Toothbrushing aid

Abstract

The subject-matter of the present disclosure relates to a computer-implemented method of providing real-time guidance to a user about brushing their teeth using a power toothbrush, PTB (10). The computer-implemented method comprising: detecting (100) a sound associated with operation of the PTB (10); classifying (102), using a detection model (52), a make and model of the PTB (10) and its mode of operation based on the detected sound; generating (104) real-time instructions to the user based on the make, model, and model of operation; and providing (106), using a device, the real-time instructions to the user.

Description

[0001] TOOTHBRUSHING AID

[0002] FIELD

[0003]

[0001] The subject-matter of the present disclosure relates to a computer-implemented method of providing real-time guidance associated with a user brushing their teeth using a power toothbrush, PTB.

[0004] BACKGROUND

[0005]

[0002] PTBs often include different modes of operation, e.g. whitening mode. However, there is often little guidance provided to a user other than what is included in an instruction manual.

[0006]

[0003] It is an aim of the subject-matter of the present disclosure to improve on the prior art.

[0007] SUMMARY

[0008]

[0004] According to an aspect of the present disclosure, there is provided a computer- implemented method of providing real-time guidance associated with a user brushing their teeth using a power toothbrush, PTB, the computer-implemented method comprising: detecting a sound associated with operation of the PTB; classifying, using a detection model, a make and model of the PTB and its mode of operation based on the detected sound; generating real-time instructions to the user based on the make, model, and mode of operation; and providing, using a device, the real-time instructions to the user.

[0009]

[0005] In this way, real-time guidance can be provided to the user regardless as to what make or model the PTB is. This is achieved by using the detected sounds to determine which real-time instructions are needed, and those instructions can be provided to the user.

[0010]

[0006] In an embodiment, the detection model may comprise a machine learning model.

[0011]

[0007] In an embodiment, wherein classifying, using the machine learning model, the make and model of the PTB and its mode of operation based on the detected sound comprises: receiving, from a microphone, an audible signal associated with the detected sound; and obtaining the make and model of the PTB and the mode of operation from the machine learning model on the received audible signal.

[0012]

[0008] In an embodiment, wherein obtaining the make and model of the PTB and the mode of operation from the machine learning model based on the received audible signal comprises: converting the audible signal from a time domain to a frequency domain; and obtaining a classification of the make and model of the PTB and its mode of operation from the machine learning model based on the frequency domain audible signal.

[0013]

[0009] In an embodiment , wherein obtaining the classification of the make and model of the PTB and its mode of operation from the machine learning model based on the frequency domain of the audible signal comprises: obtaining mel-frequency cepstrum coefficients from the frequency domain audible signal; inputting the mel-frequency cepstrum coefficients to the machine learning model; and obtaining the classification of the make and model of the PTB and its mode of operation as an output from the machine learning model.

[0014]

[0010] In an embodiment wherein the machine learning model is a neural network.

[0015]

[0011] In an embodiment wherein the detected sound comprises vibrations associated with a motor of the PTB during operation.

[0016]

[0012] In an embodiment wherein providing, using a device, the real-time instructions to the user comprises: displaying, on a display of the device, the real-time instruction as visual instructions.

[0017]

[0013] In an embodiment wherein generating real-time instructions to the user based on the make, model, and model of operation comprises: comparing the classification of the make and model of the PTB and its mode of operation to one or more lookup tables; obtaining instructions associated with the classification of the mode of operation of the make and model of the PTB from the one or more lookup tables; and generating the realtime instructions using the obtained instructions.

[0018]

[0014] In an embodiment wherein the machine learning model is a first machine learning model, the method further comprising: receiving, from a microphone, an audible instruction produced by the PTB including instructions for a user to operate the PTB according to the mode of operation, wherein generating real-time instructions to the user based on the make, model, and model of operation comprises: transforming the audible instruction for the user into visual real-time instructions using a second machine learning model, wherein providing, using a device, the real-time instructions to the user comprises: displaying, using a display of the device, the real-time instructions to the user.

[0019]

[0015] In an embodiment wherein transforming the instructions for the user into visual realtime instructions using a second machine learning model comprises: converting the audible instruction from a time domain to a frequency domain; obtaining mel-frequency cepstrum coefficients from the frequency domain audible signal; and inputting the mel- frequency cepstrum coefficients to the second machine learning model.

[0020]

[0016] In an embodiment, wherein the second machine learning model comprises one or more neural networks.

[0021]

[0017] In an embodiment, after the user has brushed their teeth using the real-time guidance, a report including information related to the brushing cycle is generated and provided to the user.

[0022]

[0018] In an embodiment, the information of the report comprises which mode the user has performed, total duration of brushing and the number of times the user has brushed that day.

[0023]

[0019] According to an aspect of the present disclosure, there is provided a transitory, or non-transitory, computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform the computer-implemented method of any preceding aspect or embodiment.

[0024]

[0020] According to an aspect of the present disclosure, there is provided a device may comprise: storage having instructions stored thereon; a processor configured to execute the instructions to: classify, using a machine learning model, a make and model of a PTB and its mode of operation based on a detected sound associated with operation of the PTB; and generating real-time instructions to the user based on the make, model, and mode of operation, wherein the device further comprises a user interface configured to provide the real-time instructions to the user.

[0025]

[0021] In an embodiment, a device further comprising: a microphone configured to detect the sound associated with operation of the PTB.

[0026]

[0022] In an embodiment, a device further comprising: a communication unit configured to receive the detected sound from an external microphone attached to the PTB.

[0027]

[0023] These and other aspects of the present invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

[0028] BRIEF DESCRIPTION OF DRAWINGS

[0029]

[0024] The embodiments of the present inventions may be best understood with reference to the accompanying figures, in which:

[0025] Figure 1 shows a diagram of a PTB;

[0030]

[0026] Figure 2 shows a diagram of an external device;

[0031]

[0027] Figure 3 shows a diagram of the external device receiving a sound produced by the PTB;

[0032]

[0028] Figure 4 is a block diagram showing the steps involved in converting the audible signal to mel-frequency cepstrum coefficients;

[0033]

[0029] Figure 5 shows a block diagram of the detection model; and

[0034]

[0030] Figure 6 shows a flow chart of the computer-implemented method of claim 1 .

[0035] DESCRIPTION OF EMBODIMENTS

[0036]

[0031] At least some of the example embodiments described herein may be constructed, partially or wholly, using dedicated special-purpose hardware. Terms such as ‘component’, ‘module’ or ‘unit’ used herein may include, but are not limited to, a hardware device, such as circuitry in the form of discrete or integrated components, a Field Programmable Gate Array (FPGA) or Application Specific Integrated Circuit (ASIC), which performs certain tasks or provides the associated functionality. In some embodiments, the described elements may be configured to reside on a tangible, persistent, addressable storage medium and may be configured to execute on one or more processors. These functional elements may in some embodiments include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Although the example embodiments have been described with reference to the components, modules and units discussed herein, such functional elements may be combined into fewer elements or separated into additional elements. Various combinations of optional features have been described herein, and it will be appreciated that described features may be combined in any suitable combination. In particular, the features of any one example embodiment may be combined with features of any other embodiment, as appropriate, except where such combinations are mutually exclusive. Throughout this specification, the term “comprising” or “comprises” means including the component(s) specified but not to the exclusion of the presence of others.

[0032] With reference to Figure 1 , a power toothbrush (PTB) 10 includes an elongate body forming a handle 12, and a head 14 at an end of the handle 12. The toothbrush also includes an energy storage module 16, a motor 17 for powering the head 14, and a controller 18. The head 14 may include bristles 19 for brushing a user’s teeth.

[0037]

[0033] When in use the PTB 10 may emit a sound. The PTB 10 will emit a sound when in use due to the vibration of the motor 17. The sound emitted will have specific characteristics such as, but not limited to, the frequency, wavelength, and amplitude. The characteristic of the sound is dependent on the make of PTB 10 used, the model of PTB 10 used and the mode the PTB 10 is operating in. Each combination of PTB 10 make, model and mode will emit a unique sound.

[0038]

[0034] With reference to Figure 2, a device 20 includes a microphone 22, a speaker 23, a display 24 and a controller 25. The device may also be called an external device because it is separate to the PTB. The controller 25 may include a processor 26 and storage 27. The computer-implemented methods described below may be embodied as electronic data defining instructions stored in the storage 27 as non-transitory computer-readable media that when executed by the processor 26 cause the processor 26 to perform the respective computer-implemented method. The instructions may be loaded onto the storage 27 and thus be embodied as transitory computer readable media.

[0039]

[0035] The device may be, but is not limited to, a mobile phone, tablet, laptop, smart watch or PC.

[0040]

[0036] With reference to Figure 3, the computer implemented method includes detecting a sound associated with operation of the PTB 10. More specifically, the computer implemented method may comprise receiving, from a microphone 22 an audible signal 30 associated with the detected sound emitted by the PTB 10. The detected sound may comprise vibrations associated with the motor 17 of the PTB 10 during operation.

[0041]

[0037] The computer implemented method may be implemented as part of an application on the device.

[0042]

[0038] As shown in Figure 4, the audible signal 30 may then be converted from a time domain into a frequency domain 40. Upon conversion of the audible signal 30 to the frequency domain 40, mel-frequency cepstrum coefficients 42 may be obtained from the frequency domain audible signal 40.

[0039] With reference to Figure 5, a detection model 52 is provided for classifying a make and model of the PTB 10 and its mode of operation based on the detected sound. The detection model takes an input 50 e.g., the mel-frequency cepstrum coefficients 42, and generates an output 54. The output 54 in this case will be a classification of the PTB 10. The classification classifies the make, the model, and the mode of operation of the PTB 10.

[0043]

[0040] The detection model 52 may comprise a machine learning model. The machine learning model may be a neural network. The machine learning model may be trained on training data including sound data generated by a variety of different PTB 10 makes and models as well as their modes of operation. Specifically, the training data may include the mel-frequency cepstrum coefficients as inputs 50, and the associated make, model, and model of operation as outputs 54. The machine learning model will classify the training example, e.g. an example of a mel frequency cepstrum coefficients, as being associated with a particular make, model, and mode of operation of a PTB. The machine learning model may store this data in the storage 27.

[0044]

[0041] When an unknown PTB 10 is to be classified, the mel-frequency cepstrum coefficients 42 may be input to the trained machine learning model. The machine learning model classifies the make, model, and mode of operation of the PTB 10 using the mel- frequency cepstrum coefficients 42. As such, the computer implemented method may obtain the make and model of PTB 10 and the mode of operation from the machine learning model based on the received audio signal. Specifically, the computer implemented method may obtain the classification of the make and model of the PTB 10 and its mode of operation from the machine learning model based on the frequency domain of the received audible signal 30. Even more specifically, the computer implemented method may obtain the classification of the make and model of the PTB 10 and its mode of operation as an output 54 from the machine learning model.

[0045]

[0042] Typically, a set of user instructions is associated with each operational mode of the PTB 10. The instructions originate from the manufacturer. For example, the PTB 10 used in a deep cleaning mode may instruct the user to brush each segment of the mouth more than once, whereas a whitening mode may instruct the user to brush each segment for a longer period of time. The invention is not limited to these examples and there are many operational modes of a PTB 10, and their instructions are not only limited to extending the length of brushing.

[0043] The way in which non-connected PTBs 10 typically convey their instructions to the user is by writing the instructions in the user manual. This means that the user must either memorise the instructions or have the manual present each time they brush their teeth to follow the instructions. The intended purpose of this invention is to generate real-time instructions to the user based on the make, model, and mode of operation and then provide, using a device, the real-time instructions to the user.

[0046]

[0044] A set of instructions associated with each operational mode of a specific make and model of PTB 10 may be stored in the storage 27. These instructions of the PTB 10 may be stored in the storage 27 together with the machine learning model. The computer- implemented method may comprise Comparing the classification of the make and model of the PTB 10 and its mode of operation to one or more lookup tables.

[0047]

[0045] The lookup tables may be stored in the storage 27. The lookup tables includes the make, model and mode of operation, and the corresponding instructions. Then, the computer-implemented method may comprise obtaining instructions associated with the classification of the mode of operation of the make and model of the PTB 10 from the one or more lookup tables.

[0048]

[0046] The computer-implemented method may comprise generating the real-time instructions using the obtained instructions.

[0049]

[0047] The instructions may be provided in numerous ways. It is believed that the best way to provide the instructions in real-time, is by displaying, on a display of the device, the real-time instructions as visual instructions.

[0050]

[0048] Another method that non-connected PTB’s 10 may currently provide their brushing instructions to the user is by making an audible sound. The audible sound may correspond to a certain action that the user must perform to adhere to the instructions of the operational mode that they are using. The issue with this however is that the audible sound may be masked by the sound of the motor 17 itself and the user may not hear the audible sound. This method of providing instructions to the user does not ease the burden of needing to remember what each audible sound means.

[0051]

[0049] The microphone 22 may receive the audible instruction produced by the PTB 10 including instructions for a user to operate the PTB 10 according to the mode of operation. To overcome the inherent disadvantages of using an audible instruction, the real-time instructions to the user based on the make, model and mode of operation comprises transforming the audible instructions for the user into visual real-time instructions using a second machine learning model. Transforming the instructions for the user into visual real-time instructions may comprise using a second machine learning model. The second machine learning model may comprise one or more neural networks. The second machine learning model may be a transformer model trained to convert audible media into visual media. The training data may thus include audible instructions and their desired visual equivalents. The real-time instructions may then be provided to the user by displaying, using a display of a device.

[0052]

[0050] To avoid repeating features which have already been described in this specification, the machine learning model works in exactly the same way as the machine learning model that is used for detecting the sound of the PTB 10 itself. The second machine learning model converts the audible instructions from a time domain to a frequency domain, obtains the mel-frequency coefficients from the frequency domain audible signal, and inputs the mel-frequency cepstrum coefficients into the second machine learning model the same way as the first machine learning model.

[0053]

[0051] As the device will have the information associated with the user’s brushing for a brushing cycle based off the generated real-time instructions, a report including information relating to the brushing cycle may be generated and provided to the user after the user has brushed their teeth using the real-time guidance.

[0054]

[0052] The report may comprise information such as the mode in which the user has performed their brushings, the total duration of brushing, and the number of times the user has brushed their teeth that specific day.

[0055]

[0053] With reference to Figure 6, a computer-implemented method of providing real-time guidance associated with a user brushing their teeth using a power toothbrush, PTB (10), may be summarised as including: detecting 100 a sound associated with operation of the PTB (10); classifying 102, using a detection model (52), a make and model of the PTB (10) and its mode of operation based on the detected sound; generating 104 real-time instructions to the user based on the make, model, and mode of operation; and providing 106, using a device, the real-time instructions to the user.

[0056]

[0054] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments.

[0055] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of 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. A single processor or other unit may fulfil the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measured cannot be used to advantage. Any reference signs in the claims should not be construed as limiting the scope.

Claims

CLAIMS1 . A computer-implemented method of providing real-time guidance to a user about brushing their teeth using a power toothbrush, PTB (10), the computer- implemented method comprising: detecting a sound associated with operation of the PTB (10); classifying, using a detection model (52), a make and model of the PTB(10) and its mode of operation based on the detected sound; generating real-time instructions to the user based on the make, model, and model of operation; and providing, using a device, the real-time instructions to the user.

2. The computer-implemented method of Claim 1 , wherein the detection model (52) comprises a machine learning model.

3. The computer-implemented method of Claim 2, wherein classifying, using the machine learning model, the make and model of the PTB (10) and its mode of operation based on the detected sound comprises:Receiving, from a microphone (22), an audible signal (30) associated with the detected sound; and obtaining the make and model of the PTB (10) and the mode of operation from the machine learning model based on the received audible signal (30).

4. The computer-implemented method of Claim 3, wherein obtaining the make and model of the PTB (10) and the mode of operation from the machine learning model based on the received audible signal (30) comprises:Converting the audible signal (30) from a time domain to a frequency domain (40)c; andObtaining a classification of the make and model of the PTB (10) and its mode of operation from the machine learning model based on the frequency domain audible signal (30).

5. The computer-implemented method of Claim 4, wherein obtaining the classification of the make and model of the PTB (10) and its mode of operation from the machine learning model based on the frequency domain of the audible signal (30) comprises: obtaining mel-frequency cepstrum coefficients (42) from the frequency domain audible signal (40); inputting the mel-frequency cepstrum coefficients (42) to the machine learning model; and obtaining the classification of the make and model of the PTB (10) and its mode of operation as an output (54) from the machine learning model.

6. The computer-implemented method of any preceding claim, wherein the machine learning model is a neural network.

7. The computer-implemented method of any preceding claim, wherein the detected sound comprises vibrations associated with a motor (17) of the PTB (10) during operation.

8. The computer-implemented method of any preceding claim, wherein providing, using a device, the real-time instructions to the user comprises: displaying, on a display (24) of the device, the real-time instruction as visual instructions.

9. The computer-implemented method of Claim 8, wherein generating real-time instructions to the user based on the make, model, and model of operation comprises: comparing the classification of the make and model of the PTB (10) and its mode of operation to one or more lookup tables; obtaining instructions associated with the classification of the mode of operation of the make and model of the PTB (10) from the one or more lookup tables; and generating the real-time instructions using the obtained instructions.

10. The computer-implemented method of any of Claims 1 to 8, wherein the machine learning model is a first machine learning model, the method further comprising: receiving, from a microphone (22), an audible instruction produced by the PTB (10) including instructions for a user to operate the PTB (10) according to the mode of operation, wherein generating real-time instructions to the user based on the make, model, and model of operation comprises: transforming the audible instruction for the user into visual real-time instructions using a second machine learning model, wherein providing, using a device, the real-time instructions to the user comprises: displaying, using a display (24) of the device, the real-time instructions to the user.

11. The computer-implemented method of Claim 10, wherein transforming the instructions for the user into visual real-time instructions using a second machine learning model comprises: converting the audible instruction from a time domain to a frequency domain; obtaining mel-frequency cepstrum coefficients from the frequency domain audible signal; and inputting the mel-frequency cepstrum coefficients to the second machine learning model.

12. The computer-implemented method of Claim 11 , wherein the second machine learning model comprises one or more neural networks.

13. The computer-implemented method of any preceding claim, wherein after the user has brushed their teeth using the real-time guidance, a report including information related to the brushing cycle is generated and provided to the user.

14. The computer-implemented method of Claim 13 wherein the information of the report comprises which mode the user has performed, total duration of brushing and the number of times the user has brushed that day.

15. A device comprising: storage having instructions stored thereon; a processor configured to execute the instructions to: detect a sound associated with operation of the PTB (10); classify, using a detection model (52), a make and model of a PTB (10) and its mode of operation based on a detected sound associated with operation of the PTB (10); and generating real-time instructions to the user based on the make, model, and model of operation; wherein the device further comprises a user interface configured to provide the real-time instructions to the user.

Images