Method for adjusting cleaning power of electric toothbrush, electric toothbrush, medium and program product

Abstract

The application provides a power toothbrush cleaning force adjusting method, a power toothbrush, a medium and a program product. The method comprises the following steps: collecting a pressure signal in real time and generating a real-time pressure distribution heat map; generating a bleeding event mark of each sub-region according to the change of the hemoglobin light absorption rate; generating an orthodontic contact mark containing an orthodontic state position coordinate according to a metal contact characteristic waveform corresponding to the pressure signal and combining with toothbrush posture data; dynamically correcting a regional pressure threshold baseline according to the bleeding event mark, the orthodontic contact mark, a historical pressure overrun record and a user sensitivity level to obtain a dynamic pressure upper limit threshold; generating a final force adjusting coefficient through a weighted fusion algorithm according to the real-time pressure value of each sub-region in the real-time pressure distribution heat map, the dynamic pressure upper limit threshold, the bleeding event mark and the orthodontic contact mark; and dynamically adjusting the driving current of the motor based on the final force adjusting coefficient to adjust the output cleaning force of the motor.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for electric toothbrushes, specifically to a method for adjusting the cleaning intensity of an electric toothbrush, an electric toothbrush, a media, and a program product. Background Technology

[0002] In existing technologies, electric toothbrushes primarily control cleaning intensity using fixed-level adjustment or static range management based on historical brushing data. Fixed-level adjustment is the most basic implementation, allowing users to manually switch between preset high, medium, and low levels, setting the motor's vibration frequency and torque, with no automatic adjustment throughout the brushing process. Some smart electric toothbrushes collect brushing intensity data via pressure sensors or motor load detection modules, combining the average intensity of past brushing sessions with a fixed standard deviation to define a single standard brushing intensity range. When the real-time intensity exceeds this range, they only issue warnings via lights or vibrations. Some solutions even stop the motor when the intensity exceeds the preset fixed range, failing to achieve active adaptive adjustment of intensity. Furthermore, all adjustment logic is based on overall brushing intensity statistics, without differentiating the tolerance levels of different areas of the oral cavity.

[0003] For example, Chinese invention patent CN113940776A proposes an adaptive control method, which includes detecting the current brushing intensity value S of the electric toothbrush while it is working; obtaining the standard brushing intensity range X of the electric toothbrush; comparing the current brushing intensity value S with the standard brushing intensity range X; and controlling the electric toothbrush to issue a prompt message if the current brushing intensity value S is not within the standard brushing intensity range X. This method aims to avoid excessive or insufficient brushing intensity while making the brushing intensity more suitable for the user's personalized needs, applicable to different groups of people, protecting sensitive gums while maintaining power output, and improving the user experience. However, the above solution still has the following shortcomings: (1) The above solution defines the standard range by statistically analyzing the average of historical brushing events. It cannot dynamically respond to real-time changes in intensity during brushing. When the range is exceeded, it only issues a prompt message. It does not achieve automatic adaptive adjustment of cleaning intensity and requires manual intervention from the user, resulting in poor user experience and protection effect.

[0004] (2) The above scheme is based on the historical average intensity to define the linear range. It does not take into account the differences in gingival tolerance in different areas of the oral cavity, the actual oral physiological characteristics such as the contact of orthodontic appliances, etc. It cannot monitor high-risk conditions such as gingival bleeding in real time, and therefore cannot provide targeted protection for sensitive and easily damaged areas of the oral cavity. Summary of the Invention

[0005] This invention provides a method for adjusting the cleaning intensity of an electric toothbrush, an electric toothbrush, a media, and a program product.

[0006] According to one aspect of the present invention, a method for adjusting the cleaning intensity of an electric toothbrush is provided, comprising: real-time acquisition of pressure signals generated by the contact between the bristles and oral tissues during brushing, and generating a real-time pressure distribution heatmap based on the pressure signals; generating bleeding event markers for each sub-region of the oral cavity based on changes in hemoglobin light absorption rate during brushing; generating orthodontic contact markers including orthodontic position coordinates based on the metal contact characteristic waveforms corresponding to the pressure signals and combined with toothbrush posture data; determining regional pressure threshold baselines for each sub-region of the oral cavity based on historical brushing data, and dynamically correcting the regional pressure threshold baselines during brushing based on real-time detected bleeding event markers, orthodontic contact markers, historical pressure exceedance records, and user sensitivity levels to obtain dynamic pressure upper limit thresholds for each sub-region; generating a final intensity adjustment coefficient using a weighted fusion algorithm based on the real-time pressure values ​​of each sub-region in the real-time pressure distribution heatmap, the dynamic pressure upper limit thresholds, the bleeding event markers, and the orthodontic contact markers; and dynamically adjusting the drive current of the motor in the electric toothbrush based on the final intensity adjustment coefficient to adjust the output cleaning intensity of the motor.

[0007] According to at least one embodiment of the present invention, an electric toothbrush cleaning intensity adjustment method is provided, which collects pressure signals generated by the contact between the bristles and oral tissues during brushing in real time, and generates a real-time pressure distribution heat map based on the pressure signals. The method includes: continuously collecting pressure signals at a preset sampling frequency through a thin-film pressure sensor array, wherein the thin-film pressure sensor array is arranged in a ring or partitioned manner, and each bristle bundle corresponds to an independent sensing unit; performing analog-to-digital conversion on the pressure signals collected by each sensing unit and then processing the data; and generating the real-time pressure distribution heat map based on the data processing results.

[0008] According to at least one embodiment of the present invention, an electric toothbrush cleaning intensity adjustment method generates a bleeding event marker for each sub-region based on the changes in hemoglobin light absorption rate in each sub-region of the oral cavity during brushing. The method includes: detecting the hemoglobin light absorption rate in each sub-region; calculating the relative change rate of the hemoglobin light absorption rate relative to a reference light absorption rate; determining that a microbleeding event has occurred and generating a bleeding event marker for the corresponding sub-region when the relative change rate is greater than a change rate threshold persists for multiple sampling cycles and artifacts caused by brush head friction with the gums are excluded within the multiple sampling cycles.

[0009] According to at least one embodiment of the present invention, an electric toothbrush cleaning intensity adjustment method generates an orthodontic contact marker containing orthodontic state position coordinates based on the metal contact characteristic waveform corresponding to the pressure signal and combined with toothbrush posture data. The method includes: performing high-frequency sampling on the pressure signal and extracting time-domain and frequency-domain features; determining whether metal contact exists based on the time-domain and frequency-domain features to obtain a preliminary determination result; performing spatial verification on the preliminary determination result based on the toothbrush posture data; and generating an orthodontic contact marker and corresponding orthodontic state position coordinates if the verification passes.

[0010] According to at least one embodiment of the present invention, an electric toothbrush cleaning intensity adjustment method determines the regional pressure threshold baseline of each sub-region in the oral cavity based on historical brushing data, comprising: dividing the historical brushing data into sub-regions, establishing a machine learning model independently for each sub-region to learn the correlation between the pressure distribution and bleeding probability of each sub-region, and generating the regional pressure threshold baseline of each sub-region.

[0011] According to at least one embodiment of the present invention, an electric toothbrush cleaning intensity adjustment method dynamically corrects the regional pressure threshold baseline during brushing based on real-time detected bleeding event markers, orthodontic contact markers, historical pressure exceedance records, and user sensitivity levels to obtain a dynamic pressure upper limit threshold for each sub-region. The method includes: obtaining the regional pressure threshold baseline for the corresponding sub-region during the brushing process; determining a bleeding factor and an orthodontic factor based on the bleeding event markers and orthodontic contact markers; determining a pressure history factor based on historical pressure exceedance records; determining a user adjustment factor based on the user sensitivity level; taking the minimum value among the bleeding factor and the orthodontic factor, and then multiplying it sequentially by the regional pressure threshold baseline, the pressure history factor, and the user adjustment factor to obtain a dynamic threshold; and performing a first-order low-pass filter on the dynamic threshold to obtain the dynamic pressure upper limit threshold.

[0012] According to at least one embodiment of the electric toothbrush cleaning intensity adjustment method of the present invention, the process of generating the final intensity adjustment coefficient includes: calculating the bleeding influence factor at the current moment based on the bleeding influence factor at the previous moment, the forgetting coefficient and the bleeding event marker at the current moment; Based on the hemorrhage influencing factors at the current moment, the local risk adjustment coefficient for each sub-region at the current moment is calculated using the following formula:

[0013] in, This represents the local risk adjustment coefficient of sub-region i at time t; , , These represent the bleeding penalty weight, orthodontic penalty weight, and pressure overload penalty weight, respectively. This represents the hemorrhage influencing factor of sub-region i at time t; This represents the orthodontic contact marker of sub-region i at time t. This represents the measured pressure value of sub-region i at time t. denoted as the upper limit threshold of dynamic pressure in sub-region i at time t; max indicates taking the maximum value; the minimum value among the local risk adjustment coefficients of each sub-region is selected as the global intensity adjustment coefficient; the global intensity adjustment coefficient is subjected to a first-order low-pass filter to obtain the final intensity adjustment coefficient.

[0014] According to another aspect of the present invention, an electric toothbrush is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, such that the processor performs an electric toothbrush cleaning intensity adjustment method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, a readable storage medium is provided, wherein the readable storage medium stores executable instructions, which, when executed by a processor, are used to implement the electric toothbrush cleaning intensity adjustment method of any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements an electric toothbrush cleaning intensity adjustment method according to any embodiment of the present invention.

[0017] This invention uses multi-sensor fusion to capture pressure distribution, bleeding characteristics, and orthodontic contact in real time. Combined with a dynamic threshold generation algorithm that integrates cloud modeling and local real-time inference, it achieves adaptive force adjustment, maintaining efficient cleaning while protecting delicate oral tissues. This solves the contradiction between users' personalized oral care needs and the insufficient intelligence of toothbrushes. Attached Figure Description

[0018] The accompanying drawings illustrate exemplary embodiments of the invention and, together with the description thereof, serve to explain the principles of the invention. These drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification.

[0019] Figure 1 This is a flowchart illustrating a method for adjusting the cleaning intensity of an electric toothbrush according to an embodiment of the present invention.

[0020] Figure 2 This is a flowchart illustrating a bleeding event marker generation method according to an embodiment of the present invention.

[0021] Figure 3 This is a flowchart illustrating a method for generating orthodontic contact marks according to an embodiment of the present invention.

[0022] Figure 4 This is a flowchart illustrating a method for determining a dynamic pressure upper limit threshold according to an embodiment of the present invention.

[0023] Figure 5 This is a flowchart illustrating a method for generating the final force adjustment coefficient according to an embodiment of the present invention.

[0024] Figure 6 This is a schematic structural block diagram of an electric toothbrush using a processor-based hardware implementation according to an embodiment of the present invention. Detailed Implementation

[0025] The present invention will now be described in further detail with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present invention are shown in the accompanying drawings.

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The technical solution of this invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] Figure 1 A schematic flowchart illustrating the overall process of an electric toothbrush cleaning intensity adjustment method according to one embodiment of the present invention is shown. Figure 1 The method shown includes steps S110 to S150.

[0028] S110: Real-time acquisition of pressure signals generated by the contact between the brush bristles and oral tissues during brushing, and generation of a real-time pressure distribution heatmap based on the pressure signals.

[0029] As one possible implementation, the pressure signal can be acquired using a thin-film pressure sensor array mounted (e.g., embedded) at the base of the brush head. The acquisition process can cover the entire brushing cycle. Specifically, the thin-film pressure sensor array is mounted at the base of the brush head in a ring or partitioned layout, with each bristle tuft corresponding to an independent sensing unit. A typical resolution is 8×8, the sensing pressure range is 0.05N~5N, and the accuracy is ±0.02N. The thin-film pressure sensor array continuously acquires the raw pressure signal at 100Hz~200Hz.

[0030] As one possible implementation, considering that the electric brush head is in a high-frequency vibration and complex oral cavity environment, the pressure sensor is susceptible to common-mode interference generated by motor vibration. To suppress this common-mode vibration interference, the thin-film pressure sensor array uses a flexible thin-film material and is shock-absorbing encapsulated. At the same time, it is physically isolated from the motor vibration source in its structural layout, thereby avoiding the impact of high-frequency motor vibration on the accuracy of pressure signal acquisition.

[0031] As one possible implementation, in the process of generating a real-time pressure distribution heatmap based on pressure signals, the pressure signals collected by each sensing unit can be converted from analog to digital and then processed. The real-time pressure distribution heatmap is then generated based on the data processing results. For example, data processing may include high-frequency noise removal, zero-point calibration, and temperature compensation. High-frequency noise removal can employ methods such as moving average or low-pass filtering; zero-point calibration can be performed each time the device is powered on; and temperature compensation is used to compensate for drift in conjunction with a temperature sensor. The final generated real-time pressure distribution heatmap is in two-dimensional format, recording the real-time pressure values ​​corresponding to each coordinate position.

[0032] As one possible implementation, step S110, while acquiring the pressure signal generated by the brush bristles contacting oral tissues in real time during brushing, also includes controlling a (nine-axis) attitude sensor to continuously track the brush head movement at a preset sampling frequency (e.g., 200Hz). The pressure data corresponding to each sensing unit is then synchronized with the attitude data acquired by the attitude sensor via RTOS hardware to ensure accurate correspondence between the pressure data and the attitude data. The acquired raw pressure signal can be stored in a local circular buffer and uploaded in real time via BLE.

[0033] S120: Based on the changes in hemoglobin light absorption rate in different sub-regions of the oral cavity during brushing, bleeding event markers for each sub-region are generated. Based on the metal contact characteristic waveform corresponding to the pressure signal, combined with toothbrush posture data, orthodontic contact markers containing the coordinates of the orthodontic position are generated.

[0034] As one possible implementation method, the various sub-regions within the oral cavity can be finely divided according to the gingival junction region.

[0035] Figure 2 A flowchart illustrating a bleeding event marker generation method according to one embodiment of the present invention is shown. Figure 2 The method shown includes steps S210 to S230.

[0036] S210: Detects the light absorption rate of hemoglobin in various sub-regions of the oral cavity.

[0037] For example, the hemoglobin light absorption rate of each sub-region can be detected by an optical sensor positioned between the bristles.

[0038] As one possible implementation, the optical sensor is arranged in an optical sensor array, specifically aligned with the thin-film pressure sensor array, to ensure precise localization of bleeding events. The optical sensor drives the emitted light pulses using pulse modulation and simultaneously receives reflected light signals. The received analog reflected light signals are first pre-processed by transimpedance amplification and bandpass filtering, and then converted from analog to digital to obtain a digital signal. This digital signal, along with the pressure data collected by the thin-film pressure sensor and the attitude data collected by the attitude sensor, is precisely aligned in time and space through RTOS hardware. This allows changes in the light signal detected by the optical sensor to be accurately matched with the pressure data and brush head attitude data of the corresponding area, thus establishing a correlation between the location of the bleeding event and the brushing action and contact pressure.

[0039] In one example, the modulation frequency of the pulse modulation can be set to 100Hz. By transmitting light pulses at a modulation frequency of 100Hz and simultaneously receiving reflected light signals, power consumption can be reduced and ambient light interference can be suppressed.

[0040] As one possible implementation, a dual-wavelength detection method is introduced to improve the specificity of bleeding detection. Specifically, the optical sensor also includes an infrared reference channel. Utilizing the characteristic that hemoglobin has weak absorption in the infrared band, the reflection changes caused by non-blood factors are eliminated by calculating the ratio between the main detection channel signal and the infrared reference channel signal.

[0041] S220: Calculate the relative rate of change of hemoglobin light absorbance relative to the baseline light absorbance.

[0042] As one possible implementation, before calculating the relative rate of change of hemoglobin light absorption rate relative to the reference light absorption rate, a process for obtaining the reference light absorption rate is also included. Specifically, at the beginning of each brushing session, the reflected light intensity of each sub-region under a non-bleeding state is briefly measured before the brush head contacts the teeth, and the average of multiple measurements is taken as the reference light absorption rate of that sub-region.

[0043] Furthermore, considering that dirt on the optical sensor may cause reference drift during long-term use, when it is determined that there is no bleeding and the pressure is stable during brushing, the reference light absorption rate can be slowly updated using an exponentially weighted moving average method so that the reference light absorption rate always reflects the current state of the optical sensor.

[0044] For example, the rate of change threshold can be set to 15%.

[0045] S230: If a microbleeding event occurs and the relative rate of change is greater than the rate of change threshold for multiple sampling periods, and artifacts caused by brush head friction with the gums are excluded within multiple sampling periods, a bleeding event marker for the corresponding sub-region is generated.

[0046] Artifacts can include those caused by intense friction between the brush head and the gums, and can be eliminated by combining pressure signals.

[0047] As one possible implementation, after determining that a microbleeding event has occurred, the coordinates of the bleeding hotspot with timestamps can be generated based on the mapping relationship between the digital signals corresponding to the data collected by the optical sensor and the attitude data.

[0048] Figure 3 A flowchart illustrating a method for generating orthodontic contact marks according to one embodiment of the present invention is shown. Figure 3 The method shown includes steps S310 to S340.

[0049] S310: Performs high-frequency sampling of the pressure signal during brushing and extracts time-domain and frequency-domain features.

[0050] When metal brackets or archwires come into contact with brush bristles, the material's hardness and surface geometry excite characteristic components in the pressure signal waveform that differ from those of the gingival soft tissue. These are manifested as increased high-frequency oscillation amplitude, a steeper rising edge, and concentrated energy in specific frequency bands within the spectrum. Based on these characteristics, the pressure signal acquired by each pressure sensing unit is continuously sampled at a preset high-frequency rate, and time-domain and frequency-domain features are extracted in real time. The time-domain features include peak factor and waveform factor, while the frequency-domain features include the energy proportion of a preset frequency band. In one example, the preset high-frequency sampling rate can be 1 kHz, and the preset frequency band can be 200 Hz to 500 Hz. The energy proportion of this frequency band is calculated using a Fast Fourier Transform.

[0051] S320: Determine whether there is metal contact based on time-domain and frequency-domain characteristics to obtain preliminary judgment results.

[0052] As one possible implementation, the existence of metal contact is initially determined based on time-domain and frequency-domain characteristics, including: when the peak factor of a pressure sensing unit exceeds a preset peak threshold and the energy proportion of a preset frequency band exceeds a preset energy threshold, it is initially determined that metal contact exists at the location corresponding to the pressure sensing unit. In one example, the preset peak threshold is 3.5, and the preset energy threshold is 0.25.

[0053] S330: Spatial verification of the preliminary judgment results based on toothbrush posture data.

[0054] To eliminate common-mode interference such as motor vibration, after initially determining the presence of metal contact, a spatial verification process is included, incorporating toothbrush posture data. Specifically, toothbrush posture data collected by a posture sensor is simultaneously introduced. By analyzing the current posture angle and movement trajectory of the brush head, the spatial coordinates of the pressure sensing unit, which initially indicated metal contact, are mapped to the corresponding sub-region. If multiple consecutive sampling points within the same sub-region meet the characteristics of metal contact, and the posture changes conform to the brushing motion pattern, then the presence of orthodontic device contact in that sub-region is confirmed, and the verification is successful.

[0055] S340: If the verification is successful, generate the orthodontic contact mark and the corresponding orthodontic status position coordinates.

[0056] As one possible implementation, if the verification is successful, the method also includes marking the corresponding sub-region as a highly sensitive region.

[0057] S130: Based on historical brushing data, determine the regional pressure threshold baseline for each sub-region in the oral cavity, and dynamically correct the regional pressure threshold baseline during brushing based on real-time detected bleeding event markers, orthodontic contact markers, historical pressure exceedance records, and user sensitivity levels to obtain the dynamic pressure upper limit threshold for each sub-region.

[0058] As one possible implementation method, determining the regional pressure threshold baseline for each sub-region in the oral cavity based on historical brushing data includes: dividing the historical brushing data into sub-regions, establishing a machine learning model independently for each sub-region to learn the correlation between pressure distribution and bleeding probability in each sub-region, and generating the regional pressure threshold baseline for each sub-region.

[0059] In one example, for each sub-region, a machine learning model is trained based on historical brushing data to obtain a pressure-bleeding probability mapping function for that sub-region. This pressure-bleeding probability mapping function characterizes the bleeding probability of that sub-region under different pressure values. By substituting a preset acceptable upper limit for bleeding probability into the pressure-bleeding probability mapping function, the corresponding pressure value is determined, and this pressure value can be used as the regional pressure threshold baseline for that sub-region. Exemplarily, historical brushing data may include pressure distribution time series, posture trajectory, bleeding event records, and user manual feedback.

[0060] Since most electric toothbrushes use 8 / 16-bit low-computing-power chips as their MCUs, performing the entire calculation process locally can easily lead to excessive computational latency and untimely response, failing to meet the real-time requirements of intensity adjustment. Therefore, this embodiment splits the computational task into two parts: complex cloud modeling and lightweight local inference. The cloud performs high-computing tasks such as refined oral cavity partitioning based on user historical data, machine learning model training, and generation of pressure-bleeding probability mapping functions. Only the compressed threshold baseline table and lightweight model file are sent to the local device via OTA. Specifically, the determination of the aforementioned regional pressure threshold baselines can be completed in the cloud, and a threshold baseline table is generated in the cloud based on the determined regional pressure threshold baselines of each sub-region and sent to the electric toothbrush's local storage. The machine learning model in the cloud can be updated in real time based on updates to historical brushing data, thereby updating the regional pressure threshold baselines in the threshold baseline table in real time. The updated threshold baseline table and the compressed lightweight model file can be sent to the electric toothbrush's local storage in real time or periodically via OTA as a benchmark for subsequent real-time inference.

[0061] Figure 4 A flowchart illustrating a method for determining a dynamic pressure upper limit threshold according to one embodiment of the present invention is shown. Figure 4 The method shown includes steps S410 to S440.

[0062] S410: Obtain the regional pressure threshold baseline for the corresponding sub-region during the brushing process.

[0063] For example, the regional pressure threshold baseline corresponding to the current sub-region can be found from the threshold baseline table stored locally on the electric toothbrush by looking up a table.

[0064] S420: Identify the bleeding factor and orthodontic factor based on bleeding event markers and orthodontic contact markers, respectively. Identify the pressure history factor based on historical pressure exceedance records. Identify the user adjustment factor based on the user's sensitivity level.

[0065] For example, the bleeding factor can be determined as follows: if the bleeding event flag is true, it indicates that there is gingival microbleeding in the current sub-region, and the bleeding factor is set to 0.7; if the bleeding event flag is false, it indicates that there is gingival non-bleeding in the current sub-region, and the bleeding factor is set to 1.0.

[0066] For example, the orthodontic factor can be determined as follows: if the orthodontic contact flag is true, it indicates that the current sub-region is a highly sensitive area for orthodontic contact, and the orthodontic factor is set to 0.5; if the orthodontic contact flag is false, it indicates that the current sub-region is not a highly sensitive area for orthodontic contact, and the orthodontic factor is set to 1.0.

[0067] For example, the pressure history factor can be determined based on the normalized result of the ratio of the number of times the real-time pressure value of the target sub-region exceeded the regional pressure threshold baseline in the past brushing to the total number of brushings in the past. Specifically, the ratio can be normalized to the range of 0.8-1.2.

[0068] For example, the user adjustment factor can be obtained by mapping the user sensitivity level.

[0069] S430: After extracting the minimum value from the blood factor and orthodontic factor, multiply it sequentially with the regional pressure threshold baseline, pressure history factor, and user adjustment factor to obtain the dynamic threshold.

[0070] For example, the formula for calculating the dynamic threshold can be expressed as:

[0071] in, This represents the dynamic threshold of subregion i at time t; This represents the baseline of the regional pressure threshold for sub-region i; min indicates taking the minimum value. Indicates bleeding factors; Indicates the orthodontic factor; Indicates the historical stress factor; This represents the user adjustment factor.

[0072] S440: Perform a first-order low-pass filter on the dynamic threshold to obtain the dynamic pressure upper limit threshold.

[0073] For example, a first-order low-pass filter can be expressed as:

[0074] in, This represents the upper limit threshold of dynamic pressure in sub-region i at time t; This represents the filter coefficients, with values ​​ranging from 0 to... <1; This represents the upper limit threshold of dynamic pressure in sub-region i at time t-1.

[0075] Steps S410 to S440 extract the minimum value from the blood factor and orthodontic factor to ensure that the threshold is immediately reduced under any single high-risk factor, prioritizing the protection of the most vulnerable areas. By sequentially multiplying the threshold by the regional pressure threshold baseline, pressure history factor, and user adjustment factor, the real-time risk status and individual user differences are integrated into the threshold calculation. First-order low-pass filtering of the dynamic threshold smooths threshold changes and prevents motor output jitter. The dynamic pressure upper limit threshold determination methods described above avoid time-consuming operations such as matrix operations and complex iterations, involving only low-computational-power operations such as table lookup, minimum value comparison, multiplication, and first-order low-pass filtering. This allows for millisecond-level calculations on the low-computational-power 8 / 16-bit MCUs used in electric toothbrushes, meeting the real-time requirements of force adjustment.

[0076] S140: Based on the real-time pressure values ​​of each sub-region in the real-time pressure distribution heatmap, the dynamic pressure upper limit threshold, the bleeding event marker, and the orthodontic contact marker, the final force adjustment coefficient is generated through a weighted fusion algorithm.

[0077] Figure 5 A flowchart illustrating a method for generating the final force adjustment coefficient according to one embodiment of the present invention is shown. Figure 5 The method shown includes steps S510 to S540.

[0078] S510: Calculate the bleeding impact factor at the current moment based on the bleeding impact factor and forgetting coefficient from the previous moment, and the bleeding event marker at the current moment. The calculation formula can be expressed as:

[0079] in, This represents the bleeding influencing factors at time t; This represents the bleeding influencing factors at time t-1; Indicates the marker of the bleeding event at time t; This represents the forgetting coefficient, which can be set to 0.9.

[0080] The recursive approach used in step S510 allows the impact of a single bleeding event to decay exponentially over time, preventing prolonged weakness caused by brief bleeding, while also mitigating the effects of continuous bleeding. It can approach 1.

[0081] S520: Based on the hemorrhage influencing factors at the current moment, the local risk adjustment coefficient for each sub-region at the current moment is calculated using the following formula:

[0082] in, This represents the local risk adjustment coefficient of sub-region i at time t; , , These represent the bleeding penalty weight, orthodontic penalty weight, and pressure overload penalty weight, respectively. For example, It can be set to 0.3. It can be set to 0.4. It can be set to 0.2, ensuring that the sum of the three is less than 1. Non-negative; This represents the hemorrhage influencing factor of sub-region i at time t; This represents the orthodontic contact marker of sub-region i at time t. This represents the measured pressure value of sub-region i at time t. represents the upper limit threshold of dynamic pressure in sub-region i at time t; max indicates taking the maximum value. The above formula obtains the local risk adjustment coefficient for each region by linearly superimposing three risk factors. The closer the value is to 1, the safer the corresponding sub-region is; the closer it is to 0, the higher the risk of the corresponding sub-region is.

[0083] S530: Select the minimum value among the local risk adjustment coefficients of each sub-region as the global intensity adjustment coefficient.

[0084] Step S530 ensures that all areas of the oral cavity are not subjected to excessive pressure, ensuring that the most vulnerable areas determine the overall cleaning intensity, thereby achieving precise protection.

[0085] S540: Perform a first-order low-pass filter on the global intensity adjustment coefficient to obtain the final intensity adjustment coefficient.

[0086] The first-order low-pass filtering method used in step S540 is the same as that in step S440, and will not be described in detail here.

[0087] S150: Dynamically adjusts the drive current of the motor inside the electric toothbrush based on the final force adjustment coefficient to adjust the output cleaning force of the motor.

[0088] As one possible implementation, during the process of adjusting the motor's output cleaning force, the final force adjustment coefficient can be used as an input parameter of the motor drive module. The motor's drive current can be dynamically changed according to the magnitude of the final force adjustment coefficient, thereby adjusting the motor's output torque and achieving real-time adjustment of the cleaning force.

[0089] As one possible implementation, during brushing, when the sub-region where the current brush head is located is detected as a highly sensitive area (i.e., a sub-region with orthodontic contact markings), the motor's output torque is automatically reduced from the normal torque range to the protective torque range based on the final force adjustment coefficient. In one example, the normal torque range is 0.2 N·m to 0.3 N·m, and the protective torque range is 0.05 N·m to 0.1 N·m. When the brush head leaves the highly sensitive area, the baseline cleaning force is automatically restored, that is, the motor's output torque is restored to the normal torque range.

[0090] As one possible implementation, the response delay is controlled within a delay threshold during the process from detecting a highly sensitive area to the motor's output torque being adjusted. In one example, the delay threshold is 5ms, meaning that the time from detecting a highly sensitive area to the motor's output torque dropping to the protective torque range does not exceed 5ms. This ensures that the force reduction is completed within a very short time after the brush head contacts the sensitive tissue, avoiding damage to delicate oral tissues.

[0091] As one possible implementation, the motor is a brushless motor. By adjusting the duty cycle or current amplitude of the brushless motor's drive current, continuous and smooth adjustment of the output torque can be achieved, avoiding abrupt changes in cleaning force and ensuring the comfort and continuity of cleaning effect during the brushing process.

[0092] As a further implementation, considering that electric toothbrushes rely on lithium batteries for power, high-frequency sampling and data uploading operations would significantly shorten battery life without power consumption optimization. To address this power consumption issue, this embodiment employs the following power optimization strategies: For sensor sampling, the high-frequency feature extraction modules of the optical and pressure sensors use a triggered sampling method, initiating high-frequency sampling only when the brush head detects contact pressure, and switching to low-frequency sleep sampling when no contact pressure is detected. In one example, the low-frequency sleep sampling frequency is 10Hz. For data uploading, BLE data uploading uses a batch caching method, compressing the raw data in the local circular buffer before uploading in batches, rather than uploading data one record at a time in real time, to reduce the duty cycle of the BLE module. For task scheduling, sensor acquisition, detection, and recognition tasks are split into independent threads. Each thread only starts when the trigger condition is met, releasing hardware resources when there are no tasks, avoiding power waste caused by continuous single-threaded operation; simultaneously, low-frequency tasks such as temperature sensor detection and zero-point calibration are scheduled on a timer basis to further reduce ineffective power consumption.

[0093] The present invention has the following beneficial effects: (1) By dividing the oral cavity into fine-grained regions according to the gingival junction during the cloud modeling stage, and independently establishing machine learning models for each sub-region to learn the relationship between pressure distribution and bleeding probability, and generating independent regional pressure threshold baselines for each sub-region, differentiated threshold management of different sub-regions of the oral cavity can be achieved, overcoming the shortcomings of existing technologies that define a single standard range based on overall brushing intensity statistics and cannot differentiate the tolerance of different regions.

[0094] (2) By combining real-time detected bleeding event markers, orthodontic contact markers, and user-defined sensitivity preferences during the local real-time inference stage, multiple deviation factors such as bleeding factor, orthodontic factor, pressure history factor, and user adjustment factor are calculated. The dynamic pressure upper limit threshold at the current moment is dynamically synthesized through weighted fusion. This allows the dynamic pressure upper limit threshold to be automatically adjusted according to the real-time state of the user's oral cavity, overcoming the shortcomings of existing technologies where the threshold is statically defined based on historical averages and cannot dynamically respond to real-time intensity changes during brushing. At the same time, the entire local inference process only involves simple arithmetic operations and table lookup operations, and can be updated in real time at the millisecond level, significantly reducing the demand for embedded chip computing power and storage resources.

[0095] (3) By generating bleeding event markers for each sub-region based on changes in hemoglobin light absorption rate, real-time monitoring and precise localization of gingival bleeding status can be achieved, overcoming the shortcomings of existing technologies that cannot monitor high-risk states such as gingival bleeding in real time, and providing timely triggering basis for emergency reduction of dynamic pressure upper limit threshold.

[0096] (4) By analyzing the metal contact characteristic waveform corresponding to the pressure signal, the contact of the orthodontic device can be identified. By utilizing the characteristic components that distinguish the metal bracket or archwire from the soft tissue of the gums, such as the increased high-frequency oscillation amplitude, steep rising edge of the waveform, and concentrated energy in specific frequency bands of the spectrum when the metal bracket or archwire contacts the brush bristles, the contact area of ​​the orthodontic device can be automatically identified and accurately located. This overcomes the shortcomings of the existing technology, which does not consider the actual oral physiological characteristics such as the contact of the orthodontic device and cannot provide targeted protection for orthodontic wearers.

[0097] (5) By using a recursive relationship that includes a forgetting coefficient to generate a bleeding persistence influencing factor, the impact of a single bleeding event can be exponentially reduced over time, avoiding prolonged deterioration of cleaning efficiency due to short-term bleeding. At the same time, the bleeding influencing factor approaches 1 when there is continuous bleeding, ensuring adequate protection of the area with continuous bleeding, and achieving a balance between oral tissue protection and cleaning efficiency.

[0098] (6) By dynamically changing the motor drive current based on the final force adjustment coefficient, the output torque is automatically reduced when a highly sensitive area is detected, and the response delay is controlled; after leaving the highly sensitive area, the reference cleaning force is automatically restored, which can realize the real-time adaptive adjustment of the cleaning force, overcome the defects of the prior art that only issues a prompt or stops when the range is exceeded, and requires manual intervention by the user, and can complete the automatic adjustment and restoration of the force without manual operation by the user.

[0099] According to a further embodiment of the present invention, an electric toothbrush is also provided. Figure 6 This diagram illustrates a schematic block diagram of an electric toothbrush using a processor-based hardware implementation according to an embodiment of the present invention. The hardware structure of the electric toothbrush of the present invention can be implemented using a bus architecture. The bus architecture can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the hardware. Bus 1100 connects various circuits including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400 such as peripheral devices, voltage regulators, power management circuits, external antennas, etc. Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, only one connecting line is used in this figure, but this does not indicate that there is only one bus or one type of bus. The memory 1300 stores a computer program. When the processor 1200 executes the computer program, the processor 1200 is able to execute the electric toothbrush cleaning intensity adjustment method of the above embodiment of the present invention.

[0100] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods described above. A "readable storage medium" can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples of a readable storage medium include: an electrical connection (electronic device) having one or more wires, a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM), etc.

[0101] This invention also provides a computer program product. The method of this invention can be implemented wholly or partially through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented wholly or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed, the processes or functions of this invention are performed wholly or partially.

[0102] Computer programs or instructions can be stored in a readable storage medium or transferred from one readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The readable storage medium can be any available medium capable of access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or it can include both volatile and non-volatile types of storage media.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, or characteristic described in connection with that embodiment / mode or example is included in at least one embodiment / mode or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Moreover, the specific features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.

[0108] Those skilled in the art should understand that the above embodiments are merely for illustrating the present invention and are not intended to limit the scope of the invention. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present invention.

Claims

1. A method for adjusting the cleaning intensity of an electric toothbrush, characterized in that, include: The pressure signal generated by the contact between the brush bristles and oral tissues during brushing is collected in real time, and a real-time pressure distribution heat map is generated based on the pressure signal. Based on the changes in hemoglobin light absorption rate in different sub-regions of the oral cavity during brushing, bleeding event markers for each sub-region are generated; based on the metal contact characteristic waveform corresponding to the pressure signal and combined with toothbrush posture data, orthodontic contact markers containing orthodontic position coordinates are generated. Based on historical brushing data, the regional pressure threshold baseline for each sub-region in the oral cavity is determined. During brushing, the regional pressure threshold baseline is dynamically corrected based on real-time detected bleeding event markers, orthodontic contact markers, historical pressure exceedance records, and user sensitivity levels to obtain the dynamic pressure upper limit threshold for each sub-region. Based on the real-time pressure values ​​of each sub-region in the real-time pressure distribution heatmap, the dynamic pressure upper limit threshold, the bleeding event marker, and the orthodontic contact marker, a final force adjustment coefficient is generated through a weighted fusion algorithm. The drive current of the motor inside the electric toothbrush is dynamically adjusted based on the final force adjustment coefficient to adjust the output cleaning force of the motor.

2. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, Real-time acquisition of pressure signals generated by the contact between the brush bristles and oral tissues during brushing, and generation of a real-time pressure distribution heatmap based on the pressure signals, including: Pressure signals are continuously acquired at a preset sampling frequency by a thin-film pressure sensor array, which is arranged in a ring or partitioned layout, with each bristle bundle corresponding to an independent sensing unit. The pressure signals collected by each sensing unit are converted from analog to digital and then processed. The real-time pressure distribution heat map is generated based on the data processing results.

3. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, Based on the changes in hemoglobin light absorption rate in different sub-regions of the oral cavity during brushing, bleeding event markers for each sub-region are generated, including: Detect the light absorbance of hemoglobin in each sub-region; Calculate the relative rate of change of the hemoglobin light absorbance relative to the reference light absorbance; If the relative rate of change is greater than the rate of change threshold for multiple sampling periods, and if artifacts caused by brush head friction with the gums are excluded within the multiple sampling periods, a microbleeding event is determined to have occurred, and a bleeding event marker for the corresponding sub-region is generated.

4. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, Based on the metal contact characteristic waveform corresponding to the pressure signal, and combined with toothbrush posture data, an orthodontic contact marker containing the orthodontic state position coordinates is generated, including: The pressure signal is sampled at high frequency, and its time-domain and frequency-domain features are extracted. Based on the time-domain features and the frequency-domain features, a preliminary determination result is obtained to determine whether metal contact exists. The preliminary judgment results were spatially verified based on the toothbrush posture data. If the verification is successful, generate the orthodontic contact mark and the corresponding orthodontic status position coordinates.

5. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, Based on historical brushing data, baseline regional pressure thresholds for each sub-region within the oral cavity are determined, including: The historical brushing data is divided into sub-regions, and a machine learning model is independently built for each sub-region to learn the correlation between pressure distribution and bleeding probability in each sub-region, and to generate the regional pressure threshold baseline for each sub-region.

6. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, During brushing, based on real-time detected bleeding event markers, orthodontic contact markers, historical pressure exceedance records, and user sensitivity levels, the baseline pressure threshold for the aforementioned regions is dynamically adjusted to obtain the dynamic upper limit threshold for each sub-region, including: Obtain the regional pressure threshold baseline for the corresponding sub-region during the brushing process; Based on the bleeding event markers and orthodontic contact markers, the bleeding factor and orthodontic factor are determined respectively; the pressure history factor is determined based on historical pressure exceedance records; and the user adjustment factor is determined based on the user's sensitivity level. The minimum value among the bleeding factor and the orthodontic factor is taken and then multiplied sequentially by the regional pressure threshold baseline, the pressure history factor, and the user adjustment factor to obtain the dynamic threshold. The dynamic pressure upper limit threshold is obtained by performing a first-order low-pass filter on the dynamic threshold.

7. The method for adjusting the cleaning intensity of an electric toothbrush as described in claim 1, characterized in that, The process of generating the final intensity adjustment coefficient includes: Calculate the bleeding impact factor at the current moment based on the bleeding impact factor and forgetting coefficient at the previous moment and the bleeding event marker at the current moment; Based on the hemorrhage influencing factors at the current moment, the local risk adjustment coefficient for each sub-region at the current moment is calculated using the following formula: in, This represents the local risk adjustment coefficient of sub-region i at time t; , , These represent the bleeding penalty weight, orthodontic penalty weight, and pressure overload penalty weight, respectively. This represents the hemorrhage influencing factor of sub-region i at time t; This represents the orthodontic contact marker of sub-region i at time t. This represents the measured pressure value of sub-region i at time t. This represents the upper limit threshold of dynamic pressure in sub-region i at time t; max indicates taking the maximum value. The minimum value among the local risk adjustment coefficients of each sub-region is selected as the global intensity adjustment coefficient; The global intensity adjustment coefficient is subjected to a first-order low-pass filter to obtain the final intensity adjustment coefficient.

8. An electric toothbrush, characterized in that, include: The memory stores execution instructions; as well as A processor that executes execution instructions stored in the memory, causing the processor to perform the electric toothbrush cleaning intensity adjustment method according to any one of claims 1 to 7.

9. A readable storage medium, characterized in that, The readable storage medium stores execution instructions, which, when executed by a processor, are used to implement the electric toothbrush cleaning intensity adjustment method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the electric toothbrush cleaning intensity adjustment method according to any one of claims 1 to 7.

Images