Determining the wear level of a treatment head on a personal care device

Abstract

According to one aspect, a computer-implemented method 100 for determining the lifespan of a treatment head of a personal care device is provided, the method comprising step 102 receiving a plurality of images of a treatment head, each of the plurality of images being captured at a different time during the lifespan of the treatment head; step 104 determining, for each image of the plurality of images, a wear level indicative of the wear level of the treatment head at the time the image was captured; and step 106 determining an estimated time when the treatment head should be replaced based on the plurality of wear levels.

Description

[Technical Field]

[0001] FIELD OF THE INVENTION The present invention relates to personal care devices that include treatment heads, and more particularly to determining how quickly a treatment head wears out with use. [Background technology]

[0002] Personal care devices are used by people to perform personal care activities, such as hair care activities (e.g., shaving or trimming), skin treatment activities (e.g., skin brushing), and oral care activities (e.g., tooth brushing). A different type of personal care device can be used for each personal care activity, and each personal care device can include a treatment portion, sometimes referred to as a treatment head. The treatment head of a personal care device is the portion that performs the intended treatment (e.g., cutting hair, brushing skin, or brushing teeth). Over time and with use, one or more portions of the treatment head may wear (e.g., wear down or deteriorate), resulting in a decrease in the effectiveness of the treatment head and its ability to perform the intended treatment. Thus, the treatment head can be replaceable, meaning that a user can replace only the treatment head portion of the personal care device. Summary of the Invention [Problem to be solved by the invention]

[0003] The treatment head can include a visual marker that indicates how worn the treatment head is, which can help the user replace the treatment head in a timely manner. However, treatment head wear occurs at different rates for different users depending on the frequency and nature of use, and therefore the visual marker may change very slowly over time. A user may have difficulty noticing changes in the visual marker over time and therefore have difficulty determining the optimal time to order a replacement head to ensure it arrives in a timely manner.

[0004] Therefore, what is desired is a mechanism that can quantify the degree of wear on a treatment head so that an indication of the treatment head's estimated remaining life can be provided to the user. [Means for solving the problem]

[0005] The present invention provides a mechanism that allows a quantitative assessment of a treatment head to be made so that the degree of wear on the treatment head can be estimated and communicated to a user of the personal care device in which the treatment head is used. In this way, a user who may not be able to recognize changes in the visual markers on the treatment head can be informed about the degree of wear on the treatment head so that a replacement treatment head can be ordered and installed before the worn treatment head becomes ineffective. The inventors of the present disclosure have recognized that by using computer vision-based analysis techniques (e.g., image processing algorithms) applied to images of the treatment head, it is possible to determine the wear level of the treatment head corresponding to each image and, based on how the wear level has changed over time, predict the estimated remaining life of the treatment head so that a replacement treatment head can be ordered in a timely manner.

[0006] According to a first particular aspect, a computer-implemented method for determining the lifespan of a treatment head of a personal care device is provided, comprising the steps of receiving a plurality of images of a treatment head, each of the plurality of images being captured at a different time during the lifespan of the treatment head; determining, for each image in the plurality of images, a wear level indicative of the wear level of the treatment head at the time the image was captured; and determining an estimated time when the treatment head should be replaced based on the plurality of wear levels.

[0007] By using image processing techniques to evaluate images of the treatment head to estimate the remaining life of the treatment head and therefore when the treatment head should be replaced, wear on the treatment head can be assessed in a more quantitative manner than if a user manually assessed the treatment head, for example, by determining the level of wear based on visual indicators included on the treatment head. In this way, the treatment head can be replaced in a timely manner before the level of wear on the treatment head becomes too great and causes a decrease in performance that could result in a poor experience for the user or even ineffective treatment when performing personal care activities.

[0008] In some embodiments, the method may further include determining an indication time at which the receiving device should be provided with an indication that the treatment head should be replaced based on an estimated time when the treatment head should be replaced, and generating an instruction signal to be provided to the receiving device at the indication time.

[0009] Determining each wear level can include applying an edge detection algorithm to detect visible edges in the pattern displayed on the treatment head.

[0010] In other embodiments, determining each wear level may include providing each image of the plurality of images as an input to a predictive model trained to classify the images based on an estimated wear level of the treatment head visible in the image.

[0011] Determining each wear level, in some embodiments, includes applying an object detection algorithm and / or an image segmentation algorithm to detect regions in each of the plurality of images that are expected to contain a predetermined marker, and providing each of the plurality of images as an input to a predictive model trained to detect the predetermined marker, wherein the predictive model can generate a score indicative of the wear level of the treatment head.

[0012] In another embodiment, determining an estimated time when the treatment head should be replaced includes fitting a function to the determined wear levels and determining an estimated time when the treatment head should be replaced based on the fitted function.

[0013] Determining an estimated time when the treatment head should be replaced includes using a regression algorithm applied to the determined wear levels to estimate a function representing how the wear level of the treatment head changes over time, and determining an estimated time when the treatment head should be replaced based on the estimated function.

[0014] In some embodiments, the method may further include generating a notification prompting the user of the personal care device to capture a further image showing the treatment head for provision to the receiving device.

[0015] The method may further include generating instructions for presentation to a user of the personal care device via the receiving device that prompt the user to operate at least one of the image capture device and the treatment head such that an image of the treatment head captured using the image capture device meets a set of predetermined criteria.

[0016] In some embodiments, the method includes determining that the remaining life of the treatment head is less than a predetermined duration based on an estimated time when the treatment head should be replaced, and generating a notification prompting a user of the personal care device to purchase a replacement treatment head for delivery to the receiving device.

[0017] In some embodiments, the method further comprises receiving device data indicating how the personal care device was used during a previous treatment session, and determining an estimated time when the treatment head should be replaced based on the received data.

[0018] According to a second particular aspect, there is provided a computer program product comprising a non-transitory computer readable medium having computer readable code embodied therein, the computer readable code being configured, when executed by a suitable computer or processor, to cause the computer or processor to perform any of the methods recited in the claims.

[0019] According to a third specific aspect, there is provided an apparatus for determining the lifespan of a treatment head of a personal care device, the apparatus having a processor configured to perform the steps of the methods disclosed herein.

[0020] According to a fourth embodiment, there is provided a personal care device having a body portion and an interchangeable treatment head removably coupled to the body portion; and a system having the device as disclosed herein.

[0021] In some embodiments, the system may further include an image capture device for capturing a plurality of images.

[0022] These and other aspects will be apparent from and elucidated with reference to the embodiments described hereinafter. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a flow chart illustrating an example of a method for determining the lifespan of a treatment head of a personal care device. [Figure 2] 1 is a set of images illustrating an example of an edge detection technique. [Figure 3] 10 is a graph showing an example of an estimated time when the treatment head should be replaced. [Figure 4] 10 is a flow chart of a further example of a method for determining the lifespan of a treatment head of a personal care device. [Figure 5] 1 is a schematic diagram of an example processor in communication with a computer-readable medium. [Figure 6]1 is a schematic diagram of an example of an apparatus for determining the lifespan of a treatment head of a personal care device. [Figure 7] 1 is a schematic diagram of a system for determining the lifespan of a treatment head of a personal care device. [Figure 8] 1 is a graph showing the confusion matrix of an example implementation of a prediction model in the method according to the invention; DETAILED DESCRIPTION OF THE INVENTION

[0024] Exemplary embodiments will now be described, by way of example only, with reference to the following drawings, in which:

[0025] The embodiments disclosed herein provide a mechanism by which the wear level of a treatment head of a personal care device can be determined based on an analysis of multiple images of the treatment head at various stages during its lifespan. As described below, various techniques can be used to analyze the images, and based on the analysis, it is possible to estimate when the treatment head should be replaced to reduce the likelihood that a user of the treatment head will suffer from ineffective treatment.

[0026] Referring to the drawings, Figure 1 is a flowchart of an example method 100, such as a computer-implemented method, for determining the lifespan of a treatment head of a personal care device. A personal care device may include a device or appliance used to perform a personal care activity, such as a hair cutting device, such as a hair trimmer or shaving device; a facial cleansing brush; a skin treatment device, such as a skin rejuvenation device or an intense pulsed light (IPL) device; an oral care device, such as an electric toothbrush or an air flossing device; etc. Each personal care device may include a treatment head that performs an intended treatment on a subject during use. For example, a treatment head on a shaving device may have a cutting head or blade that cuts the subject's hair during use, and a treatment head on an electric toothbrush may have a brush head attachment with bristles that clean the subject's teeth during use.

[0027] One or more portions of a treatment head of a personal care device may wear over time, for example, due to repeated engagement with a target (e.g., a target's hair or teeth) during use. For example, the blades of a shaving device may become dull, resulting in a less effective hair cutting ability, and the bristles of an electric toothbrush may become worn and misaligned, resulting in less effective tooth cleaning. Each treatment head has a lifespan that is considered to end when the treatment head has worn to such an extent that its ability to perform its intended treatment is significantly reduced.

[0028] Method 100 includes, in step 102, receiving a plurality of images of a treatment head, each of the plurality of images being captured at a different time during the life of the treatment head. Each image, for example, comprises a photograph of the treatment head, which can be captured using an image capture device such as a camera. For example, a user of the treatment head or a user of a personal care device in which the treatment head is used can take a photograph of the treatment head using, for example, a smartphone camera, and the image (e.g., image data representing the image) can be received by a device (e.g., one or more processors) performing method 100. Each image of the plurality of images shows the treatment head at a different time during its life. For example, a first image of the plurality of images can be captured on a first date after a first treatment session, and a second image of the plurality of images can be captured on a second date after a second treatment session.

[0029] Each image of the treatment head may be intended to show a particular portion of the treatment head from which a determination of the level of wear can be made. For example, each image of a treatment head of a shaving implement may be intended to show the blades, and each image of a treatment head of an electric toothbrush may be intended to show the bristles. As described below, following evaluation of the images received in step 102, a mechanism may be provided to prompt the user to capture a photograph that better shows the relevant portion of the treatment head.

[0030] The user may be prompted or requested to upload an image of the treatment head or to take a photo of the treatment head showing the relevant portion of the treatment head in its current state (e.g., the portion of the treatment head from which the level of wear can be determined). In some embodiments, the user may be guided through the image capture process by a set of instructions informing the user how to capture a suitable image (e.g., with respect to viewing angle, resolution, zoom level, lighting conditions, etc.). In other embodiments, an augmented reality (AR) stencil or template may be provided to guide the user how to capture a suitable image of the treatment head. In such an example, guidance may be provided to the user via a display on the mobile device (e.g., via an application on the user's smartphone). The mobile device may provide an indication (e.g., visual or audible) that notifies the user when conditions (e.g., viewing angle, lighting conditions, etc.) are suitable for capturing an image of the treatment head from which the level of wear can be determined.

[0031] In step 104, method 100 includes determining, for each image in the plurality of images, a wear level indicative of the wear level of the treatment head at the time the image was captured. One or more computer vision algorithms (e.g., image processing techniques) can be used to determine the wear level of the treatment head for each image. In the examples disclosed herein, the wear level determination can be performed using edge detection techniques, machine learning techniques, or object detection / segmentation techniques.

[0032] In a first example, determining each wear level (step 104) may include applying an edge detection algorithm to detect visible edges in a pattern displayed on the treatment head. The treatment head may include a pattern, symbol, or marking, the appearance of which changes over time as the treatment head wears. In one example, the skin-engaging portion of the treatment head may include a pattern, such as a grid, printed, painted, or otherwise formed on the skin-engaging portion. The skin-engaging portion of the treatment head of a shaving device may have, for example, one or more blades. As the treatment head (e.g., the skin-engaging portion of the treatment head) wears with use, the pattern formed thereon may become less visible or its appearance may change in some other manner, indicating the level of wear. In another example, as the wear level of the treatment head increases, the pattern formed beneath the skin-engaging portion may become more visible.

[0033] When the treatment head is new, the pattern is complete and perfectly visible to an observer (e.g., a user). In one example, the pattern can have a grid (e.g., hatching) formed across at least a portion of the treatment head; in a new, unused treatment head, the grid-like pattern can include a predetermined number (e.g., 500) of lines or edges that can be detected using an edge detection algorithm. FIG. 2 shows an illustration of an example of a pattern formed on a treatment head, such as the cutting portion of a shaving device. FIG. 2A shows an example of a new treatment head, in which a grid-like pattern 202 formed by a series of hatched diagonal lines is perfectly visible across the surface of the treatment head. FIG. 2B shows an example image representing edges detected in the image of FIG. 2A by an edge detection algorithm. As can be seen, a large portion of the edges (e.g., lines) present in the grid-like pattern 202 can be detected and counted. In this example, the edge detection algorithm detected 430 edges, which are believed to be associated with a new or nearly new treatment head.

[0034] FIG. 2C shows an example of a treatment head after significant use, where some of the grid pattern 202 has worn away. FIG. 2D shows an example image depicting edges detected in the image of FIG. 2C by an edge detection algorithm. In this case, 160 edges (e.g., lines) are detected, which is much fewer than in FIG. 2B. In one example, the percentage of the number of lines or edges detected using the edge detection algorithm can indicate the treatment head's wear level. For example, if half as many edges are detected as when the treatment head was new, the treatment head is considered to be 50% worn and / or at 50% of its lifespan. An advantage of using an edge detection algorithm in this manner is that no training of the algorithm is required.

[0035] In the example shown in FIGS. 2C and 2D , an image of a symbol 204 is also visible on the treatment head. The symbol 204 may be disposed (e.g., printed or painted) on a surface below the wearable portion of the treatment head. As a result, as the treatment head wears and the checkerboard pattern 202 wears away, the symbol 204 becomes more visible. The gradual appearance of the symbol 204 can provide a visual indication to the user that the treatment head is wearing down and approaching the end of its life. In some examples, an object detection algorithm can be used to locate and detect the symbol 204 in a received image of the treatment head. In such examples, the confidence level (e.g., a confidence score) with which the object detection algorithm can detect the symbol 204 can indicate the wear level of the treatment head. For example, if the object detection algorithm detects the symbol 204 with only 10% confidence (e.g., because the checkerboard pattern 202 covers most of the symbol), it can be determined that the treatment head is 10% worn. However, if the object detection algorithm detects the symbol 204 with 90% confidence, this is considered to be a high probability that a large portion of the checkerboard pattern 202 is worn, and therefore, it can be determined that the treatment head is 90% worn.

[0036] In some examples, the object detection algorithm may include a "you only look once" (YOLO) algorithm, which may determine, for each image, a score (e.g., a probability score) for each of a plurality of classes. For example, the algorithm may consider 10, 100, or other number of classes, and for each class, the algorithm may determine a score for the image. As an example, the algorithm may determine a score for each of 10 classes. The score for each class may be considered a likelihood or probability that the image belongs to that class, and each class may correspond to a different wear level. The algorithm may determine that the image belongs to the class corresponding to the highest determined score. Thus, the treatment head shown in the image may be considered to have a wear level corresponding to the wear level associated with the highest score class.

[0037] In a second example, determining each wear level (step 104) may include providing each image of the plurality of images as input to a predictive model trained to classify the image based on an estimated wear level of the treatment head visible in the image. Many different types of predictive models or algorithms can be used, including, for example, artificial neural networks (e.g., deep learning algorithms such as convolutional neural networks). The predictive model can be trained using training data having images of treatment heads with different levels of wear. In some examples, the predictive model can focus on textures present in the image, such as when the treatment head has a cutting blade for a shaving device. A new cutting blade may have a rough surface, while a used cutting blade may have a smoother surface. As shown in the examples of FIGS. 2C and 2D, one or more visual markers or symbols become visible or gradually become visible as the blade wears. In such examples, the predictive model can be trained to detect the visual markers or symbols and determine the level of wear based on how clearly the markers or symbols are visible. In some examples, the predetermined markers can have a pattern, such as a grid pattern described herein. The predictive model can provide as an output a classification into one of a set of categories indicating the estimated remaining life of the treatment head. For example, the predictive model can classify the treatment head as having 0-10% wear or 80-90% wear.

[0038] In a third example, an object detection algorithm and / or an image segmentation algorithm can be used to determine the wear level of the treatment head based on the images of the treatment head. In this example, determining each wear level (step 104) includes applying at least one of an object detection algorithm and an image segmentation algorithm to detect areas in each of the multiple images that are expected to contain a predetermined marker. As an example, the predetermined marker has symbol 204 shown in FIG. 2. An object detection algorithm or an image segmentation algorithm can be used to analyze the images of the treatment head and determine whether a marker (e.g., symbol 204) is present in the image. The object detection algorithm or the image segmentation algorithm can be trained using a set of training images that have been annotated by drawing a bounding box around the marker / symbol to be identified or by indicating the area in the image that corresponds to the marker / symbol. A predictive model trained using the YOLO (i.e., you only look once) dataset and / or the COCO (i.e., common objects in context) dataset can also be used to determine whether a symbol is present in the image. Thus, each image of the plurality of images can be provided as input to a predictive model trained to detect a predetermined marker. If the symbol is determined to be present, the treatment head can be determined to be worn. Generally, the predictive model can generate a score indicative of the treatment head's wear level. The score generated by the predictive model can include a probability score or a confidence score and / or can be based on a prediction probability, a conditional probability, confidence in the prediction, objectivity of the detection, or a combination thereof.

[0039] Referring again to FIG. 1 , method 100 includes, at step 106, determining an estimated time when the treatment head should be replaced based on the plurality of wear levels. Once method 100 determines (e.g., estimates) the wear level of the treatment head in each image (i.e., the amount the treatment head has worn at various times corresponding to the time the image was captured), an estimate can be made as to how much useful life the treatment head has remaining. In one example, determining the estimated time when the treatment head should be replaced may include fitting a function to the determined plurality of wear levels and determining an estimated time when the treatment head should be replaced based on the fitted function. The determined wear levels may be time-stamped wear levels because they indicate the wear level at a particular time.

[0040] FIG. 3 is a graph showing an example of the determined wear level of a treatment head plotted against time for each of three images captured on three different dates over the treatment head's life. In this example, point 302 represents the wear level of the treatment head determined from an image captured on a first date after a first period of use, point 304 represents the wear level of the treatment head determined from an image captured on a second date after a second period of use, and point 306 represents the wear level of the treatment head determined from an image captured on a third date after a third time period. With multiple wear levels plotted on the graph, a function is fit to the data, as shown by line 308. It will be apparent that the more data points included in the graph, the better the fit of the function. Based on the fitted function, it is possible to determine a future time / date 310 at which the treatment head's wear level will reach 100% or a predetermined wear level believed to represent the end of the treatment head's useful life. The determined treatment head life end date 310 is the date on which the treatment head is likely to be completely worn out based on the treatment head's past usage, and therefore, it can be recommended that the treatment head be replaced on the determined end date.

[0041] In some embodiments, determining an estimated time when the treatment head should be replaced (step 106) may include using a regression algorithm applied to the plurality of determined wear levels to estimate a function that represents how the treatment head's wear level changes over time. In some examples, multiple algorithms can be used, including, for example, a simple linear model such as a linear regression model, a nonlinear model, a support vector machine (SVM), an artificial neural network, an autoregressive integrated moving average (ARIMA) model, etc. The estimated time when the treatment head should be replaced may be determined based on the estimated function.

[0042] The embodiments disclosed above allow for an estimation of the date on which a treatment head will likely reach the end of its useful life. However, it would be even more useful if a treatment head user could be given advance notice of the treatment head's approaching end-of-life date so that arrangements could be made to replace the treatment head in a timely manner. For example, a user may wish to purchase a replacement treatment head one to two weeks before the estimated end-of-life date to ensure that a replacement treatment head is available in time. The embodiment described below with reference to FIG. 4 provides these additional advantages.

[0043] 4 is a flowchart of a further example method 400 (e.g., a computer-implemented method) for determining the lifespan of a treatment head of a personal care device. Method 400 may include the steps of method 100 described above. In some embodiments, method 400 may further include, at step 402, determining an indication time at which an indication that the treatment head should be replaced should be provided to the receiving device based on an estimated time at which the treatment head should be replaced. The indication time may be determined such that a recipient (e.g., a user of the receiving device) is provided sufficient notice to replace the treatment head before or at the estimated time at which the treatment head should be replaced. For example, the indication time may be determined based on an expected delivery period if a user needs to order a replacement treatment head.

[0044] At step 404, method 400 may further include generating an indication signal provided for delivery to a receiving device at the indication time. The indication signal may comprise, for example, a signal instructing the device (e.g., a personal care device, a computing device, a smartphone, a tablet computer, a wearable device, an interactive mirror, etc.) to display a message or notice informing a user of the device that the treatment head should be replaced.

[0045] In some embodiments, a user of the personal care device to which the treatment head is attached may be offered the opportunity to purchase a replacement treatment head at an appropriate time based on the determined estimate of the treatment head's end-of-life date. For example, method 400 may further include, at step 406, determining that the remaining life of the treatment head is less than a predetermined duration based on the estimated time when the treatment head should be replaced. The predetermined period may include, for example, one week, two weeks, one month, etc., and may be selected based on the characteristics of the personal care device and / or the treatment head and / or the manner in which the personal care device is used. At step 408, method 400 may further include generating a notification for delivery to a receiving device prompting the user of the personal care device to purchase a replacement treatment head. This notification may be delivered, for example, via an application to the user's smartphone, allowing the user to order a replacement treatment head so that it arrives at the user before the estimated time for replacement.

[0046] A user of the personal care device may be prompted or required to take a photo and / or upload an image of the treatment head used with the personal care device after each treatment session (e.g., after each use of the personal care device). In this manner, periodically captured images of the treatment head can be used to determine an accurate estimate of the treatment head's end-of-life date. In some embodiments, method 400 may include, at step 410, generating a notification prompting the user of the personal care device to capture additional images showing the treatment head for provision to a receiving device. For example, a message may be provided to the user's smartphone suggesting that the user take a photo of the treatment head after use to be uploaded for wear level analysis.

[0047] In some cases, the images of the treatment head received in step 102 may be deemed to be of too poor quality to allow an accurate assessment of its wear level. For example, the images of the treatment head may not have been captured under optimal lighting conditions or may have been captured from an angle that makes analysis by an edge detection algorithm difficult. In such instances, the user may be prompted or requested to capture and upload a new image of higher quality. The method 400 may further include, at step 412, generating instructions for presentation to the user of the personal care device via the receiving device, prompting the user to operate at least one of the image capture device and the treatment head such that the images of the treatment head captured using the image capture device meet a set of predetermined criteria. The instructions may include, for example, text and / or audible instructions instructing the user to move the camera (e.g., a smartphone camera) and / or the treatment head to a position where an image meeting the set of predetermined criteria can be captured. The predetermined criteria may include criteria related to lighting conditions, treatment head and / or camera orientation, image resolution, etc.

[0048] Methods 100 and 400 allow for determining an estimated time for when the treatment head should be replaced based solely on multiple photographs of the treatment head. However, in some embodiments, additional information may be available in addition to the images to determine the estimated end-of-life date of the treatment head. Thus, in some embodiments, method 400 may further include, in step 414, receiving device data indicating how the personal care device was used during previous treatment sessions. For example, data or information indicating how often the personal care device was used and the duration of each use may be provided, and / or data from one or more sensors disposed in, on, or around the personal care device, or data otherwise associated with the personal care device, may be provided. In some examples, data from an inertial measurement unit (IMU), pressure sensor, motor force sensor, and / or optical sensor may be used to determine the intensity of the personal care activity, and data from the one or more sensors may be used in determining the estimate. The data may be received via a wired or wireless connection. Thus, determining an estimated time for when the treatment head should be replaced (step 106) may further be performed based on the received data. As an example, if the received device data indicates that the personal care device is used vigorously with each use, the treatment head may wear out more quickly than if the personal care device is used gently and with little force.

[0049] The present invention also provides a computer program product. Figure 5 is a schematic diagram of an example processor 502 in communication with a computer-readable medium 504. According to an embodiment, a computer program product is provided that includes a non-transitory computer-readable medium 504 having computer-readable code embodied therein that, when executed by a suitable computer or processor 502, causes the computer or processor to perform the steps of methods 100, 400 disclosed herein. Thus, the steps of methods 100, 400 may be performed using one or more computing devices and / or one or more processors included in a computing environment, such as, for example, a server located in a cloud computing environment.

[0050] The present invention also provides a device. Figure 6 is a schematic diagram of an example device 600 for determining the lifespan of a treatment head of a personal care device. The device includes a processor 602 (e.g., processor 502) configured to perform the steps of the methods 100, 400 disclosed herein. The device 600 can include, for example, a personal care device in which the treatment head is used and a computing device such as a smartphone, a wearable device, an interactive mirror, etc. In some embodiments, the processor 602 is located within the device 600. However, in other embodiments, the processor performing the method steps may be located remotely from the device 600 and / or the personal care device.

[0051] The present invention also provides a system. Figure 7 is a schematic diagram of an example system 700 for determining the lifespan of a treatment head of a personal care device. The system 700 includes a personal care device 702 having a body portion 704 and a replaceable treatment head 706 removably coupled to the body portion. As discussed herein, the personal care device 702 can include a hair cutting device, a shaving device, an oral care device, a skin treatment device, or the like. The system 700 further includes a device 600. The device 600 can be in operative communication with the personal care device 702 such that it can communicate with and receive data from the personal care device.

[0052] In some embodiments, system 700 may further include an image capture device 708 for capturing a plurality of images. Image capture device 708 may include a camera in a mobile device such as a smartphone. In some embodiments, image capture device 708 may form part of everything housed within device 600.

[0053] FIG. 8 is a chart showing the output of an example of a test using a predictive model in the method 100 disclosed herein. The chart is a confusion matrix, which is a table showing the performance of a classification task (i.e., determining the wear level of a treatment head, which is the cutting element of a shaving device). The x-axis of the confusion matrix visualizes the true label (ground truth), and the y-axis visualizes the predicted label. Within each cell of the confusion matrix, a value ranging from 0.0 to 1.0 indicates the confidence score of the predictive model. The labels "WO_B1"..."WO_B10" represent treatment head (i.e., cutting element) wear level classes, increasing in stages from an unabraded treatment head ("WO_B1") to a completely worn treatment head ("WO_B10"). The confusion matrix shows several incorrect predictions within the + / -1 wear class (e.g., the square cell regions in "WO_B4" and "WO_B5"). The absence of a value in the "backgroundFN" row indicates that all treatment heads are detected, while the value in the "backgroundFP" column with a low confidence score indicates that the prediction model detected some erroneous bounding boxes, which were subsequently filtered out due to their low confidence scores. The absence of any values ​​in the "WO_B2" row or column is due to the fact that there were no "WO_B2" samples used in the test set. The test set contained a set of 36 images. The output shown in the confusion matrix indicates that the prediction model can accurately determine the treatment head wear level from the images.

[0054] The processor 502, 602 may comprise one or more processors, processing units, multi-core processors, or modules configured or programmed to control the device 600 in the manner described herein. In particular implementations, the processor 502, 602 may include multiple software and / or hardware modules, each configured to or intended to perform individual or multiple steps of the methods described herein.

[0055] The term "module" as used herein is intended to include a hardware element, such as a processor or element of a processor configured to perform a particular function, or a software element, such as a set of instruction data that has a particular function when executed by a processor.

[0056] It should be understood that embodiments of the present invention also apply to computer programs, particularly those on or in a carrier, adapted for carrying out the present invention. The program may be in the form of source code, object code, a source and object code intermediate code, such as a partially compiled form, or any other form suitable for use in implementing a method according to embodiments of the present invention. It should also be understood that such programs may have many different architectural designs. For example, program code implementing the functionality of a method or system according to the present invention may be subdivided into one or more subroutines. Many different ways of distributing functionality among these subroutines will be apparent to those skilled in the art. The subroutines may be stored together in an executable file to form a self-contained program. Such an executable file may contain computer-executable instructions, such as processor instructions and / or interpreter instructions (e.g., Java interpreter instructions). Alternatively, one or more or all of the subroutines may be stored in at least one external library file and linked statically or dynamically with the main program, e.g., at run time. The main program includes at least one call to at least one subroutine. The subroutines may also have function calls to one another. An embodiment of a computer program product comprises computer-executable instructions corresponding to each processing step of at least one of the methods defined herein. These instructions may be subdivided into subroutines and / or stored in one or more files, which may be linked statically or dynamically. Another embodiment of a computer program product comprises computer-executable instructions corresponding to each means of at least one of the systems and / or products defined herein. These instructions may be subdivided into subroutines and / or stored in one or more files, which may be linked statically or dynamically.

[0057] The carrier of a computer program may be any entity or device capable of carrying the program. For example, the carrier may comprise a data storage device such as a ROM, for example a CD-ROM or a semiconductor ROM, or a magnetic recording medium, for example a hard disk. Furthermore, the carrier may be a transmissible carrier such as an electric or optical signal, which may be conveyed via an electric or optical cable or by radio or other means. When the program is embodied in such a signal, the carrier may be constituted by such a cable or other device or means. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being configured for, or used for, performing the relevant method.

[0058] Variations to the disclosed embodiments can be understood and implemented by those skilled in the art practicing the principles and techniques described herein, from a study of the figures, the disclosure, and the appended claims. In the claims, the word "comprise" 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 fulfill the functions of several items recited in a claim. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used to advantage. A computer program can be stored or 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 can also be distributed in other forms, such as via the Internet or other wired or wireless communication systems. Any reference signs in the claims should not be interpreted as limiting the scope of the invention.

Claims

1. 1. A computer-implemented method for determining the lifespan of a treatment head of a personal care device, comprising: receiving a plurality of images of the treatment head, each of the plurality of images being captured at a different time during the life of the treatment head; determining, for each image of the plurality of images, a wear level indicative of the wear level of the treatment head at the time the image was captured; and determining an estimated time when the treatment head should be replaced based on the plurality of wear levels.

2. determining an indication time at which an indication that the treatment head should be replaced is provided to the receiving device based on the estimated time when the treatment head should be replaced; and generating an indication signal for providing to said receiving device at said indication time.

3. 3. The computer-implemented method of claim 1, wherein determining each wear level comprises applying an edge detection algorithm to detect visible edges in a pattern displayed on the treatment head.

4. 3. The computer-implemented method of claim 1, wherein determining each wear level comprises providing each image of the plurality of images as an input to a predictive model trained to classify images based on an estimated wear level of the treatment head visible in the image.

5. determining each wear level, applying at least one of an object detection algorithm and an image segmentation algorithm to detect regions in each of the plurality of images that are expected to contain a predetermined marker; providing each image of the plurality of images as an input to a predictive model trained to detect the predetermined marker; The computer-implemented method of claim 1 or 2, wherein the predictive model generates a score indicative of a level of wear on the treatment head.

6. determining an estimated time when the treatment head should be replaced, fitting a function to the plurality of determined wear levels; and determining an estimated time when the treatment head should be replaced based on the fitted function.

7. determining an estimated time when the treatment head should be replaced, using a regression algorithm applied to the plurality of determined wear levels to estimate a function representing how the wear level of the treatment head will change over time; and determining an estimated time when the treatment head should be replaced based on the estimated function.

8. 8. The computer-implemented method of claim 1, further comprising generating a notification prompting a user of the personal care device to capture a further image showing the treatment head for provision to a receiving device.

9. 9. The computer-implemented method of claim 1, further comprising generating instructions for presentation to a user of the personal care device via a receiving device, the instructions prompting the user to operate at least one of the image capture device and the treatment head such that an image of the treatment head captured using the image capture device meets a set of predetermined criteria.

10. determining that the remaining life of the treatment head is less than a predetermined duration based on an estimated time when the treatment head will be replaced; 10. The computer-implemented method of claim 1, further comprising generating a notification prompting a user of the personal care device to purchase a replacement treatment head for provision to a receiving device.

11. receiving device data indicative of how the personal care device was used during a previous treatment session; 11. The computer-implemented method of claim 1, further comprising determining an estimated time when the treatment head should be replaced based on the received data.

12. A computer program comprising computer readable code which, when executed by a suitable computer or processor, causes said computer or processor to carry out the method according to any of claims 1 to 11.

13. 1. A device for determining the lifespan of a treatment head of a personal care device, comprising: Apparatus having a processor for carrying out the method of any of claims 1 to 11.

14. 1. A system comprising: a personal care device having a body portion and a replaceable treatment head removably coupled to the body portion; and the apparatus of claim 13.

15. 15. The system of claim 14, further comprising an image capture device for capturing a plurality of images.

Images