Personal care device

Abstract

A personal health care device monitors one or more parameters capable of obtaining a current angle of use. For example, a motion sensor may be provided for monitoring acceleration and angular velocity. And comparing the current use angle with the ideal use angle. Feedback is provided to a user of the device using a light output loop around the device handle. The rotation of the lighting effect indicates the direction of rotation of the device required to approach the ideal angle of use.

Description

Technical Field

[0001] The present invention relates to personal care devices, and more particularly to a handheld device that assists a user in achieving the most suitable operation of the device. For example, the present invention relates to a toothbrush that assists a user in achieving good brushing techniques. Background Art

[0002] To brush teeth correctly and prevent future oral health problems, brushing techniques need to ensure that all teeth and gums are properly cleaned.

[0003] For example, the American Dental Association recommends brushing teeth twice a day with fluoride toothpaste for two minutes each time. This guidance does not describe in detail the various aspects that can achieve or interrupt a good brushing procedure. Of course, one should apply sufficient pressure, but not too much. All different sides of the teeth should be brushed, and tooth segments should not be skipped. These aspects are part of the brushing technique and, combined with the brushing routine (i.e., how often and for how long at a time), are necessary for good oral health.

[0004] It is known to provide feedback to users to help them achieve a suitable brushing routine. In the simplest electric toothbrushes, a counter is provided to guide the user to brush for at least two minutes.

[0005] In more advanced toothbrushes, the toothbrush measures whether the correct force is applied and issues a warning when the applied force is too large. Additionally, known electric toothbrushes can measure whether the user is scrubbing too much. Ideally, an electric toothbrush user should scrub much lighter than a manual toothbrush user.

[0006] In the latest generation Philips Sonicare Prestige 9900 toothbrush, there is also coverage guidance to provide feedback on whether all tooth segments have been brushed for sufficient time. Ensure, for example, that the user also brushes the inner sides of the front teeth for long enough, as these positions are often forgotten.

[0007] One aspect not addressed by currently available toothbrushes on the market is to ensure that the user brushes at the correct brushing angle. By using the correct brushing angle (45 degrees), the so-called Bass angle technique can better remove plaque near the gums.

[0008] US8393037 discloses a toothbrush that determines the tooth segment being brushed, the force being applied, and the brushing angle. For example, using a notification alert in the form of an audible beep, the user is provided with guidance to tilt the toothbrush to the optimal brushing angle (e.g., 35 degrees to 55 degrees). Sound, light, or vibration output can also be used. However, these do not provide an intuitive output signal to the user.

[0009] Conversely, once the brushing angle has been measured, the deviation from the ideal brushing angle needs to be converted into an easily interpretable feedback signal to guide the user to rotate the toothbrush clockwise or counterclockwise towards the ideal angle.

[0010] US20196 / 082819 discloses a toothbrush having an illumination ring around the top of the handle (between the handle and the head). The toothbrush has an acceleration sensor for detecting the toothbrush angle. The illumination ring is used to indicate the on / off of the toothbrush and different toothbrush angles. The illumination ring can be controlled to different intensities and different blinking frequencies.

[0011] US2013 / 074616 discloses a toothbrush having a sensor for detecting a brushing mode and also discloses an illumination ring around the toothbrush body. The illumination ring is used to indicate when the detected brushing mode matches a reference so that the user can proceed to the next brushing area. Summary of the Invention

[0012] The present invention is defined by the claims.

[0013] According to an example of one aspect of the present invention, there is provided a personal health care device, comprising:

[0014] a device head and a device handle;

[0015] a sensor configured to provide a sensor output depending on the movement or orientation of the device;

[0016] a light output ring configured to generate a rotating light-emitting effect around the device handle; and

[0017] a controller configured to process the sensor output, wherein the processor is configured to:

[0018] obtain a current usage angle from the sensor output;

[0019] determine an ideal usage angle;

[0020] compare the current usage angle with the ideal usage angle; and

[0021] control the light output ring to provide feedback to a user of the device, wherein the rotation of the rotating light-emitting effect indicates the direction of rotation of the device required to approach the ideal usage angle.

[0022] The present invention provides a device that obtains a usage angle and provides feedback to a user to rotate the device towards a better usage angle, the feedback including real-time feedback on the device. The controller can also provide offline feedback on the usage angles applied in previous personal health care procedures.

[0023] The ideal usage angle depends, for example, on the position of the device.

[0024] Sensors can be used to measure movement or orientation. For example, the sensors can include an inertial monitoring unit, such as an accelerometer and a gyroscope, to measure movement, such as the acceleration and angular velocity of the device. Another example is a force sensor, which is used to measure the (reaction) force on the head of the device (which is a vector with magnitude and direction). This can be used to obtain the angle between the head of the device and the surface applying the force to it. Therefore, various sensors can be used to determine the current usage angle.

[0025] Preferably, the controller is configured to generate a light animation, which includes a clockwise or counterclockwise light emission pattern around the light ring. Therefore, the light ring is used to provide user feedback, and the light ring generates a pattern that clearly extends clockwise or counterclockwise. For example, the light output ring includes an LED ring that defines groups of angular segments.

[0026] The light output ring can surround the base of the device handle, opposite to the device head. Alternatively, or additionally, the light output ring can surround the top of the device handle, near the device head.

[0027] The controller can include an AI model for determining the usage angle. This provides an accurate way to obtain the current usage angle. The AI model includes, for example, a long short-term memory (LSTM) model.

[0028] In a set of examples, the personal health care device includes an electric toothbrush, which has a toothbrush head and a toothbrush handle, where the usage angle is the brushing angle, and the processor is configured to determine the ideal brushing angle by:

[0029] Determining the current tooth segment where the toothbrush head is located;

[0030] Determining the ideal brushing angle based on the current brushing segment.

[0031] Therefore, the ideal brushing angle can depend on the specific brushing segment where the toothbrush head is located.

[0032] Brushing at the correct angle, also known as brushing with the Bass angle technique, can remove more dental plaque at the gum line. Therefore, the device provides assistance to the user to achieve the best brushing technique.

[0033] The controller can be configured to use both sine and cosine values to compare the current usage angle and the ideal usage angle. This enables the determination of the required rotation direction (and the required amount of rotation).

[0034] The controller can include:

[0035] A first neural network, which is used to determine the brushing angle;

[0036] A second neural network for determining a brushing section; and

[0037] A comparator for comparing an ideal brushing angle and a current brushing angle.

[0038] The first neural network includes, for example, an LSTM layer and an output layer to predict an angle (e.g., a convolutional layer having a dual-channel output providing sine and cosine components of the brushing angle). The second neural network determines the position of the toothbrush head, enabling identification of the brushing section.

[0039] A lookup table can be used, which stores ideal brushing angle values for each section. Thus, the output of the second neural network can be utilized to retrieve the ideal brushing angle. Additionally, a time threshold can be introduced such that a light animation is shown only when brushing at the wrong brushing angle exceeds a predetermined time (e.g., 4 to 10 seconds).

[0040] The present invention also provides a method for providing usage angle guidance for a personal health care device, the personal health care device including a device head and a device handle, the method comprising:

[0041] Receiving a sensor output depending on the movement or orientation of the device;

[0042] Processing the sensor output to obtain a current usage angle;

[0043] Determining an ideal usage angle;

[0044] Comparing the current usage angle and the ideal usage angle; and

[0045] Controlling a light output ring around the device handle to provide feedback to a user of the device by generating a rotating light-emitting effect around the device handle, wherein the rotation of the rotating light-emitting effect indicates the direction of rotation of the device required to approach the ideal usage angle.

[0046] The rotation speed and light intensity of the rotating light-emitting effect can depend on the brushing angle error (i.e., the difference between the ideal angle and the measured angle).

[0047] Preferably, controlling the light output ring includes generating a light animation including a clockwise or counterclockwise light-emitting pattern around the light ring.

[0048] The method can include using an AI model to determine the usage angle.

[0049] When the method is implemented by an electric toothbrush, the usage angle includes the brushing angle, and the method may then further include:

[0050] Determining a current tooth section where the toothbrush head is located according to the sensor output;

[0051] Determine the ideal brushing angle based on the current brushing section.

[0052] The present invention also provides a computer program comprising computer program code means which, when the program is run on a computer, are adapted to implement the methods defined above.

[0053] With reference to the embodiments described below, these and other aspects of the present invention will become apparent and be elucidated. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] For a better understanding of the present invention, and for a clearer illustration of how the present invention may be implemented, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0055] Figure 1 A personal care device in the form of a toothbrush is shown;

[0056] Figure 2 An angle convention for illustrating the brushing angle is shown;

[0057] Figure 3 An AI model for angle prediction is shown;

[0058] Figure 4 and Figure 5 An example of a predicted brushing angle as a function of time is shown;

[0059] Figure 6 An AI model for brushing section prediction is shown;

[0060] Figure 7 Two AI models integrated together are shown; and

[0061] Figure 8 A method of providing angle guidance for use is shown. DETAILED DESCRIPTION

[0062] The present invention will now be described with reference to the accompanying drawings.

[0063] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, systems and methods, are intended for illustrative purposes only and are not intended to limit the scope of the present invention. These and other features, aspects and advantages of the apparatus, systems and methods of the present invention will be better understood in conjunction with the following description, the appended claims and the drawings. It should be understood that the drawings are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals represent the same or similar components throughout the drawings.

[0064] The present invention provides a personal health care device that monitors one or more parameters capable of obtaining the current usage angle. For example, a motion sensor can be provided to monitor acceleration and angular velocity. The current usage angle is compared with the ideal usage angle. A light output ring around the handle of the device provides feedback to the user of the device. The rotational indication of the lighting effect indicates the direction of rotation of the device required to approach the ideal usage angle.

[0065] Figure 1 A personal care device in the form of a toothbrush is shown, which can be designed and controlled according to the present invention.

[0066] The toothbrush 100 includes a head 102 and a handle 104. The handle 104 houses sensors, and in this example, the sensors include an inertial monitoring unit 106 for monitoring the movement of the device, and preferably includes an accelerometer and a gyroscope. The sensors measure the acceleration and angular velocity of the device, and preferably, measure 3-axis acceleration and 3-axis angular velocity. Any known suitable motion tracking sensor can be used.

[0067] Other parameters capable of obtaining the head angle can be additionally or alternatively sensed, such as monitoring the force applied by the head to the teeth using a force sensor.

[0068] The controller 108 processes the output provided by the sensors, and in this example, processes the measured motion, such as acceleration and angular velocity. The controller controls the light output ring to provide feedback to the user. The feedback is a rotational lighting effect around the handle of the device. In the shown example, a first light output ring 110 is provided around the base of the handle of the device and opposite to the device head, and a second light output ring 112 is provided around the top of the handle of the device and close to the device head.

[0069] Only one light output ring can be provided, or two, or in fact more than two.

[0070] In the simplest implementation, the (or each) light output ring includes a plurality of LEDs in a circular configuration. The LEDs can emit light directly to the outside of the toothbrush, or a plastic light guide can be used to transmit the light from the printed circuit board (PCB) where the LEDs are located to the outside of the toothbrush. As an example, a convincing rotational animation can be achieved using only 8 LEDs, so it is preferably to provide 8 to 30 segments around the ring. The ring extends around the longitudinal axis of the handle.

[0071] The controller obtains the current usage angle from the sensor output. In this example, the sensor output is the measured acceleration and angular velocity. In a toothbrush, the usage angle is the brushing angle. The controller also determines the ideal usage angle and then compares the current usage angle with the ideal usage angle. The ideal usage angle depends, for example, on the position of the device, such as in the case of a toothbrush, the tooth segment where the device is being used. Control the (one or more) light output rings such that the rotation of the light-emitting effect indicates the direction of rotation of the device, i.e., the toothbrush, required to approach the ideal usage angle.

[0072] It should be noted that existing toothbrushes already include a light ring at the top or bottom of the toothbrush handle to provide user feedback during brushing. These light rings are driven, for example, by red / green / blue (RGB) LEDs, and different colors can represent different feedback messages.

[0073] The light ring used in the device of the present invention is segmented so that an animation can be generated, and the animation provides a rotational effect around the toothbrush handle. Then, the direction of rotation guides the user to achieve the appropriate rotation of the device (in the same direction as the direction of rotation of the light-emitting effect) to re-align the device to the most appropriate usage (i.e., brushing) angle.

[0074] Preferably, an AI model is used to determine the current usage angle. To explain this embodiment, a detailed example of a toothbrush application will be given. In this application, it is also necessary to determine the tooth segment because the brushing angle depends on the tooth segment. Therefore, a brushing segment prediction model is also used.

[0075] To predict the brushing angle using an AI model, the model needs to be trained. For this purpose, reference data is required to provide input data (IMU signals) and ideal outputs.

[0076] When establishing a brushing segment prediction model, human annotators can be relied upon. The annotators watch videos of users brushing their teeth and mark the tooth segments x at time steps t during brushing. For a 16-segment model, x is an integer between 1 and 16, indicating 16 segments corresponding to combinations of left / front / right, upper / lower, and inner / chewing / outer tooth segments.

[0077] When establishing a brushing angle prediction model, the annotator cannot easily determine the brushing angle between the toothbrush and the tooth / gum line from the video. Therefore, to generate reference data, a motion tracking system can be used. To generate reference data, the user is required to wear a headband and brush their teeth in front of the motion tracking system, and both the headband and the toothbrush have special motion tracking markers.

[0078] Then, based on the output of the motion tracking system, the position and orientation of the toothbrush relative to the teeth can be determined because the upper teeth are rigidly associated with the head wearing the headband using the motion tracking markers on the headband.

[0079] Figure 2 Illustrates the convention for explaining the brushing angle, where the upper image shows the upper teeth and the lower image shows the lower teeth:

[0080] P represents the contact point of the bristles with the tooth;

[0081] h represents the vector from P along the bristles to the toothbrush.

[0082] A coordinate system consisting of the following three orthogonal vectors is defined at P:

[0083] t: from left to right, tangent to the parabolic tooth curve (in the jaw plane)

[0084] n: orthogonal to the tooth curve and outward (in the jaw plane)

[0085] z: orthogonal to the jaw plane "upward".

[0086] When P is located on the upper tooth, the brushing angle β is defined as:

[0087] β = arctan2((h·n), -(h·z));

[0088] When P is located on the lower tooth, the brushing angle β is defined as:

[0089] β = arctan2((h·n), (h·z)).

[0090] The vector operation is the inner product (i.e., dot product), and thus a scalar number is passed. This scalar number is applied to the arctan2 function to obtain the brushing angle.

[0091] The arctan2 function has two arguments. It receives the cosine and sine components (or x and y offsets), and is able to correctly calculate in which of the four quadrants the resulting angle may lie.

[0092] These values can be converted to degrees by multiplying by 180 / π.

[0093] These transformations encode the geometric function of projecting the bristles onto the plane spanned by the vectors n and z. The brushing angle is:

[0094] The angle between -z (maxilla) or z (mandible) and the projected bristles.

[0095] Therefore, the brushing angle is the angle between the following two planes: (i) the tooth plane determined by (t, z), and (ii) the toothbrush plane determined by (t, h).

[0096] Based on the angle definition and explanation, when brushing a specific tooth, three categories of user movements can be defined:

[0097] (i) The toothbrush rotates around the t-axis (gingival line). Angle detection and guidance focus on guiding this movement to optimally maintain a 45-degree Bass angle.

[0098] (ii) The toothbrush moves on the tooth plane. This movement can typically be caused by holding the toothbrush more vertically rather than horizontally. To promote maximum contact with the mandibular contour, the user should be prompted to hold the toothbrush horizontally.

[0099] (iii) The toothbrush moves on the toothbrush plane. This movement does not seem natural as the toothbrush moves away from the tooth surface, but it may occur when the toothbrush moves from one tooth to the next.

[0100] In particular, movements (i) and (ii) are monitored and guided.

[0101] The algorithm calculates the brushing angle β for each time step (usually 1 / 30 second) of the brushing program and saves it together with the IMU sensor data.

[0102] During the training program, the IMU data is used as input, and the ideal brushing angle is used as the benchmark to be achieved as feedback. During the training program, the sensor data will be used as input, and the ideal brushing angle is used as the benchmark for comparison with the output of the AI model. During the training program, the AI model parameters are updated in the following way: the angle prediction is as close as possible to the benchmark angle (by minimizing the difference).

[0103] Therefore, when the AI model predicts the brushing angle, the difference from the ideal brushing angle will be minimized. This difference (loss function) should be convergent. When simply using the simple mean absolute difference of the angles, there are potential problems caused by the cyclic definition of these angles, where an angle of -179 degrees differs from an angle of +179 degrees by only 2 degrees.

[0104] To solve this problem, the cosine and sine components of the brushing angle can be predicted (effectively, a vector with length = 1), and the benchmark is converted to the cosine and sine of the benchmark angle. Next, the loss function (i.e., the loss to be minimized during training) can be expressed as 1 - cosine similarity:

[0105] L = 1 - v gt ·v pred .

[0106] The loss function is 1 - the inner product between two vectors.

[0107] Instead of this loss function, cosine similarity can be used to determine the angle error (difference) and calculate the mean square (or mean absolute) error of this error angle.

[0108] In both cases, a measure based on sine and cosine values is used to compare the current usage angle with the ideal usage angle.

[0109] As Figure 3 shown, the AI model for angle prediction includes an encoder 200, an LSTM layer 202, and a decoder 204. The brushing angle prediction is provided as output 205.

[0110] In the encoder 200, the input IMU sensor signal is filtered (linearly) by a convolutional layer 200a and scaled by a batch normalization layer 200b. This filtered signal enters the LSTM layer 202, which updates its internal (also known as hidden) state.

[0111] Next, the hidden state of the LSTM is used as the input to the decoder 204, which maps the hidden state to two channels (using a convolutional layer 204a with 2 output channels and a kernel size of 1).

[0112] In the final step, in step 204b, these two channels are normalized to represent a vector of length 1.

[0113] Figure 4 And Figure 5 shows an example of the predicted brushing angle as a function of time.

[0114] In each figure, one curve is the predicted brushing angle, and the other curve is a plot of the reference brushing angle versus time. The two curves are for two different brushing procedures. Figure 4 And Figure 5 shows the accuracy of the brushing angle prediction.

[0115] The AI model is able to determine the orientation of the toothbrush relative to the teeth rather than relative to the real world (i.e., relative to the gravity vector). To this end, the AI model takes into account the head tilt, which cannot be achieved with a simple accelerometer system as disclosed in, for example, US8393037 and using the disclosed simple mathematical formulas. In particular, the AI can improve its prediction by learning a large amount of data.

[0116] Figure 6 shows a real-time model for brushing section prediction. The architecture of the angle prediction model is very similar to the real-time model for brushing section prediction.

[0117] The same encoder 200 and LSTM layer 202 are used. Only the decoder is different, where the decoder includes a classifier 300 having multiple convolutional-batch normalization-rectified linear unit layers 300a, 300b, 300c (i.e., "conv-bn-relu" layers). For classification and segmentation problems, the decoder typically ends with a Softmax layer (softmax layer) 300d representing the sum of probabilities equal to 1. The brushing section prediction is provided as output 301.

[0118] This architectural similarity enables the encoder / LSTM weights in the brushing section prediction model to be reused in the angle prediction model. This can achieve better angle prediction because the brushing section model is trained with a much larger dataset with section labels. For example, the decoder is trained with a dataset where the brushing angle is available, or the encoder / LSTM layers are fine-tuned after certain training epochs (transfer learning).

[0119] By having only a single encoder and LSTM, and two different output heads simultaneously, two AI models can be unified into a single model that predicts both the brushing section and the brushing angle.

[0120] This is shown in Figure 7 . One head is for predicting the brushing section and the other head is for predicting the brushing angle. This model is much smaller than two separate models (only slightly larger than the original brushing section model because the decoder in the angle prediction model is very small).

[0121] The controller has a comparator whose output is used to control the halo. It determines the brushing angle for the current brushing section. For each brushing section, there is a target brushing angle β target . If the user is brushing a certain section for more than τ seconds and is more than Δ degrees away from the target brushing angle, the halo will show an animation to indicate to the user that they should rotate the toothbrush clockwise or counterclockwise (to rotate towards the target brushing angle).

[0122] The target brushing angle β target and the range Δ are both section-dependent. The time delay τ before indication is set, for example, in the range of 4 to 10 seconds.

[0123] To achieve smooth guiding behavior, the target guiding angle can start from a typical angle related to the user's personal situation (e.g., the average angle from the past 10 programs, or the typical angle from a specific population). Over time, the target angle can be moved closer to the ideal Bass angle (45 degrees). Using typical / personalized values to avoid directly giving excessive angle feedback.

[0124] The above example utilizes a light output ring formed as a line of discrete LEDs. The light output ring can alternatively be based on a flexible display such that light motion patterns can be displayed along the longitudinal axis of the toothbrush and (radially) around the toothbrush. A small (bright) display (e.g., a flat display) can be used in combination with a light guide to direct the light output to different segments, thereby forming a light ring around the handle.

[0125] The angle prediction model can also be run offline for post-brushing analysis to provide insights about the brushing in a brushing report. For example, for each segment, a report can be provided about the duration of brushing at the correct angle (using the Bass angle technique) during the brushing time. Additionally, more detailed brushing angle and time-related information can be provided for the final brushing procedure. Examples of suitable statistics are the average or median brushing angle (for each tooth segment), standard deviation, amount of coverage of the mandibular contour (in percentage), and amount of coverage of the teeth (in percentage).

[0126] Real-time angle guidance feedback is not limited to being implemented only using the light ring of an electric toothbrush. Additional feedback can also be implemented on a separate device connected to the toothbrush, such as a charging station, a smart phone, or other smart gadgets.

[0127] Directional force sensors will be integrated in the next generation of toothbrushes. Such force sensors can be used to measure the direction of the force exerted by the brush head on the teeth / gums. This provides an additional way to measure (or verify) the brushing angle.

[0128] Figure 8 A method for providing usage angle guidance for a personal health care device is shown, the personal health care device including a device head and a device handle.

[0129] In step 400, the measured acceleration and angular velocity of the device are received. In step 402, these velocities are processed to obtain the current usage angle. In step 404, the ideal usage angle is determined, and in step 406, the current usage angle and the ideal usage angle are compared.

[0130] In step 408, the light output ring around the device handle is controlled to provide feedback to the user of the device as described above.

[0131] The above example is a toothbrush based on monitoring the brushing angle. However, the correct operation of other personal care depends on the correct usage angle, such as razors and intense pulsed light (IPL) hair removal devices.

[0132] In the process of implementing the claimed invention, those skilled in the art can understand and implement variations of the disclosed embodiments by studying the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0133] The functions implemented by a processor can be implemented by a single processor or multiple separate processing units, which can be considered to jointly constitute a "processor". In some cases, these processing units can be far apart from each other and communicate with each other in a wired or wireless manner.

[0134] The fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to obtain an advantage.

[0135] A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium provided together with the hardware or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless remote communication systems.

[0136] If the term "adapted to" is used in a claim or the specification, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to". If the term "means" is used in a claim or the specification, it should be noted that the term "means" is intended to be equivalent to the term "system", and vice versa.

[0137] Any reference signs in the claims shall not be construed as limiting the scope thereof.

Claims

1. A personal health care device (100) comprising: A device head (102) and a device handle (104); A sensor (106) for providing a sensor output depending on the movement or orientation of the device; A light output ring (110, 112) for generating a rotating light-emitting effect around the device handle; And A controller (108) for processing the sensor output, wherein the processor is configured to: Obtain a current usage angle from the sensor output; Determine an ideal usage angle; Compare the current usage angle and the ideal usage angle; And Control the light output ring to provide feedback to a user of the device, wherein the rotation of the rotating light-emitting effect indicates the direction of rotation of the device required to approach the ideal usage angle.

2. The device according to claim 1, wherein, The light output ring (110, 112) includes an LED ring that defines groups of angular segments.

3. The device according to claim 1 or 2, wherein The controller (108) is configured to generate a light animation that includes a clockwise or counterclockwise light-emitting pattern around the light ring.

4. The device according to any one of claims 1 to 3, wherein, The light output ring (110) surrounds the base of the device handle, opposite the device head.

5. The device according to any one of claims 1 to 4, wherein The light output ring (112) surrounds the top of the device handle, near the device head.

6. The apparatus according to any one of claims 1 to 5, wherein The controller includes an AI model for determining the usage angle.

7. The apparatus according to claim 6, wherein The AI model includes an LSTM model.

8. The apparatus according to any one of claims 1 to 7, wherein The controller is configured to compare the current usage angle and the ideal usage angle by comparing metrics based on sine and cosine values.

9. The personal health care device according to any one of claims 1 to 8, comprising an electric toothbrush having a toothbrush head and a toothbrush handle, wherein the usage angle is a brushing angle, and the processor is configured to determine the ideal brushing angle by: Determine the current tooth segment where the toothbrush head is located; Determine the ideal brushing angle based on the current brushing segment.

10. The device according to claim 9, wherein, The controller includes: A first neural network for determining the brushing angle; A second neural network for determining the brushing segment; and A comparator for comparing the ideal brushing angle and the current brushing angle.

11. A method for providing usage angle guidance for a personal health care device, the personal health care device including a device head and a device handle, the method comprising: Receiving a sensor output depending on the movement or orientation of the device; Processing the sensor output to obtain a current usage angle; Determining an ideal usage angle; Comparing the current usage angle and the ideal usage angle; And Controlling a light output ring around the device handle to provide feedback to a user of the device by generating a rotating light-emitting effect around the device handle, wherein the rotation of the rotating light-emitting effect indicates the direction of rotation of the device required to approach the ideal usage angle.

12. The method according to claim 11, wherein, Controlling the light output ring includes generating a light animation that includes a clockwise or counterclockwise light-emitting pattern around the light ring.

13. The method according to claim 11 or 12, comprising using an AI model to determine the usage angle.

14. The method according to any one of claims 11 to 13, wherein the method is implemented by an electric toothbrush, and wherein, The usage angle includes a brushing angle, wherein the method further comprises: determining a current tooth section where the toothbrush head is located according to the sensor output; determining the ideal brushing angle based on the current brushing section.

15. A computer program, the computer program comprising computer program code means adapted to implement the method according to any one of claims 11 to 14 when the program is run on a computer.

Images