Detecting a new cutting element
By installing sensors on personal care devices to sense motor current and power, and using a decision tree model to detect new cutting elements, the problem of distinguishing between new and old cutting elements in existing technologies is solved, thus improving the accuracy of detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- KONINKLIJKE PHILIPS NV
- Filing Date
- 2024-10-16
- Publication Date
- 2026-05-15
AI Technical Summary
Existing technologies make it difficult to determine whether cutting elements on personal care devices are new or not, affecting the accuracy of end-of-life cutting element prediction algorithms.
New cutting elements can be detected by installing sensors on personal care devices to sense relevant physical parameters, such as motor current and power, and then using machine learning models such as decision trees to analyze these parameters.
It achieves accurate detection of new cutting elements, simplifies the judgment of the cutting element status, and improves the accuracy of the algorithm.
Smart Images
Figure CN122055249A_ABST
Abstract
Description
Technical Field
[0001] The subject matter of this disclosure relates to detecting new cutting elements mounted on personal care devices, computer-implemented methods for detecting new cutting elements mounted on personal care devices, computer-implemented methods for training machine learning models to detect new cutting elements mounted on personal care devices, transient or non-transitory computer-readable media, and personal care devices. Background Technology
[0002] Some algorithms for personal care devices, such as end-of-life cutting element prediction algorithms, require knowledge about whether the cutting element is new or not. However, it is difficult to determine whether a cutting element is new or not.
[0003] US2019 / 224870A1 discloses a shaving appliance system comprising a shaving appliance including a handle and a shaving head attached to the handle; a plurality of sensors disposed in the shaving head and / or handle; sensor circuitry for receiving sensor signals from the plurality of sensors and generating shaving stroke direction information from the sensor signals; and notification circuitry for determining relative shaving stroke direction information for a user based on the shaving stroke direction information and hair growth direction information electronically stored by the user. A method for converting shaving appliance sensor information into a user notification is also disclosed. The sensor circuitry can generate new blade holder event (i.e., when a new razor blade holder is attached to the handle) information and compile cumulative shaving event data occurring since the generation of the new blade holder event information. The new blade holder event can be sensed, for example, by a displacement sensor or a new blade holder sensor. It can also be manually indicated by the user or detected by the appliance by detecting a unique ID (e.g., barcode, RFID tag, physical ID) of each shaving head attached to the handle.
[0004] The purpose of this disclosure is to improve the existing technology. Summary of the Invention
[0005] This invention is defined by the claims.
[0006] According to a first aspect of the invention, a computer-implemented method is provided for detecting a new cutting element mounted on a personal care appliance. The computer-implemented method includes: sensing data representing physical parameters associated with operating the personal care appliance by sensors of the personal care appliance; detecting, based on the sensed data, whether a new cutting element has been mounted on the personal care appliance using a machine learning model; and outputting a signal indicating that the new cutting element has been mounted on the personal care appliance based on the detection. In this way, new cutting elements are easily detected. Knowledge about whether the cutting element is new or not is output by a signal, which can be used by a processor to process algorithms requiring knowledge about whether the cutting element is new or not.
[0007] In one embodiment, the physical parameters include the current and / or power of the motor used to drive the cutting element.
[0008] In one embodiment, using a machine learning model to detect whether a new cutting element has been installed on a personal care device based on sensed data includes: calculating multiple predictive factors using the sensed data; and inputting the multiple predictive factors into the machine learning model.
[0009] In one embodiment, the multiple predictors are selected from a list of predictors including: the bin distribution of motor power used last time, the ratio of the minimum power used last time to the average minimum power used in the previous three uses, the difference between the maximum power used last time and the maximum power used in the penultimate use, and the ratio of the maximum power used last time to the maximum power used in the penultimate use.
[0010] In one embodiment, the machine learning model is a decision tree. Decision trees are more advantageous than other types of machine learning models, such as neural networks, because they require relatively less processing and storage resources.
[0011] According to one aspect of the invention, a computer-implemented method is provided for training a machine learning model to detect new cutting elements mounted on a personal care appliance. The computer-implemented method includes: receiving a dataset comprising multiple predictive factors (representing physical parameters associated with operating the personal care appliance) derived from sensor-sensed data of the personal care appliance, and classifications of new and non-new cutting elements; inputting the multiple predictive factors into a machine learning model to predict whether the cutting element is new or non-new; and optimizing the machine learning model to reduce the error between the predicted classification and the classification in the dataset.
[0012] In one embodiment, the machine learning model is a decision tree.
[0013] In one embodiment, classification and regression tree algorithms are used to perform optimization of the machine learning model.
[0014] In one embodiment, the physical parameters include the current and / or power of the motor used to drive the cutting element.
[0015] In one embodiment, the multiple predictors are selected from a list of predictors including: the bin distribution of motor power used last time, the ratio of the minimum power used last time to the average minimum power used in the previous three uses, the difference between the maximum power used last time and the maximum power used in the penultimate use, and the ratio of the maximum power used last time to the maximum power used in the penultimate use.
[0016] According to one aspect of the invention, a transient or non-transitory computer-readable medium is provided having instructions stored thereon that, when executed by a processor, cause the processor to perform a computer-implemented method of any of the foregoing aspects or embodiments.
[0017] According to one aspect of the invention, a personal care device is provided, the personal care device comprising: an attachment for attaching a cutting element to the attachment; a sensor for sensing physical parameters associated with operating the personal care device; and a controller including a processor and a memory having instructions stored thereon that, when executed by the processor, cause the processor to perform a computer-implemented method of any of the foregoing aspects or embodiments.
[0018] These and other aspects of the invention will become apparent and be elucidated with reference to one or more embodiments described below. Attached Figure Description
[0019] The embodiments of the invention can be best understood with reference to the accompanying drawings, in which:
[0020] Figure 1 A schematic diagram of a personal care appliance according to one or more embodiments is shown;
[0021] Figure 2 A flowchart summarizing a computer-implemented method for detecting a new cutting element mounted on a personal care device, according to one or more embodiments, is shown.
[0022] Figure 3 A decision tree according to one or more embodiments is shown; and
[0023] Figure 4 A flowchart is shown summarizing a computer-implemented method for training a machine learning model to detect new cutting elements mounted on a personal care device, according to one or more embodiments. Detailed Implementation
[0024] At least some of the example embodiments described herein can be constructed, in whole or in part, using dedicated hardware. Terms such as “component,” “module,” or “unit” as used herein can include, but are not limited to, hardware devices that perform a particular task or provide related functionality, such as circuit devices in the form of discrete or integrated components, field-programmable gate arrays (FPGAs), or application-specific integrated circuits (ASICs). In some embodiments, the described elements can be configured to reside on a tangible, persistent, addressable storage medium and can be configured to execute on one or more processors. In some embodiments, these functional elements can include (by way of example) components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuit devices, data, databases, data structures, tables, arrays, and variables. Although example embodiments have been described with reference to the components, modules, and units discussed herein, these functional elements can be combined into fewer elements or separated into additional elements. Various combinations of optional features have been described herein, and it should be understood that the described features can be combined in any suitable combination. In particular, features of any example embodiment may be combined with features of any other embodiment where appropriate, unless such combinations are mutually exclusive. Throughout this specification, the terms "comprising" or "comprises" mean to include the specified components (one or more), but do not exclude the presence of other components.
[0025] refer to Figure 1 The personal care appliance 10 includes a cutting element 12 and a handle 14. Appliance 10 can be a personal care appliance. Personal care appliances can be beauty devices, such as hair cutting appliances. Hair cutting appliances generally involve hair trimmers, razors, epilators, and combination devices. Personal care appliance 10 can be used for trimming and shaving.
[0026] The cutting element 12 includes a stator and a movable blade, each blade including teeth. The movable blade moves relative to the stator to cut the hair between the teeth.
[0027] The handle 14 is elongated and has an attachment 15 for attaching to the cutting element. In other words, the attachment 15 is used to attach the cutting element 12 to the handle. The personal care appliance 10 also includes a motor 16, a sensor 18, a controller 20, and an energy storage unit 22.
[0028] Motor 16 may be an electric motor 16 and may be connected to the cutting element to drive the blade. Motor 16 is powered by energy from storage unit 22. Sensor may be sensor 18, which is configured to sense physical parameters associated with operating the personal care appliance 10. Physical parameters include the current and / or power of motor 16.
[0029] The controller 20 includes a processor 24 and a memory 26. The memory 26 has instructions stored thereon that, when executed by the processor 24, cause the processor to perform any of the methods described below. Thus, the memory can form a non-transitory computer-readable medium having instructions stored thereon that, when executed by the processor, cause the processor to perform any of the methods described herein. The instructions can also be provided on a temporary computer-readable medium, which can be added to the memory when, for example, an update is required.
[0030] refer to Figure 2 A computer-implemented method for detecting a new cutting element on a personal care appliance is summarized as including the following steps: S200, sensing data representing physical parameters associated with operating the personal care appliance by sensors of the personal care appliance; S202, detecting whether a new cutting element has been installed on the personal care appliance based on the sensed data using a machine learning model; and S204, based on the detection, outputting a signal indicating that the new cutting element has been installed on the personal care appliance. The output signal can be output to a processor that processes an algorithm requiring knowledge about whether the cutting element is new or not. The term "new" can mean that the cutting element has never been used before. The term "not new" can mean that the cutting element has been used at least once before. For example, some algorithms can reset their calculations when a new blade is installed.
[0031] The physical parameters include the current and / or power of the motor 16 used to drive the cutting element. Detecting whether a new cutting element has been installed on a personal care appliance based on the sensed data involves two steps. In the first step, multiple predictive factors are calculated using the sensed data. In the second step, the multiple predictive factors are fed into a machine learning model.
[0032] Multiple predictors may include one or more of the following: the bin distribution of motor power in the last use, the ratio of the minimum power in the last use to the average minimum power in the previous three uses, the difference between the maximum power in the last use and the maximum power in the penultimate use, and the ratio of the maximum power in the last use to the maximum power in the penultimate use. The term "use" may refer to a single shave.
[0033] refer to Figure 3The machine learning model can be a decision tree 30. The decision tree comprises multiple nodes 32. Each node 32 is either a branch node or a leaf node. A branch node provides a split leading to two new nodes. For example, a leaf node is an output node where the output cutting element is either new 34 or non-new 36. The split is different for each level of the tree. The split can be numerical and can be determined by training the machine learning model as described below. One of the predictor factors 38 is applied after each branch node. The value of the predictor is compared to the split, and if the predictor is less than or equal to the split, the first branch is taken. If the predictor is greater than the split, the second branch is taken. Figure 3 In this model, the first branch is the left branch, and the second branch is the right branch. This convention may be changed in other embodiments.
[0034] refer to Figure 4 A computer-implemented method for training a machine learning model to detect new cutting elements mounted on a personal care appliance is summarized as having the following steps: receiving a dataset S400, which includes multiple predictive factors (representing physical parameters associated with operating the personal care appliance) derived from sensor-sensed data of the personal care appliance, and classifications of new and non-new cutting elements; inputting the multiple predictive factors S402 into a machine learning model to predict whether the cutting element is new or non-new; and optimizing the machine learning model S404 to reduce the error between the predicted classification and the classification in the dataset.
[0035] The Classification and Regression Tree (CART) algorithm can be used to optimize machine learning models. The CART algorithm helps to identify the splits used at each level, the number of nodes, the number of leaf nodes, etc.
[0036] Although the invention has been described and illustrated in detail in the accompanying drawings and the foregoing description, such descriptions and illustrations are to be regarded as illustrative or exemplary, and not restrictive; the invention is not limited to the disclosed embodiments.
[0037] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude multiple. A single processor or other unit can perform the functions of several items recited in the claims. The fact that certain measures are recited in dissimilar dependent claims does not indicate that a combination of these measures cannot be used advantageously. No reference numerals in the claims should be construed as limiting the scope.
Claims
1. A computer-implemented method for detecting a new cutting element (12) mounted on a personal care appliance (10), the personal care appliance including a motor (16) for driving the cutting element, the computer-implemented method comprising: Data representing physical parameters associated with the motor (16) used to drive the cutting element are sensed (S200) by the sensor (18) of the personal care device; Using a machine learning model, it is determined (S202) whether the new cutting element has been installed on the personal care device based on the sensed data; as well as The detection output (S204) indicates that a new cutting element has been installed on the personal care device.
2. The computer-implemented method according to claim 1, wherein the physical parameters include the current and / or power of the motor (16) for driving the cutting element.
3. The computer-implemented method of claim 2, wherein detecting whether a new cutting element has been installed on the personal care device based on the sensed data using the machine learning model comprises: Multiple predictors (38) are calculated using the sensed data. as well as The multiple predictive factors are input into the machine learning model.
4. The computer-implemented method of claim 3, wherein the plurality of predictive factors are selected from a list of predictive factors including: the bin distribution of motor power used last time, the ratio of the minimum power used last time to the average minimum power used in the previous three times, the difference between the maximum power used last time and the maximum power used in the penultimate time, and the ratio of the maximum power used last time to the maximum power used in the penultimate time.
5. The computer-implemented method according to any one of the preceding claims, wherein the machine learning model is a decision tree (30).
6. A computer-implemented method for training a machine learning model, said machine learning model being used in the computer-implemented method for detecting a new cutting element (12) mounted on a personal care appliance (10) according to any one of claims 1 to 5, said computer-implemented method comprising: Receive (S400) a dataset including multiple predictors (38) derived from data sensed by the sensors of the personal care appliance, and a classification of new (34) cutting elements and non-new (36) cutting elements, the data representing the physical parameters associated with the motor (16) used to drive the cutting elements; The plurality of predictive factors are input (S402) into the machine learning model to predict whether the cutting element is new or not; and Optimize (S404) the machine learning model to reduce the error between the predicted classification and the classification in the dataset.
7. The computer-implemented method according to claim 6, wherein the machine learning model is a decision tree (30).
8. The computer-implemented method of claim 7, wherein the optimization of the machine learning model is performed using classification and regression tree algorithms.
9. The computer-implemented method according to any one of claims 6 to 8, wherein the physical parameters include the current and / or power of the motor (16) for driving the cutting element.
10. The computer-implemented method of claim 9, wherein the plurality of predictive factors are selected from a list of predictive factors including: the bin distribution of motor power used last time, the ratio of the minimum power used last time to the average minimum power used in the previous three times, the difference between the maximum power used last time and the maximum power used in the penultimate time, and the ratio of the maximum power used last time to the maximum power used in the penultimate time.
11. A transient or non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the processor to perform a computer-implemented method according to any one of the preceding claims.
12. A personal care appliance (10), comprising: An attachment for attaching a cutting element (12) to the attachment; Motor (16), the motor being used to drive the cutting element; Sensor (18), the sensor being used to sense physical parameters associated with the motor (16) used to drive the cutting element; as well as A controller (20) includes a processor (22) and a memory (24) having instructions stored thereon that, when executed by the processor, cause the processor to perform a computer-implemented method according to any one of claims 1 to 5.