Intelligent watch control method based on human-computer interaction and intelligent watch

Abstract

The invention discloses an intelligent watch control method based on human-computer interaction and an intelligent watch, particularly relates to the technical field of watch control, and is used for solving the technical problem of offset of touch coordinates and display coordinates caused by physical deformation of a flexible screen in the prior art. A curvature parameter and a stretching parameter of a screen deformation area are detected in real time, a touch pressure propagation attenuation gradient is combined to analyze a touch actual action area, a pressure distribution symmetry characteristic is extracted to judge a force application direction, a dynamic offset trend of the deformation area is predicted, and a dynamic mapping relation matrix of touch coordinates and display coordinates is constructed. Target display coordinates are calibrated in real time, and a display layer is driven to respond to a touch instruction; based on the dynamic coupling relationship between the deformation parameter and the touch behavior, the touch coordinate mapping rule is adaptively adjusted through a closed-loop feedback mechanism, and the touch positioning precision and the interaction reliability of the flexible screen in a dynamic deformation scene are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of watch control, and more specifically, the present invention relates to an intelligent watch control method and an intelligent watch based on human-computer interaction. Background Art

[0002] An intelligent watch can adopt a flexible display screen to improve the wearing comfort and interaction experience. The flexible screen can conform to the wrist curve and support more natural touch operations, such as swiping, tapping, and gesture recognition, becoming an important carrier for human-computer interaction. However, during dynamic use, the physical deformation of the flexible screen caused by external forces poses new technical challenges to the coordinate mapping relationship between touch detection and the display interface. Usually, the touch calibration scheme based on a fixed-form screen is difficult to meet the interaction requirements in the real-time deformation scenario of the flexible screen.

[0003] Due to the non-linear offset between the touch layer and the display layer of the flexible screen in the deformed state, there is a significant deviation between the user's touch position and the device's response position. This deviation is particularly obvious in dynamic interaction scenarios (such as wrist bending and local stretching of the screen), seriously reducing the accuracy and reliability of touch operations. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent watch control method and an intelligent watch based on human-computer interaction to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: An intelligent watch control method based on human-computer interaction, comprising the following steps: S1. Real-time detect the curvature parameter and stretching parameter of the screen deformation area; S2. Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameter and the stretching parameter, and determine the actual action area of the touch operation; S3. Extract the symmetry feature of the pressure distribution of the user's touch operation, and judge the force application direction of the touch operation according to the symmetry feature of the pressure distribution; S4. Predict the dynamic offset trend of the screen deformation area according to the force application direction and the concentration degree of the touch area; S5. Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual action area and the dynamic offset trend; S6. Real-time calibrate the target display coordinates according to the current touch coordinates and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch command corresponding to the target display coordinates.

[0006] In a preferred embodiment, the curvature parameters and stretching parameters of the screen deformation area are detected in real time, including: Detect the initial curvature parameters of the deformation area through the strain sensor array at the edge of the flexible screen; In the initial stage of deformation, activate the capacitive sensor array based on the initial curvature parameters and the preset deformation threshold; Collect the real-time stretching parameters of the deformation area through the capacitive sensor array; Generate a curvature parameter correction value for the deformation area according to the dynamic relationship between the real-time stretching parameters and the initial curvature parameters; Update the curvature parameters of the deformation area based on the curvature parameter correction value and feedback to the capacitive sensor array to adjust the detection frequency.

[0007] In a preferred embodiment, obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameters and stretching parameters, and determine the actual action area of the touch operation, including: Detect the pressure distribution data of the touch operation through the pressure sensor array, which is composed of multiple metal piezoresistors and distributed under the display layer of the flexible screen; Divide the physical deformation level of the screen deformation area according to the curvature parameters and stretching parameters, and match the corresponding relationship table between the preset deformation level and the pressure propagation attenuation gradient; Calculate the propagation attenuation rate of the touch pressure in the screen deformation area based on the pressure distribution data, and generate the propagation attenuation gradient in combination with the corresponding relationship table; Extract the coordinates of the pressure center point in the pressure distribution data, superimpose the curvature parameter correction value and the propagation attenuation gradient of the deformation area, and calculate the coordinate offset of the touch pressure action area; Screen the effective action area according to the coordinate offset and the preset gradient threshold, and determine the coordinate range of the actual action area of the touch operation.

[0008] In a preferred embodiment, extract the pressure distribution symmetry characteristics of the user's touch operation, and judge the force application direction of the touch operation according to the pressure distribution symmetry characteristics, including: Based on the pressure distribution data detected by the pressure sensor array, extract the distribution difference of the pressure values in the X-axis and Y-axis directions in the screen plane, and generate a pressure distribution symmetry parameter; Calculate the main axis direction of the pressure value distribution according to the pressure distribution symmetry parameter; Combine the curvature parameter correction value of the deformation area, adjust the calculation weight of the main axis direction, and generate a corrected main axis direction; Based on the corrected main axis direction and the preset direction determination threshold, judge that the force application direction of the touch operation is tilted to the left, tilted to the right, or vertically pressed; Associate the force application direction with the concentration of the touch area, and correct the determination result of the force application direction.

[0009] In a preferred embodiment, the main axis direction is the extending direction with the largest ratio of the distribution variances of the pressure values along the X-axis and the Y-axis.

[0010] In a preferred embodiment, according to the concentration of the force application direction and the touch area, predict the dynamic offset trend of the screen deformation area, including: Convert the force application direction into the offset direction of the screen deformation area; Determine the deformation diffusion rate according to the concentration of the touch area. The higher the concentration of the touch area, the greater the deformation diffusion rate. The deformation diffusion rate is obtained by matching through a preset concentration-rate correspondence table; Combine the offset direction and the deformation diffusion rate to generate a dynamic offset vector. The magnitude of the dynamic offset vector is the product of the deformation diffusion rate and the preset time step, and the direction is the offset direction; Based on the curvature parameter correction value of the deformation area, adjust the magnitude weight of the dynamic offset vector to generate a corrected dynamic offset vector; According to the sequence of dynamic offset vectors of the historical deformation area, predict the dynamic offset trend of the screen deformation area.

[0011] In a preferred embodiment, the offset direction is the opposite direction of the force application direction, and the offset angle is proportional to the tilt angle of the force application direction.

[0012] In a preferred embodiment, based on the actual acting area and the dynamic offset trend, construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates, including: Based on the coordinate range of the actual acting area of the touch operation, determine the conversion relationship between the touch coordinates and the display coordinates. The conversion relationship includes the scaling coefficient and the offset compensation amount of the touch coordinates; According to the predicted dynamic offset trend, adjust the weight ratio of the scaling coefficient and the offset compensation amount to generate dynamic conversion parameters; Combine the dynamic conversion parameters and the preset deformation compensation rules to construct a dynamic mapping relationship matrix. The preset deformation compensation rules are generated by experimentally calibrating the error distribution between the touch coordinates and the display coordinates under different deformation levels; Based on the dynamic mapping relationship matrix, associate the coordinate offset amount of the touch coordinates with the compensation amount of the display coordinates to generate a real-time mapping relationship from the touch coordinates to the display coordinates; Update the dynamic mapping relationship matrix to the touch response instruction parsing unit to drive the display layer to execute coordinate mapping.

[0013] In a preferred embodiment, according to the current touch coordinates and the dynamic mapping relationship matrix, calibrate the target display coordinates in real time, and drive the display layer to respond to the touch instruction corresponding to the target display coordinates, including: Extract the coordinate offset of the current touch coordinate based on the coordinate range of the actual action area of the touch operation; Match the scaling coefficient and offset compensation amount corresponding to the current touch coordinate according to the constructed dynamic mapping relationship matrix; Generate calibration parameters for the touch coordinate according to the scaling coefficient and offset compensation amount, and the calibration parameters include the horizontal calibration amount and the vertical calibration amount; Perform real-time compensation on the current touch coordinate based on the calibration parameters to generate the target display coordinate; Input the target display coordinate into the touch response instruction parsing unit to drive the display layer to execute the touch instruction; Update the calibration parameter weight of the dynamic mapping relationship matrix according to the pressure distribution symmetry feature and the force application direction of the touch operation.

[0014] On the other hand, the present invention provides an intelligent watch based on human-computer interaction, including: Deformation detection module: Real-time detect the curvature parameter and stretching parameter of the screen deformation area; Pressure propagation module: Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameter and stretching parameter, and determine the actual action area of the touch operation; Force application analysis module: Extract the pressure distribution symmetry feature of the user's touch operation, and judge the force application direction of the touch operation according to the pressure distribution symmetry feature; Dynamic prediction module: Predict the dynamic offset trend of the screen deformation area according to the force application direction and the concentration degree of the touch area; Coordinate mapping module: Construct a dynamic mapping relationship matrix between the touch coordinate and the display coordinate based on the actual action area and the dynamic offset trend; Calibration driving module: Real-time calibrate the target display coordinate according to the current touch coordinate and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch instruction corresponding to the target display coordinate.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. By dynamically perceiving the coupling relationship between the screen deformation state and the touch behavior, the touch accuracy and response speed of the flexible screen in the dynamic deformation scenario are significantly improved. Based on the real-time detected curvature parameter and stretching parameter, combined with the analysis of the pressure propagation attenuation gradient, it is possible to accurately distinguish the physical transmission characteristics of the touch pressure in the flexible screen deformation area, effectively eliminating the touch signal offset error caused by local bending or stretching of the screen; Through the joint judgment of the pressure distribution symmetry feature and the force application direction, not only can the user's touch intention be accurately identified, but also the influence of the deformation trend on the touch positioning can be predicted, realizing the dynamic pre-compensation of the touch coordinate; 2. Combine the touch area concentration with the prediction of dynamic offset trends to form a coordinate mapping mechanism with self-learning ability. Through the dynamically generated mapping relationship matrix in real time, intelligently adjust the matching rules of touch and display coordinates, so that the flexible screen can still maintain the spatial consistency between the touch point and the display interface during the continuous deformation process. It is especially suitable for multi-angle and high-frequency touch interactions in scenarios with frequent wrist movements, effectively avoiding false touches and positioning drift while ensuring touch sensitivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of an intelligent watch control method based on human-computer interaction according to the present invention; Figure 2 is a schematic structural diagram of an intelligent watch based on human-computer interaction according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1: Figure 1 An intelligent watch control method based on human-computer interaction according to the present invention is given, which includes the following steps: S1. Real-time detect the curvature parameter and stretching parameter of the screen deformation area; S2. Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameter and stretching parameter, and determine the actual action area of the touch operation; S3. Extract the pressure distribution symmetry feature of the user's touch operation, and judge the force application direction of the touch operation according to the pressure distribution symmetry feature; S4. Predict the dynamic offset trend of the screen deformation area according to the force application direction and the concentration of the touch area; S5. Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual action area and the dynamic offset trend; S6. Real-time calibrate the target display coordinates according to the current touch coordinates and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch command corresponding to the target display coordinates.

[0019] S1. Real-time detect the curvature parameter and stretching parameter of the screen deformation area, including: Detect the initial curvature parameter of the deformation area through the strain sensor array at the edge of the flexible screen; In the initial stage of deformation, activate the capacitive sensor array based on the initial curvature parameter and the preset deformation threshold; Collect the real-time stretching parameters of the deformed area through the capacitive sensor array; Generate a curvature parameter correction value for the deformed area according to the dynamic relationship between the real-time stretching parameter and the initial curvature parameter; Update the curvature parameter of the deformed area based on the curvature parameter correction value and feedback it to the capacitive sensor array to adjust the detection frequency.

[0020] Detect the initial curvature parameter of the deformed area through the strain sensor array at the edge of the flexible screen. The strain sensor array consists of multiple metal strain gauges evenly distributed at equal intervals. Each strain gauge generates a resistance change when the screen deforms. Calculate the initial curvature parameter by measuring the resistance change value. The calculation method of the initial curvature parameter is to match the resistance change difference between two adjacent strain gauges in the same deformed area with the preset resistance-curvature mapping relationship table to obtain the initial curvature parameter. The resistance-curvature mapping relationship table is obtained through experimental calibration. The experimental calibration method includes applying a deformation with a known curvature value to the flexible screen and recording the resistance change values of the corresponding strain gauges to generate the mapping table.

[0021] In the initial stage of deformation, activate the capacitive sensor array based on the initial curvature parameter and the preset deformation threshold. The preset deformation threshold is the critical curvature parameter calibrated in advance. When the initial curvature parameter exceeds this critical value, it is determined that the screen enters the initial stage of deformation and triggers the activation of the capacitive sensor array. The capacitive sensor array consists of multiple parallel electrodes, and the parallel electrodes are evenly embedded under the display layer of the flexible screen. The specific method of activating the capacitive sensor array is to apply an excitation signal with a fixed frequency to the parallel electrodes and detect the capacitance change value between adjacent electrodes. The preset deformation threshold is determined through experimental calibration. The experimental calibration method includes applying deformations with different curvature values to the flexible screen and recording the critical curvature value at which the touch operation error increases significantly as the threshold.

[0022] Collect the real-time stretching parameters of the deformed area through the capacitive sensor array. The real-time stretching parameters include the stretching length and stretching direction of the screen deformed area. The calculation method of the stretching length is to calculate the increment of the electrode spacing according to the capacitance change value between adjacent electrodes in the capacitive sensor array and match the electrode spacing increment with the preset capacitance-stretching mapping relationship table to obtain the stretching length. The calculation method of the stretching direction is to select three adjacent electrodes with the largest capacitance change value and determine the stretching direction vector according to their positional relationship. The capacitance-stretching mapping relationship table is obtained through experimental calibration. The experimental calibration method includes applying deformations with known stretching lengths and directions to the flexible screen and recording the capacitance change values of the corresponding electrodes to generate the mapping table.

[0023] Generate a curvature parameter correction value for the deformation region based on the dynamic relationship between the real-time stretching parameters and the initial curvature parameters. The dynamic relationship is the correlation function between the pre-calibrated curvature parameters and the stretching parameters, which is obtained through experimental calibration. The experimental calibration method includes applying combined deformations with different curvature values and stretching parameters to the flexible screen simultaneously and recording the corresponding touch coordinate offsets, and fitting the weight coefficients of the curvature parameters and the stretching parameters for the offsets to generate the correlation function. The specific way to generate the curvature parameter correction value is to input the stretching length and stretching direction in the real-time stretching parameters into the correlation function and calculate the compensation amount for the initial curvature parameters to obtain the curvature parameter correction value.

[0024] Update the curvature parameters of the deformation region based on the curvature parameter correction value and feedback it to the capacitive sensor array to adjust the detection frequency. The way to update the curvature parameters is to add the initial curvature parameters and the curvature parameter correction value to obtain the updated curvature parameters. The way to feedback and adjust the detection frequency is to adjust the excitation signal frequency of the capacitive sensor array according to the corresponding relationship between the updated curvature parameters and the preset curvature interval. The corresponding relationship between the preset curvature interval and the detection frequency is determined through experimental calibration. The experimental calibration method includes testing the capacitance detection accuracy at different excitation frequencies within a specific curvature interval and selecting the frequency with the highest accuracy as the detection frequency for this interval.

[0025] S2. Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation region by combining the curvature parameters and the stretching parameters, and determine the actual action region of the touch operation, including: Detect the pressure distribution data of the touch operation through the pressure sensor array, which is composed of multiple metal piezoresistors and is distributed under the display layer of the flexible screen; Divide the physical deformation levels of the screen deformation region according to the curvature parameters and the stretching parameters, and match the corresponding relationship table between the preset deformation levels and the pressure propagation attenuation gradients; Calculate the propagation attenuation rate of the touch pressure in the screen deformation region based on the pressure distribution data, and generate the propagation attenuation gradient by combining the corresponding relationship table; Extract the coordinates of the pressure center point in the pressure distribution data, superimpose the curvature parameter correction value of the deformation region and the propagation attenuation gradient, and calculate the coordinate offset of the touch pressure action region; Screen the effective action regions according to the coordinate offset and the preset gradient threshold, and determine the coordinate range of the actual action region of the touch operation.

[0026] The pressure distribution data of the touch operation is detected by a pressure sensor array. The pressure sensor array is composed of multiple metal piezoresistors and is distributed under the flexible screen display layer. The metal piezoresistors deform under the action of touch pressure and generate resistance value changes. The pressure distribution data is generated by measuring the resistance value changes. The pressure distribution data includes the pressure values at the positions of each metal piezoresistor. The calculation method of the pressure value is to match the resistance value change with a preset resistance-pressure mapping relation table to obtain the pressure value. The resistance-pressure mapping relation table is obtained through experimental calibration. The experimental calibration method includes applying a touch operation with a known pressure value to the flexible screen and recording the resistance change values of the corresponding metal piezoresistors to generate a mapping table.

[0027] The physical deformation levels of the screen deformation areas are divided according to the curvature parameter and the stretching parameter. The curvature parameter is the curvature parameter detected and updated by the strain sensor array, and the stretching parameter is the real-time stretching parameter collected by the capacitance sensor array. The division method of the physical deformation levels is to match the curvature parameter and the stretching parameter with the preset curvature grading intervals and stretching grading intervals respectively to determine the deformation level combination of the deformation area. The preset curvature grading intervals and stretching grading intervals are obtained through experimental calibration. The experimental calibration method includes applying deformations with different curvature values and stretching parameters to the flexible screen and recording the mutation critical points of the touch coordinate offsets to generate grading intervals.

[0028] Match the corresponding relation table between the preset deformation levels and the pressure propagation attenuation gradients. The corresponding relation table is obtained through experimental calibration. The experimental calibration method includes applying deformations with different deformation level combinations to the flexible screen and applying touch pressure, measuring the pressure value attenuation rate when the touch pressure propagates from the pressure center point to the screen edge, and recording the corresponding relation between the deformation level combination and the attenuation rate to generate the corresponding relation table. The pressure propagation attenuation gradient is a quantization parameter generated according to the attenuation rate.

[0029] Based on the pressure distribution data, calculate the propagation attenuation rate of the touch pressure in the screen deformation area. The calculation method is to select the position with the largest pressure value in the pressure distribution data as the pressure center point, measure the pressure value drop ratio of the adjacent metal piezoresistors in the direction from the pressure center point to the screen edge, and match the pressure value drop ratio with a preset propagation distance-attenuation rate mapping relation table to obtain the propagation attenuation rate. The propagation distance-attenuation rate mapping relation table is obtained through experimental calibration. The experimental calibration method includes applying touch pressure in the undeformed state and recording the pressure value drop ratios corresponding to different propagation distances to generate a mapping table.

[0030] The propagation attenuation gradient is generated in combination with the correspondence table. The generation method is to query the correspondence table according to the deformation level combination of the current deformation area to obtain the benchmark attenuation rate, and the benchmark attenuation rate is weighted and summed with the real-time calculated propagation attenuation rate to obtain the propagation attenuation gradient. The weighting coefficient is determined through experimental calibration. The experimental calibration method includes testing the influence of the weighting coefficient on the touch coordinate calibration accuracy under different deformation levels and selecting the optimal coefficient.

[0031] The coordinates of the pressure center point in the pressure distribution data are extracted. The coordinates of the pressure center point are calculated by selecting the position coordinates of the metal varistor with the largest pressure value in the pressure distribution data as the initial pressure center point, calculating the pressure center point offset according to the pressure value distribution of adjacent metal varistors around the initial pressure center point, and adding the initial pressure center point coordinates and the offset to obtain the final pressure center point coordinates.

[0032] The curvature parameter correction value of the deformation area and the propagation attenuation gradient are superimposed to calculate the coordinate offset of the touch pressure action area. The superposition method is to add the curvature compensation in the curvature parameter correction value and the gradient compensation in the propagation attenuation gradient according to a preset ratio to obtain a total compensation. The total compensation is multiplied by the coordinates of the pressure center point to obtain the coordinate offset. The preset ratio is obtained through experimental calibration. The experimental calibration method includes testing the influence of the ratio value on the touch coordinate calibration accuracy under different deformation levels and selecting the optimal ratio.

[0033] The effective action area is screened according to the coordinate offset and the preset gradient threshold. The preset gradient threshold is the critical value of the touch coordinate offset calibrated by experiments. When the coordinate offset exceeds the preset gradient threshold, the current touch pressure action area is determined to be the effective action area. The coordinate range of the effective action area is the coordinate interval after the coordinates of the pressure center point are superimposed with the coordinate offset. The calibration method of the preset gradient threshold includes testing the minimum recognizable error of the touch operation under different deformation levels and setting the threshold.

[0034] Determine the coordinate range of the actual effective area of ​​the touch operation. The coordinate range of the actual effective area is calculated by matching the coordinate interval of the effective effective area with the physical boundary coordinates of the screen display layer, eliminating invalid coordinate points beyond the screen boundary, and generating the final coordinate range of the actual effective area.

[0035] S3, extracting the symmetry characteristics of the pressure distribution of the user's touch operation, and determining the force direction of the touch operation according to the symmetry characteristics of the pressure distribution, including: Based on the pressure distribution data detected by the pressure sensor array, the distribution difference of the pressure value in the X-axis and Y-axis directions in the screen plane is extracted to generate the pressure distribution symmetry parameter; Calculate the principal axis direction of the pressure value distribution according to the pressure distribution symmetry parameter. The principal axis direction is the extension direction with the largest ratio of the distribution variances of the pressure values along the X-axis and the Y-axis. Adjust the calculation weight of the principal axis direction in combination with the curvature parameter correction value of the deformation area to generate the corrected principal axis direction. Based on the corrected principal axis direction and the preset direction determination threshold, determine whether the force application direction of the touch operation is tilted to the left, tilted to the right, or vertically pressed. Associate the force application direction with the touch area concentration to correct the determination result of the force application direction.

[0036] Extract the distribution difference of the pressure values in the X-axis and Y-axis directions in the screen plane from the pressure distribution data detected by the pressure sensor array to generate the pressure distribution symmetry parameter. The calculation method of the pressure distribution symmetry parameter is to separately count the total difference of the pressure values of adjacent metal piezoresistors in the X-axis and Y-axis directions, and use the ratio of the total difference value in the X-axis direction to the total difference value in the Y-axis direction as the symmetry parameter. The total difference value in the X-axis direction is the cumulative value of the absolute values of the differences between the pressure values of the metal piezoresistors at symmetric positions on the left and right sides of the screen, and the total difference value in the Y-axis direction is the cumulative value of the absolute values of the differences between the pressure values of the metal piezoresistors at symmetric positions on the upper and lower sides of the screen.

[0037] Calculate the principal axis direction of the pressure value distribution according to the pressure distribution symmetry parameter. The principal axis direction is the extension direction with the largest ratio of the distribution variances of the pressure values along the X-axis and the Y-axis. The calculation method of the distribution variance ratio is to select the metal piezoresistors within a preset radius range around the pressure center point, calculate the ratio of the variance of the pressure values in the X-axis direction to the variance of the pressure values in the Y-axis direction respectively, and determine the angle corresponding to the maximum value as the principal axis direction by traversing the variance ratios in different angular directions. The preset radius range is determined by experimental calibration. The experimental calibration method includes testing the influence of the radius range on the determination accuracy of the force application direction under different touch area concentrations and selecting the optimal value.

[0038] Adjust the calculation weight of the principal axis direction in combination with the curvature parameter correction value of the deformation area to generate the corrected principal axis direction. The specific way to adjust the weight is to convert the curvature compensation amount in the curvature parameter correction value into the weight correction coefficients in the X-axis and Y-axis directions. The calculation method of the weight correction coefficients is to match the curvature compensation amount with the preset curvature-weight mapping relationship table to obtain the weight ratios of the X-axis and Y-axis, and perform weighted calculation on the weight ratios and the original distribution variance ratio to obtain the corrected distribution variance ratio, and then re-determine the principal axis direction. The preset curvature-weight mapping relationship table is obtained through experimental calibration. The experimental calibration method includes applying deformations with different curvature values to the flexible screen and testing the determination error of the force application direction to generate the optimal weight ratio.

[0039] Based on the corrected main axis direction and the preset direction determination threshold, determine whether the force application direction of the touch operation is tilted to the left, tilted to the right, or vertically pressed. The preset direction determination threshold is the critical value of the main axis direction angle calibrated through experiments. When the angle between the corrected main axis direction and the positive direction of the X-axis is less than the first threshold, it is determined to be tilted to the right; when it is greater than the second threshold, it is determined to be tilted to the left; when it is between the first threshold and the second threshold, it is determined to be vertically pressed. The first threshold and the second threshold are determined through experimental calibration. The experimental calibration method includes collecting touch data in the typical force application directions of users and statistically setting the threshold based on the angle distribution density.

[0040] Associate the force application direction with the touch area concentration to correct the determination result of the force application direction. The touch area concentration is a density parameter of the touch pressure action area calculated from the pressure distribution data. The correction method is to adjust the interval range of the direction determination threshold according to the touch area concentration. When the touch area concentration is higher than the preset density threshold, narrow the interval range of the direction determination threshold to improve the determination sensitivity; when the touch area concentration is lower than the preset density threshold, widen the interval range of the direction determination threshold to reduce the misjudgment rate. The preset density threshold is determined through experimental calibration. The experimental calibration method includes testing the influence of the touch area concentration on the misjudgment rate of the force application direction under different deformation levels and setting the threshold.

[0041] S4. Predict the dynamic offset trend of the screen deformation area according to the force application direction and the concentration of the touch area, including: Convert the force application direction into the offset direction of the screen deformation area. The offset direction is the opposite direction of the force application direction, and the offset angle is proportional to the tilt angle of the force application direction. Determine the deformation diffusion rate according to the touch area concentration. The higher the touch area concentration, the greater the deformation diffusion rate. The deformation diffusion rate is obtained by matching through a preset concentration-rate correspondence table. Generate a dynamic offset vector by combining the offset direction and the deformation diffusion rate. The magnitude of the dynamic offset vector is the product of the deformation diffusion rate and the preset time step length, and the direction is the offset direction. Based on the correction value of the curvature parameter of the deformation area, adjust the magnitude weight of the dynamic offset vector to generate a corrected dynamic offset vector. Predict the dynamic offset trend of the screen deformation area according to the sequence of dynamic offset vectors of the historical deformation area.

[0042] Convert the force application direction into the offset direction of the screen deformation area. The offset direction is the opposite of the force application direction, and the offset angle is proportional to the tilt angle of the force application direction. For example, when the user presses the screen with a 30-degree tilt to the right, the offset direction of the deformation area is tilted to the left, and the offset angle is 30 degrees multiplied by a preset proportionality coefficient. The preset proportionality coefficient is determined through experimental calibration. The experimental calibration method includes applying force application directions with different tilt angles to the flexible screen and measuring the actual deformation offset angle, fitting the linear relationship between the force application angle and the offset angle to generate the proportionality coefficient. The value range of the proportionality coefficient is set according to the hardness of the screen material. A smaller value (such as 0.8) is taken for hard materials, and a larger value (such as 1.2) is taken for soft materials.

[0043] Determine the deformation diffusion rate according to the touch area concentration. The higher the touch area concentration, the greater the deformation diffusion rate. For example, when the user presses with a single finger (high concentration), the deformation diffusion rate is to spread to the adjacent 5 pixel areas per second, while when pressing with the palm (low concentration), the diffusion rate is to spread to the adjacent 2 pixel areas per second. The deformation diffusion rate is obtained by matching through a preset concentration-rate correspondence table. The preset concentration-rate correspondence table is generated through experimental calibration. The experimental calibration method includes applying touch operations with different touch area concentrations to the flexible screen and measuring the deformation diffusion speed. For example, applying a single-point press in the center area of the screen to record the diffusion speed, and applying a multi-point press in the edge area to record the diffusion speed, and generating a mapping table of concentration and diffusion speed.

[0044] Combine the offset direction and the deformation diffusion rate to generate a dynamic offset vector. The magnitude of the dynamic offset vector is the product of the deformation diffusion rate and the preset time step, and the direction is the offset direction. For example, if the preset time step is 100 milliseconds and the deformation diffusion rate is 5 pixels per second, the magnitude is 0.5 pixels, and the direction of the dynamic offset vector is tilted 30 degrees to the left. The preset time step is determined through experimental calibration. The experimental calibration method includes testing the balance relationship between the deformation prediction accuracy and the touch response delay at different time intervals. For example, when the time step is too short (such as 50 milliseconds), it causes prediction jitter, or when it is too long (such as 200 milliseconds), it causes response lag, and 100 milliseconds is selected as the optimal value.

[0045] Adjust the magnitude weight of the dynamic offset vector based on the curvature parameter correction value of the deformation region to generate a corrected dynamic offset vector. For example, when the curvature parameter correction value indicates that the current deformation curvature of the screen is large, the magnitude weight coefficient is adjusted to 1.1 to increase the compensation amount, and when the curvature is small, it is adjusted to 0.9 to reduce overcompensation. The magnitude weight coefficient is obtained by matching through a preset curvature-weight mapping relationship table, and the preset curvature-weight mapping relationship table is generated through experimental calibration. The experimental calibration method includes applying deformations with different curvature values to the flexible screen and testing the influence of the magnitude weight on the deformation prediction accuracy. For example, when the curvature value is 0.5, test the compensation effects of weight coefficients from 0.8 to 1.2, and select the coefficient value with the smallest error to generate the mapping table.

[0046] Predict the dynamic offset trend of the screen deformation region based on the sequence of dynamic offset vectors in the historical deformation region. For example, if the dynamic offset vectors in the previous 3 time steps before the current moment are 0.4 pixels to the left, 0.5 pixels to the left, and 0.6 pixels to the left respectively, then the prediction trend is to offset to the left and the magnitude gradually increases. The prediction method is to perform a weighted average calculation on the historical dynamic offset vector sequence, and the vector closer to the current moment has a higher weight. For example, the weight of the nearest time step is 0.5, the second nearest is 0.3, and the farthest is 0.2. The weighting coefficients are determined through experimental calibration. The experimental calibration method includes testing the improvement effects of different weight combinations on the deformation trend prediction accuracy. For example, compare the prediction errors of equal weights and decaying weights, and select the combination with the smallest error.

[0047] S5. Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual action area and the dynamic offset trend, including: Based on the coordinate range of the actual action area of the touch operation, determine the conversion relationship between the touch coordinates and the display coordinates. The conversion relationship includes the scaling coefficient and the offset compensation amount of the touch coordinates; According to the predicted dynamic offset trend, adjust the weight ratio of the scaling coefficient and the offset compensation amount to generate dynamic conversion parameters; Combine the dynamic conversion parameters with the preset deformation compensation rules to construct a dynamic mapping relationship matrix. The preset deformation compensation rules are generated by experimentally calibrating the error distribution between the touch coordinates and the display coordinates under different deformation levels; Based on the dynamic mapping relationship matrix, associate the coordinate offset amount of the touch coordinates with the compensation amount of the display coordinates to generate a real-time mapping relationship from the touch coordinates to the display coordinates; Update the dynamic mapping relationship matrix to the touch response instruction parsing unit to drive the display layer to perform coordinate mapping.

[0048] Determine the conversion relationship between touch coordinates and display coordinates based on the coordinate range of the actual action area of the touch operation. The coordinate range of the actual action area of the touch operation is a coordinate interval generated by screening the effective action area. The conversion relationship includes the scaling factor and offset compensation amount of the touch coordinates. The calculation method of the scaling factor is to use the ratio of the length of the actual action area to the physical length of the screen display layer as the horizontal scaling factor, and the width ratio as the vertical scaling factor. The calculation method of the offset compensation amount is to use the difference between the center point coordinates of the actual action area and the physical center point coordinates of the screen display layer as the initial compensation amount. The initial compensation amount is determined by experimental calibration. The experimental calibration method includes applying a touch operation in the undeformed state and measuring the deviation between the touch coordinates and the display coordinates to generate a reference compensation amount. For example, when the touch coordinates (100, 200) correspond to the display coordinates (100, 200) in the undeformed state, and the touch coordinates shift to (105, 205) after deformation, the initial compensation amount is set to (-5, -5).

[0049] Adjust the weight ratio of the scaling factor and the offset compensation amount according to the predicted dynamic offset trend to generate dynamic conversion parameters. The dynamic offset trend is the dynamic offset trend vector of the predicted screen deformation area. The specific method of adjusting the weight ratio is to convert the modulus and direction of the dynamic offset trend vector into the adjustment weights of the scaling factor and the offset compensation amount. For example, when the modulus of the dynamic offset trend vector is large, increase the weight ratio of the offset compensation amount to 70% and reduce the weight ratio of the scaling factor to 30%. The weight ratio is determined by experimental calibration. The experimental calibration method includes testing the influence of the weight ratio on the calibration accuracy of the touch coordinates under different deformation levels and selecting the optimal ratio. For example, test the calibration errors of the weight ratios 50%:50% and 70%:30% under the deformation level 2, and select 70%:30% with the smallest error as the final ratio.

[0050] Combine the dynamic conversion parameters with the preset deformation compensation rules to construct a dynamic mapping relationship matrix. The preset deformation compensation rules are generated by experimental calibration of the error distribution between the touch coordinates and the display coordinates under different deformation levels. For example, when the horizontal error of the touch coordinates is 2 pixels and the vertical error is 3 pixels under the deformation level 1, the compensation parameters are set as the horizontal scaling factor 0.98, the vertical scaling factor 1.02, and the offset compensation amount (2, 3). The deformation compensation rules are generated by experimental calibration. The experimental calibration method includes applying deformations of different deformation levels to the flexible screen and recording the error distribution between the touch coordinates and the display coordinates, and fitting the error distribution curve to generate compensation parameters. The dynamic mapping relationship matrix stores the combination relationship between different deformation levels and dynamic conversion parameters in the form of a two-dimensional array. For example, the rows of the array represent the deformation levels 1 to 5, and the columns store the corresponding scaling factors and offset compensation amounts.

[0051] Based on the dynamic mapping relationship matrix, the coordinate offset of the touch coordinate is associated with the compensation amount of the display coordinate to generate a real-time mapping relationship from the touch coordinate to the display coordinate. The association method is to query the dynamic mapping relationship matrix according to the current deformation level to obtain the corresponding scaling coefficient and offset compensation amount. For example, when the current deformation level is 2 and the weight ratio of the dynamic conversion parameter is 40% for the scaling coefficient and 60% for the offset compensation amount, the scaling coefficient 0.95 and the offset compensation amount (3, 4) corresponding to the deformation level 2 are extracted from the matrix. The final scaling coefficient is calculated as 0.95×40% + 0.98×60%, and the final offset compensation amount is (3×60% + 2×40%, 4×60% + 3×40%) to generate the real-time mapping relationship.

[0052] Update the dynamic mapping relationship matrix to the touch response instruction parsing unit to drive the display layer to perform coordinate mapping. The touch response instruction parsing unit is a touch signal processing chip built into the flexible screen. The update method is to write the real-time mapping relationship into the register of the touch signal processing chip. The touch signal processing chip converts the touch coordinate into the display coordinate according to the mapping relationship in the register. For example, when the touch coordinate is (100, 200), according to the scaling coefficient 0.97 and the offset compensation amount (5, -3) of the real-time mapping relationship, the display coordinate is calculated as (100×0.97 + 5, 200×0.97 - 3). The touch signal processing chip reads the latest mapping relationship in the register every 10 milliseconds to ensure real-time performance.

[0053] It should be noted that the parameters (scaling coefficient, offset compensation amount, weight ratio) are all generated through experimental calibration. For example, the initial compensation amount is generated by touch calibration in the undeformed state to obtain the reference parameters, the weight ratio is selected as the optimal value through error tests under the deformation level, the deformation compensation rule is generated by fitting the deformation error curve to generate the compensation parameters, the two-dimensional array structure of the dynamic mapping relationship matrix stores the compensation parameter combinations indexed by the deformation level, and the touch signal processing chip updates the mapping relationship in real time through the register. The above experimental calibration method, parameter generation logic, and hardware control process are all implemented based on known sensor technologies and signal processing principles.

[0054] S6. Calibrate the target display coordinate in real time according to the current touch coordinate and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch instruction corresponding to the target display coordinate, including: Based on the coordinate range of the actual action area of the touch operation, extract the coordinate offset of the current touch coordinate; According to the constructed dynamic mapping relationship matrix, match the scaling coefficient and offset compensation amount corresponding to the current touch coordinate; Generate calibration parameters for the touch coordinate according to the scaling coefficient and offset compensation amount. The calibration parameters include the horizontal calibration amount and the vertical calibration amount; Perform real-time compensation on the current touch coordinates based on calibration parameters to generate target display coordinates; Input the target display coordinates into the touch response instruction parsing unit to drive the display layer to execute touch instructions; Update the calibration parameter weights of the dynamic mapping relationship matrix according to the pressure distribution symmetry characteristics and the force application direction of the touch operation.

[0055] Extract the coordinate offset of the current touch coordinates based on the coordinate range of the actual action area of the touch operation. The coordinate range of the actual action area of the touch operation is the coordinate interval of the effective action area obtained by screening. The calculation method of the coordinate offset is to use the difference between the current touch coordinates and the center point coordinates of the actual action area of the touch operation as the initial offset. The initial offset is determined by experimental calibration. The experimental calibration method includes applying a touch operation in the undeformed state and measuring the reference offset between the touch coordinates and the display coordinates. For example, when undeformed, the touch coordinates (100, 200) correspond to the display coordinates (100, 200), and after deformation, the touch coordinates shift to (105, 205), then the initial offset is set to (5, 5).

[0056] Match the scaling factor and offset compensation amount corresponding to the current touch coordinates according to the constructed dynamic mapping relationship matrix. The dynamic mapping relationship matrix is a two-dimensional array generated based on the deformation compensation rule in step S5. The matching method is to query the corresponding scaling factor and offset compensation amount in the dynamic mapping relationship matrix according to the current deformation level. For example, when the current deformation level is 2, extract the horizontal scaling factor 0.95, vertical scaling factor 1.03, and offset compensation amount (3, 4) corresponding to deformation level 2 from the matrix.

[0057] Generate calibration parameters for the touch coordinates according to the scaling factor and offset compensation amount. The calibration parameters include horizontal calibration amount and vertical calibration amount. The calculation method of the horizontal calibration amount is to multiply the horizontal coordinate of the current touch coordinates by the horizontal scaling factor and add the horizontal component of the offset compensation amount. The calculation method of the vertical calibration amount is to multiply the vertical coordinate of the current touch coordinates by the vertical scaling factor and add the vertical component of the offset compensation amount. For example, when the current touch coordinates are (105, 205), the horizontal scaling factor is 0.95, the vertical scaling factor is 1.03, and the offset compensation amount is (3, 4), then the horizontal calibration amount is 105×0.95 + 3 = 102.75, and the vertical calibration amount is 205×1.03 + 4 = 215.15.

[0058] The current touch coordinates are compensated in real time based on calibration parameters to generate target display coordinates. The target display coordinates are a coordinate combination of a horizontal calibration amount and a vertical calibration amount. For example, if the horizontal calibration amount of 102.75 is rounded to 103 and the vertical calibration amount of 215.15 is rounded to 215, then the target display coordinates are (103, 215). The frequency of real-time compensation is the same as the sampling frequency of the touch signal. For example, if the touch signal is sampled 100 times per second, then the compensation calculation is executed 100 times per second.

[0059] The target display coordinates are input into the touch response instruction parsing unit to drive the display layer to execute touch instructions. The touch response instruction parsing unit is a touch signal processing chip built into the flexible screen. The driving method is to write the target display coordinates into the output register of the touch signal processing chip. The touch signal processing chip controls the display layer to refresh the touch response at the corresponding position according to the coordinate values in the register. For example, if the target display coordinates (103, 215) correspond to an icon in the upper left corner of the screen, then the click event of the icon is triggered.

[0060] The calibration parameter weights of the dynamic mapping relationship matrix are updated according to the pressure distribution symmetry feature and the force application direction of the touch operation. The pressure distribution symmetry feature is the difference parameter of the pressure distribution extracted on the X-axis and Y-axis. The force application direction is the tilt direction of the touch operation judged. The update method is to adjust the weight ratio of the horizontal and vertical calibration amounts according to the tilt angle of the force application direction. For example, when the force application direction is tilted to the left, the weight of the horizontal calibration amount is increased to 60%, and the weight of the vertical calibration amount is reduced to 40%. The weight ratio is determined by experimental calibration. The experimental calibration method includes testing the influence of the weight ratio on the touch coordinate calibration accuracy under different force application directions and selecting the optimal ratio.

[0061] The scaling factor, offset compensation amount, and weight ratio are all generated by experimental calibration. For example, the initial offset amount generates benchmark parameters through touch calibration in the undeformed state. The scaling factor and offset compensation amount are obtained by matching the deformation level and the dynamic mapping relationship matrix. The weight ratio selects the optimal value through error testing under the force application direction. The touch response instruction parsing unit writes the target display coordinates into the register in real time and drives the display layer to refresh. The above experimental calibration method, parameter generation logic, and hardware control process are all implemented based on known sensor technologies and signal processing principles.

[0062] Embodiment 2: Figure 2 A structural schematic diagram of an intelligent watch based on human-computer interaction according to the present invention is given. An intelligent watch based on human-computer interaction includes: Deformation detection module: Real-time detection of the curvature parameter and stretching parameter of the screen deformation area; Pressure propagation module: Obtain the pressure distribution data of a touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameter and the stretching parameter, and determine the actual acting area of the touch operation; Force application analysis module: Extract the symmetry characteristics of the pressure distribution of the user's touch operation, and judge the force application direction of the touch operation according to the symmetry characteristics of the pressure distribution; Dynamic prediction module: Predict the dynamic offset trend of the screen deformation area according to the concentration degree of the force application direction and the touch area; Coordinate mapping module: Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual acting area and the dynamic offset trend; Calibration driving module: Calibrate the target display coordinates in real time according to the current touch coordinates and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch instruction corresponding to the target display coordinates.

[0063] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0064] It should be noted that the present invention can be deployed on the device itself to achieve an embedded application, or can also run on a PC or other terminal with a user interface, so as to meet various hardware environments and usage requirements.

[0065] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0066] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0067] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0068] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] In addition, in each embodiment of the present application, the functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0070] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0071] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0072] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent watch control method based on human-computer interaction, characterized in that, It includes the following steps: S1. Detect the curvature parameter and stretching parameter of the screen deformation area in real time; S2. Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area by combining the curvature parameter and the stretching parameter, and determine the actual action area of the touch operation; S3. Extract the pressure distribution symmetry feature of the user's touch operation, and judge the force application direction of the touch operation according to the pressure distribution symmetry feature; S4. Predict the dynamic offset trend of the screen deformation area according to the force application direction and the concentration degree of the touch area; S5. Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual action area and the dynamic offset trend; S6. Calibrate the target display coordinates in real time according to the current touch coordinates and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch instruction corresponding to the target display coordinates.

2. The intelligent watch control method based on human-computer interaction according to claim 1, wherein, Detect the curvature parameter and stretching parameter of the screen deformation area in real time, including: Detect the initial curvature parameter of the deformation area through the strain sensor array at the edge of the flexible screen; In the initial stage of deformation, activate the capacitive sensor array based on the initial curvature parameter and the preset deformation threshold; Collect the real-time stretching parameter of the deformation area through the capacitive sensor array; Generate a curvature parameter correction value for the deformation area according to the dynamic relationship between the real-time stretching parameter and the initial curvature parameter; Update the curvature parameter of the deformation area based on the curvature parameter correction value, and feedback it to the capacitive sensor array to adjust the detection frequency.

3. A method for controlling an intelligent watch based on human-computer interaction according to claim 1, characterized in that, Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area by combining the curvature parameter and the stretching parameter, and determine the actual action area of the touch operation, including: Detect the pressure distribution data of the touch operation through the pressure sensor array, and the pressure sensor array is composed of multiple metal piezoresistors and is distributed under the display layer of the flexible screen; Divide the physical deformation level of the screen deformation area according to the curvature parameter and the stretching parameter, and match the corresponding relationship table between the preset deformation level and the pressure propagation attenuation gradient; Calculate the propagation attenuation rate of the touch pressure in the screen deformation area based on the pressure distribution data, and generate the propagation attenuation gradient by combining the corresponding relationship table; Extract the coordinate of the pressure center point in the pressure distribution data, superimpose the curvature parameter correction value and the propagation attenuation gradient of the deformation area, and calculate the coordinate offset of the touch pressure action area; Screen the effective action area according to the coordinate offset and the preset gradient threshold, and determine the coordinate range of the actual action area of the touch operation.

4. The intelligent watch control method based on human-computer interaction according to claim 1, wherein Extract the pressure distribution symmetry feature of the user's touch operation, and judge the force application direction of the touch operation according to the pressure distribution symmetry feature, including: Based on the pressure distribution data detected by the pressure sensor array, extract the distribution difference of the pressure value in the X-axis and Y-axis directions in the screen plane, and generate a pressure distribution symmetry parameter; Calculate the main axis direction of the pressure value distribution according to the pressure distribution symmetry parameter; Adjust the calculation weight of the main axis direction by combining the curvature parameter correction value of the deformation area, and generate a corrected main axis direction; Based on the corrected main axis direction and the preset direction determination threshold, judge that the force application direction of the touch operation is tilted to the left, tilted to the right or pressed vertically; Associate the force application direction with the concentration of the touch area, and correct the determination result of the force application direction.

5. The intelligent watch control method based on human-computer interaction according to claim 4, wherein, The main axis direction is the extension direction with the largest ratio of the distribution variances of the pressure values along the X-axis and the Y-axis.

6. The intelligent watch control method based on human-computer interaction according to claim 1, wherein, According to the force application direction and the concentration of the touch area, predict the dynamic offset trend of the screen deformation area, including: Convert the force application direction into the offset direction of the screen deformation area; Determine the deformation diffusion rate according to the touch area concentration. The higher the touch area concentration, the greater the deformation diffusion rate. The deformation diffusion rate is obtained by matching through a preset concentration-rate correspondence table; Generate a dynamic offset vector by combining the offset direction and the deformation diffusion rate. The magnitude of the dynamic offset vector is the product of the deformation diffusion rate and the preset time step, and the direction is the offset direction; Based on the curvature parameter correction value of the deformation area, adjust the magnitude weight of the dynamic offset vector to generate a corrected dynamic offset vector; According to the dynamic offset vector sequence of the historical deformation area, predict the dynamic offset trend of the screen deformation area.

7. An intelligent watch control method based on human-computer interaction according to claim 6, characterized in that, The offset direction is the opposite direction of the force application direction, and the offset angle is proportional to the tilt angle of the force application direction.

8. An intelligent watch control method based on human-computer interaction according to claim 1, characterized in that, Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual action area and the dynamic offset trend, including: Based on the coordinate range of the actual action area of the touch operation, determine the conversion relationship between the touch coordinates and the display coordinates. The conversion relationship includes the scaling coefficient and the offset compensation amount of the touch coordinates; According to the predicted dynamic offset trend, adjust the weight ratio of the scaling coefficient and the offset compensation amount to generate dynamic conversion parameters; Combine the dynamic conversion parameters with the preset deformation compensation rules to construct a dynamic mapping relationship matrix. The preset deformation compensation rules are generated by experimentally calibrating the error distribution between the touch coordinates and the display coordinates under different deformation levels; Based on the dynamic mapping relationship matrix, associate the coordinate offset amount of the touch coordinates with the compensation amount of the display coordinates to generate a real-time mapping relationship from the touch coordinates to the display coordinates; Update the dynamic mapping relationship matrix to the touch response instruction parsing unit to drive the display layer to execute coordinate mapping.

9. The intelligent watch control method based on human-computer interaction according to claim 1, wherein According to the current touch coordinates and the dynamic mapping relationship matrix, calibrate the target display coordinates in real time, and drive the display layer to respond to the touch instruction corresponding to the target display coordinates, including: Based on the coordinate range of the actual action area of the touch operation, extract the coordinate offset amount of the current touch coordinates; According to the constructed dynamic mapping relationship matrix, match the scaling coefficient and the offset compensation amount corresponding to the current touch coordinates; Generate calibration parameters for the touch coordinates according to the scaling coefficient and the offset compensation amount. The calibration parameters include the horizontal calibration amount and the vertical calibration amount; Perform real-time compensation on the current touch coordinates based on the calibration parameters to generate the target display coordinates; Input the target display coordinates into the touch response instruction parsing unit to drive the display layer to execute the touch instruction; According to the symmetry characteristic of the pressure distribution of the touch operation and the force application direction, update the calibration parameter weights of the dynamic mapping relationship matrix.

10. An intelligent watch based on human-computer interaction, which is used to implement the method for controlling an intelligent watch based on human-computer interaction according to any one of claims 1-9, and is characterized in that, Including: Deformation detection module: Detect the curvature parameter and the stretching parameter of the screen deformation area in real time; Pressure propagation module: Obtain the pressure distribution data of the touch operation, analyze the propagation attenuation gradient of the touch pressure in the screen deformation area in combination with the curvature parameter and the stretching parameter, and determine the actual action area of the touch operation; Force analysis module: Extract the symmetry characteristics of the pressure distribution of the user's touch operation, and judge the force application direction of the touch operation according to the symmetry characteristics of the pressure distribution; Dynamic prediction module: Predict the dynamic offset trend of the screen deformation area according to the concentration degree of the force application direction and the touch area; Coordinate mapping module: Construct a dynamic mapping relationship matrix between the touch coordinates and the display coordinates based on the actual acting area and the dynamic offset trend; Calibration drive module: Calibrate the target display coordinates in real time according to the current touch coordinates and the dynamic mapping relationship matrix, and drive the display layer to respond to the touch instructions corresponding to the target display coordinates.

Images