EP4644072A1

EP4644072A1 - User identification system

Info

Publication number: EP4644072A1
Application number: EP24173335.1A
Authority: EP
Inventors: André Christian STEFAN; Daniel Alonzo DIRKSZ; Daniele Solerio
Original assignee: Koninklijke Philips NV
Current assignee: Koninklijke Philips NV
Priority date: 2024-04-30
Filing date: 2024-04-30
Publication date: 2025-11-05
Also published as: WO2025228716A1

Abstract

Proposed embodiments aim to provide a user identification system configured to obtain force data describing the force applied to a head component of the personal care device during a usage session and identify based on this force data a minimum force value. The proposed user identification system is then configured to determine the identification of the user based on the minimum force value.

Description

FIELD OF THE INVENTION

The present invention relates to the field of personal care devices, and more particularly to systems and methods for identifying users of personal care devices.

BACKGROUND OF THE INVENTION

Modern personal care devices are often configured to allow multiple users to use the same device. For example, most personal care devices contain a treatment component that is held against a body part of the user during the use of the device. Key examples of such components are the brush head of a toothbrush that is passed along a user's oral surfaces during use to provide cleaning treatments, and the razor component of a shaving device that is held against the skin. The treatment component of some personal care device may be replaceable. This is advantageous in that it improves the longevity of the device (as the treatment component may be swapped out for a new component when it becomes worn down) and allows for the possibility that different types of treatment component can be attached to the same device. The replaceable nature of the treatment component also allows for multiple users to use the same device simply by switching out the attached treatment component.
In recent years, there has been a growing interest in personalizing the user experience of personal care devices. This often involves collecting user data describing characteristics of the user and how they operate the personal care device to provide personalized recommendations for future use of the device. However, for devices used by multiple individuals it may be difficult to distinguish which data corresponds to which user and therefore any personalized recommendations may be unreliable.

SUMMARY OF INVENTION

The invention is defined by the claims.
According to examples in accordance with an aspect of the proposed invention, there is provided a user identification system for a personal care device, the personal care device comprising a head component configured to be held against a body part of a user during use of the personal care device.
The user identification system comprises a data acquisition module configured to obtain force data describing a force applied to the head component during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session. The system also comprises a data analysis module configured to identify the minimum force value based on the obtained force data, and to determine an identification of the user of the personal care device based on the identified minimum force value.
Proposed concepts thus aim to provide schemes, solutions, concepts, designs, methods, and systems pertaining to a user identification system for a personal care device configured to identify the user of the personal care device during a given usage session based on a minimum force value.
In particular, embodiments aim to provide a user identification system configured to obtain force data describing the force applied to a head component of the personal care device during the usage session and identify within from force data a minimum force value. The proposed user identification system is then configured to determine the identification of the user based on the minimum force value.
Modern personal care devices may often be suitable to be used by multiple users. For example, powered toothbrushes are often provided with replaceable brush heads that may be swapped such that the handle unit of the device can be used by multiple individuals. Similarly, shavers or skincare devices may be configured such that they are able to have multiple users. In addition, modern personal care devices may often be provided with adjustable settings or may be configured to gather usage data that is used to provide personalized feedback and recommendations to a user. It may therefore be of great advantage to be able to determine for a given usage session of a device the identity of the individual using the device. By identifying specific users, the personal care device may be able to adapt to provide an optimized personal care experience tailored to each user. Additionally, the user identification data could be shared with health care professionals for further professional coaching.
Many personal care devices are configured to be held against a body part of the user during the use of the device in order for the device to carry out some form of personal care treatment on the user. The performance of the device may be greatly impacted by the force with which the device is held against the user's body. For example, for powered toothbrushes the pressure with which the brush head is held against the user's teeth and gums may greatly affect the cleaning treatment received. This force may also vary significantly between users. As such many personal care devices are equipped with sensors to measure this force.
It was realized by the inventors of this application that the minimum force applied to the head component of a personal care device during a given usage session is a reliable identifier of which user is operating the device. This quantity varies significantly between different users, whilst displaying little variation across different usage sessions of the same user. The proposed system therefore leverages this minimum force value identified for a usage session to determine an identification of the user of the device. The minimum force may also be an easy value to measure or calculate and therefore the proposed invention may allow for efficient and accurate determination of the identity of a user of a personal care device for a given usage session.
In summary the proposed system allows for the identification of the user of a personal care device each time the device is used. This is achieved by analysing force data describing the force applied to the head component of the personal care device during use to identify a minimum force value and then determining an identification of the user based on this minimum force value.
Ultimately, an improved component wear assessment system for a personal care device may be supported by the proposed concept(s).
In some embodiments, the minimum force value is the absolute minimum force applied to the head component by the user during the usage session. The absolute minimum may be an easy measure of the minimum force applied to the head component to calculate and may provide the most accurate identification of the user.
In other embodiments, the force data further includes information about a maximum force value applied to the head component during the usage session. The data analysis module is further configured to identify the maximum force value based on the obtained force data and determine the identification of the user of the personal care device based on the identified minimum and maximum force values. This allows for a more comprehensive understanding of the user's use of the personal care device, which may allow for a more reliable identification of the user.
In yet other embodiments, the force data further includes information about a number of times within the usage session that the force applied to the head component changes direction. The data analysis module is further configured to identify, based on the force data, the number of times the force applied to the head component changes direction during the usage session and determine the identification of the user based on this number and the minimum force value. This provides an additional statistic to be used in user identification, resulting in a more accurate determination of which user is associated with the usage session being analysed.
In some embodiments, the identification of the user includes at least one of a user identification number, a name, a gender, and an age. Thus, various different parameters may be used to identify the user of the device. For example, it may not be necessary to identify the specific user of the device but just whether the device is being used by a child or an adult.
In other embodiments, obtaining force data includes obtaining at least one force value measured by a force sensor of the personal care device configured to measure the force applied to the head component during a usage session of the personal care device by the user. Thus, the system may be configured to utilise force data already being gathered by a force sensor within the personal care device, allowing for efficient integration of the proposed user identification system into known personal care devices.
In yet other embodiments, the force data includes a plurality of force values, each force value describing the force applied to the head component during a respective time period. The data analysis module is further configured to determine a distribution of the plurality of force values, calculate a statistical force parameter value describing a parameter of the determined distribution of the plurality of force values, and determine the identification of the user of the personal care device based on the calculated statistical force parameter value and the identified minimum force value. Statistical analysis may allow for a more comprehensive understanding of the use of the device during the usage session and therefore a more reliable identification of the user.
In some embodiments, the statistical force parameter value may comprise at least one of: a percentile value of the distribution of the plurality of force values; a mean value of the distribution of the plurality of force values; a median value of the distribution of the plurality of force values; a standard deviation of the distribution of the plurality of force values; a maximum value of the distribution of the plurality of force values; a minimum value of the distribution of the plurality of force values; a range of the distribution of the plurality of force values; and a spectral analysis parameter value of the distribution of the plurality of force values. These statistical force parameters have all been shown to be useful in providing accurate user identification.
In some embodiments, the data analysis module may be further configured to: calculate a plurality of statistical force parameter values each describing a different parameter of the determined distribution of the plurality of force values; process the plurality of statistical force parameters with a machine learning model to determine at least one identifying statistical force parameter value, describing a statistical force parameter that facilitates accurate identification of the user based on the force data; and determining the identification of the user based on the at least one identifying statistical force parameter value and the minimum force value. Thus, a machine learning model may be used advantageously to identify the parameters most likely to result in accurate and reliable identification of a user based on force data. In this way, the effectiveness of the proposed user identification system may be improved.
In some embodiments, the machine learning model comprises a support vector machine (SVM). These types of machine learning models have been shown to be particularly advantageous for categorization and identification tasks.
In some embodiments, the force data comprises a plurality of force values each describing the force applied to the head component during a respective time period, and identifying the minimum force value based on the obtained force data may comprise determining a minimum value of the plurality of force values. Thus, the system may be configured to obtain multiple force values across the duration of the usage period, allowing for efficient determination of the minimum force value.
According to another aspect of the proposed invention, there is provided a personal care device comprising: a head component configured to be held against a body part of a user during use of the personal care device; a force sensor configured to measure a force applied to the head component during use of the personal care device; and the user identification system of any of the above discussed embodiments.
The personal care device may comprise at least one of: an oral care device; a hair removal device; and a skin treatment device. The proposed user identification system may therefore be advantageous in that it may be integrated into a wide range of different personal care devices.
According to yet another aspect of the proposed invention, there is provided a computer-implemented method for identifying a user of a personal care device, the personal care device comprising a head component configured to be held against a body part of a user during use of the personal care device. The method comprising: obtaining force data describing a force applied to the head component during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session; identifying the minimum force value based on the obtained force data; and determining an identification of the user of the personal care device based on the identified minimum force value.
According to another aspect of the present invention there is provided a computer program comprising code means for implementing the above computer-implemented method when said program is run on a computer.
These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

BRIEF DESCRIPTION OF FIGURES

For a better understanding of the invention, and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

FIG. 1 is a block diagram of a user identification system for a personal care device, according to a proposed embodiment;
FIG. 2 is a side view of a drivetrain assembly for a power toothbrush;
FIG. 3 is a simplified flow diagram of a method for determining an identification of a user of a personal care device, according to a proposed embodiment;
FIG. 4 is a simplified flow diagram of a method for determining an identification of a user of a personal care device according to another proposed embodiment; and
FIG. 5 is a schematic diagram of an electric shaving device comprising a user identification system, according to an aspect of the proposed invention.

DETAILED DESCRIPTION

The invention will be described with reference to the Figures.
It should be understood that the Figures are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the Figures to indicate the same or similar parts.
It should also be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, systems and methods of the present invention will become better understood from the following description, appended claims, and accompanying drawings. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
Implementations in accordance with the present disclosure relate to various techniques, methods, schemes and/or solutions pertaining to a user identification system for a personal care device, the personal care device comprising a head component configured to be held against a body part of the user during use of the personal care device. According to proposed concepts a number of possible solutions may be implemented separately or jointly. That is, although these possible solutions may be described below separately, two or more of these possible solutions may be implemented in one combination or another.
Personal care devices may be used by multiple individuals, each of whom may operate the personal care device differently and have different personal care requirements. In order to provide personalised treatment to each user, it may be beneficial to be able to determine for each usage session of the device, which user is operating the device.
The proposed invention uses the minimum force applied to a head component of the device during a given usage session to identify the user. This has been identified as a value that varies significantly between users whilst remaining relatively constant across different usage sessions by the same user. The force applied to the head component is also an easily measurable quantity, and indeed many modern personal care devices are already equipped with pressure sensors for measuring this. The proposed method of identifying users based on the minimum force applied to the head component may therefore be particularly advantageous in providing accurate and reliable identification of users.
In summary, an exemplary embodiment of the proposed user identification system for personal care devices contains the following modules:

A. Data Acquisition: this module is configured to acquire force data describing the force applied to a head component (which is the component of the personal care device configured to be held against a body part of the user during its operation) during a usage session of the personal care device. The usage session refers to any period of time in which the personal care device is operated for which there is only a single user of the personal care device. The force data comprises information describing a minimum force value being the minimum force applied to the head component during the usage session. This value may be easily extracted from the force data or may need to be calculated from the force data.
B. Data Analysis: the obtained force data may be analysed in various different ways in order to identify the user of the personal care device. Statistical analysis may be used beneficially in certain embodiments to summarise the force data and aid in accurate user identification. Certain functions of the data analysis module may be carried out using a machine learning algorithm. For example, calculated statistical measures of the force data may be fed to a machine learning algorithm which has been trained on a plurality of similar datasets to determine the optimal measures on which to base the identification of the user of the personal care device. Crucially, the data analysis module is configured to base the identification of the user on the minimum force value.

Referring now to Fig. 1, there is depicted a user identification system 100 for a personal care device, the personal care device comprising a head component configured to be held against a body part of a user during use of the personal care device, according to a proposed embodiment.
The user identification system 100 comprises a data acquisition module 110 configured to obtain force data 115 describing a force applied to the head component during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session. By this it is meant that the minimum force value is contained within the force data 115 or may be calculated from the force data 115. The usage session described herein is a period of time over which the personal care device is used by only a single user.
In this exemplary embodiment, obtaining force data comprises obtaining at least one force value measured by a force sensor of the personal care device configured to measure the force applied to the head component during the usage session of the personal care device by the user. Thus, the data acquisition module is adapted to permit communication between a force sensor within the personal care device and the user identification system 100 to obtain from the force sensor the force data 115. Once the force data has been obtained by the data acquisition module 110 it is then transmitted to a data analysis module 120 of the user identification system.
The data analysis module 120 is configured to identify the minimum force value based on the force data 115, and to determine an identification of the user of the personal care device based on the identified minimum force value. In this exemplary embodiment, the force data comprises a plurality of force values each describing the force applied to the head component of the personal care device during a respective time period, and identifying the minimum force value based on the obtained force data comprises determining a minimum value of the plurality of force values. The minimum force value is taken to be the absolute minimum value of the force applied to the head component of the personal care device during the usage session.
Thus, in this example, a force sensor within the personal care device is configured to take measurements of the force applied to the head component of the personal care device during the usage session. These measured values are transmitted to the data acquisition module 110 of the user identification system 100. The data analysis module 120 then identifies the minimum measured value of the force applied to the head component of the personal care device and uses this value to determine an identification of the user.
In this exemplary embodiment the determined identification of the user comprises a unique user identification number i.e. each user of the personal care device is assigned a unique number and the user identification system 100 is configured to determine the user identification number of the user of the device during a given usage session.
In this exemplary embodiment the determination of the user identification relies on the use of historic use data of the personal care device. For example, historic usage data of the personal care device describing the force applied to the head component of the personal care device during several historic usage sessions of the personal care device may be stored. The force data of each usage session is tagged with a user identification number describing which user of the device is associated with each usage session. This tagged data is then used to train a machine learning model to determine the user identification number of a usage session based on the minimum force value of a current usage session.
Suitable machine-learning algorithms for being employed in the present invention will be apparent to the skilled person. Examples of suitable machine-learning algorithms include decision tree algorithms and artificial neural networks. Other machine-learning algorithms such as logistic regression, support vector machines or Naive Bayesian models are suitable alternatives.
In particular, an algorithm based on SVM (Support Vector Machine) may be used. This is a supervised learning method and operates by identifying the ideal hyperplane for dividing data into multiple classes. The margin, or distance between the hyperplane and the closest data points (i.e. personal care device) from each category - this may also be referred to as the support vector - is maximised. SVM looked for the hyperplane that minimized categorisation errors and effectively categorises training data while also having a good generalization to new data. In case the data cannot be separated into categories based on a linearly calculation, SVM can use kernel functions to convert data into a higher-dimensional space where a separating hyperplane can be created. This gives SVM robustness and strong generalization capabilities, making it a flexible and effective tool for this type of application.
The structure of an artificial neural network (or, simply, neural network) is inspired by the human brain. Neural networks are comprised of layers, each layer comprising a plurality of neurons. Each neuron comprises a mathematical operation. In particular, each neuron may comprise a different weighted combination of a single type of transformation (e.g., the same type of transformation, sigmoid etc. but with different weightings). In the process of processing input data, the mathematical operation of each neuron is performed on the input data to produce a numerical output, and the outputs of each layer in the neural network are fed into the next layer sequentially. The final layer provides the output.
Methods of training a machine-learning algorithm are well known. Typically, such methods comprise obtaining a training dataset, comprising training input data entries and corresponding training output data entries. An initialized machine-learning algorithm is applied to each input data entry to generate predicted output data entries. An error between the predicted output data entries and corresponding training output data entries is used to modify the machine-learning algorithm. This process can be repeated until the error converges, and the predicted output data entries are sufficiently similar (e.g. ±1%) to the training output data entries. This is commonly known as a supervised learning technique.
For example, weightings of the mathematical operation of each neuron may be modified until the error converges. Known methods of modifying a neural network include gradient descent, backpropagation algorithms and so on.
The training input data entries for the machine learning algorithm of the data analysis module described above correspond to a set of historic force data describing the force applied to the head component of the personal care device during several historic usage sessions of the personal care device. The training output data entries correspond to the user identification number associated with each set of historic force data. In other words, the machine learning algorithm of the present invention may be trained using a deep learning algorithm configured to receive an array of training inputs and respective known outputs, wherein a training input comprises historic force data of a historic usage session of a personal care device and a respective known output comprises a user identification number of the usage session. In this way a machine learning model may be trained to determine a user identification number based on a minimum force value.
Although in this embodiment, the minimum force value is the absolute minimum force applied to the head component by the user during the usage session, in alternative embodiments this may not be the case. For example, before the minimum force value is identified, the force data may be filtered to remove data corresponding to short time scale variations in the force applied to the head component of the personal care device. The minimum force value may therefore describe the lowest force value that is applied to the head component of the personal care device for a continuous minimum period of time. Alternatively, the minimum force data may comprise the minimum force value applied to the personal care device in a predetermined direction.
Similarly, other aspects of the user identification system 100 may be implemented differently in other embodiments. For example, the force data may not comprise a plurality of force values describing the force applied to the head component at various time periods within the usage session but may instead simply comprise a single minimum force value i.e. a force sensor of the personal care device could be configured only to measure the minimum force applied to the head component during a usage session.
Further the force data may not be obtained directly from a force sensor integrated into the personal care device. The force sensor may be external to the personal care device and may in some examples be integrated into the proposed user identification system. This would be advantageous in allowing the application of the proposed system to personal care devices that are not already equipped with force or pressure sensors for detecting the force applied to a head component of the device during its use.
In further embodiments, the identification of the user may not be a user identification number as discussed above. In some embodiments the identification of the user may be at least one of: a name; a gender; and an age. In some instances, for example when a device has a large number of different users displaying similar use habits, it may not be possible to accurately determine a specific user from the minimum force value. In this instance it may still be possible and beneficial to determine demographic characteristics of the user, for example whether they are a child or an adult and their gender, which may aid in providing personalized feedback and recommendations to the user.
The data analysis module need not utilise a machine learning model as discussed above. Determining the identification of the user based on the minimum force value may instead comprise comparing the minimum force values to values stored in a look-up table and identifying the user based on this comparison.
It will be understood that the data analysis module and the data acquisition module may be formed of conventional processor components. Although discussed as distinct modules in this document, the data analysis module and the data acquisition module may comprise a single processor.
As discussed above, the system makes use of processors to perform the data processing. The processor can be implemented in numerous ways, with software and/or hardware, to perform the various functions required. The processor typically employs one or more microprocessors that may be programmed using software (e.g., microcode) to perform the required functions. The processor may be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.
Examples of circuitry that may be employed in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).
In various implementations, the processor may be associated with one or more storage media such as volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM. The storage media may be encoded with one or more programs that, when executed on one or more processors and/or controllers, perform the required functions. Various storage media may be fixed within a processor or controller or may be transportable, such that the one or more programs stored thereon can be loaded into a processor.
Referring now to FIG. 2, a side view of a drivetrain assembly for a power toothbrush 200 is depicted.
The power toothbrush 200 comprises a head component 210 (i.e., brush head) connected to an actuator (i.e. drive train) 220. In operation, the actuator is configured to drive the brush head 210 to vibrate. The user passes the brush head across their oral surfaces during use of the device in order to provide mechanical cleaning of their teeth.
The drivetrain 220 comprises a motor 230 which generates the required torque for driving the brush head 210. The motor 230 is connected to the brush head 210 via an elastic structure comprising three torsional springs: a rear spring 240, a front spring 245, and a coupling spring 250. The rear spring connects at one end to the motor and at its other end to a positionally fixed frame unit 260. The front spring 245 connects the frame unit 260 to the brush head. The coupling spring directly connects the motor 230 to the brush head 210. The arrangement of these components results in a mechanism designed to allow the brush head 210 to move in response to the motor's actuation, with the spring elements 250, 245, and 240 providing a resilient force that may contribute to the brush head's motion during operation.
The user identification system 100 (not shown) may be used to determine an identification of the user of the power toothbrush 200 during a usage session of the device. The user identification system may be integrated into the personal care device 100 or may exist in a separate device. For example, the personal care device 100 may comprise an external processing system. In this latter case, the personal care device 200 may be equipped with components known in the art for measuring and transmitting force data describing the force applied to the head component of the power toothbrush 200 during a usage session of the device to the data acquisition unit of the external user identification system.
The actuator 220 is a common type of actuating mechanism used in personal care devices which is known as a double-resonant actuator. One characteristic feature of the operation of a double-resonant actuator is that it displays inherent load stroke stability when driven at a special frequency. When driving at this frequency, if the load on the actuator increases (i.e., the force applied to the brush head 210 increases) the stroke of the motor (indicated by the arrow 270) increases to compensate for the damping effect produced by the increased load. This results in the stroke value of the brush head (indicated by the arrow 280 in Fig. 2) remaining relatively stable as the load on the actuator varies. Therefore, the load on the actuator may be a key factor affecting the operation of the personal care device. Since this parameter is also highly variable between different users, the inventors of this application realised that force data and in particular the minimum force value (i.e., the smallest load applied to the actuator) may be leveraged to automatically identify different users of a personal care device. The proposed system is therefore particularly adept at identifying the user of a device from sensor data and thereby allowing for personalised feedback and operation of the personal care device to be provided.
Referring now to FIG. 3, a simplified flow diagram of a computer-implemented method 300 for identifying a user of a personal care device. The method 300 begins with the force data acquisition step 310 comprising obtaining force data. This force data describes the force applied to the head component of the personal care device during a usage session of a personal care device. In this exemplary embodiment, the force data comprises information about the minimum and maximum force values applied to the head component during the usage session, as well as the number of times the force applied to the head component changes direction during the usage session.
The method then proceeds to a step 320 of identifying, based on the obtained force data, a minimum force value describing the minimum force applied to the head component of the personal care device during a usage session of the device. Depending on the form of the obtained force data this may comprise simply identifying the lowest value of a plurality of force values or may comprise calculating a minimum force value based on analysis of the distribution of force values measured. The method 300 also comprises, in a step 330, identifying, based on the force data, a maximum force value describing the maximum force applied to the head component of the personal care device during the usage session.
The method 300 further involves the identification, in a step 340, based on the force data, of the number of times the force applied to the head component changes direction during the usage session. For example, the force data may comprise a plurality of force values describing the component of the force applied to the head component of the personal care device in a direction perpendicular to the surface of the user body part the head component is being applied to. Therefore, a positive force value may denote a pressure force applied to the head component in a direction perpendicularly away from the surface of the body part of the user towards the personal care device. A negative force value then denotes a pulling force applied to the head component in a direction perpendicularly towards the surface of the body part of the user and away from the personal care device. In this instance, the number of times the force applied to the head component changes direction comprises the number of times within the usage session the value of the force applied to the head component changes from a positive value to a negative value i.e., the number of zero-crossings within the force data.
It will be understood that the force need not be measured in this perpendicular direction. The force data may describe the force applied to the head component along any suitable axis. The number of zero-crossings within the force data would then still be a suitable measure of the number of times the force applied to the head component changes direction. Alternatively, the force data may comprise more detailed directional data describing the direction of the force applied to head component during the usage session, and identifying the number of times the force applied to the head component changes direction may comprise analysis of this detailed directional data.
Once these three values have been determined, the method 300 proceeds to a step 350 of determining an identification of the user of the device based on the minimum force value, the maximum force value, and the number of times the force applied to the head component changes direction during the usage session. Thus, the proposed method for identifying a user associated with a given usage session of a personal care based on force data describing the force applied to a head component of the person care device may leverage all three of: the minimum force, the maximum force, and the number of times within the usage session that the force applied to the head component changes direction. The combination of these three features has been shown to be optimal for accurately identifying the user associated with a given usage session.
Referring now to Fig. 4, there is depicted a simplified flow diagram of a computer-implemented method 400 for identifying a user of a personal care device according to an alternative embodiment.
The user identification method 400 begins with a force data acquisition step 410, comprising obtaining force data. This force data comprises a plurality of force values describing the force applied to the head component of the personal care device at respective times during a usage session of a personal care device. The force data further comprises information about the minimum force applied to the head component during the usage session.
Following the force data acquisition step 410, the method 400 proceeds to a minimum force identification step 420. In this step, the minimum force value applied during the usage session is identified based on the obtained force data.
Step 430 of the method 400 comprises, determining, based on the force data, a distribution of the plurality of force values of the force data. Once the distribution has been determined, the method proceeds to a step 440 of calculating a plurality of statistical force parameter values of the force data, each describing a different parameter of the determined distribution of the plurality of force values. The statistical force parameter values comprise at least one of: a percentile value of the distribution of the plurality of force values; a mean value of the distribution of the plurality of force values; a median value of the distribution of the plurality of force values; a maximum value of the distribution of the plurality of force values; a minimum value of the distribution of the plurality of force values; and a range of the distribution of the plurality of the force values.
Alternatively, the statistical analysis may involve the use of spectral analysis. For example, a fast Fourier transform, or a discrete Fourier transform may be used to analyse the distribution of the plurality of force values. Parameters relating to the composition of the distribution may then be determined that are used in the identification of a user from the force data.
Once the plurality of statistical force parameter values have been calculated, the method proceeds to a step 450 comprising processing the plurality of statistical force parameters with a machine learning model to determine at least one identifying statistical force parameter value describing a statistical force parameter that facilitates accurate identification of the user based on the force data.
Suitable machine-learning algorithms for being employed in the present invention will be apparent to the skilled person. Examples of suitable machine-learning algorithms include decision tree algorithms and artificial neural networks. Other machine-learning algorithms such as logistic regression, support vector machines or Naive Bayesian models are suitable alternatives.
In particular, an algorithm based on SVM (Support Vector Machine) may be used. This is a supervised learning method and operates by identifying the ideal hyperplane for dividing data into multiple classes. The margin, or distance between the hyperplane and the closest data points (i.e. personal care device) from each category - this may also be referred to as the support vector - is maximised. SVM looked for the hyperplane that minimized categorisation errors and effectively categorises training data while also having a good generalization to new data. In case the data cannot be separated into categories based on a linearly calculation, SVM can use kernel functions to convert data into a higher-dimensional space where a separating hyperplane can be created. This gives SVM robustness and strong generalization capabilities, making it a flexible and effective tool for this type of application.
Training of the machine learning model discussed above may rely on simulated or historic force data of personal care devices. The training input data entries for the machine learning model correspond to example statistical force parameter values for different usage sessions of a personal care device. These may correspond to real force data of real usage sessions or simulated stroke data of simulated usage sessions. The training output data entries correspond to the identification of the user of the device for each usage sessions. In other words, the machine learning algorithm of the present invention may be trained using a deep learning algorithm configured to receive an array of training inputs and respective known outputs, wherein a training input comprises a plurality of training statistical force parameters of a usage session and a respective known output comprises a determined identification of the user of the personal care device. Training of the machine learning model thereby identifies the most useful statistical force parameters on which to base an identification of the user and forms a trained model capable of identifying the user based on these parameters. This may then be qualified using the minimum force value which has been shown to be the key parameter for determining user identity from force data.
Finally, once the at least one identifying statistical force parameter has been determined the method proceeds to a step 460, comprising determining the identification of the user on the at least one identifying statistical force parameter value and the minimum force value.
Although the method 400 a plurality of statistical force parameter values are calculated and a machine learning model used to identify within the plurality of statistical force parameter values at least one identifying statistical force parameter value, in other embodiments this need not be the case. For example, in an alternative embodiment, only a single statistical force parameter value may be calculated that has been predetermined to be a good indicator of the identity of a user of the device. Determining the identification of the user may then be based on the minimum force value and the calculated single statistical force parameter.
Referring now to FIG. 5, there is depicted a schematic diagram of a personal care device 500 according to a proposed embodiment.
In this exemplary embodiment, the personal care device 500 is an electric shaving device comprising a head component 540 connected to a handle 550 that houses functional components of the personal care device 500.
The electric shaving device 500 further comprises an actuator 520, housed within the handle 550, which is configured to drive vibratory shaving elements 510 of the head component 540 to vibrate during operation of the personal care device 500. The head component 540 further comprises a force sensor 530 configured to measure the force with which a user presses the shaving elements 510 against their skin during use of the device 500. The body 550 may also comprise a power unit (not shown) to provide power to the actuator 520.
The electric shaving device 500 further comprises the user identification system 100 comprising the data acquisition module 110 and the data analysis module 120. As discussed with reference to Fig. 1, the data acquisition module of the user identification system 100 is configured to obtain force data describing a force applied to the head component 540 during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session. The data analysis module of the user identification system 100 is then configured to identify the minimum force value based on the obtained force data, and to determine an identification of the user of the personal care device based on the identified minimum force value.
In this exemplary embodiment, the electric shaving device 500 further comprises a force sensor 530 configured to obtain the force data. This is then transmitted to the user identification system 100.
Although discussed in the context of an electric shaver, it will be understood that the user identification system of the proposed invention may be integrated into a wide variety of personal care devices that comprise head components configured to be held against a body part of a user during use. For example, the personal care device may comprise at least one of: an oral care device; a skin treatment device; and a hair removal device. The user identification system 100 may be adapted to suit the specific requirements of these different types of personal care devices. For instance, the user identification system 100 may be configured to analyse different forms of force data, use different algorithms for user identification, or provide different types of feedback depending on whether the personal care device is an oral care device, a skin treatment device, or a hair removal device.
The proposed methods and systems may be implemented in hardware or software, or a mixture of both (for example, as firmware running on a hardware device). To the extent that an embodiment is implemented partly or wholly in software, the functional steps illustrated in the process flow diagrams may be performed by suitably programmed physical computing devices, such as one or more central processing units (CPUs) or graphics processing units (GPUs). Each process - and its individual component steps as illustrated in the flow diagrams - may be performed by the same or different computing devices. According to embodiments, a computer-readable storage medium stores a computer program comprising computer program code configured to cause one or more physical computing devices to carry out a control method as described above when the program is run on the one or more physical computing devices.
Storage media may include volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM, optical discs (like CD, DVD, BD), magnetic storage media (like hard discs and tapes). Various storage media may be fixed within a computing device or may be transportable, such that the one or more programs stored thereon can be loaded into a processor.
To the extent that an embodiment is implemented partly or wholly in hardware, some of the blocks shown in the block diagrams may be separate physical components, or logical subdivisions of single physical components, or may be all implemented in an integrated manner in one physical component. The functions of one block shown in the drawings may be divided between multiple components in an implementation, or the functions of multiple blocks shown in the drawings may be combined in single components in an implementation. Hardware components suitable for use in 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 to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.
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 measures cannot be used to advantage. If a computer program is discussed above, it may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. If the term "adapted to" is used in the claims or description, it is noted the term "adapted to" is intended to be equivalent to the term "configured to". Any reference signs in the claims should not be construed as limiting the scope.
The flow diagrams and block diagrams in the Figures 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 the flow diagrams or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flow diagrams and combinations of blocks in the block diagrams and/or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

A user identification system (100) for a personal care device, the personal care device comprising a head component configured to be held against a body part of a user during use of the personal care device, wherein the user identification system comprises:
a data acquisition module (110) configured to obtain force data (115) describing a force applied to the head component during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session; and

a data analysis module (120) configured to identify the minimum force value based on the obtained force data, and to determine an identification of the user of the personal care device based on the identified minimum force value.
The user identification system of claim 1, wherein the minimum force value is the absolute minimum force applied to the head component by the user during the usage session.
The user identification system of any of claims 1 and 2, wherein the force data further comprises information about a maximum force value applied to the head component during the usage session,
and wherein the data analysis module is further configured to identify (330) the maximum force value based on the obtained force data and determine (350) the identification of the user of the personal care device based on the identified minimum and maximum force values.
The user identification system of any preceding claim, wherein the force data further comprises information about a number of times within the usage session that the force applied to the head component changes direction,
and wherein the data analysis module is further configured to identify (340), based on the force data, the number of times the force applied to the head component changes direction during the usage session and determine (350) the identification of the user based on this number and the minimum force value.
The user identification system of any preceding claim, wherein the identification of the user comprises at least one of:
a user identification number;

a name;

a gender; and

an age.
The user identification system of any preceding claim, wherein obtaining force data comprises obtaining at least one force value measured by a force sensor of the personal care device configured to measure the force applied to the head component during a usage session of the personal care device by the user
The user identification system of any preceding claim, wherein the force data comprises a plurality of force values, each force value describing the force applied to the head component during a respective time period, and
wherein the data analysis module is further configured to:
determine (430), based on the force data, a distribution of the plurality of force values;

calculate (440) a statistical force parameter value describing a parameter of the determined distribution of the plurality of force values; and

determine (460) the identification of the user of the personal care device based on the calculated statistical force parameter value and the identified minimum force value.
The user identification system of claim, wherein the statistical force parameter comprises at least one of:
a percentile value of the distribution of the plurality of force values;

a mean value of the distribution of the plurality of force values;

a median value of the distribution of the plurality of force values;

a standard deviation of the distribution of the plurality of force values;

a maximum value of the distribution of the plurality of force values;

a minimum value of the distribution of the plurality of force values;

a range of the distribution of the plurality of force values; and

a spectral analysis parameter value of the distribution of the plurality of force values.
The user identification system of any of claims 7 and 8, wherein the data analysis module is further configured to:
calculate (440) a plurality of statistical force parameter values each describing a different parameter of the determined distribution of the plurality of force values;

process (450) the plurality of statistical force parameters with a machine learning model to determine at least one identifying statistical force parameter value, describing a statistical force parameter that facilitates accurate identification of the user based on the force data; and

determine (460) the identification of the user based on the at least one identifying statistical force parameter value and the minimum force.
The user identification system of claim 9, wherein the machine learning model comprises a support vector machine (SVM).
The user identification system of any preceding claim, wherein the force data comprises a plurality of force values each describing the force applied to the head component during a respective time period,
and wherein identifying the minimum force value based on the obtained force data comprises determining a minimum value of the plurality of force values.
A personal care device (500) comprising:
a head component (540) configured to be held against a body part of a user during use of the personal care device;

a force sensor (530) configured to measure a force applied to the head component during use of the personal care device; and

the user identification system (100) of any of claims 1-11.
The personal care device of claim 12, wherein the personal care device comprises at least one of:
an oral care device;

a hair removal device; and

a skin treatment device.
A computer-implemented method for identifying a user of a personal care device, the personal care device comprising a head component configured to be held against a body part of a user during use of the personal care device, wherein the method comprises:
obtaining force data describing a force applied to the head component during a usage session of the personal care device by the user, the force data comprising information about a minimum force value applied to the head component during the usage session;

identifying the minimum force value based on the obtained force data; and

determining an identification of the user of the personal care device based on the identified minimum force value.
A computer program comprising code means for implementing the method of claim 14.