Oral care device recommendation system

Abstract

A computer-implemented recommendation system is used to recommend types of oral care accessories to be used with oral care devices. The recommendations consider information about the user's oral geometry and, preferably, user behavior information about how a particular user performs their oral care using the oral care device. The recommendations are based on modeling the mechanical interactions between one or more oral care accessories from a set of accessories and the user's oral geometry when the user performs an oral care routine. From the modeling, a cleanliness metric is determined, representing the effectiveness of the oral care routine when using the one or more oral care accessories.

Description

Technical Field

[0001] This invention relates to oral care devices, such as toothbrushes, brushing connectors, and oral rinsing systems, and particularly to a system for recommending oral care products or accessory types, such as brush heads or brushing connectors of the bow type. Background Technology

[0002] As is well known, the cleaning effectiveness of oral hygiene devices largely depends on an individual's cleaning technique and their dental arch geometry.

[0003] Different users may require different oral care accessories to achieve optimal performance. Such accessories may include brush heads, brush heads with integrated nozzles, multi-surface brushes, brushing interfaces, irrigator nozzles, brush heads with light sources / LEDs for tissue processing during brushing, etc.

[0004] Therefore, manual and electric toothbrush heads come in many different shapes and hardness / stiffness levels. Furthermore, mouthpieces in different sizes (arch width, length) or clamping levels are available to cover a wider range of teeth and jaw types for different groups. Clamping limits how much lateral and vertical force is applied to the teeth when they are inserted into the occlusal disc of the mouthpiece.

[0005] However, users are often unaware of which oral care accessories, such as which brush head design or which toothbrush design, result in the best possible personal cleaning performance and user experience.

[0006] WO 2019 / 215447 discloses a smart toothbrush system that uses a real 3D representation of a user's teeth and displays brushing data on that 3D representation. The display provides feedback to the user to improve their brushing technique.

[0007] US 2012 / 171657 discloses another toothbrush that has a display for showing the user's personal care plan. Summary of the Invention

[0008] This invention is defined by the claims.

[0009] According to an example of one aspect of the invention, a computer-implemented recommendation system is provided for recommending types of oral care accessories to be used as part of an oral care device, the system comprising:

[0010] Inputs are used to receive input data including information about the oral geometry of the user to whom the attachment is to be recommended; and

[0011] Processor, the processor being adapted to:

[0012] Model the interaction between one or more oral care accessories from a set of oral care accessories and the user's oral geometry;

[0013] The modeling determines a cleaning metric, which represents the effectiveness of the oral care routine when using the one or more oral care accessories; and

[0014] Based on the cleanliness metrics, recommendations for suitable oral care accessories to be used with oral care devices are provided from a set of different oral care accessories.

[0015] This set of oral care accessories may include readily available, commercially available products, or it may include a design created from a set of modular building blocks, which can then be manufactured.

[0016] This system provides users with recommendations on the types of attachments that can be used as part of an oral care device, based at least on the user's oral cavity geometry. This ensures improved oral care outcomes by guaranteeing the selection of the most suitable attachment for each individual user.

[0017] Oral geometry can relate to all of a user's teeth, but it can also relate to only a subset of teeth. For example, it may involve a selected area of ​​the jaw / dental arch or only a critical tooth geometry in which poor cleaning is typically observed.

[0018] The system also includes input data for receiving user behavior information, including information about how a particular user uses oral care devices to perform their oral care, and the processor is adapted to model the interaction between the one or more oral care accessories and the user's oral geometry as the user performs an oral care routine in the manner described. This is of interest when the cleaning routine depends on the user's own technology, such as a toothbrush or oral rinsing system. Recommendations are then made based at least on the user's oral geometry and their oral cleaning characteristics.

[0019] It should be noted that for brushing interface systems, using only oral cavity geometry information may be of interest. Therefore, it is recommended to use interface of specific sizes (e.g., small, medium, large, extra-large) with a certain brushing arch length and width, as well as cluster-to-tooth clamping.

[0020] Oral care accessories include, for example, the head (brush head or dental floss nozzle) of an oral care device (electric toothbrush or oral rinsing system). Therefore, the device has a handle attached to the head.

[0021] It is possible to model the interaction between all oral care accessories in the group and the user's oral geometry, but alternatively, it is only necessary to model a subset of oral care accessories to find suitable recommendations.

[0022] Cleanliness metrics are derived, for example, by modeling the contact stresses between oral cleaning attachments and teeth. These contact stresses can be used to evaluate cleaning performance and the risk of damaging teeth or gums.

[0023] Other cleaning metrics can be used, such as frictional energy or power density, or the time it takes for a certain stress to be applied to the tooth or biofilm surface. For example, recommendations can be given to the user based on cleaning effectiveness assessed based on metrics related to the removal of biofilm, plaque, or other substances to be removed from the teeth. For example, the applied contact shear stress or force generated by the movement of the bristles or the fluid impacting the surface can be used as part of a sensor system to generate appropriate recommendations (and provide other recommendations, as described below).

[0024] This recommendation can be based on modeling of shear energy (sliding work) or frictional power. For example, pressure thresholds can be used to distinguish clean and uncleaned areas, where thresholds can cover pressure ranges such as <1 kPa, 1 kPa–10 kPa, 10 kPa–30 kPa, 30 kPa–50 kPa, and >50 kPa, depending on the material being removed. This information can be converted into an area fraction or percentage of cleaned teeth, and then further used to provide recommendations and / or other recommendations and feedback to the user. For example, a personalized video animation of a simulated cleaning process can be sent to the user's app, providing indirect feedback or information about the effectiveness of the recommended or currently used brush head, and how cleaning effectiveness will change if different brushing techniques are used (hereinafter referred to as "behavioral information"). It can also show the effects of wear on oral attachments (brush heads) over time.

[0025] The system may include inputs for receiving input data including the user's medical information. This medical information may not be specific to the use of the device and may include age, gender, and electronic medical record (EMR) information, such as information about pregnancy or other comorbidities related to oral health. The EMR may access one or more databases, such as those of hospitals, insurance providers, dental providers, or government databases, through a communication system. For example, oral health indices may exist, such as indices related to plaque levels, staining, gum condition, and halitosis. This information may include, for example, plaque maps (overlaying oral geometry information) or staining index images, or other health-related information, such as pregnancy, gingivitis, etc.

[0026] The system may include input for receiving input data including operational information about the oral care device. For an electric toothbrush, this operational information may include, for example, the operating frequency, the amplitude of the brush head movement, the frequency of the brush head movement, or the duration of the applied frequency / movement. For a dental floss device, the operational information may include, for example, the frequency of the fluid jet pulses, the velocity of the fluid jet pulses, the fluid flow rate, and the fluid pressure. For an oral care device that includes additional radio frequency (RF) generator circuitry, the operational information may include radio frequency in the range of 100 kHz to 300 GHz. For a brushing interface, the information may include the operating frequency or movement pattern of the brushing arch or individual segments of the brushing arch.

[0027] Operational information may also include information about the different device settings used. For example, a user can select a specific cleaning mode on the device (deep cleaning, contrast, sensitive gums). This will change the characteristics of the device, such as through different brushing motions generated by the device, like different sweep amplitudes or different actuation motions of the drive system that oscillates with the brush head.

[0028] The system may include input for receiving input data including status information about oral care accessories. This status information pertains to the condition of the oral care accessories, such as being derived from one or more images of the accessories taken during use of the device. Status information for the brush head may pertain to, for example, the brush head geometry (including, for example, the material, geometry, and structure of the bristles), bristle layout, tuft layout, trimming profile, and changes in tuft geometry, such as flaring due to wear. It typically pertains to the condition of the toothbrush head or toothbrush head bristles. For dental floss devices, it may pertain to the primary device function or condition of the floss head or rinsing head or the spray nozzle of the floss head or rinsing head (e.g., nozzle clogging causing an increase in measured fluid pressure within the device).

[0029] The processor can also be adapted to provide recommendations for suitable handles for oral care accessories and / or suitable operating settings for the handles of oral care accessories. Therefore, the system can recommend the most suitable combination of handles, operating settings, and oral care accessories.

[0030] Oral geometry information includes, for example, tooth geometry data derived from 2D or 3D tooth images. This tooth geometry data provides information such as identifying missing teeth and identifying dental implants and their locations.

[0031] The system may include input for receiving at least one input image from an image capture system, and the processor is adapted to process the image to derive oral cavity geometry information required to perform interactive modeling. Therefore, the geometry information may be input to the system from an external source (e.g., an EMR database or from previous dental scans), or it may be generated by the system using image analysis.

[0032] Tooth geometry data may include information such as tooth segmentation or the level of residual plaque and staining. Plaque or staining indices can be overlaid onto digital images or images showing stained plaque and staining on teeth.

[0033] The system may also include, for example, a database of data related to the medical history of the set of oral care accessories and / or users. For instance, if the oral care accessory is a brush head, the database could be the brush head geometry used for different brush heads, along with the material properties and shape of each filament or cluster used. Oral care accessories can then be matched with users based on their geometry and care routines (e.g., brushing characteristics). Therefore, the data pertains to the characteristics of oral care accessories, such as design parameters and material properties.

[0034] The system may also include input for receiving images of currently used oral care accessories, wherein the processor is also adapted to provide recommendations on when to replace the oral care accessories.

[0035] In this way, the system can inform users of the type of oral care attachments they are using and when to replace worn attachments.

[0036] The processor can also be adapted to provide suggestions based on user behavior. Therefore, the system can act as a learning aid to improve oral care routines, such as the user's brushing technique, to achieve optimal results.

[0037] In one example, oral care accessories include, for instance, a brush head, and oral care devices include an electric toothbrush with a handle to which the brush head is attached.

[0038] In this context, user behavior information may include one or more of the following:

[0039] Brushing power,

[0040] Brushing angle;

[0041] Brushing speed and motion patterns; and

[0042] The location to be scrubbed and the time spent on each location.

[0043] This information can be obtained using a sensor system that monitors the direction and magnitude of motion (e.g., using an accelerometer device) and force (e.g., using a pressure or force sensor).

[0044] In another example, the oral care accessory includes a brushing bow, and the oral care device includes an interface toothbrush having a handle to which the brushing bow is attached.

[0045] The present invention also provides an oral care system, the oral care system comprising:

[0046] A handle having a drive mechanism and a connection interface for connecting an oral care accessory to the handle;

[0047] Recommendation systems as defined above; and

[0048] At least one oral care accessory recommended by the recommendation system.

[0049] Recommendation systems can be implemented on devices that are remote from the subject, such as mobile phones, tablets, or cloud-based servers.

[0050] Oral care accessories or handles of oral care devices may include, for example, a sensor system for providing sensor information from which behavioral information can be derived.

[0051] The sensor system includes, for example, one or more of the following:

[0052] Force measurement system;

[0053] Toothbrushing angle measurement system;

[0054] Motion detection system;

[0055] Position measurement system.

[0056] One or more parts of the sensor system can be separated from the oral care device, such as motion detection using optical motion tracking.

[0057] The present invention also provides a computer-implemented method for recommending types of oral care accessories to be used with oral care devices, the method comprising:

[0058] Receive input data including information about the oral geometry of the user to whom the attachments are to be recommended;

[0059] Receive input data including user behavior information about how the specific user uses the oral care device to perform their oral care;

[0060] When a user performs an oral care routine in the manner described, the interaction between one or more oral care attachments from a set of oral care attachments (or their constituent parts) and the user's oral geometry is modeled.

[0061] The modeling determines a cleanliness metric, which represents the effectiveness of an oral care routine when using the one or more oral care accessories; and

[0062] Based on the cleanliness metrics, recommendations for suitable oral care accessories for use with oral care devices are provided from a set of different oral care accessories.

[0063] This method can be implemented through a computer program running on the device itself or a remote device, or through a cloud-based platform that can connect to other systems, such as digital manufacturing systems, hospital suites, or insurance and supplier platforms.

[0064] These and other aspects of the invention will become apparent from the embodiments described below. Attached Figure Description

[0065] To better understand the invention and to more clearly illustrate how to implement it, reference will now be made to the accompanying drawings by way of example only, wherein:

[0066] Figure 1 An oral care system was shown;

[0067] Figure 2 shows an example of the contact stress distribution of the premolar geometry, which was calculated as part of simulation results of four different toothbrush designs relative to a user's tooth model.

[0068] Figure 3 Two different tooth geometries are shown, divided into regions of interest for cleaning;

[0069] Figure 4 The diagram shows 2D tooth surface lines and gingival lines that can form part of the geometric information.

[0070] Figure 5 The diagram shows a 2D tooth surface line representing the innermost extent of the tooth, which can again be used as part of the geometry information;

[0071] Figure 6 The landmark of a single tooth is shown; it can also form part of the geometric information.

[0072] Figure 7 The brush head and a set of brush heads with different designs are shown;

[0073] Figure 8a Show the roll angle, Figure 8b Show the pitch angle, Figure 8c Show the deflection angle;

[0074] Figure 9This demonstrates how a smartphone app can use a reference database based on interaction modeling to recommend oral care accessories or handles, or both; and

[0075] Figure 10 A computer-implemented method for recommending types of oral care accessories to be used with oral care devices is shown. Detailed Implementation

[0076] The invention will be described with reference to the accompanying drawings.

[0077] It should be understood that while the detailed description and specific examples indicate exemplary embodiments of the apparatus, system, and method, they are for illustrative purposes only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, system, and method of the present invention will become more readily apparent from the following description, the appended claims, and the accompanying drawings. It should be understood that the drawings are merely schematic and not drawn to scale. It should also be understood that the same reference numerals are used in all the drawings to denote the same or similar parts.

[0078] This invention provides a computer-implemented recommendation system for recommending types of oral care accessories to be used in conjunction with oral care devices. The recommendations take into account at least information about the user's oral cavity geometry, and preferably also user behavior information about how a particular user uses the oral care device to perform their oral care.

[0079] For example, oral cavity geometry information can be obtained through optical intraoral scanning or through CT, MRI, etc. When user behavior information is also used, this information can be obtained through optical measurements using multiple cameras or by using a sensor toothbrush, which, for example, uses embedded force sensors and accelerometers to measure force and acceleration.

[0080] Figure 1 An oral care system is shown, which includes an oral care device 10 and an oral care accessory 12 for use with the oral care device.

[0081] The invention will be described in detail with reference to oral care systems in the form of electric toothbrushes and recommended systems. Therefore, in this case, the oral care device 10 includes an oral care accessory 12 in the form of an electric toothbrush handle and a brush head. However, any other attachable oral care accessory may be considered, such as a rinsing nozzle, a brush head with an integrated nozzle or light source (or any other sensor or actuator), or a (partial) cleaning interface (brush bow).

[0082] The system also features a computer-implemented recommendation system for recommending types of oral care accessories, such as brush heads, for use by specific users.

[0083] Figure 1The recommendation system is implemented using various components. In the example shown, processing is performed in multiple locations, including a local processor 20 and a remote external processor 23. The local processor 20 is the processor of the mobile phone 22, on which the app is loaded to implement the recommendation system. The external processor can be implemented on any other remote device, such as a tablet or workstation, or as a data (analysis) engine in the cloud.

[0084] However, the described processing can be implemented in different ways, with different processing divisions between the oral care device itself, the user's local device (e.g., a mobile phone), and an external processor. The oral care device may be used solely to collect sensor data and process that data elsewhere, or alternatively, some sensor data processing may be performed at the oral care device itself.

[0085] Based on Figure 1 The architecture shown is used to describe an example, and is for illustrative purposes only.

[0086] The mobile phone receives usage information from the oral care device, specifically the toothbrush handle 10 in this example. This usage information pertains to user behavior information regarding how a particular user uses the oral care device to perform their oral care, i.e., how they brush their teeth. This applies to the toothbrush example, but may not be necessary for an interface implementation performing hands-free cleaning. The usage information also enables the determination of the brush head's position and / or orientation measurements relative to the teeth. For an oral rinsing system, the user behavior information may pertain to the path followed by the attachment, the timing of the attachment at different locations along the path, and the angle of the attachment at different locations along the path over time.

[0087] This information is obtained, for example, through a pressure or force sensor 11 mounted in the brush head 12 (or handle) and motion and angle sensors 24 such as a triaxial accelerometer and / or a triaxial gyroscope. In this example, the motion sensors are in the handle, but may also be located within the brush head (or other connectable cleaning or treatment unit).

[0088] A pressure sensor can also be located in the handle, and the connection between the handle and the brush head provides usage information related to the pressure applied to the teeth or gums.

[0089] As a minimum, the normal force vector (i.e., the reaction force component of the platen perpendicular to the brush head) is measured by a pressure or force sensor. The interaction between the brush head and the tooth or gingival surface can be modeled when combined with (i) information related to brushing dynamics (brush head amplitude and velocity, brush head movement / velocity along the dental arch), (ii) the position and / or orientation of the brush head at that particular (contact) time, and (iii) its position relative to the user's oral cavity geometry.

[0090] User behavior information derived from sensor information includes, for example, one or more of the following:

[0091] Brushing power,

[0092] Brushing angle;

[0093] Brushing speed; and

[0094] Position and / or motion measurements.

[0095] Position and motion can be obtained through tracking and measurement systems, such as optical measurement systems or inertial measurement units (IMUs).

[0096] The sensor system may also, or alternatively, have an external optical measurement system. For example, motion or position tracking can be achieved using reflective markers attached to the oral care device and the user's face, and captured using a camera, or derived from accelerometer, tooth geometry, and position data.

[0097] As a minimum, behavioral information can indicate the level of force a user applies during their oral care process.

[0098] A short-range transmitter 26 (e.g., Bluetooth or Zigbee) transmits behavioral information (BI) to a mobile phone via a short-range receiver (not shown), where it is used as an input to the processor 20.

[0099] The processor 20 has another input for receiving oral cavity geometry information about the user to whom the attachment is to be recommended.

[0100] In one example, the oral cavity geometry information is 3D scan data 30 received from an external database, which is populated by the dentist, for example, when preparing the oral scan.

[0101] In other examples, oral geometry information is extracted from 2D images. This can be stored again in a remote database, but it can also be generated by a mobile phone camera or by a dedicated 3D camera mounted on a rod inserted into the oral cavity and activated to capture 3D images. Oral scan data can be used, for example, as input to finite element or computer vision fitting algorithms to determine cleaning effectiveness.

[0102] This system can be used to recommend pre-existing oral care accessory designs. In this case, a database 32 is also provided, containing data related to a set of oral care accessories, components, and their material properties. For the example of a toothbrush head, the database stores information related to the geometry of different toothbrush heads, such as dozens of different toothbrush head designs from different manufacturers. The brush head is then matched to the user based on their geometry and care routines, such as brushing characteristics.

[0103] As an optional additional feature, the system can define ideal oral care accessories, such as a model of a brush head design based on selected component blocks (a group of components that, when assembled, form a semi-custom brush head design), thus ultimately enabling the manufacture of a user-specific design. This option is discussed further below.

[0104] In order to make recommendations, the external processor 23 performs a cleaning efficacy simulation based on the aforementioned information source.

[0105] Specifically, the interaction between oral care accessories and the user's oral geometry is modeled based on how the user performs their oral care routine. From this modeling, a cleanliness metric is derived, representing the effectiveness of the oral care routine when using one or more of the oral care accessories. Recommendations for suitable oral care accessories to use are then provided from a set of different accessories.

[0106] In this example, external processor 23 processes geometric and user behavior information to recommend suitable oral care attachments from a set of predefined different oral care attachments. Optional additional features exist for designing ideal oral care attachments through a design optimization process using predetermined building blocks and assembly groups that, when assembled, form a brush head. This optimal personalized design can then be offered to a digital manufacturing workshop 35 or shared with a connected platform or system 36 of dental professionals, insurance companies, or oral care providers, for example, to gain approval or to enable strategic negotiation of pre-ordered models, allowing them to track progress in oral health or oral care adherence while using new brush heads.

[0107] Animations of optimal cleaning techniques can also be generated, for example, by an external processor 23, for display to the user on a mobile phone 22. These simulations can include user feedback regarding the expected cleaning performance of the brush head on the geometry of the user's mouth.

[0108] Figure 1 The processor 20 is also shown to have a third input for receiving an image 34 of the currently used oral care attachment. The processor can then be further adapted to provide recommendations on when to replace the oral care attachment. This image can be taken periodically using a mobile phone, for example, weekly or bi-weekly. In this way, the system can inform the user of the type of oral care attachment being used and when worn attachments should be replaced.

[0109] In addition to recommending suitable accessories (such as brush heads), the system can analyze brushing performance and provide suggestions based on user behavior (such as guidance when needed). Therefore, the system can be used as a learning aid to improve oral care routines, such as brushing techniques, for optimal results.

[0110] Improved brushing behavior can be achieved by recommending reduced brushing force, altered brushing angle (increased or decreased), extended brushing time, or personalized device firmware updates. Brushing behavior recommendations are provided by mapping actual brushing behavior and ideal brushing behavior (force, angle, speed, time per tooth position) onto digital personal dentition information, performing sensitivity analysis on key brushing factors (i.e., computational modeling and simulation of interactions with different factors and settings), and providing users with feedback on how this affects the predicted cleaning performance of a selected brush head.

[0111] Brush head designs optimized for specific populations (e.g., the Asian market) may exist. Information collected by the system can be used to provide additional recommendations, such as suggestions for the best-fitting interface, and recommendations for the most suitable whitening treatment plan for gingival line protection (masking) or localized light activation through contour scanning.

[0112] Processing geometric and behavioral information, for example, involves determining the contact stress on the teeth, thereby enabling the assessment of cleaning performance and the risk of damage to the teeth or gums.

[0113] For the toothbrush example, a bristle contact stress model can be used for this purpose. This provides a model of the interaction between the bristles and the teeth. Equivalent interaction models can be used for other types of oral care devices.

[0114] As mentioned above, recommendations can be based on modeling how users combine general and / or specific characteristics of their teeth and oral cavity to perform their cleaning routines (e.g., brushing, cleaning, or flossing). The outcome of an oral care routine can be optimized by changing certain parameters, such as brush head type, trimming profile, brushing speed, force, brushing angle, and time spent on each tooth element.

[0115] The software algorithms and models implemented by processor 23 are used to evaluate the cleaning effectiveness of the brush head and enable performance prediction simulation.

[0116] This recommendation is based, for example, on a bristle reach and contact stress model.

[0117] The inputs to a recommender system include:

[0118] (i) A digital geometric model (CAD) of the subject's dentition or an oral scan dataset. This can be obtained, for example, through an intraoral scan or by first creating a model of the dentition and then creating a digital model from the scan or model, or from images / scans derived from sensor-based feedback. The scanning and / or modeling of the dentition only needs to be performed once and can be done in a dentist's office or at a brush head resale point. This can also be done at home using dedicated equipment or via a smartphone extension or via a built-in camera system in the brush head.

[0119] (ii) User-specific brush processing data, such as orientation, force, and movement. This data may be generated by appropriately sensing brush heads and / or brush handles (potentially in conjunction with external hardware, such as a camera or motion tracking system).

[0120] (iii) Data related to the oral cleaning device: geometry, design constraints, frequency, amplitude, material properties, etc.

[0121] The system then uses a computational model with specific object inputs to calculate cleaning effectiveness. This model can then be adapted to optimize effectiveness. Optimizable variables can be related to the brush head or the user's handling technique, or both. The model considers relevant physical quantities associated with cleaning teeth through brushing, such as bristle flexure, contact and friction between bristles, and between bristles and teeth and gums.

[0122] An example of this model is the finite element model, a widely used method for numerically solving partial differential equations. In this model, bristles can be described using beams or solid elements. The bristles are attached to virtual platforms on the relevant sides, which can be modeled as deformable solid or rigid bodies. The system is then brought into contact with a virtual oral cavity geometry consisting of at least teeth and gums (gingival tissue). By using a suitable contact algorithm, the interactions between the bristles themselves and between the bristles and the dentition can be described. The contact algorithm will provide a contact force vector for each pair of discrete blocks of the contacting model.

[0123] The oral cavity geometry can be described using a deformable solid or rigid element employing finite element methods. The behavior of the bristles is then determined by a constitutive model that correlates strain with the stresses of the various materials involved, based on the prescribed motion of the platen, and by contact algorithms and their parameter values ​​(e.g., the coefficient of friction).

[0124] Instead of specifying the movement of the tabletop, its position and orientation can also be modeled as a function of the applied user force and other individual user parameters (such as scrubbing speed and scrubbing handle angle).

[0125] Various information can be obtained from such models, such as the shear stress applied to the tooth surface by the movement of the bristles, the dynamic movement and final reach of the bristles, and the amount of bristle opening caused by the applied user force.

[0126] Besides the finite element method, other methods or combinations thereof can be used to solve the mathematical equations describing the physical quantities involved in oral cleaning, such as the finite volume method, smoothed particle hydrodynamics, and the discrete element method. Depending on the relevant physical quantities to be described, combinations of methods can be used, for example, to describe fluid-structure interactions.

[0127] Cleaning effectiveness is evaluated based on measures related to the removal of biofilm, plaque, or other substances from teeth. For example, the (maximum) applied contact shear stress or force generated by the movement of the brush bristles can be determined.

[0128] Another example of a metric could be the shear energy or frictional power applied at the location where a single bristle (or a portion of it) has been placed on the tooth surface. Alternatively, it could be the total shear energy applied by all (multiple portions) of the bristles in contact with a specific location on the tooth surface. In another example, a pressure threshold could be used to distinguish between clean and uncleaned areas, where the threshold covers pressure ranges such as <1 kPa, 1 kPa–10 kPa, 10 kPa–30 kPa, 30 kPa–50 kPa, and >50 kPa, depending on the material to be removed.

[0129] Figure 2 shows four examples of contact stress distribution for premolar geometry, which was calculated as part of simulation results of four different toothbrush designs relative to a user's tooth model.

[0130] Figure 2A The results of two toothbrush designs are shown. Figure 2B The results for two other toothbrush designs are shown. The dataset in Figure 2 is an example of a so-called heatmap (or contour map) showing the distribution of contact stress on the tooth surface. They are results of a virtual brushing process, in which a finite element model of the brush head moves along a virtual tooth row using a certain orientation and force load. By solving the mathematical equations describing the physical quantities, the contact stress occurring between the bristles and the tooth surface over time can be discovered.

[0131] When the contact stress value is greater than zero, contact has occurred between the bristles and the tooth surface. By tracking these locations, the reach of the brush head can be determined. Reach is the first requirement for cleaning. Higher values ​​indicate stronger contact. Ideally, for plaque removal, the stress value should be within a certain range; too low and the plaque layer is unaffected, too high and the plaque layer is disturbed or removed, but the tooth surface may also be damaged. Furthermore, excessively high contact stress values ​​at the gum line are an uncomfortable measurement.

[0132] The contact stress threshold can be set, for example, as a recommended limit that the brush head should not exceed. A minimum tangential contact stress threshold (or other metrics, such as frictional energy, frictional power density, or pressure applied over a certain period of time) can also be set to ensure plaque removal and thus determine cleaning effectiveness.

[0133] The output of this system may include:

[0134] (i) Personalized direction (angle / force / movement / position) used during brushing to improve cleaning effectiveness. Therefore, the system can provide feedback on how to improve cleaning.

[0135] (ii) Recommending the best off-the-shelf brush head based on the current processing profile. The system can select a specific cleaning head for a particular tooth geometry (molars, premolars, incisors) or tooth region (e.g., interdental, gingival, or facial side), or for a specific dentition geometry (e.g., with missing teeth, curved teeth);

[0136] (iii) Recommend the best off-the-shelf brush head with an improved recommended processing mode.

[0137] (iv) As an optional additional feature of the system (besides allowing selection from an off-the-shelf set of existing brush heads), personalized semi-custom brush head designs can originate from a predefined set of buildables that, when assembled by a user or software algorithm (based on oral geometry), form a full brush head to which a recommended interactive simulation is performed. This includes, for example, defining optimized trim profiles (i.e., bristle zone geometry) for the personalized brush head, as well as optimizing brush head geometry, tuft layout, materials for digital fabrication, and building blocks / sets.

[0138] (v) Determine when parts of oral hygiene appliances need to be replaced.

[0139] (vi) Select a specific handle for the head (i.e., the main tool of the oral care device).

[0140] Figure 3 The diagram shows the geometry of the molars in the left column and the geometry of the premolars in the right column, which are depicted in segments according to the Rustogi classification, and are used to evaluate the plaque removal efficacy of a toothbrush in different tooth regions / areas.

[0141] Region-based segmentation is based on a synthetic tooth model generated from the input data. Segments are used for reach and plaque removal scoring, enabling the quantification of cleaning efficacy across separated regions. Different brush heads are then compared to a model of the user's teeth based on efficacy at the gingival line, cleaning ability between teeth, and total tooth area. The naming conventions for these regions are shown. The interdental regions between two teeth are segments D and F, and the regions at the gingival line are segments A, B, and C. The facial side is divided into regions E, G, H, and I.

[0142] Taking into account factors such as cluster spacing, length, size, angle, material, cluster area size and shape, and trimming contours, more specific or customized brush heads can be designed. When the handle can apply different motion patterns to the attached accessories, the optimal handle or settings can also be recommended for a specific user.

[0143] In one example, external processor 23 implements a computational model to determine at least one oral care cleaning optimization, including simulations of the interaction between a synthetic version of an oral care accessory (cleaning unit) and oral geometry information, specifically digital geometry data of teeth and / or digital geometry data of the mouth (which forms part of the oral geometry information). The external processor can also perform simulations of the interaction between synthetic versions of multiple different oral care accessories and this digital geometry data. Thus, the synthetic or virtual form of the oral care accessory interacts with a user's teeth and / or oral cavity simulation to determine oral care cleaning optimizations, which may involve multiple simulations of components from different oral care accessories or different building blocks.

[0144] These simulations of the interaction between synthetic versions of one or more oral care accessories and digital geometry data of teeth and / or mouth can be based on one or more of the following:

[0145] The user's confirmed user-specific behavioral information;

[0146] Status information regarding the functional performance of oral care accessories;

[0147] Operational information for oral care accessories (frequency, amplitude, etc.).

[0148] In this way, modeling algorithms such as those implemented by the external processor 23 can take into account how users actually clean their teeth.

[0149] Simulation can provide the determination of at least one metric used as a performance indicator for oral care accessories to indicate or determine oral care cleaning optimization. Therefore, one or more cleaning metrics are used to determine oral care cleaning optimization.

[0150] This metric can be calculated based on a modeling of the synthesized toothbrush (or oral irrigator or dental floss device or a combination of toothbrush and dental floss devices, or other oral hygiene devices) with a synthetic model of the teeth, dentition, and / or mouth, which is a representation of the user's teeth, dentition, and mouth. Such modeling can be used to determine different metrics for different oral care accessories used by the user in different ways, which can illustrate how the user actually cleans their teeth (i.e., how they previously cleaned their teeth), or how they might clean their teeth.

[0151] Therefore, metrics calculated in this way can be used to select the best oral care attachments for users, choose the best way to clean their teeth, select combinations of components to form an ideal cleaning system for the user, and provide recommendations on how they can improve their dental hygiene. This allows for optimization tailored to specific users, involving which oral care attachments and which oral cleaning devices to use, and how users can better improve their oral care routines.

[0152] As mentioned above, modeling can be used to generate designs for oral care attachments that are ideally suited to the user. In other words, optimized digital designs can be generated through computational simulations of the interaction between the modeled oral care attachment and the modeled teeth and / or mouth.

[0153] The user's oral cavity geometry information and / or the user's oral cavity geometry data may include one or more of the following:

[0154] Different tooth sizes;

[0155] Different tooth shapes;

[0156] Tooth arch curvature;

[0157] Mouth size;

[0158] The shape of the mouth;

[0159] Different tooth orientations;

[0160] Orientation of one or more implants;

[0161] Are there teeth in a specific location in the oral cavity?

[0162] Whether there are implants in specific locations in the oral cavity;

[0163] The appearance and geometry of the gingival line (width, thickness, and pocket geometry of the gums).

[0164] This geometric data of teeth and / or mouth is derived, for example, from one or more images of the user's teeth and / or mouth, and / or from information provided by a dental practitioner, and / or from data acquired during at least one oral care cleaning procedure of the user.

[0165] Figure 4 The 2D tooth surface line 50 and gingival line 52, which can form part of the geometric data, are shown.

[0166] Figure 5 A 2D tooth surface line (which is the lingual line) representing the innermost extent of tooth 60 is shown, which can again be used as part of the geometry data.

[0167] Figure 6 The diagram shows the landmarks on each tooth, which can also form part of the geometric data. Geometric information can be derived from 3D scans (or 2D tooth images) or from dental impressions, scans, or plaster casts. Geometric data includes, for example, information on tooth segmentation and landmark locations and statistics.

[0168] Figure 7 The top of the brush head is shown. The design is characterized by geometric information (e.g., trimming profile and layout, such as cluster size, length, area, bristle area, and cluster density) and material information (e.g., bending stiffness, Poisson's ratio). The brush head, for example, has a key region 80. A set of three different brush heads is schematically shown at the bottom of the figure. This represents different brush head designs in a simplified schematic form.

[0169] As described above, user behavior information includes, for example, one or more of the following: brushing force, brushing angle, and brushing speed, which are related to the movement along the dental arch.

[0170] Figure 8a The relevant first brushing angle is shown; the roll angle is the angle of rotation about the long axis of the toothbrush handle.

[0171] Figure 8b The relevant second brushing angle is shown; the pitch angle, which is the rotation angle about the first minor axis of the oral care device, causes the brush head to lift or tilt relative to the tooth surface.

[0172] Figure 8c The relevant third brushing angle is shown; the deflection angle, which is the rotation angle about the second minor axis of the oral care device, causes the brush head to rotate or twist in the in-plane on the tooth surface.

[0173] Roll angle describes the angle of rotation about the long axis of the toothbrush handle or brush head, while pitch angle and yaw angle describe rotation about an axis perpendicular to the roll angle.

[0174] As described above, one example of the present invention enables the actual (or alternatively, ideal) brushing behavior (in terms of force, angle, and speed) and brush head geometry (trimming profile, layout, material) to be combined to produce a personalized solution.

[0175] One possible goal could be to predict the optimal performance of a brush head for a specific gingival line or interdental arrangement, the user's most critical tooth regions, or geometry (molars, premolars, incisors, canines, maxilla, or mandible), based on historical medical data such as dental plaque maps or images, or for overall cleaning. As mentioned above, the best-performing brush head can be selected from a list of existing brush heads based on parameter fitting, feature extraction, and / or contact stress mapping.

[0176] Another possible goal could be to develop brush heads that predict optimal performance for different teeth (molars, premolars, incisors, canines), reflecting the user's most critical tooth areas.

[0177] Another possible goal could be to define the optimal trimming profile for personalized brush heads (based on modeling results of semi-custom brush heads achieved through a modular design approach using building blocks). The design can be optimized based on geometry and / or material. Digital manufacturing can then be used to produce the optimized brush head.

[0178] Another possible goal is to provide recommendations on brushing behavior and optimize brushing behavior through coaching.

[0179] This system can be learned, allowing it to be trained to predict how brushing behavior will change for new designs and to account for that change in the simulation and selection of personalized brush heads. The modeling system can include machine learning elements, such as neural networks already trained on data to determine that information. This deviates from the conventional assumption that brushing behavior is independent of brush head design.

[0180] Another goal is to provide replacement recommendations. The simulation can be based on the latest images of the brush head, using both used and open brush heads to indicate whether replacement is needed.

[0181] Another input that can be provided to the recommendation system is an indication of the actual cleaning performance generated by a specific oral care routine. For example, a staining solution can be used to visually display clean and unclean areas. The system can then process images of the oral areas to which this staining solution has been applied to provide feedback on the actual cleaning performance.

[0182] The present invention includes at least the ability to recommend the best available attachment (e.g., a toothbrush head) from a predefined set of available models or a predefined set of modular building blocks when arranged with a toothbrush head. Each of these can be modeled in software, thereby allowing for the evaluation of cleaning performance.

[0183] Figure 9 To illustrate the modular design method described above, design building blocks are generated, for example, for toothbrushes involving different cluster types, lengths, patterns, etc. New designs can then be created automatically based on the modular approach or through user-generated designs, which can be generated by the user themselves in an appropriate app.

[0184] Figure 9 A reference database is shown, in this case involving oral care accessories including brush heads. A list of 92 standard brush head designs exists, along with the option to add custom versions to the list. Items in the list can be accessed via a drop-down menu provided by the app.

[0185] There is also a handle option list 94. An operating mode can also be selected for the chosen handle from list 96. Operating modes, for example, allow the user to select general cleaning goals, such as improving gum health, deep cleaning, or cleaning options for sensitive teeth.

[0186] To create a custom brush head, list 97 of modular blocks can be used. These are design modules that can be combined, such as cluster layouts in different areas of the brush head. More detailed cluster design features (such as material type or other mechanical properties) are also available from list 98. These modules allow the user to make an initial guess by using drop-down menus. The user selects a combination of brush head and handle features (which can be the currently used handle and brush head), and recommendations are obtained based on the interaction modeling described above regarding whether the selection is the best choice. If not, the best alternative is provided again based on interaction modeling.

[0187] Then you can do as Figure 1 The example shown is a modular version designed by the manufacturer.

[0188] Figure 10 A computer-implemented method for recommending types of oral care accessories to be used with oral care devices is shown. An example for a brush head is given, but the invention can also be applied to interface devices, combination brush and floss brush heads with fluid dispensing nozzles, or any other oral care accessories.

[0189] In step 100, oral geometry information about the user to whom the attachment is to be recommended is received.

[0190] In step 102, user behavior information about how a specific user uses oral care equipment to perform their oral care is received.

[0191] In step 104, general user-related information is received, which is not necessarily specific to oral care, such as age, gender, medical records for missing teeth, or the presence or absence of certain dental implants. Any information related to the user's health status can be obtained from the EMR (Electronic Medical Record). Oral health indices such as plaque, stains, gums, and halitosis can also be used as input.

[0192] In step 106, the device operation data received includes: operating frequency; type of brush head movement (oscillation, rotation-vibration, sweeping, tapping, and combinations thereof); amplitude of brush head movement; frequency of brush head movement; frequency of fluid jet pulses; velocity of fluid jet pulses; fluid flow rate; fluid pressure; and RF generator settings.

[0193] In step 108, operational and / or status information of the oral care accessory is received, such as status information derived from one or more images of the oral care accessory. This status information may be based on brush head geometry data; bristle arrangement; cluster layout; trimming contours; changes in cluster geometry over time; and changes in cluster color. Measurements can be derived from the status of the toothbrush head or brushing interface, the status of the bristles of the toothbrush head or brushing interface, the status of the dental floss / rinse head, or the status of the nozzle of the dental floss / rinse head. Brush head geometry data may include the bristle material, bristle geometry, and structure.

[0194] The use of some or all of these information sources can be implemented by the system.

[0195] In step 110, available information, including at least oral cavity geometry information, is processed to provide recommendations for suitable oral care attachments from a set of predefined different oral care attachments for use with oral care devices. An additional option is to provide user-specific manufacturing designs.

[0196] In step 112, the recommendation is provided to the user as output or as a manufacturing instruction.

[0197] The invention has been described in conjunction with a toothbrush system. However, the invention can be applied to fluid dental floss cleaning systems, where different nozzle designs are possible, and recommendations are made for the most suitable nozzle design.

[0198] As mentioned above, machine learning algorithms can be used to provide more accurate and reliable recommendations (or user-specific designs). A machine learning algorithm is any self-trained algorithm that processes input data to produce or predict output data. Here, the input data includes oral cavity geometry information and behavioral information, and the output data includes output recommendations.

[0199] The software platform (the connected ecosystem) can be trained using (real-time) brushing behavior information (force, speed, angle, time spent at each position) acquired during brush use with different existing brush heads. For example, it can be assumed that brushing behavior is constant over a typical brush head usage period (3 months) and is independent of the brush head design selected or chosen by the platform. To accommodate these assumptions (if not entirely valid), the simulation can be "adjusted" to current brush behavior (e.g., the user might apply more force if the brush wears out). This, for example, applies to simulations regarding replacement recommendations.

[0200] Furthermore, continuous training of a system with brushing behavior information obtained with different brush heads (many consumers frequently use different brush heads) can predict how brushing behavior will change with new designs, and take this change into account in performance prediction simulations and recommendations or selections of (personalized) ideal brush heads.

[0201] Behavioral information can be raw motion and force information, or it can be preprocessed to derive contact stress levels or contact stress maps. Geometric information, for example, is data about the gingival line and / or tooth segmentation.

[0202] The suitable machine learning algorithms used in this invention will be apparent to those skilled in the art. Examples of suitable machine learning algorithms include decision tree algorithms and artificial neural networks. Other machine learning algorithms, such as logistic regression, support vector machines, or natural Bayesian models, are suitable alternatives.

[0203] Artificial neural networks (or simply neural networks) are inspired by the human brain in their structure. A neural network consists of multiple layers, each containing multiple neurons. Each neuron performs a mathematical operation. Specifically, each neuron may include different weighted combinations of a single type of transformation (e.g., transformations of the same type with different weights, sigmoid transformation, etc.). In processing the input data, the mathematical operation of each neuron is performed on the input data to produce a digital output, and the outputs of each layer in the neural network are sequentially fed to the next layer. The final layer provides the output.

[0204] Methods for training machine learning algorithms are well-known. Typically, such methods involve obtaining a training dataset that includes training input data entries and corresponding training output data entries. An initialized machine learning algorithm is applied to each input data entry to generate a predicted output data entry. The error between the predicted output data entry and its corresponding training output data entry is used to modify the machine learning algorithm. This process can be repeated until the error converges and the predicted output data entry is sufficiently similar to the training output data entry (e.g., ±1%). This is often referred to as a supervised learning technique.

[0205] For example, in machine learning algorithms formed by neural networks, the mathematical operations (weights) of each neuron can be modified until the error converges. Known methods for modifying neural networks include gradient descent, backpropagation, and others.

[0206] The training input data entries correspond to, for example, oral geometry and behavioral information, as well as historical data (geometry, material of previously used brush heads), and the training output data entries correspond to recommended or oral care accessory features.

[0207] As described above, this system utilizes a processor to perform data processing. The processor can be implemented in various ways, using software and / or hardware, to perform a variety of required functions. A processor typically employs one or more microprocessors that can be programmed using software (e.g., microcode) to perform the desired functions. A processor can be implemented as a combination of dedicated hardware for performing certain functions and one or more programmable microprocessors and associated circuitry for performing other functions.

[0208] Examples of circuits that may be used in various embodiments of the present invention include (but are not limited to) conventional microprocessors, application-specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).

[0209] In various implementations, a processor may be associated with one or more storage media, such as volatile and non-volatile computer memories (e.g., RAM, PROM, EPROM, and EEPROM). The storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform the required functions. Various storage media may be embedded within the processor or controller, or may be transferable or available in the cloud, allowing one or more programs stored thereon to be loaded into the processor.

[0210] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0211] A single processor or other unit can implement the functions described in the claims.

[0212] The fact that certain measures are described in mutually different dependent claims does not imply that combinations of these measures cannot be used advantageously.

[0213] Computer programs can be stored / distributed on suitable media, such as optical or solid-state media provided with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0214] If the term “suitable” is used in the claims or specification, it should be noted that the term “suitable” is intended to be equivalent to the term “configured as”.

[0215] Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A computer-implemented recommendation system for recommending types of oral care accessories to be used as part of an oral care device, the system comprising: Used to receive input including input data about the oral geometry of the user to whom the attachment is recommended (30). Used to receive input including user behavior information about how a particular user performs their oral care using an oral care device with accessories; as well as Processor (23), said processor is adapted to: When the user performs an oral care routine in the manner described, the interaction between one or more oral care accessories from a set of oral care accessories and the user's oral geometry is modeled. The modeling determines a cleanliness metric that represents the effectiveness of the oral care routine when the one or more oral care accessories are used; as well as Based on the cleanliness metric, recommendations for suitable oral care accessories to be used with the oral care device are provided from a set of different oral care accessories.

2. The system of claim 1, comprising: Input is used to receive input data including the user's medical information.

3. The system according to any one of claims 1 to 2, comprising: For receiving input data including operational information about the oral care device; and / or Input is used to receive input data including status information about the oral care accessories; and / or The processor is used to receive input images from an image capture system, and the processor is adapted to process the images to derive the oral cavity geometry information.

4. The system according to any one of claims 1 to 2, wherein the processor is further adapted to: provide recommendations for a suitable handle for the oral care accessory and / or suitable operating settings for the handle of the oral care accessory.

5. The system of any one of claims 1 to 2, further comprising: A database of data related to a set of oral care accessories (32).

6. The system of any one of claims 1 to 2, further comprising: The processor is used to receive input data including an image (34) of the currently used oral care accessory, wherein the processor is also adapted to provide recommendations on when to replace the oral care accessory.

7. The system according to any one of claims 1 to 2, wherein the processor (23) is further adapted to provide suggestion information about user behavior information.

8. The system according to any one of claims 1 to 2, wherein the oral care accessory includes a toothbrush head, and the oral care device includes an electric toothbrush, the electric toothbrush including a handle, the toothbrush head being attached to the handle.

9. The system according to claim 8, wherein the user behavior information includes one or more of the following: Scrubbing power Scrubbing angle; Scrubbing speed; and The location to be scrubbed and the time spent on each location.

10. The system according to any one of claims 1 to 2, wherein the oral care accessory includes a brushing bow, and the oral care device includes an interface toothbrush having a handle to which the brushing bow is connected.

11. An oral care system, comprising: A handle having a drive mechanism and a connection interface for connecting an oral care accessory to the handle; The recommendation system according to any one of claims 1 to 10; and At least one oral care accessory recommended by the recommendation system.

12. The system of claim 11, wherein the oral care accessory or the handle of the oral care system comprises: A sensor system for providing sensor information, wherein behavioral information can be derived from the sensor information, wherein the sensor system includes one or more of the following: Force measurement system; Scrub angle measurement system; Motion detection system; and Position measurement system.

13. A computer-implemented method for recommending types of oral care accessories to be used with oral care devices, the method comprising: Receive input data including information about the oral geometry of the user to whom the attachments are to be recommended; Receive input data including user behavior information about how a particular user performs their oral care using the oral care device with accessories; When the user performs an oral care routine in the manner described, the interaction between one or more oral care accessories from a set of oral care accessories and the user's oral geometry is modeled. The modeling determines a cleanliness metric that represents the effectiveness of the oral care routine when the one or more oral care accessories are used; as well as Based on the cleanliness metrics, recommendations for suitable oral care accessories to be used with oral care devices are provided from a set of different oral care accessories.

14. A computer program comprising computer program code components, wherein when the program is run on a computer, a remote device, or a cloud-based platform, the computer program code components are adapted to implement the method according to claim 13.

Images