to vibration scans caused by actuators operating in modes or ranges outside of typical operating conditions, this invention modifies the amplitude and / or duty cycle of the actuator's vibrations (i.e., performs an amplitude scan). By acquiring a dataset during the amplitude scan, additional unique vibration response-related features can be present in the dataset, which can be detected / identified for predicting the characteristics of personal care devices. In other words, as an alternative to frequency vibration scans outside the normal operating range of the actuator, amplitude and / or duty cycle scans are used (by inducing a changed vibration response) to further enhance the features present in the dataset.

[0015] In other words, the actuator is controlled to change the amplitude and / or duty cycle of the actuator's movement that causes the personal care device to vibrate. A dataset is acquired in response to the change in amplitude and / or duty cycle, allowing additional or enhanced features to exist in the dataset that can be used to predict the characteristics of the personal care device. As a result, improved characteristic prediction can be achieved compared to the case where the actuator simply moves with a single given amplitude and / or duty cycle.

[0016] For clarity, personal care devices can be, for example, electric toothbrushes / mouthpieces, electric shavers, or skin scrubbers. Of course, the invention can be applied to a variety of other personal care devices configured to provide personal care functions for the user. Personal care devices can be handheld and / or portable.

[0017] In some embodiments, the actuator can be controlled to vibrate at an operating frequency scheme while varying the amplitude and / or duty cycle of the vibration.

[0018] In other words, actuator vibration is controlled according to an operating frequency scheme (one or more normal / typical frequencies operated by the personal care device).

[0019] Operation frequency schemes can be based on the frequency of personal care operation modes.

[0020] The personal care operating mode frequency scheme can correspond to the normal use of a personal care device (e.g., a single operating setting of the actuator of an electric toothbrush). This may mean that the user is unlikely to notice when the dataset is collected, and it may be collected during typical use of the personal care device. Essentially, this means that the actuator does not need to be controlled in a specific way (e.g., vibration scanning) to cause vibration of the personal care device in order to capture the dataset. In other words, the actuator is only controlled to change the amplitude and / or duty cycle at its normal operating frequency. Therefore, the present invention provides for acquiring datasets without operating the actuator outside of normal operating conditions, settings, and / or ranges.

[0021] The characteristics of personal care devices may include the predicted condition of the replaceable parts of the personal care device, the predicted type of the replaceable parts of the personal care device, the predicted assembly state of the replaceable parts of the personal care device, the predicted user of the personal care device, and / or the predicted user type of the personal care device.

[0022] Replaceable parts can be any component of a personal care device, the assembly, condition, and type of which affect the operation of the personal care device. For example, a replaceable part can be a brush head, shaving head, or any other part or component that may come into contact with a user's surface.

[0023] The predicted condition can indicate the level of degradation of the replaceable part relative to the new condition. In other words, the predicted condition reflects the amount of wear on the replaceable part.

[0024] The predicted type of replaceable parts can indicate the construction, model, version, brand, or type of replaceable parts for personal care devices.

[0025] Predicted assembly status can indicate whether replaceable parts are assembled / mechanically connected to the personal care device. In some cases, predicted assembly status can indicate whether replaceable components are correctly assembled and to what extent.

[0026] The predicted users can be specific individual users or predicted user types (i.e., user classifications).

[0027] Each of the aforementioned features can be used to notify users of changes to the operating settings of a personal care device and / or to provide additional information to users of the personal care device to improve the user experience. Of course, other features can also be predicted using the disclosed methods, as will be apparent to those skilled in the art.

[0028] The dataset may include accelerometer data describing acceleration on at least one axis of a personal care device.

[0029] It has been shown that datasets including accelerometer data in only one dimension / one axis (obtained during variations in amplitude and / or duty cycle within the operating range) are sufficient to facilitate the prediction of personal care device characteristics. This can be relatively simple to generate, and the hardware for generating such data exists in many existing personal care devices. Furthermore, many personal care devices include inertial motion units (IMUs) that capture three-dimensional acceleration data, which potentially further improves the accuracy of predictions.

[0030] When accelerometer data describes 3-axis acceleration, the method may further include calculating norm vector data describing the absolute vector length of the acceleration based on the accelerometer data; and serializing the accelerometer data and norm vector data for each of the 3 axes into a single data segment.

[0031] Alternatively or additionally, the dataset may include sound data that describes the sounds produced by a personal care device.

[0032] It has been shown that sound / noise / audio data provides sufficient information about the vibration of personal care devices to facilitate characteristic prediction.

[0033] Alternatively or additionally, the dataset may include current data describing the motor current of the actuator.

[0034] Similarly, the current data is shown to provide sufficient information about the vibration of the personal care device to facilitate characteristic prediction. Current data can be obtained from the motor itself or via, for example, a battery connected to the motor. The motor can be a component that influences the movement of an actuator, thereby causing vibration in the personal care device.

[0035] Specifically, the obtained dataset may include values ​​describing the operating parameters of personal care devices, with a range of up to one second.

[0036] In other words, the dataset includes values ​​spanning up to one second, or signals lasting one second. By limiting the time span of the dataset, processing and analysis can be simplified. Of course, the dataset can span more or less time, but approximately one second allows for accurate prediction of characteristics while maintaining reasonable complexity.

[0037] The obtained dataset may include values ​​describing operating parameters of a personal care device sampled at a rate of at least 800 Hz. In some embodiments, the obtained dataset may include values ​​describing operating parameters of a personal care device sampled at a rate of at least 1.6 kHz.

[0038] Sampling the operating parameters at a rate of at least 800 Hz is beneficial to ensure that the unique characteristics of the personal care device's vibration are present in the dataset. 1.6 kHz may be preferred to ensure that no unique features are missed, although the complexity increases with the size of the dataset.

[0039] This method may also include at least a normalized portion of the dataset. Therefore, when predicting the characteristics of personal care devices, variations in the dataset due to, for example, differences between personal care devices (materials, shapes, conditions, etc.) or the preservation of the usage context of the personal care devices (e.g., location, environment, etc.) when the dataset was acquired can be taken into account. This can lead to more accurate predictions of personal care devices.

[0040] In response to the personal care device being in a static state or in an operational state, a dataset describing the operating parameters is obtained.

[0041] A static state can be any state in which a personal care device is not moved or vibrated by an external device (e.g., due to user movement). For example, a static state could correspond to when the personal care device is charging or idle in the user's hand. This ensures that the vibration response of the personal care device to the movement of the actuator depends only on the personal care device itself. Therefore, this can be advantageous when the characteristics predicted from the dataset are only related to the personal care device and / or replacement parts themselves, as the impact of external influences (e.g., the user moving the personal care device) can be minimized.

[0042] The operational usage state can be any state in which the personal care device is being manipulated by a user (e.g., when using the device to perform a personal care routine). In this way, the vibration response of the personal care device will be influenced by the user and will therefore vary with different users and user types. Therefore, this embodiment may be preferred when the characteristic to be predicted is an external characteristic, such as the user and / or user type. Of course, other characteristics of the personal care device can be predicted in this state, but additional processing of the dataset may be required.

[0043] Processing the dataset may include processing at least a portion of the dataset with a feature classification machine learning algorithm to determine predictive features of personal care devices.

[0044] Feature-based machine learning algorithms can be AI-based algorithms that are adapted to receive a dataset and output predictions related to the characteristics of a personal care device. Therefore, a feature-based machine learning algorithm can identify features within a dataset that indicate a particular characteristic of a personal care device and output predictions based on those identified features.

[0045] In some examples, the method may also include generating a spectrogram image based on at least a portion of the dataset; and processing the spectrogram image using a feature classification machine learning algorithm to determine predictive features of the personal care device.

[0046] Generate a spectral image from (at least a portion of) the dataset. That is, process the dataset using known methods to generate the spectral image. For example, the Fast Fourier Transform (FFT) can be used to process the dataset to generate the spectral image. The spectral image contains multiple FFTs, each corresponding to a time point. Each FFT represents the frequency intensity of the vibration response of the personal care device at the time point captured by the dataset.

[0047] Subsequently, the spectral image is fed to a feature classification machine learning algorithm. This algorithm processes the spectral image and can identify various features that indicate the characteristics of a personal care device. Therefore, predictive features can be provided.

[0048] In some embodiments, the feature classification machine learning algorithm can be a spectral image classifier. A spectral image classifier classifies features in an image into different categories based on the spectral features of those features. Therefore, this algorithm is well-suited for processing / analyzing spectral images. More specifically, the feature classification machine learning algorithm can be a CNN classifier or an FCNN classifier.

[0049] Furthermore, feature classification machine learning algorithms can be CNN classifiers comprising 3 to 6 convolutional layers. Fewer convolutional layers in a CNN result in lower computational complexity and require less memory and processing resources. However, they also become less powerful. 3 to 6 convolutional layers offer a balance between the size and power of the CNN classifier.

[0050] According to another aspect of the present invention, a computer program including computer program code means is provided, wherein when the computer program is run on a computer, the computer program code means are adapted to implement the method of the proposed embodiment.

[0051] According to another aspect of the present invention, a personal care device is provided, comprising:

[0052] The actuator is configured to vibrate the personal care device during use;

[0053] The controller is configured to control the actuator by changing the amplitude and / or duty cycle of the actuator's vibration to cause varying vibrations in the personal care device;

[0054] Sensors are configured to acquire a dataset describing operating parameters of the personal care device during vibration of the personal care device in response to a control actuator; and

[0055] The processor is configured to process at least a portion of the dataset to determine predictive characteristics of personal care devices.

[0056] These and other aspects of the invention will become apparent from the embodiments described below. Attached Figure Description

[0057] To better understand the invention and to more clearly illustrate how to implement it, reference will now be made to the accompanying drawings by way of example only, in which:

[0058] Figure 1 A flowchart of a method for predicting the characteristics of a personal care device according to one embodiment is shown;

[0059] Figure 2 It is a personal care device according to an example embodiment;

[0060] Figure 3 A simplified block diagram of a computer in which one or more portions of an embodiment may be employed is provided. Detailed Implementation

[0061] The invention will be described with reference to the accompanying drawings.

[0062] It should be understood that the accompanying drawings are merely schematic and not drawn to scale. It should also be understood that the same reference numerals are used in all the accompanying drawings to denote the same or similar parts.

[0063] It should also be understood that while the detailed description and specific examples indicate exemplary embodiments of the apparatus, system, and method, they are intended for illustrative purposes only and not to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, system, and method of the present invention will become more readily apparent from the following description, the appended claims, and the drawings. The fact that certain measures are recited in mutually different dependent claims does not imply that combinations of these measures cannot be advantageously used.

[0064] Schemes, solutions, concepts, designs, methods, and systems for predicting the characteristics of vibrations in personal care devices during use due to actuators are proposed. Specifically, the actuator is controlled such that the amplitude and / or duty cycle of the actuator's vibration causes changes in the vibration of the personal care device. As the vibration of the personal care device changes, a dataset describing the operating parameters of the personal care device is obtained. This dataset may include features describing the characteristics of the personal care device (e.g., the condition, type, or assembly state of replaceable parts of the personal care device, the user of the personal care device, or the user type, etc.). Therefore, the dataset is processed to determine the predicted characteristics.

[0065] The disclosed embodiments provide a method for evaluating personal care devices based on vibration-related operating parameters, such as a dataset describing operating parameters obtained from a microphone, accelerometer, load sensor, actuator motor current sensor, or sensor for the current of a battery connected to the actuator. The dataset is enhanced by controlling the actuator of the personal care device to move with varying amplitude and / or duty cycle during data capture (i.e., by performing amplitude and / or duty cycle scans). Therefore, more and / or enhanced features indicative of the characteristics of the personal care device may exist in the dataset. The dataset is then processed to determine predicted characteristics (e.g., the condition, type, or assembly state of replaceable parts of the personal care device, the user or user type of the personal care device, etc.).

[0066] Differences in predictive characteristics lead to differences in the vibration response of personal care devices to actuator movement. These differences in vibration response may depend on (i.e., may amplify or diminish) the amplitude and / or duty cycle of actuator movement. Therefore, by varying the amplitude and / or duty cycle, additional and improved characteristics can be presented in the dataset, facilitating the refinement of the determination of predictive characteristics for personal care devices.

[0067] Furthermore, the disclosed embodiments can also be implemented using existing personal care device hardware, thus eliminating the need for expensive and complex additional components and sensors. In other words, no additional sensors (e.g., NFC sensors) are required to implement the invention. This is because the invention relies on operating parameter signals that maintain vibration response information, which may already be generated by sensors already implemented in personal care devices for various other functions. For example, the solution could utilize signals from a 3-axis or 1-axis accelerometer, the current from the actuator's motor, microphone or load sensor signals—many of which are typically present in personal care devices.

[0068] Furthermore, actuators present in many personal care devices can be controlled to have varying amplitudes and / or duty cycles. In practice, this method can be executed when the actuator moves at a given frequency. Such a frequency can be the same as the frequency at which the actuator moves during normal / typical operation of the personal care device. Therefore, not only is additional hardware unnecessary, but the user is unlikely to notice the actuator operating in this manner (because the disclosed method does not require frequency scanning or operation of the actuator at unusual frequencies).

[0069] By effectively predicting the characteristics of personal care devices, the user experience can be improved. In fact, characteristic prediction can be used to adjust the operation of personal care devices to improve personal care actions, prevent potential malfunctions, and / or improve the safety of personal care devices. Furthermore, in the case of medical personal care devices, this information can help prevent unsafe situations and provide traceable evidence when needed.

[0070] Taking a toothbrush as an example, the disclosed embodiments can be implemented in existing hardware. This is true even when an inertial motion unit (IMU) sensor is absent, because the invention is capable of working with many vibration-related operating parameters, such as motor current, sound / noise signals, or load sensor signals. Some embodiments specify capturing and processing operating parameter values ​​for ~1 second to provide predictions of personal care device characteristics. Therefore, due to limited memory and processing requirements, the disclosed embodiments can be implemented as new software installed on existing devices.

[0071] However, it is worth noting that the present invention can be implemented in a wide variety of personal care devices (and replaceable parts). For example, the characteristics of shaving devices (including shaving heads) or skin scrubbers (including scrubbing heads) can be evaluated. Therefore, it is worth noting that while toothbrushes (including brush heads) may particularly benefit from the present invention, it can also provide advantages for many other personal care devices.

[0072] Furthermore, methods for predicting the characteristics of personal care devices can be implemented in the handle of the personal care device, on an external processor, or even in the cloud or on an edge processing system.

[0073] The dataset used to predict the characteristics of replaceable parts describes the operating parameters of personal care devices (as the personal care device vibrates in response to the movement of the actuator, and is controlled by changing the amplitude and / or duty cycle of the vibration). Available operating parameters relate to the vibrational response of the personal care device to the movement of the actuator, such as acceleration (in one or more dimensions), sound / noise, load, and motor / system current.

[0074] In some embodiments, the dataset is obtained in response to the personal care device being in a static state. For example, a static state could be when the personal care device is charging, indicating that the device is at a charging station, or simply being static. A static state could also be when a user is manipulating the personal care device but not applying any load to it (e.g., holding a toothbrush but not applying pressure to the teeth, or holding a razor but not pressing the shaving head against any hair). This ensures that features related to motion / vibration caused by the user or other sources of motion and / or vibration are minimized in the dataset. This is useful when evaluating predictions of characteristics that are only relevant to the personal care device itself, such as the condition, assembly, and type of replaceable parts of the personal care device.

[0075] However, datasets can also be obtained in use. That is, datasets can be obtained when the personal care device is being actively used to perform associated personal care functions. However, more sophisticated machine learning algorithms (e.g., increased layers) and larger datasets (e.g., acquired at higher rates, with greater bit depth and longer time spans) may be required to ensure the accuracy of predictions for characteristics that are only related to the personal care device. When the predicted characteristics are users and / or user types (i.e., characteristics associated with but not solely related to the personal care device), datasets obtained in use may be necessary.

[0076] The dataset can span approximately one second, but it can span longer time periods to improve prediction accuracy, or shorter time periods to reduce the computational complexity of prediction.

[0077] The dataset can be sampled at a rate of at least 800 Hz, preferably 1.6 kHz, to capture a frequency range containing unique characteristics. Note that the rate can depend on the selected operating parameters. For example, acceleration data can be preferably captured at 1.6 kHz, while sound and current can be captured at 16 kHz. In practice, the operating speed of the personal care device may affect its frequency response, thus affecting the rate at which data should be sampled. For example, a toothbrush operating at 200 Hz may have data sampled at a rate of 1.6 kHz, while a toothbrush operating at 500 Hz may require a higher sampling rate.

[0078] Furthermore, capturing the dataset at different bit depths (i.e., resolutions) can also affect computational complexity and prediction accuracy. For audio data, 16-bit data can be captured, acceleration data can be captured at 12 bits, and current data can be captured at 8 or 16 bits.

[0079] Of course, the selected operating parameters, data length, rate, and dataset resolution may depend on the chosen personal care device for implementing the invention. Those skilled in the art will fully understand the range of selected parameters for the dataset and will be able to adjust these parameters for the chosen application.

[0080] Furthermore, the dataset can be preprocessed before being used to predict the characteristics of replaceable parts. Particularly advantageously, the dataset can be normalized to account for variations in amplitude (e.g., those caused by manufacturing variations in personal care devices). This mitigates variability between individual personal care devices.

[0081] Specifically, when the operating parameter is acceleration, the data format of acceleration data (e.g., from a 3-axis accelerometer) can be improved through preprocessing. Acceleration values ​​for each different axis (XYZ) can also include a norm (N) calculation as a fourth set of values, achieved through serialization or concatenation. Four sets of values ​​(XYZN) sampled at 1600Hz over a 2.5-second time span will produce 16,000 data points (similar to a microphone sampling at 16kHz for 1 second). This 3-axis accelerometer data format can be advantageous compared to, for example, single-axis accelerometer data, data from a microphone, load data, or current data, because it also includes vibration direction information from the serialized data format. Normalization can be performed on each value in the set of values ​​XYZN to preserve the direction information in the signal.

[0082] Once a dataset describing the operating parameters is obtained, and optionally preprocessed, this dataset can be used to determine the predictive characteristics of personal care devices. This can be done using any algorithm suitable for identifying features in the dataset and associating those features with predictive characteristics.

[0083] In a particular embodiment, the dataset can be fed to a feature classification machine learning algorithm / model to determine predictable features. That is, the method for determining predictable features can be an AI-based or neural network-based algorithm. This ensures particularly robust predictions, especially for unseen datasets.

[0084] Artificial neural networks (or simply neural networks (NNs)) are structured with inspiration from the human brain. A neural network consists of multiple layers, each containing multiple neurons. Each neuron performs a mathematical operation. Specifically, each neuron may include different weighted combinations of a single type of transformation (e.g., the same type of transformation, a sigmoid transform, etc., but with different weights). In processing the input data, the mathematical operation of each neuron is performed on the input data to produce a digital output, and the outputs of each layer in the neural network are sequentially fed to the next layer. The final layer provides the output.

[0085] Several types of neural networks exist, such as convolutional neural networks (CNNs), fully connected neural networks (FCNNs), and recurrent neural networks (RNNs). Some examples of this invention implement feature classification machine learning algorithms as spectral image classifiers, such as CNNs or FCNNs.

[0086] Specifically, feature classification machine learning algorithms can be classic convolutional neural network (CNN) classifiers with a finite number of layers. CNNs with 3 to 6 convolutional layers have been shown to provide efficient processing of spectral images. Furthermore, these small CNN-based algorithms can be readily used in embedded firmware that may exist in existing personal care devices. Alternatively, cloud processing is also possible due to the small sample size.

[0087] Given a dataset describing the operating parameters of a personal care device during vibration, a feature classification machine learning algorithm can predict the characteristics of replaceable parts. For example, a feature classification machine learning algorithm can determine the type of replaceable parts for a personal care device or its user. In any case, the algorithm is trained on a previous dataset associated with known characteristics of the personal care device.

[0088] Methods for training machine learning algorithms are well-known. Typically, such methods involve obtaining a training dataset that includes training input data entries and corresponding training output data entries. An initialized machine learning algorithm is applied to each input data entry to generate a predicted output data entry. The error between the predicted output data entry and its corresponding training output data entry is used to modify the machine learning algorithm. This process can be repeated until the error converges and the predicted output data entry is sufficiently similar to the training output data entry. This is often referred to as supervised learning.

[0089] For example, the weights of the mathematical operations for each neuron can be modified until the error converges. Known methods for modifying neural networks include gradient descent, backpropagation, and other algorithms.

[0090] The training input data entries for the feature classification machine learning algorithm can correspond to example test datasets describing the operating parameters of a personal care device during vibration of the device. For each of the multiple test datasets, the training output data entries correspond to known features of the personal care device. That is, a training algorithm is used to train the machine learning algorithm, which is configured to receive an array of training inputs and corresponding known outputs, where the training inputs include one of the test datasets and the corresponding known outputs include known features. In this way, when a dataset describing the operating parameters of a personal care device during vibration (amplitude and / or duty cycle changes) of the device is provided, the machine learning algorithm is trained to output predicted features.

[0091] In some embodiments, the dataset is converted into a spectrogram image, and the characteristics of the personal care device are predicted based on the features found in the spectrogram image. That is, processing is simplified by converting the dataset into a spectrogram image, which can be efficiently processed by machine learning algorithms to identify features for predicting the characteristics of replaceable parts. Therefore, the disclosed method can provide sensitive predictive devices.

[0092] Specifically, the dataset is used to generate spectral images contained within the dataset, representing the signal strength at various frequencies in the vibrational response of the personal care device over time. Therefore, low-resolution (e.g., 128×128 pixels) spectral images can be generated, which have been shown to perform characteristic classification with very high accuracy. Of course, higher-resolution images can be generated to ensure the accuracy of characteristic predictions, but this would likely require significantly more computational resources.

[0093] The generation of spectra can be achieved using known methods, such as applying multiple Fast Fourier Transforms (FFTs) to the dataset. Those skilled in the art will readily understand the various applications and implementations of FFTs on datasets.

[0094] Once the spectral image is generated, it can be fed into a feature classification machine learning algorithm (e.g., a trained neural network). The feature classification machine learning algorithm can then process the spectral image to predict the features of personal care devices.

[0095] Turning Figure 1 The flowchart presents a method for predicting the characteristics of personal care devices.

[0096] This method relates to a personal care device including an actuator that causes the personal care device to vibrate during use. The personal care device can be a device including an actuator that moves, causing a vibrational response in the personal care device. Moreover, the personal care device may vibrate, but the vibration may not be part of its function. Essentially, a personal care device includes an actuator that can cause a mechanical action that results in (measurable) vibration of the personal care device, whether the personal care device is used for a personal care function or for another function. However, in some cases, the personal care device may be a vibrating personal care device that vibrates to perform a function. The actuator can be controllable to operate with varying amplitudes and / or duty cycles. The actuator can be controllable to operate at various frequencies, but this is not necessary for the present invention. Therefore, it is simply possible to control the actuator to move at a typical frequency during normal operation of the personal care device (i.e., not suitable for promoting the present invention).

[0097] Personal care devices can be, for example, electric toothbrushes, razors, skin scrubbers, etc. Personal care devices may include replaceable parts, i.e., any component of the personal care device that deteriorates over time and / or with use, making it necessary for the user to replace it. Deterioration over time or with use can lead to a reduction in the effectiveness of the device's personal care functions. Therefore, the user may need to replace older replaceable parts with newer ones. Therefore, predicting the characteristics of the personal care device associated with replaceable parts may be useful to facilitate appropriate operating setting selection and / or to provide appropriate information.

[0098] In step 110, the actuator is controlled by changing the amplitude and / or duty cycle of the actuator's vibration to cause a change in the vibration of the personal care device.

[0099] In other words, a control signal is provided to the actuator, causing it to move in such a way that the amplitude and / or duty cycle of the actuator's periodic movement is altered. In one example, only the amplitude of the actuator's movement is changed (i.e., not the duty cycle or frequency), resulting in a varying vibration response of the personal care device. In another example, only the duty cycle of the actuator's movement is changed (i.e., not the duty cycle or frequency), resulting in a varying vibration response of the personal care device. In yet another example, both the amplitude and the duty cycle of the actuator's movement are changed (i.e., not the frequency), resulting in a varying vibration response of the personal care device. The varying vibration response of the personal care device represents various characteristics of the personal care device.

[0100] During amplitude and / or duty cycle scanning, the actuator's movement frequency can remain constant. Alternatively, the movement frequency can be varied according to a normal operating control scheme. Essentially, the actuator is controlled to oscillate at one or more normal operating frequencies, which typically move at one or more normal operating frequencies during use of the personal care device, while the amplitude and / or duty cycle of the movement varies.

[0101] In step 120, a dataset describing the operating parameters of the personal care device during vibration is obtained. The dataset is acquired / obtained in response to a controlled actuator (with varying amplitude and / or duty cycle) such that the vibration response characteristics of the personal care device in response to the varying amplitude and / or duty cycle are present in the dataset. In other words, the dataset is captured when the actuator has varying moving amplitude and / or duty cycle.

[0102] The dataset may include one or more of the following: accelerometer data describing acceleration on one axis of the personal care device, accelerometer data describing acceleration on three axes of the personal care device, acoustic data describing the sound produced by the personal care device, and / or current data describing the motor current of the actuator. Other operating parameters for capturing characteristics indicative of the vibration of the personal care device may also be considered. However, the above-mentioned operating parameters may be particularly suitable for measuring the vibration of personal care devices.

[0103] In some cases, the obtained dataset may include values ​​describing the operating parameters of the personal care device, spanning up to one second. Of course, values ​​spanning a larger time range can be obtained (and subsequently used to generate spectral images), but one second may be sufficient to provide a dataset with extractable vibration-related features for predicting the characteristics of the personal care device. Furthermore, the obtained dataset may include values ​​describing the operating parameters of the personal care device sampled at a rate of at least 800 Hz to clearly capture vibration-related features.

[0104] Step 120 may also include an (optional) sub-step of preprocessing the dataset. For example, the dataset may be normalized to account for any variations between similar types of personal care devices (e.g., material differences, minor malfunctions, different environmental conditions). This may include changing all values ​​in the dataset so that they are referenced between, for example, 0 and 1 or -1 and 1.

[0105] Furthermore, in cases where the dataset includes accelerometer data describing triaxial acceleration, preprocessing may include using the accelerometer data to compute (using known methods) norm vector data describing the absolute vector length of the acceleration. Such norm vector data can then be concatenated with serialized accelerometer data (in each of the three axes) to generate a dataset consisting of a single data segment containing accelerometer data and norm vector data for each of the three axes.

[0106] In step 130, at least a portion of the dataset is processed to determine the predictive characteristics of personal care devices.

[0107] A variety of algorithms or methods can be used to process datasets and extract vibration-response-related features within the datasets in order to predict the characteristics of personal care devices.

[0108] In a specific example, a feature classification machine learning algorithm can be used to process a dataset to determine predictive characteristics of a personal care device. A feature classification machine learning algorithm can be any AI-based (e.g., neural network) algorithm configured to process a dataset describing the operating parameters of a personal care device to identify and classify features in order to determine the characteristics of the personal care device.

[0109] More specifically, the dataset can first be converted into spectroscopic data (using multiple FFTs). Then, the spectroscopic data can be converted into spectroscopic images using known methods. Therefore, the spectroscopic images can then be processed using feature classification machine learning algorithms. Thus, predictive features of personal care devices can be determined in a computationally inexpensive yet efficient manner.

[0110] continue, Figure 2 A personal care device 200 according to an example embodiment is shown. In this case, an electric toothbrush is shown. However, it is worth noting that this is merely for illustrative purposes, and the personal care device 200 can be any type of device for personal care (not just oral care).

[0111] The personal care device 200 includes an actuator 210, a controller 220, a sensor 230, and a processor 240, the actuator 210 being configured to vibrate the personal care device 200 during use.

[0112] The controller 220 is configured to control the actuator 210 by changing the amplitude and / or duty cycle of the actuator 210's vibration, thereby causing a varying vibration in the personal care device 200. In other words, the controller 220 generates a control signal that causes the actuator 210 to move with a varying amplitude and / or duty cycle. Thus, the personal care device 200 vibrates by the movement of the actuator 210.

[0113] Sensor 230 acquires a dataset describing the operating parameters of the personal care device 200 during vibration of the personal care device 200. Sensor 230 acquires the dataset in response to controller 220 controlling actuator 210. Therefore, the operating parameters described by the dataset may include vibration response-related features for predicting the characteristics of the personal care device 200.

[0114] The dataset can be any of the datasets described above and can be acquired using any of the methods described above. While sensor 230 is described herein as being provided as part of personal care device 200, sensor 230 can also be provided as part of an external device. For example, sensor 230 could be a microphone mounted on a charger base / pedestal. Sensor 230 could also be a load sensor that measures the force exerted by the surface of the personal care device on the user's surface. Alternatively or additionally, sensor 230 can retrieve previously stored datasets from memory and provide said datasets to processor 240.

[0115] Processor 240 is configured to process at least a portion of the dataset to determine predictive characteristics of personal care device 200. Processor 240 can be configured to perform the above-mentioned... Figure 1 Any of the steps described.

[0116] Similar to sensors, although processor 240 is described as part of personal care device 200, it can also be located externally to personal care device 200. For example, processor 240 can wirelessly connect to sensor 230 to receive data sets. Processor 240 can be provided in the form of a smartphone, or processor 240 can be implemented in the cloud or other external processing services.

[0117] The resulting predictive characteristics of the personal care device 200 can be used to provide outputs instructing the user to take actions to improve the personal care functionality of the device 200. Alternatively or additionally, the predictive characteristics can be used to modify the operating parameters of the personal care device 200 to ensure that potential malfunctions do not occur, unpleasant noise is not generated, and the operation of the personal care device 200 is optimized. Other uses of the predictive characteristics will be apparent to those skilled in the art.

[0118] Therefore, this invention can facilitate improved prediction of the characteristics of personal care devices. This is because a dataset with enhanced vibration response characteristics is obtained by controlling the actuator through changing n amplitudes and / or duty cycles of the actuator's vibration. Utilizing improved characteristic prediction, a better user experience and improved delivery of personal care functions can be achieved.

[0119] Figure 3An example of a computer 300 in which one or more portions of an embodiment may be employed is shown. The various operations discussed above can utilize the capabilities of computer 300. For example, one or more portions of a system for controlling a handheld device may be incorporated into any element, module, application, and / or component discussed herein. In this regard, it should be understood that system functional blocks may run on a single computer or may be distributed across several computers and locations (e.g., via Internet connection), such as cloud-based computing infrastructure.

[0120] Computer 300 includes, but is not limited to, PCs, workstations, laptops, PDAs, handheld devices, servers, memory, microcontroller units, integrated processors, AI accelerators, etc. Typically, in terms of hardware architecture, computer 300 may include one or more processors 310, memory 320, and one or more I / O devices 330 communicatively coupled via a local interface (not shown). The local interface may be, for example, but not limited to, one or more buses or other wired or wireless connections, as known in the art. The local interface may have additional elements, such as controllers, buffers (caches), drivers, repeaters, and receivers, to enable communication. Furthermore, the local interface may include address, control, and / or data connections to enable appropriate communication between the aforementioned components.

[0121] Processor 310 is a hardware device for executing software that can be stored in memory 320. Processor 310 can be any custom or commercially available processor, central processing unit (CPU), digital signal processor (DSP), tensor processing unit (TSP) specifically designed for neural processing, dedicated AI accelerator / processing unit, or auxiliary processor among several processors associated with computer 300, and processor 310 can be a semiconductor-based microprocessor or microprocessor (in the form of a microchip).

[0122] Memory 320 may include any or a combination of the following: volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and non-volatile memory elements (e.g., ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic tape, optical disc read-only memory (CD-ROM), magnetic disk, floppy disk, cartridge memory, cassette tape, etc.). Furthermore, memory 320 may incorporate electronic, magnetic, optical, and / or other types of storage media. Note that memory 320 may have a distributed architecture, where various components are geographically separated but accessible by processor 310.

[0123] The software in memory 320 may include one or more individual programs, each including an ordered list of executable instructions for implementing logical functions. According to an exemplary embodiment, the software in memory 320 includes a suitable operating system (O / S) 340, a compiler 360, source code 350, and one or more application programs 370. As shown, the application program 370 includes multiple functional components for implementing the features and operations of the exemplary embodiment. According to an exemplary embodiment, the application program 370 of computer 300 may represent various applications, computing units, logic, functional units, processes, operations, virtual entities, and / or modules, but the application program 370 is not intended to be limiting.

[0124] Operating system 340 controls the execution of other computer programs and provides scheduling, input-output control, file and data management, memory management, communication control, and related services. The inventors envision that application program 370, used to implement the exemplary embodiment, can be applied to all commercially available operating systems.

[0125] Application 370 can be a source program, an executable program (object code), a script, or any other entity including a set of instructions to be executed. When it is a source program, it is typically translated by a compiler (e.g., compiler 360), assembler, interpreter, etc., which may or may not be included in memory 320 to operate appropriately in conjunction with O / S 340. Furthermore, application 370 can be written in an object-oriented programming language with classes of data and methods, or a procedural programming language with routines, subroutines, and / or functions, such as, but not limited to, C, C++, C#, Pascal, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA.NET, etc.

[0126] I / O device 330 may include input devices, such as, but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Furthermore, I / O device 330 may also include output devices, such as, but not limited to, a printer, monitor, etc. Finally, I / O device 330 may also include devices for transmitting input and output, such as, but not limited to, a NIC or modulator / demodulator (for accessing remote devices, other files, devices, systems, or networks), radio frequency (RF) or other transceivers, telephone interfaces, bridges, routers, etc. I / O device 330 also includes components for communication on various networks such as the Internet or intranets.

[0127] If the computer 300 is a PC, workstation, intelligent device, etc., the software in the memory 320 may also include a Basic Input / Output System (BIOS) (omitted for simplicity). The BIOS is a set of basic software routines that initialize and test the hardware, start the O / S 340, and support data transfer between hardware devices during startup. The BIOS is stored in some type of read-only memory such as ROM, PROM, EPROM, EEPROM, etc., so that the BIOS can be executed when the computer 300 is activated.

[0128] When the computer 300 is in operation, the processor 310 is configured to execute software stored in the memory 320 to transfer data to and from the memory 320, and to control the overall operation of the computer 300 according to the software. Application programs 370 and O / S 340 are read, in whole or in part, by the processor 310, may be cached within the processor 310, and then executed.

[0129] When application 370 is implemented as software, it should be noted that application 370 can actually be stored on any computer-readable medium for use by or in connection with any computer-related system or method. In the context of this document, a computer-readable medium can be an electronic, magnetic, optical, or other physical device or apparatus that can contain or store computer programs used by or in connection with a computer-related system or method.

[0130] Application 370 may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device (e.g., a computer-based system, a processor-containing system, or other system capable of fetching and executing instructions from and from an instruction execution system, apparatus, or device). In the context of this document, "computer-readable medium" can be any means capable of storing, transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, devices, or propagation media.

[0131] The proposed Figure 1 one or more control methods and Figure 2The system(s) can be implemented in hardware or software, or a combination of both (e.g., as firmware running on a hardware device). With regard to embodiments implemented partially or entirely in software, the functional steps shown in the process flowchart can be executed by appropriately programmed physical computing devices, such as one or more central processing units (CPUs) or graphics processing units (GPUs). Each process and its constituent steps as shown in the flowchart can be executed by the same or different computing devices. According to an embodiment, a computer-readable storage medium stores a computer program including computer program code configured to cause the one or more physical computing devices to perform the control methods described above when the program is run on one or more physical computing devices.

[0132] Storage media can include volatile and non-volatile computer memories, such as RAM, PROM, EPROM and EEPROM, optical discs (such as CD, DVD, BD), and magnetic storage media (such as hard disks and magnetic tapes). Various storage media can be fixed within a computing device or can be portable, allowing one or more programs stored on them to be loaded into a processor.

[0133] With regard to embodiments implemented in part or in whole in hardware, Figure 2 The block diagram illustrates that some blocks may be separate physical components, logical subdivisions of a single physical component, or may all be implemented in an integrated manner within a single physical component. In embodiments, the functionality of one block shown in the figures may be divided among multiple components, or in embodiments, the functionality of multiple blocks shown in the figures may be combined in a single component. Hardware components suitable for embodiments of the present invention include, but are not limited to, conventional microprocessors, application-specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs). One or more blocks may be implemented as a combination of dedicated hardware performing certain functions and one or more programmable microprocessors and associated circuitry performing other functions.

[0134] By studying the accompanying drawings, disclosure, and appended claims, those skilled in the art can understand and implement variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude multiple. A single processor or other unit can implement the functions of several items recounted in the claims. The fact that certain measures are recited in mutually different dependent claims does not imply that combinations of these measures cannot be advantageously used. If a computer program has been discussed above, it can be stored / distributed on suitable media, such as optical storage media or solid-state media provided with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. If the term "suitable" is used in the claims or description, it should be noted that the term "suitable" is intended to be equivalent to the term "configured as." Any reference numerals in the claims should not be construed as limiting the scope.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions comprising one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions indicated in the blocks may not occur in the order shown in the figures. For example, depending on the function involved, two consecutively shown blocks may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action or executes a combination of dedicated hardware and computer instructions.

Claims

1. A method for predicting characteristics of a personal care device, the personal care device including an actuator that vibrates the personal care device during use, the method comprising: (110) The actuator is controlled to cause a change in the vibration of the personal care device by changing the amplitude and / or duty cycle of the actuator's vibration; In response to controlling the actuator, a dataset describing the operating parameters of the personal care device during vibration of the personal care device is obtained (120); as well as Process at least a portion of the dataset to determine (130) the predictive characteristics of the personal care device.

2. The method of claim 1, wherein controlling (110) the actuator further comprises controlling the actuator to vibrate at an operating frequency scheme while changing the amplitude and / or duty cycle of the vibration.

3. The method according to claim 2, wherein the operation frequency is based on the frequency of personal care operation modes.

4. The method according to any one of the preceding claims, wherein the characteristics of the personal care device include the predicted condition of the replaceable parts of the personal care device, the predicted type of the replaceable parts of the personal care device, the predicted assembly state of the replaceable parts of the personal care device, the predicted user of the personal care device, and / or the predicted user type of the personal care device.

5. The method according to any one of the preceding claims, wherein the dataset includes accelerometer data describing acceleration on at least one axis of the personal care device.

6. The method of claim 5, wherein the accelerometer data describes three-axis acceleration, and wherein the method further comprises: Based on the accelerometer data, a norm vector data describing the absolute vector length of acceleration is calculated; as well as The accelerometer data and norm vector data for each of the three axes are serialized into a single data segment.

7. The method according to any one of the preceding claims, wherein the dataset includes sound data describing sounds generated by the personal care device.

8. The method according to any one of the preceding claims, wherein the dataset includes current data describing the motor current of the actuator.

9. The method according to any one of the preceding claims, wherein the dataset describing the operating parameters is obtained in response to the personal care device being in a static state or in response to the personal care device being in an operational use state (120).

10. The method according to any one of the preceding claims, wherein the obtained dataset includes values ​​describing the operating parameters of the personal care device, the values ​​spanning up to 1 second, and wherein the obtained dataset includes values ​​describing the operating parameters of the personal care device, the operating parameters being sampled at a rate of at least 800 Hz, and optionally the operating parameters being sampled at a rate of at least 1.6 kHz.

11. The method according to any one of the preceding claims, wherein processing the dataset comprises: At least a portion of the dataset is processed using a feature classification machine learning algorithm to determine (130) the predicted features of the personal care device.

12. The method of claim 11, further comprising: Generate spectral images based on at least a portion of the dataset; as well as The spectral image is processed using the feature classification machine learning algorithm to determine (130) the predicted features of the personal care device.

13. The method of claim 12, wherein the feature classification machine learning algorithm is a spectral image classifier, and optionally, wherein the feature classification machine learning algorithm is a CNN classifier or an FCNN classifier.

14. A computer program including computer program code means, wherein when the computer program is run on a computer, the computer program code means is adapted to implement the method of any one of claims 1 to 13.

15. A personal care device, comprising: Actuator (210) is configured to vibrate the personal care device during use; The controller (220) is configured to control the actuator by changing the amplitude and / or duty cycle of the actuator's vibration to cause varying vibrations in the personal care device; Sensor (230) is configured to obtain a dataset of operating parameters describing the personal care device during vibration of the personal care device in response to control of the actuator; as well as The processor (240) is configured to process at least a portion of the dataset to determine predictive characteristics of the personal care device.

Images