Method and system for characterizing a user of a personal care device - Patents.com

Abstract

1. A method for identifying a characteristic of a user of a personal care device (10) having a sensor (28), a controller (30), and a database (34), the method comprising: training (320) the personal care device with training data, the method comprising: (i) acquiring (322) sensor data for at least one personal care session for each of at least two different users; (ii) extracting (324) a plurality of features from each of the personal care sessions via an extraction module; and (iii) using the extracted features to train (328) a classifier for identifying a characteristic of each of the at least two users of the device, the method further comprising: acquiring (330) sensor data for at least a portion of a new personal care session; extracting (340) a plurality of features from the sensor data for the new personal care session; and using the trained classifier to identify (360) a characteristic of the user of the device.

Description

[Technical field]

[0001] The present invention relates generally to methods and systems for identifying or characterizing a user of a personal care device. [Background technology]

[0002] To promote proper use and operation of personal care devices, some devices include one or more sensors that measure relevant information about the user's operating characteristics and behavior and use it to provide feedback to the user. The feedback can be provided to the user in real time or after the end of an operating session. However, for some appliances, it is common for multiple users to share one device and exchange components that contact the user's body. In this situation, the system needs to be able to match each usage session to a specific user profile in order to provide personalized feedback to the appropriate user. In the case of real-time feedback, the user can be identified by the app since he or she has access to a smartphone during the operating session and every user typically has an individual user account. For some usage situations, such as post-session feedback, the system cannot rely on an external device to identify the user and may not know who the user is. Indeed, currently, it is not possible to identify the user of the device without external information provided by the user. As a result, it may be impossible to provide personalized usage session feedback to the appropriate user. Summary of the Invention [Problem to be solved by the invention]

[0003] Thus, there is a continuing need in the art for methods and systems that accurately identify a user of a personal care device and / or characteristics of the user without requiring an external identifier for the user. [Means for solving the problem]

[0004] The present invention relates to a method and system for identifying or characterizing a user of a personal care device. For example, when applied to a personal care device, the method and system of the present invention allows for the identification of a user and thus provides personalized feedback to the identified user. The system acquires sensor data for a number of personal care sessions for two or more users of the personal care device and extracts features from each of the personal care sessions to train a classifier to identify one or more characteristics of each of the two or more users of the device. Once the device is trained, the system acquires sensor data for a new personal care session, extracts features from the new personal care session, and uses the classifier to identify the user or a characteristic of the user. Once the user is identified, the device uses the information to, among other things, modify parameters of the personal care device, provide feedback to the user, or continue training of the device.

[0005] In general, in one aspect, a method is provided for identifying a characteristic of a user of a personal care device having a sensor, a controller, and a database, the method including: (i) training the personal care device with training data, the step of acquiring sensor data for at least one personal care session for each of at least two different users of the personal care device via the sensor, extracting a plurality of features from each of the personal care sessions via an extraction module of a processor, and training a classifier using the extracted plurality of features to identify a characteristic of each of the at least two users of the personal care device, the method further including: (ii) acquiring sensor data for at least a portion of a new personal care session initiated by one of the at least two users of the personal care device via the sensor, (iii) extracting a plurality of features from the sensor data for the new personal care session, and (iv) identifying a characteristic of the user of the personal care device using the trained classifier.

[0006] According to one embodiment, the method further comprises reducing a number of features extracted from one or more of the personal care sessions prior to the training step using a dimensionality reduction process.

[0007] According to one embodiment, the method further comprises reducing a number of features extracted from the new personal care session prior to the training step using a dimensionality reduction process.

[0008] According to one embodiment, the method further comprises providing feedback to the user or a third party based on the identified characteristics.

[0009] According to one embodiment, the method further comprises modifying a parameter of the personal care device based on the identified characteristic.

[0010] According to one embodiment, the identified characteristic of the user is a user identification. According to one embodiment, the identified characteristic of the user is a user operational or usage parameter.

[0011] According to one embodiment, the classifier comprises a predictive model.

[0012] According to one embodiment, the sensor is an inertial measurement unit.

[0013] According to one aspect, a personal care device configured to identify a characteristic of a user is provided, the personal care device having a sensor configured to acquire sensor data for a plurality of personal care sessions, a training module and a classifier, the training module configured to acquire sensor data from the sensor for at least one personal care session for each of at least two different users of the personal care device, extract a plurality of features from each of the personal care sessions via an extraction module of a processor, and train a classifier using the extracted features to identify a characteristic of each of the at least two users of the personal care device, the controller further configured to receive sensor data from the sensor for at least a portion of a new personal care session initiated by one of the at least two users of the personal care device, extract a plurality of features from the sensor data for the new personal care session, and the classifier configured to use the extracted features from the new personal care session to identify a characteristic of the user of the personal care device.

[0014] According to one embodiment, the controller further comprises a dimensionality reduction module configured to reduce a number of features extracted from one or more of the personal care sessions prior to the identifying step and / or configured to reduce a number of features extracted from the new personal care session prior to the identifying step.

[0015] According to one embodiment, the controller is further configured to provide feedback to the user based on the identified characteristics. According to one embodiment, the controller is further configured to modify a parameter of the personal care device based on the identified characteristics.

[0016] For purposes of this disclosure, the term "controller" is used herein to generally describe various devices associated with the operation of an oral care device, system, or method. A controller may be implemented in various ways (e.g., using dedicated hardware) to perform various functions discussed herein. A "processor" is an example of a controller that utilizes one or more microprocessors, which may be programmed with software (e.g., microcode) to perform various functions discussed herein. A controller may be implemented using a processor, or may be implemented without a processor, or may be implemented as a combination of dedicated hardware to perform some functions and a processor (e.g., one or more programmed microprocessors and associated circuitry) to perform other functions. Examples of controller elements that may be used 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).

[0017] In various implementations, a processor or controller may be associated with one or more storage media (generally referred to herein as "memory", e.g., volatile or non-volatile computer memory). In some implementations, the storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform at least some of the functions discussed herein. The various storage media may be fixed within a processor or controller, or may be transportable such that one or more stored programs are loaded into a processor or controller to implement various aspects of the disclosure discussed herein. The terms "program" or "computer program" are used herein in a general sense to refer to any type of computer code (e.g., software or microcode) that may be utilized to program one or more processors or controllers.

[0018] The term "user interface" as used herein refers to an interface between a human user or operator and one or more devices that enable communication between the user and the devices. Examples of user interfaces that may be utilized in various embodiments of the present disclosure include, but are not limited to, switches, potentiometers, buttons, dials, sliders, trackballs, display screens, various types of graphical user interfaces (GUIs), touch screens, microphones, and other types of sensors that may receive some form of human-generated stimulus and generate a signal in response thereto.

[0019] It is to be understood that all combinations of the above and additional concepts discussed in more detail below (provided such concepts are not mutually inconsistent) are contemplated as part of the inventive subject matter disclosed herein, and in particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as part of the inventive subject matter disclosed herein.

[0020] These and other aspects of the invention will be elucidated and elucidated with reference to the embodiment(s) described hereinafter.

[0021] In the drawings, like reference characters generally refer to the same parts throughout the different views, and the drawings are not necessarily to scale, emphasis generally being placed upon illustrating the principles of the invention. [Brief description of the drawings]

[0022] [Figure 1] 1 is a diagram of a personal care device according to one embodiment. [Diagram 2] FIG. 1 is a schematic diagram of a personal care system according to one embodiment. [Diagram 3] FIG. 2 is a flow diagram of a method for characterizing a user of a personal care device according to one embodiment. [Figure 4] FIG. 2 is a schematic diagram of angles representing the orientation of a personal care device relative to gravity according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] This disclosure describes various embodiments of methods and systems that utilize sensor data to identify a user of the device to provide feedback. More generally, the applicant has recognized that it may be beneficial to provide a system for identifying or characterizing a user of a personal care device. Accordingly, the methods and systems described or contemplated herein provide a personal care device configured to acquire sensor data for a plurality of personal care sessions for two or more users of the personal care device, where the personal care sessions are brushing sessions, shaving sessions, washing sessions, or any other personal care sessions. The device extracts features from each of the personal care sessions to train a classifier to identify one or more characteristics of each of the two or more users of the device. Once the device is trained, the system acquires sensor data for a new personal care session, extracts features from the new personal care session, and uses a classifier to identify the user or a user's characteristics. According to one embodiment, the device uses the information to, among other things, modify parameters of the personal care device, provide feedback to the user, or continue to train the device.

[0024] The embodiments and implementations disclosed or contemplated herein may be utilized with any personal care device. Examples of suitable personal care devices include an electric toothbrush, an electric flossing device, an oral irrigator, a tongue irrigator, a shaver, a skin care device, or other personal care device. However, the disclosure is not limited to these listed devices, and thus the disclosures and embodiments described herein may encompass any personal care device.

[0025] 1, in one embodiment, a personal care device 10 is provided that includes a handle or body portion 12 and a head member 14, which is typically the portion that operates against the human body. The head member, or portions thereof, may be removable, for example, for different operations, for replacement when worn, or to allow different users to wear personalized components.

[0026] The main body 12 typically has an at least partially hollow housing for housing the components of the personal care device. The main body 12 may have a drive train assembly including a motor 22 for generating motion and a transmission element or drive train shaft 24 for transmitting the generated motion to the head member 14. The personal care device may have a power source (not shown), which may include, for example, one or more rechargeable batteries (not shown) that can be charged in a charging holder in which the personal care device 10 is placed when not in use. The main body 12 further includes a user input 26 for activating and deactivating the drive train. The user input 26 allows a user to operate the personal care device 10, for example to switch the device on and off. The user input 26 may be, for example, a button, a touch screen, or a switch.

[0027] The personal care device 10 includes one or more sensors 28 configured to obtain sensor data. The sensors 28 are shown in the body portion 12 in FIG. 1, but may be located anywhere in the device, including, for example, in the head member 14 or elsewhere in or on the device. According to one embodiment, the sensors 28 are configured to provide a measurement of six axes of relative motion (three axes of translation and three axes of rotation), for example, using a three-axis gyroscope and a three-axis accelerometer. As another example, the sensors 28 are configured to provide a measurement of nine axes of relative motion, for example, using a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. Other sensors may be used, alone or in combination with these sensors, including, but not limited to, gyroscopes, capacitive sensors, cameras, photocells, and other types of sensors. Many different types of sensors may be used, as described or contemplated herein. According to one embodiment, the sensors 28 are configured to generate information indicative of the acceleration and angular orientation of the personal care device 10. The sensor may include two or more sensors 28 that together function as a six-axis or nine-axis spatial sensor system.

[0028] The sensor data generated by the sensor 28 is provided to the controller 30. According to one embodiment, the sensor 28 is integrated with the controller 30. The controller 30 may take the form of one or more modules and is configured to operate the personal care device 10 in response to inputs, such as inputs obtained via the user input 26. The controller 30 may include, for example, a processor 32 and a memory or database 34. The processor 32 may take any suitable form, including, but not limited to, a microcontroller, multiple microcontrollers, a circuit, a single processor, or multiple processors. The memory or database 34 may take any suitable form, including non-volatile memory and / or RAM. The non-volatile memory may include a read only memory (ROM), a hard disk drive (HDD), or a solid state drive (SSD). The memory may store, among other things, an operating system. The RAM is used by the processor for temporary storage of data. According to one embodiment, the operating system may include code that, when executed by the controller 30, controls the operation of the hardware elements of the personal care device 10. According to one embodiment, the connectivity module 38 transmits the collected sensor data and may be any module, device or means capable of transmitting a wired or wireless signal, including but not limited to Wi-Fi, Bluetooth, near field communications and / or cellular modules.

[0029] 2, in one embodiment, a user characterization system 200 is shown. The user characterization system 200 is an embodiment of the personal care device 10, and may be an embodiment of any personal care device disclosed or contemplated herein. According to other embodiments, the user characterization system 200 may be implemented in more than one device. For example, one or more of the modules or components of the user characterization module 200 may be implemented in a remote device, such as a smartphone, tablet, wearable device, computer, or other computer.

[0030] The user characterization system includes a controller 30 having a processor 32 and a memory 34. The user characterization system also includes a sensor 28 configured to obtain information about the angle, movement, or other parameters of the device or the user. The user characterization system also includes a training module 210, an extraction module 220, a dimension module 230, and a classifier 240. The extraction module, classifier, and dimension module may or may not be components or elements of the training module. The user characterization system optionally includes a user interface 46 that provides information to the user. The user interface 46 may be or include a feedback module that provides feedback to the user via tactile, auditory, visual, and / or any other type of signal.

[0031] According to one embodiment, the sensor 28 is an accelerometer, gyroscope, or any other type of sensor suitable or configured to obtain sensor data about the position, movement, or other physical parameters of the device. According to one embodiment, the sensor 28 is configured to generate information indicative of the acceleration and angular orientation of the personal care device 10. The sensor data generated by the sensor 28 may be provided to the controller 30 or other components of the device or system, including external devices or applications.

[0032] According to one embodiment, the extraction module 220 is a component of the device and / or a module or element of the controller 30 or the training module 210. The extraction module is configured, designed or programmed to extract one or more features from a feature vector from the sensor data using signal processing. These features provide information that differs from one user to another and can therefore be used for identification.

[0033] According to one embodiment, the dimension module 230 is a component of the device and / or a module or element of the controller 30 or the training module 210. The optional dimension module is configured, designed or programmed to reduce the number of features extracted by the extraction module 220. The number of features extracted in the feature extraction step may be very large, which may lead to poor performance of the predictive model. Therefore, according to one embodiment, the dimension module may estimate a dimensionality reduction matrix that may be used to reduce the total number of features used to train the predictive model.

[0034] According to one embodiment, the classifier 240 is a component of the device and / or a module or element of the controller 30 or training module 210. The classifier 240 is trained using data from the extraction module and / or dimension module to identify users of the personal care device and / or characteristics of users of the device. Once the classifier is trained, it is configured, designed or programmed to utilize new sensor data to determine which user a usage session belongs to.

[0035] According to one embodiment, the training module 210 is a component of the apparatus and / or a module or element of the controller 30 or the training module 210. The training module is configured to train a classifier using training data acquired by the sensor and processed by the extraction module and / or the dimension module as described or contemplated herein.

[0036] Referring to Figure 3, in one embodiment, a flow diagram of a method 300 for identifying or characterizing a user of a personal care device is shown. The method takes advantage of the fact that every user has a unique operating pattern or technique. For example, several aspects of the user's operating technique, such as typical device orientation and movement patterns, can be measured using one or more sensors present in the device, and this information can be used to identify users within a group of people, such as a family.

[0037] According to one embodiment, the method has two phases: a training phase and a deployment phase. In the training phase, data from several usage sessions is collected from all users who use the same personal care device in order to generate a predictive model. During this phase, the user identifies himself / herself so that his / her identity can be associated with the collected data. For example, the user identifies himself / herself using an external device or a software application, or any other identification method. In the deployment phase, once a predictive model has been generated in the training phase, the model is used to automatically identify the user. According to another embodiment, the user's identification may be obtained, for example, by requesting the user to connect the device to the app, or by identifying the relevant head, for example, using an RFID tag in the head, if present.

[0038] According to one embodiment, all steps in both the training and deployment phases are performed by the personal care device, in alternative embodiments, the method steps are distributed between the personal care device and a second device in communication with the personal care device, such as a smartphone, computer, server or other device.

[0039] At step 310 of the method, a personal care device 10 is provided. The personal care device 10 may be any device described or contemplated herein. For example, the personal care device 10 may include a main handle or body portion 12, a head member 14, a motor 22, a user input 26, and a controller 30 with a processor 32. The personal care device also includes a sensor 28, such as an accelerometer and / or a gyroscope.

[0040] In step 320 of the method, the personal care device is trained using training sensor data as described or contemplated herein. According to one embodiment, training the personal care device to identify a user or a user's characteristics comprises one or more steps 322-328, which may be repeated multiple times, including during a deployment phase.

[0041] In step 322 of the method, the personal care device acquires sensor data for at least one personal care session for each user of the device. Typically, the personal care device acquires sensor data for multiple personal care sessions for each user. According to one embodiment, the more training sessions that are analyzed, the more training data is used to train the classifier, and the better the classifier can identify users. The number of training sessions required may depend at least in part on the number of users of the device.

[0042] According to one embodiment, the personal care device or components of the device, such as a controller and / or a training module, determine the number of personal care sessions required to reliably identify the user of the device during the deployment phase. According to one embodiment, the number of personal care sessions required to train the classifier may be determined based on the number of users of the device. Thus, a user may input information to the device or system indicating the expected number of users of the device, and the device may be programmed or configured to obtain training data for a predetermined number of personal care sessions for each user based on the provided information. According to another embodiment, the number of personal care sessions required to train the classifier may be determined based on a self-determination of accuracy by the device. For example, the device may perform an initial estimation of accuracy or determine the confidence in the classification performed by the classifier. As merely one example, the device may compare the prediction or classification with the actual identification of the user provided during the training or deployment phase and determine, based on cross-validation, whether further training sessions are required or whether the classifier is sufficiently prepared for the deployment phase.

[0043] In step 324 of the method, the extraction module extracts a number of features from each of the personal care sessions. According to one embodiment, discriminatory features are extracted from the sensor data for all usage sessions recorded by the device. The selection of features depends on the sensors present in the device. For example, the device may include at least one inertial measurement unit, which may consist of an accelerometer and / or a gyroscope and / or a magnetometer.

[0044] According to one embodiment, several features may be extracted from the sensor. For example, a highly discriminatory feature for user recognition that can be obtained from the sensor is the distribution of the orientation of the personal care device 10 with respect to gravity during a usage session. With reference to Fig. 4, in one embodiment, the orientation of the device with respect to gravity is represented by two angles (θ and φ), and point G represents the measurement of the gravity vector in the device's local coordinate system provided by the sensor.

[0045] Once the orientation angles θ and φ are calculated for the entire usage session, a joint probability distribution can be estimated, for example using a normalized 2D histogram. For example, the angular distribution for a first user may be significantly different from the distribution for a second user, suggesting that this can be used to distinguish between users. The values ​​in each bin in the histogram can be considered as features for classification.

[0046] According to one embodiment, features related to movement patterns may also be extracted from the sensor data. For example, gyroscope measurements with angular velocity for different users' usage sessions may be used for user identification. Examples of discriminatory features include, but are not limited to, (i) the standard deviation or variance of the gyroscope measurements during a usage session, (ii) the number of peaks present in the signal, (iii) the average height and width of the peaks in the signal, and / or (iv) the energy present at specific frequencies measured after applying a Fourier transform or other analysis.

[0047] According to one embodiment, if other sensors are present in the device, other discriminatory features may be extracted, such as (i) the average force applied to the device during a usage session if a force sensor is present, (ii) the duration of the usage session if the device has a clock capable of determining the time, (iii) the proximity pattern during the usage session if the device has a proximity sensor such as a capacitive or optical sensor, (iv) facial features commonly used for face recognition if the device includes a camera, and / or (v) the duration of the usage session, among others.

[0048] In an optional step 325 of the method, the extracted features are stored in a database, such as memory 34. Alternatively, the extracted features are stored remotely from the device, in a remote server, database, or other storage unit. According to one embodiment, the system may store data for multiple usage sessions before proceeding with downstream steps, or may analyze data from a single usage session upon completion and / or may analyze data in real time.

[0049] In an optional step 326 of the method, a dimension module reduces the number of features extracted from one or more personal care sessions. According to one embodiment, the number of features extracted from the acquired sensor data can potentially be very large. For example, a two-dimensional orientation histogram can represent thousands of features depending on the angular resolution selected. However, training a predictive model from a high-dimensional feature space with a large number of features using a limited number of training samples can result in poor predictive performance. Therefore, utilizing a dimension module to reduce the number of features extracted improves the speed and functionality of the processor and the method.

[0050] According to one embodiment, a dimension reduction step is optionally performed to reduce the total number of features prior to classification. Many techniques can in principle be used for dimension reduction, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and / or Isomap, although many other dimension reduction methods are also possible. According to one embodiment, some form of regularization may be necessary due to the small sample sizes used.

[0051] According to one embodiment, the dimension module 230 utilizes a regularized version of LDA or PCA followed by LDA. When using a linear method such as PCA or LDA, the dimensionality reduction step is performed using the equation:

number

number

[0052] According to one embodiment, during the training phase, the matrix W is estimated from the training database according to some criteria. During the unfolding phase, this matrix is ​​used to reduce the dimensionality of the features according to Equation 1.

[0053] In step 328 of the method, the extracted features are used to train a predictive model to identify features of each of at least two different users of the personal care device. According to one embodiment, once the training database is generated, a predictive model may be trained using machine learning algorithms such as support vector machines, k-nearest neighbors, logistic regression, and / or decision trees, among other possible machine learning algorithms. During the training phase, the predictive model may be used to identify regions of the feature space that should be associated with each user. Once these regions are identified, during the evolution phase, anonymous data may be classified as belonging to a particular user.

[0054] According to one embodiment, the more data collected during the training phase, the better the classifier's performance. However, since the user may need to provide identification information during the training phase, it is advantageous to make the training phase as short as possible to reduce the burden on the user. Therefore, in some embodiments, there may be a trade-off between performance and user convenience. Thus, the training phase may be designed to minimize the training sessions while achieving a desired level of performance. According to one embodiment, the number of training sessions may be selected depending on the number of users sharing the same device, since more data is required to achieve a certain performance level when many users share the same device.

[0055] At this stage, the personal care device or a system or device in communication with the personal care device has a classifier configured to identify characteristics of a user of the device during a subsequent personal care session. For example, the classifier of the device or system may be configured to identify which of a plurality of users is using the device. The classifier of the device or system may be configured to identify user operating characteristics, including whether the user presses hard or soft, among other characteristics.

[0056] In step 330 of the method, in the deployment phase, the personal care device acquires sensor data from the sensor 28 for a new personal care session by a currently unknown user of the device, but the currently unknown user is one of the users that provided personal care session data during the training phase. The sensor may communicate the acquired sensor data to the controller and / or extraction module. The sensor data may be used immediately or may be stored or queued for later analysis.

[0057] In step 340 of the method, an extraction module extracts features from the new personal care session according to any of the methods or processes described or contemplated herein. For example, the extraction module may extract one or more features from sensor data, depending on, for example, the sensors present in the device.

[0058] In optional step 350 of the method, a dimension module reduces the number of features extracted from the new personal care session by any of the methods or processes described or contemplated herein. For example, the dimension module may reduce the number of features extracted using techniques such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and / or Isomap, although many other dimensionality reduction methods are possible. In optional step 350, the dimension module reduces the number of features extracted from the new washing session by applying the same transformation derived during the training phase in step 326 to the new data.

[0059] In step 360 of the method, a trained classifier uses the extracted features to identify one or more characteristics of a previously unidentified user of the personal care device. The characteristics may be the identity of the user or usage parameters of the user and / or personal care session. For example, the characteristics may be information about how hard the user presses, among other things. According to one embodiment, the classifier compares the one or more extracted features to the feature space generated during the training phase to identify which user data the new personal care session data best matches.

[0060] In an optional step 370 of the method, the system uses the identified one or more characteristics to associate sensor data acquired during a personal care session with the identified user. This may be used, for example, to evaluate one or more parameters of the user's personal care session. Alternatively, this may be used to perform further training of the classifier.

[0061] In an optional step 380 of the method, the system uses the identified characteristic or characteristics to provide feedback to the user or a third party. For example, the system may inform the user that the personal care device is being fitted with a head member associated with a different user. As another example, the system may inform the user that the user is pressing harder or softer than normal. According to one embodiment, the user's identity may be used to assess the risk profile of users who share a device with other users and / or to prevent users from inappropriately claiming to have performed a personal care session when in fact it was another user. This may be used, for example, by dental insurance providers. Many other examples are possible.

[0062] In an optional step 309 of the method, the system may use the identified characteristic or characteristics to modify one or more parameters or settings of the device. For example, the device may have programming indicating that a user prefers a particular setting during a personal care session and may use the user's identification to automatically activate that setting. As another example, the device may recognize that a new head member has been put on for the user based on the user's identification and a signal from the head member. This may activate a timer or user count associated with the head member. Many other modifications or settings of the device are possible.

[0063] All definitions defined and used herein should be understood to take precedence over dictionary definitions, definitions in documents incorporated by reference herein, and / or ordinary meanings of the defined words.

[0064] The indefinite articles "a" and "an," as used in the specification and claims, unless expressly stated otherwise, should be understood to mean "at least one."

[0065] The phrase "and / or" as used in the specification and claims should be understood to mean "either or both" of the elements so listed, in some cases conjointly and in other cases discretely. Multiple elements listed with "and / or" should be construed in the same manner, i.e., as "one or more" of the elements so listed. Elements other than those elements expressly identified by the "and / or" clause may optionally be present, whether related or unrelated to those elements expressly identified.

[0066] "Or" as used herein and in the claims should be understood to have the same meaning as "and / or" as defined above. For example, when separating items in a list, "or" or "and / or" should be interpreted as inclusive, i.e., to include at least one of a number or list of elements, and also more than one, optionally including additional unlisted items. Only words expressly indicating the contrary, such as "only one" or "exactly one" or, when used in the claims, "consisting of," will indicate the inclusion of only one element of a number or list of elements. In general, the word "or" as used herein should be interpreted as indicating exclusive alternatives when accompanied by exclusive words such as "either," "one," "only one," or "exactly one."

[0067] The phrase "at least one" as used herein and in the claims, in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of every element expressly listed in the list of elements, and not excluding any combination of elements in the list of elements. This definition allows for the optional presence of elements other than those expressly identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to those elements expressly identified.

[0068] It should also be understood that, unless expressly indicated, in any method recited in a claim that includes more than one step or action, the order of those steps and actions of the method is not necessarily limited to the order in which the steps and actions of the method are recited.

[0069] In the claims and the above specification, all transitional phrases such as "comprising," "including," "carrying," "having," "containing," "involving," "holding," "composed of," and the like, are to be understood as open-ended, i.e., meaning including but not limited to. Only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases.

[0070] While several inventive embodiments have been described and illustrated herein, those skilled in the art will readily conceive of a variety of other means and / or structures for performing the functions and / or obtaining one or more of the results and / or advantages described herein. Each such variation and / or modification is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are intended to be examples, and that the actual parameters, dimensions, materials, and / or configurations will depend on the particular application in which the teachings of the present invention are utilized. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. Thus, the foregoing embodiments are presented by way of example only, and that, within the scope of the appended claims and their equivalents, the inventive embodiments may be practiced otherwise than as expressly described and claimed. The inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. Furthermore, any combination of two or more of such features, systems, articles, materials, kits, and / or methods is included within the inventive scope of the present disclosure, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

Claims

1. 1. A method for identifying a characteristic of a user of a personal care device having a sensor, a controller, and a database, the method comprising: training the personal care device with training data, the method comprising: acquiring sensor data for at least one personal care session for each of at least two different users of the personal care device via the sensor; extracting a plurality of features from each of the personal care sessions via an extraction module of a processor; and training a classifier using the extracted plurality of features to identify characteristics of each of the at least two users of the personal care device, the method further comprising: acquiring, via the sensor, sensor data for at least a portion of a new personal care session initiated by one of at least two users of the personal care device; extracting a plurality of features from the sensor data for the new personal care session; using the trained classifier to identify characteristics of a user of the personal care device; The method according to claim 1,

2. 10. The method of claim 1, further comprising: reducing a number of features extracted from one or more of the personal care sessions prior to the training step using a dimensionality reduction process.

3. The method of claim 1 , further comprising associating at least some of the sensor data acquired during the new personal care session with an identified characteristic of the user.

4. The method of claim 1 , further comprising providing feedback to the user or a third party based on the identified characteristics.

5. The method of claim 1 , further comprising altering a parameter of the personal care device based on the identified characteristic.

6. The method of claim 1 , wherein the identified characteristic of the user is the user's identity.

7. The method of claim 1 , wherein the identified characteristics of the user are parameters of the personal care device when utilized by the user.

8. The method of claim 1 , wherein the classifier comprises a predictive model.

9. The method of claim 1 , wherein the sensor is an inertial measurement unit.

10. 1. A personal care device configured to identify a characteristic of a user, the personal care device comprising: a sensor configured to acquire sensor data for a plurality of personal care sessions; a controller having a training module and a classifier, the training module configured to acquire sensor data from the sensor for at least one personal care session for each of at least two different users of the personal care device, extract a plurality of features from each of the personal care sessions via an extraction module of a processor, and use the extracted plurality of features to train a classifier for identifying characteristics of each of the at least two users of the personal care device; having The controller is further configured to receive sensor data from the sensor for at least a portion of a new personal care session initiated by one of the at least two users of the personal care device, and to extract a plurality of features from the sensor data for the new personal care session; the classifier is configured to identify a characteristic of a user of the personal care device using the extracted features from the new personal care session. Personal care devices.

11. 11. The personal care device of claim 10, wherein the controller further comprises a dimensionality reduction module configured to reduce a number of features extracted from one or more of the personal care sessions prior to the identifying step, and configured to reduce a number of features extracted from the new personal care session prior to the identifying step.

12. The personal care device of claim 10 , wherein the controller is further configured to provide feedback to the user based on the identified characteristic.

13. The personal care device of claim 10 , wherein the controller is further configured to modify a parameter of the personal care device based on the identified characteristic.

14. The personal care device of claim 10 , wherein the identified characteristic of the user is an identity of the user and / or a parameter of the personal care device when utilized by the user.

15. The personal care device of claim 10 , wherein the classifier comprises a predictive model.

Images