Sensor-based systems and methods for analyzing shaving performance

Abstract

Sensor-based systems and methods for analyzing shaving performance. A shaving device includes a handle having a connection structure connected to a hair cutting appliance (e.g., a blade). Sensor data is collected from a sensor associated with the shaving device during one or more shaving strokes during which a user shaves with the shaving device. Shaving stroke data is determined from sensor data defining one or more shaving strokes. The shaving stroke data and thresholds are input into a model (e.g., an artificial intelligence model) to output a user-specific shaving score. The generation of the user-specific shaving fraction includes comparing the shaving stroke data to a threshold to determine a deviation from the threshold. An output is generated based on the user-specific shaving score.

Description

TECHNICAL FIELD

[0001] The present disclosure relates generally to sensor-based systems and methods, and more particularly to sensor-based systems and methods that analyze shaving performance. BACKGROUND

[0002] Generally, shaving performance can be summarized as a tradeoff between closeness and irritation, where an individual can generally achieve either an increase in shaving closeness (removing more hair) but at the risk of irritation or redness of his or her skin, or a lower closeness shave (leaving more hair) but at the risk of reduced skin irritation. The individual generally attempts to balance this tradeoff to achieve his or her desired end result by manually adjusting the amount, direction, and pressure (or load) of stroke applied during shaving. Increasing the amount of stroke, stroking against the direction of hair growth, or applying increased pressure during stroking generally will result in both increased closeness and increased risk of skin irritation. However, there is generally a shaving pressure point beyond which there is minimal increase in closeness benefit with a high risk of undesirable skin irritation.

[0003] Accordingly, a problem has arisen with respect to existing shaving razors and their use, where an individual desiring a close shave generally applies too much stroke, too much stroke against the direction of hair growth, and / or too much pressure (or load) during a shaving session, which is the mistaken impression that this will improve the closeness of the end result. The problem is extremely pronounced given the variety of models, brands, and types of shaving razors currently available to an individual, where each model, brand, and type of shaving razor has different components, blades, sharpness, and / or other different configurations, all of which can vary significantly in the amount, direction, and pressure (or load) of stroke required, and for each shaving razor type, in order to achieve a close shave with little or no skin irritation (e.g., with little or no hair left behind). This problem is particularly severe because such existing shaving razors, which can be configured differently, provide little or no feedback or guidance to help an individual achieve a close shave without irritating the skin.

[0004] For the foregoing reasons, there is a need for sensor-based systems and methods that analyze shaving performance. SUMMARY

[0005] Sensor-based shaving systems and methods for analyzing shaving performance are described herein. Generally, the sensor-based shaving systems and methods include a shaving device (e.g., a shaving razor such as a wet shaving razor). The shaving device can include a handle and a connection structure for connecting a hair-cutting implement (e.g., a razor blade). The shaving device can also include or be associated with a shaving event sensor (e.g., a load sensor) to collect shaving data of a user. Real-time feedback and / or indicators can be provided to the user via an indication, for example, a green light-emitting diode (LED) feedback when the user applies pressure within or below a unique threshold, or a red LED feedback when the user applies pressure above the user's unique threshold.

[0006] Reducing skin irritation can be determined by various factors, including, for example, shaving behavior of the user and wear on the cartridge (e.g., razor blade). Other external factors can also be determinative, such as the presence of a shaving formulation and / or environmental conditions (e.g., wet shaving or dry shaving). Such factors can be measured electronically by sensors associated with the shaving device and / or reported as data provided by the user, for example, via a display screen. The sensor and / or user-provided data can be input into a smart algorithm, such as an artificial intelligence model and / or other model, to output a user-specific shaving score that can be displayed to the user. The user can monitor, track, or otherwise use the output and feedback (e.g., the user-specific shaving score) to modify his or her behavior and seek to improve his or her user-specific shaving score, resulting in less real-world skin irritation and, in turn, a better shaving experience or performance.

[0007] The indication and / or load feedback features as provided by the sensor-based systems and methods alert the user to behaviors that prevent causing skin irritation and encourage behaviors that reduce skin irritation. Thus, analyzing the user's load threshold (e.g., unique threshold) to determine deviations from the threshold during a shaving session can allow the user to prevent skin damage. For example, the vast majority of user shaving sessions are typically in the range of 50 grams force (gf) to 500 gf, and the average peak load during a shaving session is approximately in the range of 200 gf to 250 gf. Based on this data, the user's load threshold (e.g., unique threshold) can be set or determined for the user's shaving device, for example, 250 gf, for example, at least as an initial target value, to encourage the user to change his or her behavior to have his or her specific load or pressure (as applied to his or her skin or face) within the lower half of the typical load range, or at least within a deviation, to reduce skin irritation. Using a unique threshold that can be specific to each user, as described herein, provides a stimulation benefit at the specific user level for the reduction of load or pressure to the user's skin or face.

[0008] Generally, in various embodiments, unique, specific, and / or personalized thresholds as used, stored, and / or implemented by shaving devices as described herein can be generated and / or used to provide unique, specific, and / or personalized shaving feedback and performance to a corresponding specific user to reduce skin irritation.

[0009] More specifically, according to various embodiments herein, a sensor-based method for analyzing shaving performance is disclosed. The sensor-based method can include collecting, by one or more processors, sensor data from one or more sensors of a shaving device having a blade, the sensor data being collected during one or more shaving strokes of a user shaving with the shaving device. The sensor-based method can further include determining, based on the sensor data, shaving stroke data defining the one or more shaving strokes. The sensor-based method can further include inputting the shaving stroke data and a threshold into a model executing on the one or more processors to output a user-specific shaving score. The generation of the user-specific shaving score can include comparing the shaving stroke data to the threshold to determine a deviation from the threshold. The sensor-based method can further include generating an output based on the user-specific shaving score.

[0010] In further embodiments, as described herein, a sensor-based system is configured to analyze shaving performance. The sensor-based system includes a shaving device having a blade and including one or more sensors. The sensor-based system further includes one or more processors communicatively coupled to the shaving device. The sensor-based system further includes a memory communicatively coupled to the one or more processors. The sensor-based system further includes a model configured to execute on the one or more processors. The sensor-based system further includes computing instructions stored on the memory and, when executed by the one or more processors, cause the one or more processors to collect sensor data from the one or more sensors of the shaving device. The sensor data can be collected during one or more shaving strokes of a user shaving with the shaving device. The computing instructions can further be executed by the one or more processors to determine, based on the sensor data, shaving stroke data defining the one or more shaving strokes. The computing instructions can further be executed by the one or more processors to input the shaving stroke data and a threshold into the model to output a user-specific shaving score. The generation of the user-specific shaving score can include comparing the shaving stroke data to the threshold to determine a deviation from the threshold. The computing instructions can further be executed by the one or more processors to generate an output based on the user-specific shaving score.

[0011] In further embodiments, a non-transitory computer-readable medium storing computing instructions that, when executed by one or more processors, are used to analyze shaving performance is disclosed. The computing instructions, when executed by the one or more processors, can cause the one or more processors to collect, from one or more sensors of a shaving device having a blade, sensor data collected during one or more shaving strokes of a user shaving with the shaving device. The computing instructions, when executed by the one or more processors, can also cause the one or more processors to determine, based on the sensor data, shaving stroke data defining the one or more shaving strokes. The computing instructions, when executed by the one or more processors, can also cause the one or more processors to input the shaving stroke data and a threshold into a model executing on the one or more processors to output a user-specific shaving score. Generation of the user-specific shaving score can include comparing the shaving stroke data to the threshold to determine a deviation from the threshold. The computing instructions, when executed by the one or more processors, can also cause the one or more processors to generate an output based on the user-specific shaving score.

[0012] In accordance with the above, as well as the disclosure herein, the present disclosure includes improvements in computer functionality or to other technologies at least because the present disclosure describes (e.g., in some embodiments) shaving devices and / or servers communicatively connected to the shaving devices that are improved, where the intelligence or predictive capabilities of the shaving devices and / or servers are enhanced by trained models (e.g., sensor-based learning models) that can include machine learning models. In such embodiments, the models executing on the servers and / or at the shaving devices are able to accurately identify user-specific shaving scores, which define real-world shaving performance of users, based on sensor data from one or more sensors of the shaving devices. That is, with respect to some embodiments, the present disclosure describes improvements in the functionality of the computer itself or “any other technology or technical field” because the shaving devices and / or servers communicatively connected thereto are enhanced with sensor-based learning models to accurately predict, detect, or determine unique user-specific shaving scores for various users. This is an improvement over the prior art at least because prior systems lack such predictive or classification functionality and are fundamentally incapable of accurately analyzing sensor data and / or data sets of a particular user to determine a unique user-specific shaving score that is designed to be implemented on a shaving device to provide outputs that are specific to real-world activities of the user. The predicted outputs provided by the models can be used to improve the underlying device (e.g., shaving device) by way of causing the cartridge or blade of the shaving device to receive maintenance and / or replacement, thereby improving real-world operation and longevity of the shaving device.

[0013] For similar reasons, the present disclosure relates to improvements in, at least, the field of computing devices for shaving devices (e.g., shaving razors), as the present disclosure describes or introduces improvements to computing devices in the field of shaving devices, whereby shaving devices as described herein utilize models to update and enhance, whether on the shaving device or via communication with a server, to detect and track real-world usage of the device by a user.

[0014] Further, the present disclosure includes the application of certain claim elements with or by use of specific machines, such as shaving devices having hair cutting implements (e.g., blades). The shaving devices include sensors for collecting sensor data during one or more shaving strokes by a user utilizing the shaving device.

[0015] Further, the present disclosure includes specific features beyond the well-known, routine, conventional activities in the art, or adds non-routine steps that limit the claims to specific useful applications, such as analyzing shaving performance as described herein.

[0016] The advantages will become apparent to those skilled in the art upon reading the following detailed description of the preferred embodiments in conjunction with the drawings. As will be realized, the embodiments of the application are capable of other and different embodiments, and their details are capable of modifications in various aspects. Accordingly, the drawings and descriptions should be regarded as illustrative in nature and not as restrictive. BRIEF DESCRIPTION OF DRAWINGS

[0017] The drawings described below depict various aspects of the systems and methods disclosed herein. It is to be understood that each drawing depicts an embodiment of a particular aspect of the disclosed systems and methods and that the drawings are meant to be consistent with the possible embodiments thereof. Furthermore, where possible, the following description refers to the accompanying drawings in which the drawing numbers refer to the same or like parts throughout the several views.

[0018] The arrangements discussed currently are shown in the drawings, it being understood, however, that the present embodiments are not limited to the precise arrangements and tools shown, wherein:

[0019] Figure 1 An example sensor-based system configured to analyze shaving performance is exemplified in accordance with various embodiments disclosed herein.

[0020] Figure 2 Another example of a sensor-based system having multiple shaving devices and configured to analyze shaving performance of respective users is exemplified in accordance with various embodiments disclosed herein.

[0021] Figure 3A flowchart or algorithm illustrating an example sensor-based method of analyzing shaving performance according to various embodiments disclosed herein is exemplified.

[0022] Figure 4A is a table defining example inputs for a model for determining or outputting a user-specific shaving score according to various embodiments disclosed herein.

[0023] Figure 4B is another table defining additional example inputs for a model for determining or outputting a user-specific shaving score according to various embodiments disclosed herein.

[0024] Figure 5 is a table defining example metrics, inputs, and data sources that can be used by a model (e.g., an artificial intelligence model) for outputting a user-specific shaving score according to various embodiments disclosed herein.

[0025] Figure 6 An example is exemplified of a user shaving with a shaving device as described in Figure 1 and Figure 2 according to various embodiments disclosed herein.

[0026] Figure 7 An example user interface presented on a display screen of a user computing device according to various embodiments disclosed herein is exemplified.

[0027] The accompanying drawings depict preferred embodiments for purposes of illustration only. Alternative embodiments of the systems and methods exemplified herein can be employed without departing from the principles of the application described herein. DETAILED DESCRIPTION

[0028] Figure 1 An example sensor-based system 100 configured to analyze shaving performance according to various embodiments disclosed herein is exemplified. As shown in embodiments of Figure 1 The sensor-based shaving system 100 includes a shaving device 150 (e.g., a grooming device) having (i) a handle 150h including a connection structure 150c, and (ii) a hair cutting implement 150i connected to the connection structure 150c, according to various embodiments disclosed herein. Figure 1 In embodiments of the sensor-based shaving system 100, the shaving device 150 is exemplified as a shaving razor having a detachable hair cutting implement 150i (e.g., a razor blade or a cartridge). As described herein, the shaving device can include other similar shaving devices including, for example, but not limited to, at least one of an electric shaver, a shaving razor, or an epilator.

[0029] The sensor-based shaving system 100 also includes a shaving event sensor 154 (e.g., a load sensor) configured to collect sensor data and, thus, measure user behavior associated with a user’s shaving event. The shaving event sensor 154 can include one or more of a displacement sensor, a load sensor, a motion sensor, an optical sensor, an audio sensor, and / or a temperature sensor. In Figure 1 embodiments, the shaving event sensor 154 is communicatively coupled to the shaving device 150, where the shaving event sensor 154 is positioned on the shaving device 150. In other embodiments, the shaving event sensor 154 can be communicatively coupled to a charging station (not shown) of the shaving device (e.g., the shaving device 150), a cradle (not shown) for holding or receiving the shaving device (e.g., the shaving device 150), or a computing device (e.g., a user computing device 111c1 as exemplified herein) having a processor executing a digital app, for example, via wired or wireless communication. Figure 2

[0030] The sensor-based shaving system 100 also includes a transceiver 158. In various embodiments, the transceiver 158 can be a wired or wireless transceiver positioned on or in the shaving device 150. The transceiver 158 can include any one or more of a wired connection or a wireless connection, such as a Bluetooth connection, a Wi-Fi connection, a cellular connection, and / or an infrared connection. In various embodiments, the transceiver 158 is communicatively coupled to the shaving device, a charging station (not shown) of the shaving device, a cradle (not shown) for holding or receiving the shaving device (e.g., the shaving device 150), or a computing device (e.g., a user computing device 111c1 as exemplified herein) having a processor executing a digital app. Figure 2

[0031] The sensor-based shaving system 100 also includes a processor 156 (e.g., a microprocessor) and is communicatively coupled to the shaving event sensor 154 and the transceiver 158, for example, via a computing bus or a printed circuit board (PCB). The processor 156 is configured to receive, send, and analyze data (e.g., shaving data) provided from the shaving event sensor 154 and / or the transceiver 158. In various embodiments, the processor 156 is configured to execute computing instructions stored on a memory 157 (e.g., of the shaving device 150) communicatively coupled to the processor 156. The instructions can cause the processor 156 to collect data from the shaving event sensor. The data can include shaving data defining a shaving event, for example, such as one or more shaving strokes with which a user shaves with the shaving device.

[0032] In Figure 1 ​​In implementations, the processor 156 is exemplified as on-board on the shaving device 150. For example, in some implementations, generation of the user-specific shave score can be implemented by an on-board processor on the shaving device (e.g., the shaving device 150). For example, in some aspects, a model (e.g., an artificial intelligence model) can be stored in the memory 157 and configured to execute on the processor 156. The computing instructions stored on the memory 157, when executed by the processor 156, can cause the processor 156 to collect sensor data from the sensors 154 during one or more shaving sessions in which the user shaves with the shaving device 150. The processor 156 can determine, based on the sensor data, shave session data defining the one or more shaving sessions. The shave session data and the threshold value can be input into the model to output the user-specific shave score. Generation of the user-specific shave score can include comparing the shave session data to the threshold value to determine a deviation from the threshold value. The processor 156 executing the model stored in the memory 157 can generate an output based on the user-specific shave score. The output can be a displayed value or a value sent to a computer network and / or server as described herein.

[0033] Additionally or alternatively, the processor 156 can be located off-board and non- on-board the shaving device. For example, the processor 156 can be located on a cradle, on a charging station to which the shaving device 150 is connected. Still further, in some aspects, the processor 156 can include a processor of a user computing device (e.g., the user computing device 111cl). In further aspects, the user-specific shave score can be implemented by a non-on-board processor (e.g., a processor of the server 102 as described herein) communicatively coupled to the shaving device (e.g., the shaving device 150) via a wired or wireless computer network. Still further, in some implementations, the non-on-board processor can be configured to execute as part of one or more processors including at least one of a base station of the shaving device (e.g., the shaving device 150), a mobile device (e.g., the user computing device 111cl as exemplified herein), or a remote computing device (e.g., the server 102, which can be a cloud-based server as described herein). Figure 2 Figure 2 In such implementations, the shaving device 150 can send and / or receive sensor data, shave data, and / or data sets to a computer network device 160 (e.g., the server 102 as described herein) via, for example, its transceiver 158 and / or processor. The computer network device, for example, can be a router, a Wi-Fi router, a hub, or a switch capable of sending and receiving data on a computer network. Figure 2

[0034] Figure 2 ​​Another example of a sensor-based system 200 according to various embodiments disclosed herein is illustrated, which has multiple shaving devices and is configured to analyze shaving performance of respective users. For example, in Figure 2 embodiments, the sensor-based system 200 includes a shaving device 150 as described in Figure 1 embodiments. The sensor-based system 200 also includes a second shaving device 170. The shaving device 170 is configured the same or similar as described herein for Figure 1 embodiments. For example, the shaving device 170 is configured to be communicatively coupled to a computer network device 180 (e.g., coupled to a server 102 as shown in Figure 2 embodiments), which can be a router, a Wi-Fi router, a hub or switch, a cable that sends and receives packet data over a computer network (e.g., computer network 120), for example.

[0035] In example embodiments, Figure 2 the sensor-based system 200 includes a server 102, which can include one or more computer servers. In various embodiments, the server 102 includes multiple servers, which can include multiple, redundant, or replicated servers as part of a server farm. In further embodiments, the server 102 can be implemented as a cloud-based server, such as a cloud-based computing platform. For example, the server 102 can be any one or more cloud-based platforms, such as MICROSOFT AZURE, AMAZON AWS, or the like. The server 102 can include one or more processors 104 and one or more computer memories 106.

[0036] The memory 106 can include one or more forms of volatile and / or non-volatile, fixed and / or removable memory such as read only memory (ROM), electronically programmable read only memory (EPROM), random access memory (RAM), erasable electronically programmable read only memory (EEPROM), and / or other hard drives, flash memory, MicroSD cards, etc. The memory 106 can store an operating system (OS) (e.g., Microsoft Windows, Linux, UNIX, etc.) that can facilitate the functionality, apps, methods, or other software as discussed herein. The memory 106 can also store a model 108 (e.g., sensor-based learning), which can be an artificial intelligence-based model such as a machine learning model trained on shaving data or datasets, or other models as described herein. Additionally or alternatively, the model 108 can also be stored in a database 105 that is accessible by or otherwise communicatively coupled to the server 102. The memory 106 can also store machine-readable instructions, including any of one or more applications, one or more software components, and / or one or more application programming interfaces (APIs), which can be implemented to facilitate or perform these features, functionalities, or other disclosures described herein, such as any methods, processes, elements, or limitations illustrated, depicted, or described for the various flowcharts, illustrations, diagrams, figures, and / or other disclosures herein. For example, at least some of the applications, software components, or APIs can be, can include, or otherwise be part of an imaging-based machine learning model or component such as the model 108, each of which can be configured to facilitate various functionalities thereof discussed herein. It will be appreciated that one or more other applications executed by the processor 104 are contemplated.

[0037] The processor 104 can be connected to the memory 106 via a computer bus that is responsible for transmitting electronic data, data packets, or other electronic signals to and from the processor 104 and the memory 106 in order to implement or perform machine-readable instructions, methods, processes, elements, or limitations as illustrated, depicted, or described for the various flowcharts, illustrations, diagrams, figures, and / or other disclosures herein.

[0038] The processor 104 can interface with the memory 106 via a computer bus to execute an operating system (OS). The processor 104 can also interface with the memory 106 via a computer bus to create, read, update, delete, or otherwise access or interact with data stored in the memory 106 and / or database 105 (e.g., a relational database such as Oracle, DB2, MySQL, or a NoSQL-based database such as MongoDB). Data stored in the memory 106 and / or database 105 can include all or a portion of any data or information described herein, including, for example, sensor data, shaving data, and / or data sets (e.g., first or subsequent data sets regarding sensor and / or shaving data) or other information of a user, user profile data including demographics, age, race, skin type, etc., and / or prior shaving data associated with one or more shaving devices or appliances. For example, in some embodiments, user profile data can be obtained via a questionnaire or display form in a software application associated with the shaving device 150, e.g., as shaving event data reported by a user via a user computer device 111c1.

[0039] In some aspects, data (e.g., such as sensor data or user data) can be collected from multiple shaving devices (e.g., the shaving device 150 and the shaving device 170). Such data can be used to train the model 108, which can be stored on the memory 106 and / or downloaded to the shaving device 150 for storage on the memory 157 and / or execution by the processor 156.

[0040] Referring to Figure 2 The server 102 can also include a transceiver configured to transmit (e.g., send and receive) data to one or more networks or local terminals, such as the computer network 120 and / or the terminal 109 (for rendering or visualization) via one or more external / network ports. In some embodiments, the server 102 can include a client-server platform technology, such as ASP.NET, Java J2EE, Ruby on Rails, Node.js, a web service, or an online API, which responds to receiving and in response to electronic requests. The server 102 can implement a client-server platform technology that can interact with the memory 106 (including applications, components, APIs, data, etc. stored therein) and / or the database 105 via a computer bus to implement or execute machine-readable instructions, methods, processes, elements, or limitations as exemplified, depicted, or described with respect to various flowcharts, illustrations, diagrams, figures, and / or other disclosure herein.

[0041] According to some embodiments, the server 102 can include or interact with one or more transceivers (e.g., WWAN, WLAN, and / or WPAN transceivers) that function according to IEEE standards, 3GPP standards, or other standards and that can be used to receive and transmit data via external / network ports connected to a computer network 120. In some embodiments, the computer network 120 can include a private network or local area network (LAN). Additionally or alternatively, the computer network 120 can include a public network, such as the Internet.

[0042] The server 102 can also include or implement an operator interface configured to present information to and / or receive input from an administrator or operator. As shown, the operator interface can provide a display screen (e.g., via the terminal 109). The server 102 can also provide I / O components (e.g., ports, capacitive or resistive touch-sensitive input panels, keys, buttons, lights, LEDs) that are directly accessible via the server 102 or attached to the server or indirectly accessible or attached via the terminal 109. According to some embodiments, an administrator or operator can access the server 102 via the terminal 109 to view information, make changes, input training data, and / or perform other functions. Figure 2

[0043] As described above, in some embodiments, the server 102 can perform functionality as part of a “cloud” network as discussed herein, or can otherwise communicate with other hardware or software components within the cloud to send, retrieve, or otherwise analyze data or information described herein.

[0044] ​Generally, computer programs or computer-based products, applications, or code (e.g., models such as artificial intelligence models (e.g., sensor-based learning model 108), or other computational instructions described herein) can be stored on computer-usable storage media or on tangible, non-transitory computer-readable media (e.g., standard random access memory (RAM), optical discs, universal serial bus (USB) drives, etc.) in which such computer-readable program code or computer instructions are embodied, wherein the computer-readable program code or computer instructions can be installed or otherwise adapted to be executed by processor 104 (e.g., in conjunction with a corresponding operating system in memory 106) to facilitate, implement, or perform machine-readable instructions, methods, processes, elements, or limitations as illustrated, depicted, or described in the various flowcharts, diagrams, figures, and / or other disclosures herein. In this regard, program code can be implemented in any desired programming language and can be implemented as machine code, assembly code, bytecode, interpretable source code, etc. (e.g., via Golang, Python, C, C++, C#, Objective-C, Java, Scala, ActionScript, JavaScript, HTML, CSS, XML, etc.).

[0045] like Figure 2 As shown, server 102 is communicatively connected to shaving devices 150 and 170 via computer network 120. As described herein, each of shaving devices 150 and 170 may be connected to its respective computer network device 160, 180 (e.g., connected to server 102), which may be a router, Wi-Fi router, hub, or switch capable of sending and receiving packet data on the computer network (e.g., computer network 120). Specifically, computer network devices 160 and 180 may include routers, wireless switches, or other such wireless connection points that communicate with user computing devices (e.g., user computing devices 111c1 and 112c1) via wireless communication 122 based on any one or more of various wireless standards, such as IEEE 802.11a / b / c / g (WIFI), BLUETOOTH, etc., as non-limiting examples.

[0046] The server 102 is also communicatively connected to user computing devices, including user computing device 111cl and user computing device 112cl, via base stations 111b and 112b via computer network 120. The base stations 111b and 112b can include cellular base stations such as cell towers, thereby communicating with user computing devices (e.g., user computing device 111cl and user computing device 112cl) via wireless communications 121 based on any one or more of a variety of mobile phone standards, including NMT, GSM, CDMA, UMTS, LTE, 5G, and the like.

[0047] User computing devices, including user computing device 111cl and user computing device 112cl, can be connected to shaving devices 150 and 170, either directly or via computer network devices 160 and 180. Additionally or alternatively, shaving devices 150 and 170 can be connected to server 102 via base stations 111b or 112b and / or computer network devices 160 and 180 over computer network 120.

[0048] User computing devices (e.g., user computing device 111cl and user computing device 112cl) can include mobile and / or client devices for accessing and / or communicating with server 102. In various embodiments, user computing devices (e.g., user computing device 111cl and user computing device 112cl) can include cellular phones, mobile phones, tablet devices, personal data assistants (PDAs), and the like, including, as non-limiting examples, APPLE iPhone or iPad devices or GOOGLE ANDROID-based mobile phones or tablets. Moreover, user computing devices (e.g., user computing device 111cl and user computing device 112cl) can implement or execute an operating system (OS) or mobile platform, such as Apple’s iOS and / or Google’s Android operating system. Any of user computing devices (e.g., user computing device 111cl and user computing device 112cl) can include one or more processors and / or one or more memories for storing, implementing, or executing computing instructions or code (e.g., mobile applications), as described in various embodiments herein.

[0049] User computing devices (e.g., user computing device 111cl and user computing device 112cl) can include wireless transceivers to transmit wireless communications 121 and / or 122 to and receive wireless communications from base stations 111b and / or 112b. In this way, data (e.g., such as sensor and / or user data) can be transmitted to server 102 via computer network 120 for training models and / or generating outputs based on user-specific shave scores as described herein.

[0050] In some aspects, a shaving device (e.g., shaving device 150) can be communicatively coupled to a user computing device having a display screen. The display screen can output or present various data as described herein, including, for example, a user-specific shave score. For example, a user computing device (e.g., user computing device 111c1 and user computing device 112c1) can include a display screen for displaying graphics, images, text, data, interfaces, graphical user interfaces (GUIs), and / or such visualizations or information as described herein. For example, a display screen of a user computing device (e.g., user computing device 111c1) can display images to a user via an application (app) executing on the user computing device (e.g., user computing device 111c1), for example, such as an output. The application can execute instructions via a programming language to receive shaving data and present it on the display screen of the user computing device. For example, the application can be implemented via one or more application programming languages, including, for example, SWIFT or Java via for APPLE iOS and Google Android platforms, respectively. In various embodiments, the display or GUI indication can include one or more visualizations of data and / or scores based on sensor data (e.g., load or pressure scores), data output (e.g., raw or processed data), user data, and / or graphs of data (e.g., raw or processed data). Such displays, GUIs, or other visualizations can be presented or implemented via an application configured to execute on a user computing device (e.g., user computing device 111c1 as described herein). In such embodiments, the application can be configured to receive shaving data and present it on the display screen of the user computing device (e.g., user computing device 111c1).

[0051] In some embodiments, the displayed data can be provided by the transceiver 158 and can be customized by the user. For example, in various embodiments, the transceiver 158 is configured to provide an indication directly to the user (e.g., via an LED), or additionally or alternatively, to another device (e.g., a user computing device as described herein) providing the indication. The user can customize which, if any, of these ways of providing an indication. Figure 2 The user computing device 111c1) is illustrated. The user can customize which, if any, of these ways of providing an indication.

[0052] In some aspects, user-specific shaving scores may be stored in a memory (e.g., memory 157) communicatively coupled to one or more processors. Additionally or alternatively, user-specific shaving scores may be tracked by comparing them with one or more of the following: other user-specific shaving scores generated for the user (e.g., based on the use of shaving device 150); and / or shaving scores generated for other users (e.g., users of a second shaving device 170).

[0053] Figure 3 A flowchart or algorithm illustrating an example sensor-based method 300 for analyzing shaving performance according to various embodiments disclosed herein is provided. At block 302, the sensor-based method 300 includes collecting sensor data from one or more sensors of a shaving device (e.g., shaving device 150) having blades by one or more processors.

[0054] In various respects, one or more processors may be processors of the shaving device itself (e.g., processor 156). Additionally or alternatively, one or more processors may be processors of one or more servers (e.g., processor 104) that communicate with the processor (e.g., processor 156) of the shaving device (e.g., shaving device 150).

[0055] Furthermore, in an example of method 300, sensor data is collected during one or more shaving strokes performed by the user using the shaving device. For example, Figure 6 Examples of utilization based on the various implementation schemes disclosed herein are provided. Figure 1 and Figure 2 The shaving device described (e.g., shaving device 150) is used to shave an example user (e.g., user 600u). Figure 6 In the example, user 600u has performed two shaving strokes (i.e., shaving stroke 601s and shaving stroke 602s) using shaving device 150. As user 600u moves the razor across their skin, sensor 154 collects sensor data. Sensor data may include position data, orientation data, and pressure or load data, including pressure or load data (e.g., load data 602l) at points on the user's (e.g., user 600u) skin, such as those applied by the razor or other cutting tool. Sensor data can be analyzed to determine the direction, path, and count of user shaving strokes (e.g., shaving strokes 601s and 602s) for a given shaving period (e.g., the time period between the start and end of the shaving period).

[0056] At block 304, the sensor-based method 300 includes determining, based on the sensor data, shave pass data defining one or more shave passes. In various aspects, the shave pass data can define a plurality of characteristics of the shaving device, including, as non-limiting examples, the shaving device as applied to the user’s skin, the user’s behavior or use of the shaving device, and / or other characteristics as described herein. For example, in some aspects, the shave pass data can include a pass pressure (e.g., a pressure applied to the user’s skin by the blade). The shave pass data can also include a count of one or more shave passes made with the blade (e.g., a number of passes made by the user for a given shaving session). The shave pass data can also include a frequency of one or more shave passes made with the blade (e.g., a number of passes made per a given unit of time). The shave pass data can also include a blade pivot angle (e.g., an angle of the blade relative to the user’s skin), a rinse count (e.g., a number of times the user rinses), a rinse duration (e.g., how long the user rinses), a water temperature (e.g., a Fahrenheit or Celsius value of water used while rinsing or shaving), and / or a razor temperature (e.g., a Fahrenheit or Celsius value of a razor used while shaving).

[0057] Additionally or alternatively, the shave pass data can include a speed of one or more shave passes made with the blade (e.g., a speed at which the shaving device is moved over the user’s skin). Additionally or alternatively, the shave pass data can include a number of shaving sessions during a blade life of the blade (e.g., a number of times the user uses the blade). Additionally or alternatively, the shave pass data can include an acceleration of one or more shave passes made with the blade (e.g., how quickly or slowly the user initiates and / or stops the blade and / or shaving device for a given pass). Additionally or alternatively, the shave pass data can include a direction of one or more passes made with the blade (e.g., an upward pass, a downward pass, a leftward pass, a rightward pass, and / or whether the pass is against the grain of the user’s hair or with the grain of the user’s hair). The shave pass direction can also include a direction based on a degree from a reference direction, such as straight up. Additionally or alternatively, the shave pass data can include a pass length (e.g., measured in inches or centimeters).

[0058] Additionally or alternatively, the shave pass data can include a pass duration (e.g., a time taken by the user to complete a shave pass), a pass location (e.g., a location of a given pass on the user’s body), a shave duration (e.g., a time taken by the user to complete a shaving session, as defined from a start to an end of a full shave), a duration between shaves (e.g., a time between two shaving sessions), and / or a duration between passes (e.g., a time between two given passes made by the user using the shaving device).

[0059] Further referenceFigure 3 At block 306, the sensor-based method 300 includes inputting the shave session data and the threshold into a model executing on one or more processors, where the model is configured (e.g., trained) to output a user-specific shave score. The generation of the user-specific shave score can include comparing the shave session data as described herein to the threshold to determine a deviation from the threshold. Additionally or alternatively, the generation of the user-specific shave score can include inputting as input to the model a threshold that can be specific to the user in order to determine a deviation from the threshold.

[0060] Figure 4A and Figure 4B Examples of a simple model (e.g., which can include the model 108) for determining or outputting a user-specific shave score are provided. In particular, Figure 4A is a table defining example inputs for a model for determining or outputting a user-specific shave score in accordance with various embodiments disclosed herein. In Figure 4A Examples, the example model uses a load metric determined from sensor data generated during one or more shave sessions with a shaving device (e.g., the shaving device 150). The load metric defines a pressure applied to the user’s skin. The pressure and / or load metric can be provided as input to the model to determine a user-specific shave score specific to the pressure and / or load metric applied by the user for a given shave session. In Figure 4A Examples, the user’s shave score is related (e.g., inversely) to the load and / or pressure data on a 0-100 scale. Further, in Figure 4A Examples, the model is configured to be “goal-driven,” where the user-specific shave score is determined on a range of scores (e.g., with values 0-100 related to the load / pressure data), where the user is encouraged to apply, for example, less pressure in order to achieve a higher user-specific shave score. In this way, the user-specific shave score can enhance the user’s shaving performance by allowing for reduced pressure, thus resulting in less irritated skin after the shave session.

[0061] Figure 4B is a further table defining further example inputs for a model for determining or outputting a user-specific shave score in accordance with various embodiments disclosed herein. In Figure 4B Examples, the same load metric and pressure management are configured and applied as described for the model of Figure 4A Examples, the same load metric and pressure management are configured and applied as described for the model of Figure 4BThe model of 108 can also input an indication of blade age. In various aspects, the blade age indicates the age of a blade (e.g., a cartridge of a razor). Determination of blade age can include a total number of strokes on the cartridge, a total time of strokes on the cartridge, a number of shaves on the cartridge, a total load on the cartridge, and / or a type of cartridge. Any of these values can be input by a user or detected by sensors (e.g., sensors 154) of the shaving device 150. Additionally, one or more of the metrics can be used to determine a blade condition, which can be a value that defines a condition, e.g., at a given point in time, on a scale that indicates an overall quality of the blade. In such aspects, the model 108 can input the load metric, the pressure data, the blade age data, and / or the blade condition data as inputs in order to output a user-specific shave score. In Figure 4A In an example of 108, the user’s shave score is related (e.g., inversely) to the load and / or pressure data on a 0-100 scale and blade age. Further, for a given shave, Figure 4A In an example of 108, the user’s shave score is related (e.g., inversely) to the load and / or pressure data on a 0-100 scale and blade age. Further, for a given shave, Figure 4B The model of 108 can be “goal-driven” in that the user-specific shave score is determined within a score range (e.g., with a value of 0-100 determined from load, pressure, and blade age data), where the user is encouraged to apply, e.g., less pressure and the blade has a new blade age and / or better blade condition in order to achieve a higher user-specific shave score. In this way, the user-specific shave score can enhance the user’s shaving performance by allowing for reduced pressure and new blade usage, thus resulting in less irritated skin after a shaving session.

[0062] Additionally or alternatively, the model (e.g., such as the model 108) can include an artificial intelligence model, such as a machine learning model. In such aspects, the model can be trained by one or more processors (e.g., the processor 104) with sensor data, shaving session data, pressure data, and / or other data as described herein, which can include user-specific sensor or shaving session data determined during one or more shaving sessions of a plurality of respective users shaving with respective shaving devices (e.g., the shaving device 150 and / or the shaving device 170). Such training data can be received via the computer network 120, e.g., from a plurality of devices (e.g., the shaving device 150 and / or the shaving device 170) used by respective users. The model can be trained to output a user-specific shave score for a new user (e.g., the user 600u) based on the data.

[0063] For example, in various embodiments, a machine learning imaging model (e.g., model 108) as described herein can be trained using supervised or unsupervised machine learning procedures or algorithms. The machine learning procedures or algorithms can employ neural networks, which can be deep learning neural networks, or a combined learning module or procedure that learns in one or more feature or feature data sets (e.g., sensor data, shaving stroke data, pressure data, load data, blade life data, blade condition data, or any other data as described herein). The machine learning procedures or algorithms can also include natural language processing, semantic analysis, automated reasoning, regression analysis, support vector machine (SVM) analysis, decision tree analysis, random forest analysis, K-nearest neighbor analysis, Naive Bayes analysis, clustering, reinforcement learning, and / or other machine learning algorithms and / or techniques. In some embodiments, artificial intelligence and / or machine learning based algorithms can be included as libraries or packages that execute on the imaging server 102. For example, the libraries can include TENSORFLOW based libraries, PYTORCH libraries, and / or SCIKIT-LEARN Python libraries.

[0064] Machine learning can involve identifying and recognizing patterns in existing data (such as training a model based on sensor data and / or shaving stroke data of a user when shaving with a shaving device) in order to facilitate predictions or recognitions with subsequent data (such as using a model to generate a user-specific shave score as described herein).

[0065] Machine learning models (such as model 108 described herein for some embodiments) can be created and trained based on example data (e.g., sensor data and / or shaving data) as input or data (which can be referred to as “features” and “labels”) in order to make effective and reliable predictions when provided new input (such as test or production level data or input). In supervised machine learning, a machine learning procedure operating on a server, computing device, or additional processor can be provided with example inputs (e.g., “features”) and their associated or observed outputs (e.g., “labels”) in order for the machine learning procedure or algorithm to determine or discover rules, relationships, patterns, or additional machine learning “models” that map such inputs (e.g., “features”) to outputs (e.g., “labels”), for example by determining weights or other metrics across various feature categories and / or assigning weights or other metrics to a model. Such rules, relationships, or additional models can then be provided as subsequent inputs in order for a model executing on a server, computing device, or additional processor to predict an expected output based on the discovered rules, relationships, or models.

[0066] In unsupervised machine learning, a server, computing device, or another processor can be tasked with finding its own structure in unlabeled example inputs, where, for example, multiple training iterations are performed by the server, computing device, or another processor to train multiple model generations until a satisfactory model is generated, e.g., a model that provides sufficient prediction accuracy when given test-level or production-level data or inputs. The disclosure herein can use one or both of such supervised or unsupervised machine learning techniques.

[0067] For example, the server 102 can receive load data, stress data, or other data as described herein, which can be used to train a sensor-based learning model (e.g., the model 108) to generate a user-specific shave score. In some embodiments, the sensor-based learning model can be retrained upon occurrence of a predetermined triggering event (e.g., such as passage of an amount of time, detection of a first use, a new shaving session, and / or after a software upgrade to a shaving device). In some embodiments, the model 108 can be further trained with user profile data in conjunction with other data (e.g., load data or questionnaire data), where the user profile data adjusts the output of the model 108 based on user responses or inputs to the user profile data.

[0068] Figure 5 Table 500 of example metrics, inputs, and data sources that can be used by a model (e.g., an artificial intelligence model, such as the model 108 described herein) to output a user-specific shave score in accordance with various embodiments disclosed herein. The model 108 can take many data types as illustrated in Table 500 as inputs and / or training data, including sensor data (i.e., sensor inputs), user inputs, or other data as described herein. The model is trained and configured to output a user-specific shave score based on the inputs and training data, respectively. Figure 1

[0069] For example, as shown in Table 500, various metrics, inputs, and data sources that can be used to calculate a user-specific shave score are illustrated. Table 500 provides examples of these different metrics, inputs, and data sources based on input data. Various different combinations and / or permutations of metrics, inputs, and data sources can be used as training data and / or input into the model 108 in order to calculate or otherwise generate a user-specific shave score. Further, it should be understood that additional or different data can be used to calculate a user-specific shave score as described herein in addition to that shown in Table 500. Figure 5

[0070] Figure 5 ​​​In the example of table 500, the table 500 includes different types 502 of data defined across various metrics 504, each based on one or more inputs 506. For example, goal-driven types of data can define metrics configured for achieving a particular user goal (e.g., user feedback about shaving, measured stroke characteristics, user input about skin sensitivity and / or shaving goals, blade life, shaving conditions, and / or shaving attributes such as irritation and closeness, and stress management). As a non-limiting example, goals can include reducing skin irritation or closeness of shave. Such metrics can be based on sensors, shaving strokes, and / or other data (e.g., user input or sensor-detected data) used to determine the relevant metrics. These can include any one or more of user feedback about shaving, measured stroke characteristics, user input about skin sensitivity and shaving goals, blade life, and / or shaving conditions. In various aspects, shaving conditions can include location of shaving (e.g., sink vs. shower, and / or home vs. away), body area being shaved (e.g., as calculated by motion sensors or user input), time of shaving (e.g., weekday vs. weekend, AM vs. PM), type of shaving formulation, duration of formulation on user’s face, water temperature (e.g., via temperature sensors), and / or number of rinses during shaving.

[0071] As another example as shown in table 500, user-normalized types of data can define metrics configured for normalizing a user’s behavior to a baseline value for which the expected shaving performance is known (e.g., improvement in stress management, stroke behavior, blade conditions). Such metrics can be based on sensors or other data (e.g., user input or sensor-detected data) used to determine the relevant metrics. These can include any one or more of delta (e.g., difference) in goal-driven stress management between nominal shaving and shaving history, measured stroke characteristics relative to previous shaves, blade life, and / or blade life compared to blade change recommendations.

[0072] As another example, as shown in Table 500, population normal type data can define metrics (e.g., shave conditions, shave data history, shave efficiency, and regimen) configured to normalize a user’s behavior to that of other users (e.g., users achieving high performance shaves). Such metrics can be based on sensors or other data (e.g., user input or sensor detected data) used to determine the relevant metric. These can include any one or more of: shave conditions (e.g., wet or dry), measured number of shaves with a cartridge before being discarded by the user, patterns observed in shave behavior data prior to a previous cartridge discard, measurements of shave efficiency for different facial regions (e.g., time per region, direction of travel per region, load behavior per region, each of which can be compared to an ideal load in the facial region). Inputs can also include user regimen (e.g., frequency) of purchasing products through an application (e.g., an application as described herein). Figure 7

[0073] It should be appreciated that the different types 502, metrics 504, and one or more inputs 506 are merely examples, and different, additional, or fewer inputs can be used to define different and / or additional metrics and objectives for training a model (e.g., model 108).

[0074] In various aspects, a model (e.g., such as model 108) can be associated with a threshold value. For example, processor 156 and / or processor 104 can compare a threshold value to its output. Additionally or alternatively, a threshold value can be provided as an input for comparison and / or analysis. The threshold value can influence the output value of the user-specific shave score. Specifically, the user-specific shave score can be based on one or more of: a number of one or more user shave strokes detected as having a value above or below a threshold value for the user. Additionally or alternatively, the user-specific shave score can be based on a magnitude of one or more user shave strokes detected as having a value above or below a threshold value deviation from a threshold value for the user. Further still, additionally or alternatively, the user-specific shave score can be based on a duration of one or more user shave strokes detected as having a value above or below a threshold value for the user.

[0075] In some aspects, the threshold value for the user can include one or more of a universal threshold value (e.g., factory or default setting), a user selected threshold value (e.g., high, medium, or low mode), and / or a unique threshold value for the user (e.g., as determined by a diagnostic shave for the user, which can determine a baseline threshold value specific to the user).

[0076] ​In some aspects, user-specific data can be collected from a user. Such user-specific data can include one or more of user input provided to a graphical user interface (GUI) via a presented form or questionnaire and / or one or more of initial data sets defining one or more initial shaving strokes of the user. In such aspects, the model can be configured by adjusting or updating the model with the user-specific data of the user. The value of the output of the user-specific shave score can then be adjusted based on the user-specific data of the user. For example, in such aspects, a user can manually adjust the unique threshold value up or down, for example, based on their own personal preferences or goals, by providing manual user input and / or baseline shaving data. For example, a baseline stroke behavior can be determined for the user based on the initial data set. A shaving stroke deviation for the user can then be determined by comparing the baseline stroke behavior and the shaving stroke data. The user-specific shave score can be based on the shaving stroke deviation. For example, if a user has 200 strokes in a diagnostic shave, but later needs 300 strokes due to cartridge wear (e.g., reduced blade quality), this can identify a shaving stroke deviation. In another example, the number of strokes can be a first speed, but then can drop to a second speed, thereby defining increased drag and pull due to cartridge wear.

[0077] Additionally or alternatively, the unique threshold value can be configured to be adjustable by the user. Such embodiments allow the user to adjust the unique threshold value by adjusting different threshold percentage values or by setting different modes. For example, while a self-learning model (e.g., model 108) as described herein can be used to set the unique threshold value, such that it properly measures the load for most users, a user can want to manually adjust their own unique threshold value up or down. In such embodiments, the user can select one or more modes (e.g., a high mode, a medium mode, and / or a low mode) to adjust their threshold value. The selection can be made, for example, via a software application (app) (e.g., as described herein with respect to FIG. 6) executing on the user computing device. Figure 7

[0078] ​Additionally or alternatively, user profile data of the user can be acquired, e.g., via a software application (app) executing on the user computing device. This user profile data can then be used to help determine the user’s “mode” during the computation of the unique threshold, without the user having to explicitly manually select the mode. In such aspects, the threshold of the user is determined by analyzing user input or device data including one or more of: user ratings of shaving events reported by the user, blade type, cartridge type, shaving formulation type, style type, style match result, and hair type (e.g., coarse, fine, dense, sparse, etc.). Such data can be determined from user input, device settings, and / or other sensors (temperature sensor and / or hydrometer) of the shaving device (e.g., shaving device 150).

[0079] Further reference is made to Figure 3 At block 308, sensor-based method 300 includes generating an output based on the user-specific shaving score. In some aspects, the output can include one or more visual indicia, such as, for example, one or more light-emitting diodes (LEDs) on the shaving device (e.g., shaving device 150).

[0080] Other outputs can include activating components of the shaving device at a particular time. For example, when a high-load shaving stroke in one or more shaving strokes is detected, one or more of a motor, a visual indicator (e.g., LED), a haptic indicator, and / or an audible indicator of the shaving device can be activated. In some aspects, the high-load shaving stroke can include a pressure value that is above or below a threshold deviation from the threshold value.

[0081] Figure 7 An example graphical user interface (GUI) 702 as presented on a display screen 700 of a user computing device (e.g., user computing device 111cl) in accordance with various embodiments disclosed herein is illustrated. For example, as shown in the example of FIG. 4, user interface 702 can be implemented or presented via an application (app) executing on user computing device 111cl. As shown in the example of FIG. 4, user interface 702 can be implemented or presented via a native application executing on user computing device 111cl. In the example of FIG. 4, user computing device 111cl is a smartphone, such as, for example, an iPhone®. Figure 7 Figure 7 Figure 2 ​​The described user computer device, for example, wherein user computing device 111c1 is exemplified as an Apple iPhone implementing the Apple iOS operating system and having a display screen 700. User computing device 111c1 can execute one or more native applications (apps) on its operating system. Such native applications can be implemented or encoded (e.g., as computational instructions) in a computational language (e.g., SWIFT) executed by the user computing device operating system (e.g., Apple iOS) through the processor of user computing device 111c1.

[0082] Additionally or alternatively, the user interface 702 may be implemented or presented via a web interface, such as via a web browser application, like Safari and / or Google Chrome applications, or other such web browsers.

[0083] like Figure 7 As illustrated in the example, the user interface 702 includes an output of a user-specific shaving score 704 generated by an algorithm or other programming instructions as described for method 300, and presented on display 700 as via GUI 702. The user-specific shaving score 704 displays a value “81,” which can be a value selected from 100 for user 600u, reflecting that user 600u has 81% better shaving performance compared to a baseline value and / or other users (e.g., data collected from shaving device 170, where user 600u uses shaving device 150). Such a score can indicate the likelihood of improved shaving performance (e.g., a value closer to 100 indicates ideal shaving performance). In various aspects, GUI 702 can provide a corresponding user-specific electronic recommendation 712 based on the user-specific shaving score 704, which has a message 712m instructing the user to apply less pressure.

[0084] In some aspects, GUI 702 may include status information. For example, status information 706 may include output generated as described by the algorithm or other programming instructions for method 300, which has an indication of the expected blade life (e.g., 56%) of the blade or blade holder based on a user-specific shaving fraction 704. In various aspects, expected blade life may be or may be limited to the wear (e.g., blade mileage) that the user can cause on the blade before the user should replace it. For example, an output generated as described by the algorithm or other programming instructions for method 300 may inform the user that the user has shaved thirty times with the blade and expects five shaves remaining.

[0085] In some aspects, the status information can include an output generated by the algorithm described for method 300 or in further programming instructions that includes a virtual reward based on the user-specific shave score. For example, as shown in FIG. 7, a quantity of 3427 shave points is shown as a virtual reward earned by the user to, for example, maintain the shave score above a certain value and / or use of the application of the GUI 702 within a given time period. In some aspects, the virtual reward can be used as a value or discount for a next purchase of a product related to the shaving device 150. Figure 7

[0086] Further, the indication can include a further indication or other recommendation to update or replace the blade based on the expected blade life. In various aspects, the further indication or recommendation can be based on the user-specific shave score, the number of strokes, the duration of the shaving session, or other shave-related data or inputs as described herein. Generally, the expected blade life value can be used to determine when to recommend replacing the blade, for example, if it is determined that the user exerts more pressure on the blade, the blade is recommended to be replaced sooner.

[0087] In some aspects, the user-specific electronic recommendation can include a product recommendation for a product based on the user-specific shave score and / or the user-specific electronic recommendation 712. For example, the GUI 702 can present a product recommendation 722 that indicates that the user should purchase a product 724r to meet the user-specific electronic recommendation 712. The user can select 724s to order or otherwise receive the product from the GUI.

[0088] In some aspects, the output generated by the algorithm described for method 300 or in further programming instructions can include initiating a replacement blade for shipping to the user based on the indication or otherwise the user shave score or other data provided herein.

[0089] Additionally or alternatively, the output generated by the algorithm described for method 300 or in further programming instructions can include an electronic communication sent to a computing device (e.g., user computing device 111cl) that provides information to the user (e.g., 600u) of shipping of a new blade (e.g., product 724r). The indication can be sent to a server 102 of a manufacturer or other provider of the product in order to initiate the shipping.

[0090] ​In various implementations, the user-specific shave score 704, the user-specific electronic recommendation 712, the message 712m, the status information 706, and / or the product recommendation 722 can be transmitted from the server 102 to the user's user computing device via the computer network for presentation on a display screen of the user computing device. In such aspects, the server 102 can have received sensor data, shave session data, user data, and / or other data to generate or determine various scores and / or recommendations, which can then be transmitted to the shaving device 150 and / or the user computing device 111cl via the computer network 120.

[0091] In other implementations, transmission to the server 102 does not occur, where the user-specific shave score 704, the user-specific electronic recommendation 712, the message 712m, the status information 706, and / or the product recommendation 722 can instead be generated locally by a model (e.g., 108) executing and / or implemented on the shaving device 150 and / or the user's mobile device (e.g., user computing device 111cl) and presented by a processor of the mobile device on a display screen of the mobile device (e.g., user computing device 111cl), or otherwise output or provided, as described herein.

[0092] Aspects of the disclosure

[0093] The following aspects are provided as examples in accordance with the disclosure herein and are not intended to limit the scope of the disclosure.

[0094] An aspect of a sensor-based method of analyzing shaving performance includes: collecting, by one or more processors, sensor data from one or more sensors of a shaving device having a blade, the sensor data collected during one or more shaving sessions of a user shaving with the shaving device; determining, based on the sensor data, shave session data defining the one or more shaving sessions; inputting the shave session data and a threshold into a model executing on the one or more processors to output a user-specific shave score, wherein generation of the user-specific shave score includes comparing the shave session data to the threshold to determine a deviation from the threshold; and generating an output based on the user-specific shave score.

[0095] Another aspect includes the above-described sensor-based method of analyzing shaving performance, wherein the shave session data includes: a session pressure, a count of the one or more shaving sessions with the blade, and a frequency of the one or more shaving sessions with the blade.

[0096] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the shave stroke data includes one or more of: stroke pressure, a count of the one or more shave strokes with the blade, a frequency of the one or more shave strokes with the blade, a speed of the one or more shave strokes with the blade, a number of shave sessions during a blade life of the blade, an acceleration of the one or more shave strokes with the blade, one or more stroke directions with the blade, stroke length, blade pivot angle, rinse count, rinse duration, water temperature, and razor temperature.

[0097] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the shave stroke data includes one or more of: stroke duration, stroke location, shave duration, duration between shaves, and duration between strokes.

[0098] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the threshold for the user includes one or more of: a generic threshold, a user-selected threshold, and a unique threshold for the user.

[0099] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the threshold for the user is determined by including analyzing user input or device data, the user input or device data including one or more of: a user rating of a shave event reported by the user, a blade type, a cartridge type, a shave formulation type, a style type, a style match result, a hair type, and a duration between shaves.

[0100] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the user-specific shave score is based on one or more of: a number of the one or more user shave strokes detected as having a value above or below the threshold for the user, a magnitude of the one or more user shave strokes detected as above or below a threshold deviation from the threshold for the user, and a duration of the one or more user shave strokes detected as having a value above or below the threshold for the user.

[0101] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output includes one or more visual indicia.

[0102] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output includes presenting the user-specific shave score via a graphical user interface (GUI) on a display screen.

[0103] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: collecting user-specific data, the user-specific data comprising at least one of: (a) one or more user inputs, or (b) an initial data set defining one or more initial shaving strokes of a user; and configuring the model by adjusting or updating the model with the user-specific data of the user, wherein the output of the user-specific shaving score is adjusted based on the user-specific data of the user.

[0104] The sensor-based method of any of the preceding aspects, further comprising: generating, by the one or more processors, a user-specific electronic recommendation based on the user-specific shaving score.

[0105] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: wherein the user-specific electronic recommendation comprises a product recommendation for a manufactured product.

[0106] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: wherein the shaving device is communicatively coupled to a user computing device having a display screen, and wherein the sensor-based method further comprises presenting, by the one or more processors, the user-specific shaving score on the display screen of the user computing device.

[0107] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output comprises an indication identifying an expected blade life of the blade based on the user-specific shaving score.

[0108] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the indication comprises an indication to update or replace the blade based on the expected blade life.

[0109] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output comprises initiating a replacement blade for shipment to a user based on the indication.

[0110] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: when a high-load shaving stroke of the one or more shaving strokes is detected, activating one or more of: a motor of the shaving device, a visual indicator, a haptic indicator, or an audible indicator, wherein the high-load shaving stroke comprises a pressure value that is higher or lower than a threshold deviation from a threshold value.

[0111] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the model is an artificial intelligence model, and wherein the sensor-based method further comprises training, by the one or more processors, the model with respective user-specific pressure data and respective shave session data determined during one or more training shave sessions of respective users shaving with respective shaving devices, wherein the model is trained to output the user-specific shave score.

[0112] An aspect includes a sensor-based system configured to analyze shaving performance, the sensor-based system comprising: a shaving device having a blade and comprising one or more sensors; one or more processors communicatively coupled to the shaving device; a memory communicatively coupled to the one or more processors; a model configured to execute on the one or more processors; and computing instructions stored on the memory and that, when executed by the one or more processors, cause the one or more processors to: collect sensor data from the one or more sensors of the shaving device, the sensor data collected during one or more shave sessions of a user shaving with the shaving device; determine shave session data defining the one or more shave sessions based on the sensor data; input the shave session data and a threshold into the model to output a user-specific shave score, wherein generation of the user-specific shave score comprises comparing the shave session data to the threshold to determine a deviation from the threshold; and generate an output based on the user-specific shave score.

[0113] An aspect includes a non-transitory computer-readable medium storing computing instructions that, when executed by one or more processors, cause the one or more processors to: collect sensor data from one or more sensors of a shaving device having a blade, the sensor data collected during one or more shave sessions of a user shaving with the shaving device; determine shave session data defining the one or more shave sessions based on the sensor data; input the shave session data and a threshold into a model executing on the one or more processors to output a user-specific shave score, wherein generation of the user-specific shave score comprises comparing the shave session data to the threshold to determine a deviation from the threshold; and generate an output based on the user-specific shave score.

[0114] Additional aspects of the disclosure

[0115] The following additional aspects are provided as examples in accordance with the disclosure herein and are not intended to limit the scope of the disclosure.

[0116] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output includes an electronic communication sent to a computing device that provides information to the user of a shipment of a new blade.

[0117] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: determining a baseline travel behavior of the user based on the initial data set; and determining a shaving session deviation by comparing the baseline travel behavior and the shaving session data, wherein the user-specific shaving score is further based on the shaving session deviation.

[0118] Another aspect includes the sensor-based method of any of the preceding aspects, further comprising: storing the user-specific shaving score in a memory communicatively coupled to the one or more processors; and tracking the user-specific shaving score by comparing the user-specific shaving score to one or more of: (a) other user-specific shaving scores generated for the user; (b) shaving scores generated for other users.

[0119] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the output includes a virtual reward based on the user-specific shaving score.

[0120] Another aspect includes the sensor-based method of any of the preceding aspects, wherein the one or more visual indicia include one or more light-emitting diodes (LEDs) on the shaving device.

[0121] Additional Considerations

[0122] While the present disclosure sets forth specific embodiments of various implementations, it is understood that the scope of the present description is defined by the claims set forth at the end of this patent and equivalents thereof. The specific embodiments are to be considered in a demonstrative sense rather than a restrictive sense, and the scope of the present description is defined by the claims set forth at the end of this patent and equivalents thereof. The specific embodiments are illustrative of one or more ways to make and use the present implementations.

[0123] The following additional considerations apply to the foregoing discussion. Throughout this specification, plural instances can implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations can be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations can be implemented as a combined structure or component. Similarly, structures and functionality presented as a single component can be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.

[0124] Additionally, certain embodiments are described herein as including logic or a number of routines, subroutines, applications, or instructions. These can constitute either software (e.g., code embodied on a machine-readable medium or in a transmission signal) or hardware. In hardware, the routines, etc., are tangible units capable of performing certain operations and can be configured or arranged in a certain manner. In example embodiments, one or more computer systems (e.g., a standalone, client or server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) can be configured by software (e.g., an application or application portion) as a hardware module that operates to perform certain operations as described herein.

[0125] The various operations of example methods described herein can be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute processor-implemented modules that operate to perform one or more operations or functions. The modules referred to herein may, in some example embodiments, comprise processor-implemented modules.

[0126] Similarly, the methods or routines described herein can be at least partially processor- implemented. For example, at least some of the operations of a method can be performed by one or more processors or processor-implemented hardware modules. The performance of certain of the operations can be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the processor or processors can be located in a single location (e.g., within a home environment, an office environment, or as a server farm), while in other embodiments the processors can be distributed

[0127] The performance of certain of the operations can be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the one or more processors or processor- implemented modules can be located in a single geographic location (e.g., within a home environment, an office environment, or a server farm). In other embodiments, the one or more processors or processor-implemented modules can be distributed across multiple geographic locations.

[0128] This DETAILED DESCRIPTION is understood to be only illustrative, and not descriptive of every possible embodiment, as such description would be impractical and unnecessary. Alternative embodiments will become apparent to those of ordinary skills in the art, using the disclosure presented herein or known in the art, or by experimentation.

[0129] Those of ordinary skill in the art will realize and understand that numerous modifications, changes, substitutions, and alterations can be made to the embodiments described herein without departing from the scope of the application, and that these modifications, changes, substitutions, and alterations are intended to fall within the scope of the inventive concept.

[0130] The patent claims at the end of this document are not intended to be interpreted, in light of 35 U.S.C. § 112(f), unless explicit reference is made to conventional means-plus-function language, such as "a means for" or "a step for" language found in the claims. The systems and methods described herein relate to improvements in computer functionality, and improvements in the functioning of conventional computers.

[0131] The dimensions and values disclosed herein are not to be understood as being strictly limited to the exact numerical values recited. Instead, unless otherwise specified, each such dimension is intended to mean both the recited value and a functionally equivalent range surrounding that value. For example, a dimension disclosed as "40 mm" is intended to mean "about 40 mm."

[0132] Every document cited herein, including any cross referenced or related patent or application and any patent application or patent to which this application claims priority or benefit thereof, is hereby incorporated herein by reference in its entirety unless expressly excluded or otherwise limited. The citation of any document is not an admission that it is prior art with respect to any invention disclosed herein or that it alone, or along with any other other prior art documents, teaches, suggests or discloses any such invention. Further, to the extent that any meaning or definition of a term in this document conflicts with any meaning or definition of the same term in a document incorporated by reference, the meaning or definition assigned to that term in this document shall control. In addition, as used in this application, the singular forms "a," "an," and "the" include plural reference unless the context clearly dictates otherwise.

[0133] While particular embodiments of the present application have been illustrated and described, it would be obvious to those skilled in the art that various other changes and modifications can be made without departing from the spirit and scope of the application. It is therefore intended to cover in the appended claims all such changes and modifications that are within the scope of this application.

Claims

1. A sensor-based method for analyzing shaving performance, comprising: Sensor data is collected by one or more processors from one or more sensors of a shaving device (150) having blades (150i), the sensor data being collected during one or more shaving strokes by a user using the shaving device; Based on the sensor data, determine the shaving stroke data that defines the one or more shaving strokes; The shaving stroke data and the threshold are input into a model (108) executed on one or more processors to output a user-specific shaving score, wherein the generation of the user-specific shaving score includes comparing the shaving stroke data with the threshold to determine a deviation from the threshold; and Output is generated based on the user-specific shaving score.

2. The sensor-based method according to claim 1, wherein the shaving stroke data includes one or more of the following: (a) Stroke pressure, the count of the one or more shaving strokes performed with the blade, and the frequency of the one or more shaving strokes performed with the blade; (b) Stroke pressure, count of the one or more shaving strokes performed with the blade, frequency of the one or more shaving strokes performed with the blade, speed of the one or more shaving strokes performed with the blade, number of shaving periods during the blade's blade life, acceleration of the one or more shaving strokes performed with the blade, direction of the one or more strokes performed with the blade, stroke length, blade pivot angle, rinse count, rinse duration, water temperature, and razor temperature; and / or (c) Stroke duration, stroke position, shave duration, duration between shaves and duration between strokes.

3. The sensor-based method according to any one or more of claims 1 or 2 above, wherein the user's threshold includes one or more of the following: a general threshold, a user-selected threshold, and a unique threshold for the user.

4. The sensor-based method according to any one or more of claims 1 to 3, wherein the threshold of the user is determined by analyzing user input or device data, the user input or device data including one or more of the following: user rating of shaving events reported by the user, blade type, blade holder type, shaving accessory type, style type, style matching result, hair type, and duration between shaves.

5. The sensor-based method according to any one or more of claims 1 to 4, wherein the user-specific shaving score is based on one or more of the following: the number of one or more user shaving strokes detected to have a value higher or lower than the user's threshold, the magnitude of one or more user shaving strokes detected to have a value higher or lower than the threshold of the user, and the duration of one or more user shaving strokes detected to have a value higher or lower than the user's threshold.

6. The sensor-based method according to any one or more of claims 1 to 5, wherein the output includes one or more of the following: (a) one or more visual markers; and / or (b) The user-specific shave fraction is presented via a graphical user interface (GUI) on the display screen.

7. The sensor-based method according to any one or more of claims 1 to 6 further comprises: Collect user-specific data, which includes at least one of the following: (a) one or more user inputs, or (b) an initial dataset defining one or more initial shaving strokes for the user; and The model is configured by adjusting or updating the model using the user's user-specific data. The output of the user-specific shaving score is adjusted based on the user's user-specific data.

8. The sensor-based method according to any one or more of claims 1 to 7, further comprising: The one or more processors generate user-specific electronic recommendations based on the user-specific shave score.

9. The sensor-based method according to any one or more of claims 1 to 8, further comprising: The user-specific electronic recommendations mentioned above include product recommendations for manufactured products.

10. The sensor-based method according to any one or more of claims 1 to 9, further comprising: The shaving device is communicatively coupled to a user computing device with a display screen. Furthermore, the sensor-based method further includes the one or more processors displaying the user-specific shaving score on the display screen of the user's computing device.

11. The sensor-based method according to any one or more of claims 1 to 10, wherein the output includes an indication of the expected blade life of the blade based on the user-specific shaving fraction.

12. The sensor-based method of claim 11, wherein the indication includes an indication to update or replace the blade based on the expected blade life.

13. The sensor-based method of claim 11, wherein the output includes initiating a replacement blade delivery to the user based on the indication.

14. The sensor-based method according to any one or more of claims 1 to 13, further comprising: When a high-load shaving stroke is detected in one or more of the shaving strokes, one or more of the following are activated: the motor, visual indicator, tactile indicator, or auditory indicator of the shaving device. The high-load shaving stroke includes a pressure value that is higher or lower than a threshold deviation from the threshold.

15. The sensor-based method according to any one or more of claims 1 to 14, The model mentioned therein is an artificial intelligence model, and The sensor-based method further includes: The model is trained by the one or more processors using user-specific pressure data and corresponding shaving stroke data determined during one or more training shaving strokes of the respective user while multiple respective users are shaving with their respective shaving devices. The model is trained to output the user-specific shave score.

Images