A notebook computer touch interaction intelligent control method
By combining multi-sensor collaboration and machine learning models, automated and personalized control of laptop touch interaction has been achieved, solving problems such as accidental touches and cumbersome scene switching, and improving user experience and device energy efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SOWORTH INTELLIGENT MFG (ZHONGSHAN) CO LTD
- Filing Date
- 2026-03-06
- Publication Date
- 2026-06-09
AI Technical Summary
Existing touch interaction control methods for laptops suffer from problems such as accidental touches, cumbersome scene switching, fixed sensitivity that cannot adapt, and low sensor recognition accuracy, making it difficult to meet diverse and personalized needs.
By employing multi-sensor collaboration, multi-source signals are simultaneously acquired through a three-dimensional sensor array, and combined with machine learning models for scene recognition and dynamic adaptive control, refined touch interaction is achieved.
It enables automated and contextualized touch interaction, improves user experience and device energy efficiency, avoids accidental touches, simplifies operation processes, and adaptively adjusts touch parameters according to user habits and environmental changes.
Smart Images
Figure CN122172988A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of laptop computer control technology, specifically to a laptop computer touch interaction intelligent control method and system, which is particularly suitable for improving the intelligence, scenario adaptability and user experience of laptop computer touch interaction. Background Technology
[0002] Existing touchscreen interaction control methods for laptops have many shortcomings. Touchpads typically rely on shortcut keys to be manually turned on or off, and users are prone to accidental cursor movement due to palm strikes while typing, interfering with operation. Switching between scenarios such as waking up by opening the lid and exiting sleep mode requires manual operation, which is cumbersome. In addition, touch sensitivity is usually a fixed setting or requires manual adjustment by the user, and cannot adapt to changes in user habits or environment, resulting in poor versatility and difficulty in meeting diverse and personalized usage needs.
[0003] While some technologies attempt to detect user hand positions using single sensors such as infrared or capacitive sensors to control touchpads, these methods are susceptible to blind spots and environmental interference, resulting in low accuracy and a lack of comprehensive judgment and coordinated control for complex usage scenarios. Therefore, the industry urgently needs to develop a method that can intelligently perceive user intentions, accurately identify usage scenarios, and automatically execute refined touch interaction control. Summary of the Invention
[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a smart control method for touch interaction in laptops. This method achieves automation, contextualization, and personalization of touch interaction through multi-sensor collaboration, intelligent scene recognition, and dynamic adaptive control, significantly improving user experience and device energy efficiency.
[0005] To solve one of the aforementioned technical problems, the following technical solution is adopted: This application discloses a smart control method for touch interaction on a laptop computer, including the following steps: Step S1: Simultaneously acquire multi-source sensor signals using a three-dimensional sensor array deployed on a laptop computer; Step S2: Perform three-level anti-interference and normalization preprocessing on the multi-source sensor signals to generate a standardized data matrix; Step S3: Input the standardized data matrix into the machine learning-based scene recognition model, and combine it with the user's historical operation data to identify the current user scenario; Step S4: Based on the identified usage scenario, execute the corresponding refined touch interaction control operation; Step S5: Collect user touch operation data and environmental parameters in real time, dynamically adjust touch sensitivity and perform full-scene sensor calibration; Step S6: After performing the control operation, provide multiple feedbacks and switch to the standby control mode when an anomaly is detected.
[0006] To better achieve the purpose of the invention, the present invention also has the following superior technical solutions: In some embodiments, the three-dimensional sensing array includes: At least two sets of high-precision infrared sensors are arranged between the keyboard and the touchpad; a dual-axis angle sensor is arranged at the hinge of the device; multiple sets of capacitive sensors are evenly distributed along the edge of the touchpad; an ambient light sensor and a temperature sensor are arranged at the palm rest of the device; and each sensor collects data using a synchronous triggering mechanism.
[0007] In some embodiments, the three-level anti-interference processing in step S2 includes: First stage: Low-pass filtering is used to remove power frequency and environmental noise interference; Second stage: Adaptive threshold filtering is used to dynamically adjust the filtering threshold according to ambient temperature and light intensity; Third stage: Cross-validation and fusion of infrared and capacitance signals are performed to remove invalid signals.
[0008] In some embodiments, the scene recognition model is a lightweight model optimized based on a convolutional neural network, which can recognize multiple scenarios including keyboard intensive use scenarios, touchpad exclusive use scenarios, opening the lid to wake up scenarios, temporary absence and sleep scenarios, password login scenarios, and idle scenarios; the model can be dynamically iteratively optimized based on the user's historical operation data.
[0009] Step S4 includes: In scenarios involving intensive keyboard use, the touchpad is automatically turned on and off based on the frequency of keyboard input. In the scenario of waking up from an open lid, the system performs graded wake-up and display brightness adjustment based on the opening angle and ambient light intensity. When leaving the hibernation scenario, hibernation control is implemented based on user distance, duration, and operation status. In password login scenarios, the password input is verified and the touchpad status and feedback prompts are controlled in conjunction with it.
[0010] In some embodiments, step S5 includes: Based on long-term user touch operation data, users are classified using clustering algorithms, and touch sensitivity and response speed are adjusted for different user types; the sensitivity thresholds of infrared and capacitive sensors are automatically calibrated according to changes in ambient temperature; and all sensors are automatically and comprehensively calibrated periodically.
[0011] In some embodiments, the multiple feedback in step S6 includes indicator light status, tiered prompt sounds, and optional screen pop-ups; the backup control mode is activated when a sensor or main control chip malfunction is detected, and manual control has the highest priority.
[0012] This application also discloses a laptop computer, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the laptop computer touch interaction intelligent control method as described above.
[0013] This method employs multi-source signal collaborative acquisition and preprocessing: a three-dimensional stereo sensor array with optimized layout synchronously acquires multi-source signals such as infrared, angle, capacitance, light, and temperature, and performs three levels of anti-interference and normalization processing to form high-quality input data.
[0014] Accurate scene identification based on machine learning: By using a lightweight machine learning model, combined with preprocessed data and user historical behavior data, multi-dimensional features are extracted to identify a variety of typical use scenarios with high accuracy.
[0015] Contextualized and refined control: Different control strategies are executed for different identified scenarios, such as intelligent touchpad on / off, tiered wake-up / sleep, password login linkage, and game mode switching.
[0016] Touch parameter adaptation and dynamic calibration: Based on the cluster analysis results of users' long-term operation patterns, the touch sensitivity is adaptively adjusted; combined with changes in ambient temperature and regular schedules, the sensor is dynamically calibrated in all scenarios.
[0017] Multi-level feedback and anomaly handling: Provides multiple feedback mechanisms such as visual and auditory feedback, and seamlessly switches to backup control mode when the system malfunctions, ensuring control reliability.
[0018] Thanks to the above-mentioned technical solutions, the problem of accidental touches on the touchpad in scenarios such as typing is fundamentally avoided through multi-dimensional sensing and intelligent recognition; automatic perception and seamless control are achieved in scenarios such as opening the lid, leaving, and logging in, simplifying user operations; at the same time, touch parameters are adaptively adjusted according to user habits and environmental changes, improving personalized experience and operational efficiency; in addition, intelligent sleep and wake-up strategies effectively reduce standby power consumption, and feedback and anomaly handling mechanisms ensure that control is always reliable. Attached Figure Description
[0019] Figure 1 This is an overall flowchart of the intelligent control method for touch interaction on a laptop computer according to the present invention; Figure 2 This is a schematic diagram of the layout of the three-dimensional sensor array of the present invention on a laptop computer; Figure 3This is a schematic diagram of the architecture of the signal preprocessing and scene recognition module of the present invention; Figure 4 This is an example diagram of the scenario-based refined control logic of the present invention. Detailed Implementation
[0020] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The embodiments are only intended to provide a clearer understanding of the technical features, objectives and effects of the present invention.
[0021] This application discloses a smart control method for touch interaction on a laptop computer, including the following steps: Step S1: Simultaneously acquire multi-source sensor signals using a three-dimensional sensor array deployed on a laptop computer; Step S2: Perform three-level anti-interference and normalization preprocessing on the multi-source sensor signals to generate a standardized data matrix; Step S3: Input the standardized data matrix into the machine learning-based scene recognition model, and combine it with the user's historical operation data to identify the current user scenario; Step S4: Based on the identified usage scenario, execute the corresponding refined touch interaction control operation; Step S5: Collect user touch operation data and environmental parameters in real time, dynamically adjust touch sensitivity and perform full-scene sensor calibration; Step S6: After performing the control operation, provide multiple feedbacks and switch to the standby control mode when an anomaly is detected.
[0022] The three-dimensional sensor array includes: At least two sets of high-precision infrared sensors are arranged between the keyboard and the touchpad; a dual-axis angle sensor is arranged at the hinge of the device; multiple sets of capacitive sensors are evenly distributed along the edge of the touchpad; an ambient light sensor and a temperature sensor are arranged at the palm rest of the device; and each sensor collects data using a synchronous triggering mechanism.
[0023] The scene recognition model is a lightweight model optimized based on convolutional neural networks, which can identify multiple scenarios, including keyboard intensive use scenarios, touchpad exclusive use scenarios, opening the lid to wake up scenarios, temporary absence and sleep scenarios, password login scenarios, and idle scenarios; the model can be dynamically iteratively optimized based on the user's historical operation data.
[0024] The three-level anti-interference processing in step S2 includes: First stage: Low-pass filtering is used to remove power frequency and environmental noise interference; Second stage: Adaptive threshold filtering is used to dynamically adjust the filtering threshold according to ambient temperature and light intensity; Third stage: Cross-validation and fusion of infrared and capacitance signals are performed to remove invalid signals.
[0025] Step S4 includes: In scenarios involving intensive keyboard use, the touchpad is automatically turned on and off based on the frequency of keyboard input. In the scenario of waking up from an open lid, the system performs graded wake-up and display brightness adjustment based on the opening angle and ambient light intensity. When leaving the hibernation scenario, hibernation control is implemented based on user distance, duration, and operation status. In password login scenarios, the password input is verified and the touchpad status and feedback prompts are controlled in conjunction with it.
[0026] Step S5 includes: Based on long-term user touch operation data, users are classified using clustering algorithms, and touch sensitivity and response speed are adjusted for different user types; the sensitivity thresholds of infrared and capacitive sensors are automatically calibrated according to changes in ambient temperature; and all sensors are automatically and comprehensively calibrated periodically.
[0027] The multiple feedbacks in step S6 include indicator light status, tiered prompt sounds, and optional screen pop-ups; the backup control mode is activated when a sensor or main control chip malfunction is detected, and manual control has the highest priority.
[0028] This application also discloses a laptop computer, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the laptop computer touch interaction intelligent control method as described above.
[0029] Example 1: This embodiment provides a smart control method for touch interaction on a laptop computer, applied to a Soworth laptop computer equipped with the aforementioned three-dimensional sensor array and main control chip.
[0030] like Figure 1 As shown, the method flow is as follows: (1) When the system is powered on and initialized, all sensors are triggered synchronously with a period of 10ms to start collecting data.
[0031] (2) The acquired raw signals are sent to the preprocessing unit of the main control chip. First, a low-pass filter with a frequency set to 100Hz is used to remove power frequency interference. Then, based on the current temperature sensor reading (e.g., 25℃) and light sensor reading (e.g., 300 lux), an adaptive filtering threshold is dynamically calculated and applied. Finally, the infrared array signal and the capacitor array signal are time-aligned and cross-checked to remove abnormal data points caused by instantaneous interference. All valid signals are normalized to the [0,1] interval to form a 10×12 standardized data matrix (assuming 12 types of features are extracted).
[0032] (3) Input the data matrix together with the user's operation logs for the past 30 days (such as average key frequency, touch interval, etc.) retrieved from the local encrypted storage area into the pre-trained lightweight CNN scene recognition model. The model outputs the probability distribution of the current scene, and takes the scene corresponding to the highest probability as the recognition result, such as "keyboard intensive use scene".
[0033] (4) Execute control based on recognition results: If it is a "keyboard intensive use scenario" and continuous keyboard operation is detected without effective touch signal, the touchpad is turned off immediately. At the same time, monitor the real-time key frequency: if the key frequency is ≥5 times / second, the touchpad is turned on again after a delay of 8 seconds after the last keyboard operation; if the key frequency is low, it is turned on after a delay of 3 seconds.
[0034] (5) During user usage, the background continuously records data such as touch pressure and area preference. Every 24 hours, the K-means algorithm is used to cluster recent data, accurately update user type labels, and fine-tune the touchpad sensitivity parameter by 5% accordingly.
[0035] (6) Read the temperature sensor data once per hour. If the ambient temperature changes by more than 5°C compared to the last calibration reference, adjust the detection threshold of the infrared and capacitive sensors according to the preset ratio.
[0036] (7) After any control operation is performed, corresponding feedback will be given through the LED indicator on the device and the mini speaker. Users can also enable on-screen pop-up prompts in the settings.
[0037] (8) The system continuously monitors the sensor data stream and the status of the main control chip. If a sensor signal is continuously lost abnormally or the processor load is abnormal, the error code is immediately recorded in the log, and the highest priority control of the touchpad is automatically returned to the user for manual switching. At the same time, the red indicator light flashes rapidly at a frequency of 2Hz to sound an alarm until the fault is cleared.
[0038] Through the above process, the laptop can intelligently adapt to user behavior and provide a precise, smooth, and energy-efficient touch interaction experience in various scenarios.
Claims
1. A smart control method for touch interaction on a laptop computer, characterized in that, Includes the following steps: Step S1: Simultaneously acquire multi-source sensor signals using a three-dimensional sensor array deployed on a laptop computer; Step S2: Perform three-level anti-interference and normalization preprocessing on the multi-source sensor signals to generate a standardized data matrix; Step S3: Input the standardized data matrix into the machine learning-based scene recognition model, and combine it with the user's historical operation data to identify the current user scenario; Step S4: Based on the identified usage scenario, execute the corresponding refined touch interaction control operation; Step S5: Collect user touch operation data and environmental parameters in real time, dynamically adjust touch sensitivity and perform full-scene sensor calibration; Step S6: After performing the control operation, provide multiple feedbacks and switch to the standby control mode when an anomaly is detected.
2. The intelligent control method for touch interaction of a laptop computer according to claim 1, characterized in that, The three-dimensional sensor array includes: At least two sets of high-precision infrared sensors are arranged between the keyboard and the touchpad; A dual-axis angle sensor is positioned at the fuselage pivot. Multiple sets of capacitive sensing sensors are evenly distributed along the edge of the touchpad; An ambient light sensor and a temperature sensor are located on the palm rest of the device. Each sensor acquires data using a synchronous triggering mechanism.
3. The intelligent control method for touch interaction of a laptop computer according to claim 1, characterized in that, The three-level anti-interference processing in step S2 includes: First stage: Low-pass filtering is used to remove power frequency and environmental noise interference; The second level: Adaptive threshold filtering is used, which dynamically adjusts the filtering threshold according to ambient temperature and light intensity; Level 3: Cross-validate and fuse infrared and capacitive signals to remove invalid signals.
4. The intelligent control method for touch interaction of a laptop computer according to claim 1, characterized in that, The scene recognition model is a lightweight model optimized based on convolutional neural networks, which can recognize multiple scenarios including keyboard intensive use scenarios, touchpad exclusive use scenarios, opening the lid to wake up scenarios, temporary absence and sleep scenarios, password login scenarios, and idle scenarios; the model can be dynamically iteratively optimized based on the user's historical operation data.
5. The intelligent control method for touch interaction of a laptop computer according to claim 4, characterized in that, Step S4 includes: In scenarios involving intensive keyboard use, the touchpad is automatically turned on and off based on the frequency of keyboard input. In the scenario of waking up from an open lid, the system performs graded wake-up and display brightness adjustment based on the opening angle and ambient light intensity. When leaving the hibernation scenario, hibernation control is implemented based on user distance, duration, and operation status. In password login scenarios, the password input is verified and the touchpad status and feedback prompts are controlled in conjunction with it.
6. The intelligent control method for touch interaction of a laptop computer according to claim 1, characterized in that, Step S5 includes: Based on long-term user touch operation data, users are classified using clustering algorithms, and touch sensitivity and response speed are adjusted for different types of users. The sensitivity thresholds of the infrared and capacitive sensors are automatically calibrated based on changes in ambient temperature. Perform automatic full calibration of all sensors regularly.
7. The intelligent control method for touch interaction of a laptop computer according to claim 1, characterized in that, The multiple feedbacks in step S6 include indicator light status, tiered prompt sounds, and optional screen pop-ups; the backup control mode is activated when a sensor or main control chip malfunction is detected, and manual control has the highest priority.
8. A laptop computer, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the laptop computer touch interaction intelligent control method as described in any one of claims 1 to 7.