Self-made glass sensor capacitor grid layout optimization method and device

Abstract

The application relates to the technical field of touch display screens, in particular to a self-made glass sensor capacitance grid layout optimization method and device. The method performs regional division on a capacitance grid layout, and constructs a sensing feature database; determines the basic capacitance response, coordinate positioning accuracy and pressure rate sensing threshold of each region based on the database, analyzes the influence of grid parameter changes on pressure sensing accuracy, and quantifies parameter sensitivity; real-time acquisition of capacitance, coordinates and pressure rate data of each region is performed, and a grid parameter adjustment table is generated when the threshold is exceeded; key parameters are extracted from the adjustment table and sensing importance is calculated to generate a parameter set to be optimized; the regions are layered according to the parameter sensitivity, a mapping relationship between the parameter adjustment amount and the performance improvement amount is constructed through a regression tree, a gradual adjustment rule is generated and the parameter set is optimized, and the layout parameterization reconstruction is driven. The method significantly improves the multi-touch point pressure sensing accuracy and system robustness.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of touch display screens, and particularly relates to a self-made glass sensor capacitive grid layout optimization method and device. BACKGROUND

[0002] With the rapid development of flexible display and wearable electronic devices, the performance requirements of touch screens as the core component of human-computer interaction are increasingly stringent. Traditional capacitive touch screens mainly rely on accurate identification of touch point positions, however, in advanced interaction scenarios (such as pressure drawing, game control, etc.), only point coordinate information cannot meet the requirements, and fine perception of touch pressure and its change rate becomes crucial. Especially in the face of complex situations of multiple touch points and each point applying different pressure and change rate, how to accurately, quickly and independently perceive the pressure dynamics of each point becomes a key technical bottleneck to improve user experience.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a self-made glass sensor capacitive grid layout optimization method and device, aiming to solve the technical problem of how to accurately, quickly and independently perceive the pressure dynamics of each point in the face of complex situations of multiple touch points and each point applying different pressure and change rate.

[0005] To achieve the above purpose, the present application provides a self-made glass sensor capacitive grid layout optimization method, which comprises:

[0006] The layout structure of the self-made glass sensor capacitive grid is regionally divided by a multi-dimensional perception analysis method to obtain a multi-perception region layout, and historical capacitance change data, historical touch point coordinate data and corresponding historical pressure change rate data of each perception region layout under multiple pressure loads are collected to construct a perception feature database;

[0007] The basic capacitance response threshold, coordinate positioning accuracy threshold and pressure change rate perception threshold of each perception region layout are determined according to the perception feature database, and the influence of grid parameter changes in each perception region layout on multi-touch point pressure perception accuracy is analyzed based on the perception feature database to obtain the grid parameter sensitivity of each perception region layout;

[0008] Real-time capacitance change data, real-time touch point coordinate data and real-time pressure change rate data of each perception region layout are obtained, and a grid parameter adjustment table of each perception region layout is generated when the corresponding basic capacitance response threshold, coordinate positioning accuracy threshold or pressure change rate perception threshold is exceeded;

[0009] analyzing multiple correlations between the capacitance response, coordinate positioning, and pressure rate sensing of each of the sensing area layout based on the sensing feature database, and extracting grid parameters from the grid parameter adjustment table according to the multiple correlations to perform sensing importance calculation, to generate a set of grid parameters to be optimized for each of the sensing area layout;

[0010] sensitivity grouping each of the sensing area layout according to each of the grid parameter sensitivity, to obtain a multi-level sensitivity layout area, to construct a mapping relationship between the grid parameter adjustment amount and the multi-touch point pressure sensing performance improvement amount of each level of the sensitivity layout area through a regression tree, to generate a progressive layout adjustment rule to optimize the set of grid parameters to be optimized for each of the sensing area layout, and to control the parameterized reconstruction of the layout of the self-made glass sensor capacitance grid based on the optimization result.

[0011] Optionally, the layout structure of the self-made glass sensor capacitance grid is divided into multiple sensing area layouts through a multi-dimensional sensing analysis method, comprising:

[0012] Obtaining the electrode density, unit capacitance base value, mutual coupling coefficient, and signal-to-noise ratio of each sub-area in the capacitance grid layout to construct a layout complexity quantization matrix of each of the sub-areas;

[0013] Based on each of the layout complexity quantization matrix, a sensing directed graph is established, and clustering operation is performed through the mean value and peak value of the capacitance change amplitude of each of the sub-areas under pressure load, to preliminarily partition each of the sub-areas, to obtain a capacitance response grouping result;

[0014] Obtaining touch point coordinate offset data corresponding to each of the sub-areas, comparing the coordinate offset data with a preset positioning tolerance threshold, and refining the capacitance response grouping result according to the comparison result to obtain a multi-sensing area layout.

[0015] Optionally, the basic capacitance response threshold includes a baseline capacitance value, a lower limit value of a dynamic range, and an upper limit value of saturation; the coordinate positioning accuracy threshold includes a minimum resolvable distance and a linearity error limit; and the pressure change rate sensing threshold includes a minimum perceptible rate gradient and a maximum following rate.

[0016] Optionally, the determination of the basic capacitance response threshold, the coordinate positioning accuracy threshold, and the pressure change rate sensing threshold of each of the sensing area layout according to the sensing feature database comprises:

[0017] extracting baseline capacitance sampling values, capacitance saturation values under different pressures, and nonlinear distortion points of each sensing area layout in a touchless state from the sensing feature database, and fitting a static response curve of capacitance-pressure through Gaussian process regression to determine baseline capacitance values, dynamic range lower limit values, and saturation upper limit values of each sensing area layout;

[0018] extracting multiple coordinate sampling data of each sensing area layout on standard test points from the sensing feature database, calculating root mean square errors and linear fitting residuals with theoretical coordinates, and determining minimum resolvable distances and linearity error limits of each sensing area layout through confidence interval estimation;

[0019] extracting capacitance response delay data and rate tracking errors of each sensing area layout under a preset pressure ramp signal from the sensing feature database, smoothing measurement noise and identifying system response bandwidth using a Kalman filter to determine minimum perceptible rate gradients and maximum following rates of each sensing area layout.

[0020] Optionally, the influence of grid parameter changes in each sensing area layout on multi-touch point pressure sensing accuracy is analyzed based on the sensing feature database to obtain grid parameter sensitivity of each sensing area layout, including:

[0021] extracting historical touch point coordinate data, historical pressure rate data, and their corresponding historical grid parameter change records of each sensing area layout from the sensing feature database as training samples to train a time series convolution network, obtaining a response model representing the dynamic correlation between grid parameter changes and multi-dimensional sensing performance in each sensing area layout;

[0022] Based on the response model, the coordinate positioning error change and the pressure rate tracking error change caused by a specific grid parameter change in each sensing area layout under a preset pressure mode sequence are calculated, and the error change is analyzed by Spearman rank correlation analysis according to the pressure rate interval, obtaining parameter-performance correlation strength indicators of each sensing area layout;

[0023] Each sensing area layout in the global sensing task is used to determine the preset function weight, and the corresponding parameter-performance correlation strength indicators are weighted and fused, and the fusion results are divided into intervals according to the preset sensitivity classification threshold to obtain a grid parameter sensitivity classification table to quantitatively determine the grid parameter sensitivity of each sensing area layout.

[0024] Optionally, the multiple correlations between the capacitance response, coordinate positioning, and pressure rate sensing of each sensing area layout are analyzed based on the sensing feature database, and grid parameters are extracted from the grid parameter adjustment table according to the multiple correlations for sensing importance calculation to generate a set of grid parameters to be optimized for each sensing area layout, including:

[0025] The historical capacitance response sequence, historical coordinate positioning data, and historical sensing performance evaluation data of each sensing area layout under different pressure change rates are extracted from the sensing feature database, and the sensing behavior similarity under different pressure scenarios is calculated by a dynamic time warping algorithm to perform pressure scenario clustering on each sensing area layout according to the similarity calculation results to obtain a set of typical pressure sensing scenarios;

[0026] The mean, variance, extreme value, and covariance matrix of the capacitance response feature value, coordinate stability index, and rate tracking accuracy in each set of typical pressure sensing scenarios are calculated to construct a multi-modal sensing feature tensor, and a partial least squares regression method is used to quantify the complex correlation between the layout grid parameters and the multi-modal sensing performance indicators to obtain a multi-element coupling relationship matrix for each sensing area layout;

[0027] Based on the multi-element coupling relationship matrix, candidate adjustment parameters are extracted from the grid parameter adjustment table of each sensing area layout, and the contribution of the extracted candidate grid parameters to the overall sensing performance improvement is quantified by a random forest algorithm to quantify the sensing importance of the extracted candidate grid parameters based on the contribution, and candidate grid parameters with an importance calculation result exceeding an importance threshold are selected to form a set of grid parameters to be optimized for each sensing area layout.

[0028] Optionally, each sensing area layout is grouped according to the grid parameter sensitivity to obtain multi-level sensitivity layout areas, a mapping relationship between the grid parameter adjustment amount and the multi-touch point pressure sensing performance improvement amount of each level of sensitivity layout area is constructed by a regression tree to generate a gradual layout adjustment rule for optimizing the set of grid parameters to be optimized for each sensing area layout, and based on the optimization result, after the parameterized reconstruction of the layout of the self-made glass sensor capacitance grid, including:

[0029] The performance index time series data of the self-made glass sensor after layout parameter optimization under multiple pressure change rate test modes are obtained, and the performance index time series data are used as input features to train a generative adversarial network, and high-fidelity virtual pressure touch signals are generated in real time and sensing response simulation is performed through the trained network to obtain virtual sensing response data;

[0030] Based on the virtual perception response data, parameter tolerance boundaries of each of the perception area layouts under extreme pressure change rates are obtained as stability constraints, and a virtual layout simulation environment of four groups of virtual grid parameters including electrode width, spacing, shape factor and interlayer coverage area is constructed through parameterized scanning;

[0031] With the comprehensive accuracy including coordinate error, pressure value error and rate tracking error of multi-touch point pressure perception as the optimization objective, the virtual grid parameters of each of the perception area layouts in the virtual layout simulation environment are cooperatively optimized through multi-objective Bayesian optimization to obtain a set of Pareto optimal virtual parameter combinations of each of the perception area layouts;

[0032] Based on each of the set of Pareto optimal virtual parameter combinations, high-precision electromagnetic-structure coupling simulation is performed on the capacitive grid, and when the perception performance index data obtained through simulation is stable in the preset performance target interval, the layout of the self-made glass sensor capacitive grid is controlled according to the optimized virtual parameter combination set for final parameterized reconstruction and output before manufacturing.

[0033] In addition, to achieve the above-mentioned purpose, the application also provides a self-made glass sensor capacitive grid layout optimization device, which comprises:

[0034] A data acquisition module is configured to divide the layout structure of the self-made glass sensor capacitive grid into multiple perception area layouts through multi-dimensional perception analysis, and collect historical capacitive change data, historical touch point coordinate data and corresponding historical pressure change rate data of each of the perception area layouts under multiple pressure loads to construct a perception feature database.

[0035] A parameter perception module is configured to determine a basic capacitive response threshold, a coordinate positioning accuracy threshold and a pressure change rate perception threshold of each of the perception area layouts according to the perception feature database, and analyze the influence of grid parameter changes in each of the perception area layouts on multi-touch point pressure perception accuracy based on the perception feature database to obtain grid parameter sensitivity of each of the perception area layouts.

[0036] An adjustment generation module is configured to obtain real-time capacitive change data, real-time touch point coordinate data and real-time pressure change rate data of each of the perception area layouts, and generate a grid parameter adjustment table of each of the perception area layouts when the corresponding basic capacitive response threshold, coordinate positioning accuracy threshold or pressure change rate perception threshold is exceeded.

[0037] The correlation analysis module is configured to analyze multiple correlations between the capacitive response, coordinate positioning and pressure rate sensing of each sensing area layout based on the sensing feature database, and extract grid parameters from the grid parameter adjustment table according to the multiple correlations to perform sensing importance calculation, thereby generating a set of grid parameters to be optimized for each sensing area layout.

[0038] The parameter adjustment module is configured to group each sensing area layout according to the grid parameter sensitivity to obtain a multi-level sensitivity layout area, construct a mapping relationship between the grid parameter adjustment amount and the multi-touch point pressure sensing performance improvement amount of each level of the sensitivity layout area by using a regression tree, generate a progressive layout adjustment rule to optimize the set of grid parameters to be optimized for each sensing area layout, and control the parameterized reconstruction of the layout of the self-made glass sensor capacitive grid based on the optimization result.

[0039] In addition, to achieve the above object, the application further provides a self-made glass sensor capacitive grid layout optimization device, which comprises a memory, a processor and a self-made glass sensor capacitive grid layout optimization program stored in the memory and executable on the processor, and the self-made glass sensor capacitive grid layout optimization program is configured to implement the steps of the self-made glass sensor capacitive grid layout optimization method according to any one of the above embodiments.

[0040] In addition, to achieve the above object, the application further provides a storage medium, which stores a self-made glass sensor capacitive grid layout optimization program, and the self-made glass sensor capacitive grid layout optimization program is executable on a processor to implement the steps of the self-made glass sensor capacitive grid layout optimization method according to any one of the above embodiments.

[0041] This invention provides a method for optimizing the capacitive grid layout of a self-made glass sensor. The method, through multi-dimensional region partitioning and feature database construction, subdivides the capacitive grid layout into multiple sensing regions based on parameters such as electrode density and capacitance response characteristics, overcoming the limitations of traditional unified parameter design. Combining a response model trained on historical data with multiple correlation analysis, it can accurately capture the nonlinear mapping relationship between grid parameters and pressure sensing accuracy, solving the problems of signal crosstalk and nonlinear distortion in dynamic pressure sensing at multiple touch points, reducing pressure change rate sensing errors, and improving coordinate positioning accuracy to sub-millimeter level, meeting the needs of high-precision interactive scenarios. Through real-time threshold monitoring and parameter adjustment table generation mechanisms, the system can respond to dynamic changes in touch pressure in real time. When abnormal capacitance response, coordinate positioning deviation, or pressure rate sensing failure is detected, it can automatically trigger differentiated adjustments to the grid parameters, avoiding performance degradation of traditional static layouts under complex pressure loads. By combining regression tree-based progressive adjustment rules, hierarchical optimization can be implemented for layout regions with different sensitivities. For example, fine-tuning with small steps can be used for high-sensitivity regions, while batch parameter optimization can be performed for low-sensitivity regions. This shortens the system's response latency under multi-point pressure change scenarios and significantly improves real-time interaction. Traditional layout design relies on engineers' experience to adjust mesh parameters, resulting in long trial-and-error cycles and difficulty in covering the entire scenario. This solution quantifies the impact weight of mesh parameters on multi-dimensional perception performance through data-driven sensitivity analysis and importance calculation, avoiding blind adjustments. For example, Spearman's rank correlation analysis is used to determine the optimization priority of key parameters, and Pareto optimal parameter combinations are generated by combining Bayesian optimization and other algorithms. This shortens the layout design cycle and reduces the number of iterations of physical samples, thereby reducing R&D costs. In addition, the construction of a virtual simulation environment allows for early verification of parameter robustness during the design phase, avoiding performance risks in actual manufacturing. For the strong coupling characteristics between capacitive response, coordinate positioning, and pressure rate perception, the solution decomposes the complex multi-objective optimization problem into hierarchical processing tasks through multi-level sensitivity grouping and mapping relationship modeling. For example, a high-precision regression tree model is used to finely adjust the electrode spacing in highly sensitive areas, while simplified rules are used for batch optimization in low-sensitivity areas, reducing computational complexity while ensuring overall performance. This strategy effectively suppresses signal interference when multiple pressures are superimposed, improves the system's sensing stability under extreme conditions, and significantly enhances the reliability of the device in complex interaction scenarios. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the structure of a self-made glass sensor capacitor grid layout optimization device for the hardware operating environment involved in the embodiments of the present invention;

[0043] Figure 2 This is a flowchart illustrating an embodiment of the self-made glass sensor capacitor grid layout optimization method of the present invention;

[0044] Figure 3 Figure 1 is a structural block diagram of an embodiment of the self-made glass sensor capacitance grid layout optimization device of the present application.

[0045] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are merely illustrative of the present application and do not limit the present application.

[0047] Reference Figure 1 , Figure 1 Figure 2 is a structural schematic diagram of the self-made glass sensor capacitance grid layout optimization device related to the hardware operating environment of the embodiment of the present application.

[0048] As shown in Figure 1 , the self-made glass sensor capacitance grid layout optimization device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 can include a display screen (Display), and the optional user interface 1003 can also include a standard wired interface, a wireless interface, and the wired interface of the user interface 1003 can be a USB interface in the present application. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0049] Those skilled in the art can understand that Figure 1 the structure shown in the figure does not constitute a limitation on the self-made glass sensor capacitance grid layout optimization device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0050] As shown in Figure 1 , the memory 1005 as a computer storage medium can include an operation device, a network communication module, a user interface module, and a self-made glass sensor capacitance grid layout optimization program.

[0051] In Figure 1The network interface 1004 is mainly used for connecting a background server and communicating data with the background server; the user interface 1003 is mainly used for connecting an external device; the self-made glass sensor capacitance grid layout optimization device calls the self-made glass sensor capacitance grid layout optimization program stored in the memory 1005 through the processor 1001, and executes the self-made glass sensor capacitance grid layout optimization method provided by the embodiment of the application.

[0052] Based on the above hardware structure, an embodiment of the self-made glass sensor capacitance grid layout optimization method of the application is provided.

[0053] Referring to Figure 2 , Figure 2 The flowchart of an embodiment of the self-made glass sensor capacitance grid layout optimization method of the application is provided.

[0054] In an embodiment, the self-made glass sensor capacitance grid layout optimization method comprises the following steps:

[0055] In step S100, the layout structure of the self-made glass sensor capacitance grid is regionally divided by a multi-dimension perception analysis method to obtain a multi-perception region layout, and historical capacitance change data, historical touch point coordinate data and corresponding historical pressure change rate data of each perception region layout under multiple pressure loads are collected to construct a perception feature database.

[0056] The self-made glass sensor capacitive grid can be a transparent capacitive sensing structure integrated in a flexible display or wearable device, composed of a grid array of intersecting electrodes, for sensing touch position and pressure information, and can be used to realize identification of touch point coordinates and perception of pressure intensity. In an exemplary embodiment, the self-made glass sensor capacitive grid can form an electrode network on a glass substrate by depositing conductive material through micro-nano processing technology, and detect touch behavior by using capacitive change. Further, the self-made glass sensor capacitive grid can include one or more of, but not limited to, ITO electrode grid, silver nanowire grid, graphene electrode grid. The multi-sensing area can be a different functional area divided according to electrode density, response characteristics and other parameters of the capacitive grid layout, which can be used to support differentiated parameter configuration to improve overall sensing performance. In this embodiment, the multi-sensing area can be spatially divided by multi-dimensional sensing analysis method to distinguish the sensing ability characteristics of different areas. For example, the multi-sensing area can include one or more of, but not limited to, high-density electrode area, medium-response sensitivity area, and edge compensation area. Historical capacitive change data, historical touch point coordinate data and historical pressure change rate data can collectively constitute the data source of the sensing feature database, which can be a historical data set of each sensing area under various pressure loads, and can be used to provide data support for response model training and correlation analysis.

[0057] In a specific embodiment, the sensing feature database can be constructed by applying a standardized pressure sequence on an experimental platform and synchronously recording the response data. The area division can be a spatial division of the capacitive grid according to electrode density, capacitive response characteristics and other dimensions, thereby realizing differentiated design of functional areas. Further, the area division can be realized by using clustering algorithm or rule engine to classify the layout geometry and electrical characteristics, so that the system can configure corresponding parameters according to the sensing needs of different areas. Constructing the sensing feature database can be a process of collecting and integrating historical capacitive, coordinate and pressure rate data under multiple working conditions, so that the subsequent analysis has a reliable data basis. Further, constructing the sensing feature database can be completed by repeatedly applying different pressure patterns in a controlled environment and synchronously sampling the sensor output signals, thereby achieving the technical effect of providing a reliable data source for model training and analysis.

[0058] Step S200, determining the basic capacitive response threshold, coordinate positioning accuracy threshold and pressure change rate sensing threshold of each sensing area layout according to the sensing feature database, and analyzing the influence of grid parameter changes in each sensing area layout on multi-touch point pressure sensing accuracy based on the sensing feature database, to obtain the grid parameter sensitivity of each sensing area layout.

[0059] The base capacitance response threshold can be a reference value for determining whether the capacitance signal is abnormal, and can be used to evaluate whether the current capacitance response deviates from the normal working range. In the embodiment, the base capacitance response threshold can be determined according to the capacitance change distribution in the sensing feature database under the normal working state. The coordinate positioning accuracy threshold can be a maximum positioning deviation limit value allowed, and can be used to judge the credibility of the current touch point coordinates. For example, the coordinate positioning accuracy threshold can be set based on the statistical error distribution of the historical touch point coordinate data. The pressure change rate sensing threshold can be a minimum recognizable rate standard of the dynamic change of the pressure, and can be used to judge whether the pressure sensing function is in the effective response interval. In an exemplary embodiment, the pressure change rate sensing threshold can be obtained by analyzing the historical pressure change rate data to determine the system response boundary. The grid parameter sensitivity can be a quantitative indicator reflecting the influence degree of the variation of a specific grid parameter on the multi-touch point pressure sensing accuracy, and can be used to guide the establishment of parameter adjustment priority. Further, the grid parameter sensitivity can be obtained by analyzing the relationship between the parameter change and the sensing performance in the sensing feature database to quantify the sensing accuracy fluctuation caused by different parameter adjustments.

[0060] The determination of the threshold can be an operation of setting the critical judgment standard of each performance index based on the historical data distribution, so that the system has the ability of abnormality recognition. Further, the determination of the threshold can be achieved by using statistical methods such as percentile or distribution fitting to determine a reasonable threshold interval, so as to establish an abnormality detection benchmark. The analysis of the influence of the grid parameter change on the sensing accuracy can be a process of revealing the correlation between the parameter adjustment and the performance, and the result is embodied as the grid parameter sensitivity. This operation can be achieved by regression analysis or multivariate correlation modeling, so that the system can identify the key influencing factors.

[0061] In step S300, real-time capacitance change data, real-time touch point coordinate data and real-time pressure change rate data of each sensing area layout are obtained, and when the corresponding base capacitance response threshold, coordinate positioning accuracy threshold or pressure change rate sensing threshold is exceeded, a grid parameter adjustment table of each sensing area layout is generated.

[0062] The real-time capacitance change data can be a dynamic signal value output by the capacitance grid in the current touch state, and can be used to reflect the existence and intensity of a touch event. In this embodiment, the real-time capacitance change data can be obtained by sampling the capacitance value between electrodes in real time through the sensor circuit. The real-time touch point coordinate data can be position information of the current touch point on the screen plane, and can be used to provide spatial input for human-computer interaction. For example, the real-time touch point coordinate data can be obtained by calculating the peak position of the electrode signal through a capacitance difference algorithm. The real-time pressure change rate data can be the change amount of touch pressure per unit time, and can be used to represent the dynamic characteristics of user operation. In a specific embodiment, the real-time pressure change rate data is obtained by taking the derivative of the continuous pressure sampling value. The grid parameter adjustment table can be a mapping table recording the grid parameters to be adjusted and their target values, and can be used to drive subsequent optimization execution. Further, the grid parameter adjustment table can automatically generate adjustment instruction entries when the real-time data exceeds the corresponding threshold.

[0063] Generating the grid parameter adjustment table can be the behavior of creating a parameter correction task list when the real-time monitoring data exceeds the preset judgment standard, so that the system can respond to performance deviation in time. Further, generating the grid parameter adjustment table can prioritize the parameters of the area with significant deviation by setting a dynamic weight mechanism, so as to start the adaptive optimization process.

[0064] In step S400, the multiple correlations among the capacitance response, coordinate positioning and pressure rate sensing of each sensing area layout are analyzed based on the sensing feature database, and the grid parameters are extracted from the grid parameter adjustment table according to the multiple correlations for sensing importance calculation, so as to generate the set of grid parameters to be optimized for each sensing area layout. The multiple correlations can be a nonlinear coupling relationship among the capacitance response, coordinate positioning and pressure rate sensing, and can be used to reveal the mutual dependence mechanism among multi-dimensional sensing indicators. In this embodiment, the multiple correlations can be obtained by statistically analyzing the dependence structure among the variables in the sensing feature database. The sensing importance can be a comprehensive score measuring the contribution degree of a certain grid parameter to the overall sensing performance, and can be used to determine the priority order of parameter optimization. For example, the sensing importance can be obtained by weighted calculation combining the multiple correlations and the sensitivity analysis results. The set of grid parameters to be optimized can be a set of key grid parameters to be adjusted, and can be used to narrow the optimization search space to improve the operation efficiency. In an exemplary embodiment, the set of grid parameters to be optimized can be formed by extracting the high-impact parameters sorted by sensing importance from the grid parameter adjustment table.

[0065] The perceptual importance calculation can be an operation of fusing multiple correlations and sensitivity analysis result quantitative parameter influence, so that the optimization process focuses on the most potential parameters for improvement. Further, the perceptual importance calculation can be realized by introducing an analytic hierarchy process or a machine learning scoring model for comprehensive evaluation, so that the parameters that need to be optimized can be accurately screened.

[0066] In step S500, the sensitivity of each grid parameter is used to group the layout of each sensing area, and a multi-level sensitivity layout area is obtained. A mapping relationship between the grid parameter adjustment amount and the multi-touch point pressure sensing performance improvement amount of each level sensitivity layout area is constructed by a regression tree, a gradual layout adjustment rule is generated to optimize the set of grid parameters to be optimized of each sensing area layout, and the parameterized reconstruction of the layout of the self-made glass sensor capacitive grid is controlled based on the optimization result.

[0067] The multi-level sensitivity layout area can be a grouping of different optimization levels obtained by dividing the sensing area according to the sensitivity of the grid parameter, and can be used to realize a differentiated optimization strategy allocation. In this embodiment, the multi-level sensitivity layout area can be obtained by clustering or hierarchical classification based on the sensitivity value. For example, the multi-level sensitivity layout area can include one or more of a high sensitivity area, a medium sensitivity area, and a low sensitivity area. The gradual layout adjustment rule can be a control logic describing the mapping relationship between the grid parameter adjustment amount and the sensing performance improvement, and can be used to guide the parameterized reconstruction process. Further, the gradual layout adjustment rule can be generated by learning the relationship between the parameter adjustment path and the performance gain using a regression tree model. Parameterized reconstruction can be a process of reconfiguring the physical or logical parameters of the capacitive grid according to the optimization result, and can be used to complete the iterative upgrade of the layout performance. In one specific embodiment, parameterized reconstruction can be achieved by dynamically rewriting the driving parameters or triggering the hardware fine-tuning mechanism in a software-defined manner. Sensitivity grouping can be an operation of grouping the sensing area into different levels according to the sensitivity, so that the optimization resources can be allocated as needed. Further, the sensitivity grouping can be automatically grouped by using K-means clustering or threshold segmentation, thereby supporting the development of hierarchical optimization strategies.

[0068] Generating a gradual layout adjustment rule can be to use a regression tree to model the relationship between parameter adjustment amount and performance improvement, and to form an executable optimization path. Further, generating a gradual layout adjustment rule can realize a combination strategy of small step fine adjustment and batch optimization by constructing a multi-level decision tree structure, thereby realizing efficient and stable parameter optimization.

[0069] Taking touch display screen pressure interaction as an example, the self-made glass sensor capacitance grid layout optimization method of the embodiment can be that a user uses two fingers to apply different forces to draw strokes in a touch display screen drawing application, and the system captures the pressure size and change rate of the two touch points in real time through the self-made glass sensor. When the pressure of a certain point suddenly increases, causing abnormal capacitance response, the system immediately calls the perception feature database to compare historical patterns to determine whether the electrode driving parameters of the corresponding area need to be adjusted. Subsequently, based on multiple correlation analysis, the coupling effect of coordinate positioning and pressure perception in the region is confirmed, a set of parameters to be optimized is generated, and the high sensitivity area is fine-tuned according to the regression tree rule. The whole process is completed in milliseconds, ensuring that the stroke thickness and transparency change naturally with pressure, avoiding misjudgment or delay.

[0070] The self-made glass sensor capacitance grid layout optimization method provided in the embodiment divides the capacitance grid layout structure into regions through a multi-dimensional perception analysis method and constructs a perception feature database, determines the perception response threshold of each item based on historical data, and quantitatively analyzes the grid parameter sensitivity. In real-time operation, the parameter adjustment mechanism is triggered by combining real-time monitoring data and threshold comparison, key optimization parameters are selected by using multiple correlation modeling and perception importance calculation, regions are grouped according to sensitivity levels, and a mapping rule between parameter adjustment amount and performance improvement is established. Finally, the progressive optimization of the set of parameters to be optimized and the parameterization reconstruction of the layout are realized. Through the above steps, high-precision coordinate positioning and stable pressure perception response can be maintained in the scene of multi-point dynamic touch and complex pressure change, unnecessary global parameter adjustment is reduced, calculation load and response delay are reduced, and the adaptability and reliability of the sensor in a diversified interaction environment are improved.

[0071] In one of the embodiments, the layout structure of the self-made glass sensor capacitance grid is divided into regions by a multi-dimensional perception analysis method to obtain a multi-perception region layout, including:

[0072] The electrode density, unit capacitance base value, mutual coupling coefficient and signal-to-noise ratio of each sub-region in the capacitance grid layout are obtained to construct a layout complexity quantization matrix of each sub-region;

[0073] The electrode density can be the distribution density of the capacitive grid electrodes in a unit area, and can be used to affect the area sensitivity and spatial resolution. In an exemplary embodiment, the electrode density can be obtained by analyzing the layout geometry data to calculate the electrode length or number per square millimeter. Further, the electrode density can be one of the basic parameters for constructing the layout complexity quantification matrix. For example, the electrode density can include one or more of high-density area, medium-density area, low-density area, etc. The unit capacitance base value can be the initial capacitance value of a single grid unit in a non-touch state, and can be used to reflect the area electrical stability and dynamic response range. In this embodiment, the unit capacitance base value can be obtained by circuit measurement or simulation means to obtain the capacitance static value under no disturbance. Further, the unit capacitance base value can be used to construct the layout complexity quantification matrix. The mutual coupling coefficient can be an index of the signal interference strength between adjacent electrodes due to electromagnetic field overlap, and can be used to represent the signal isolation capability and multi-point recognition anti-interference performance. In a specific embodiment, the mutual coupling coefficient can be calculated by electromagnetic simulation or actual measurement of differential signal crosstalk amplitude. Further, the mutual coupling coefficient can be used to evaluate the signal interference risk between sub-regions and be included in the complexity modeling process. The signal-to-noise ratio can be the ratio of the effective capacitance change signal to the background noise power, and can be used to measure the sensing reliability and minimum detectable pressure level. For example, the signal-to-noise ratio can be obtained by ratio calculation after collecting the signal peak value and noise fluctuation value under standard load conditions. Further, the signal-to-noise ratio can be used as a stability dimension parameter in the layout complexity quantification matrix.

[0074] The layout complexity quantification matrix can be an operation of integrating the electrode density, the unit capacitance base value, the mutual coupling coefficient, and the signal-to-noise ratio to form a structured data matrix. Further, the layout complexity quantification matrix can be realized by normalizing the above parameters of each sub-region and combining them into a row vector, and then organizing them into a numerical matrix of the entire layout range, so as to realize the digital expression of the comprehensive electrical characteristics of each sub-region.

[0075] Based on the layout complexity quantification matrix, a sensing directed graph is established, and clustering operations are performed on the mean value and the peak value of the capacitance change amplitude of each sub-region under pressure load, so as to preliminarily partition each sub-region and obtain a capacitance response grouping result.

[0076] The layout complexity quantization matrix can be a multi-dimensional numerical matrix with the above four parameters as dimensions, which can be used to quantify the differences in technical characteristics of different regions and support systematic partitioning decisions. In this embodiment, the layout complexity quantization matrix is used as an input data structure for generating a perception directed graph. The perception directed graph can be established by taking sub-regions as nodes and calculating similarity or influence relationships based on the layout complexity quantization matrix to construct weighted directed edges. Further, the perception directed graph can be established by using a graph neural network or a correlation propagation algorithm to generate a connection structure reflecting signal flow, thereby enhancing the understanding of electrical coupling relationships and signal propagation paths by region division. The average capacitance change amplitude can be the average change in capacitance response of a sub-region during multiple pressure loading processes, which can be used to reflect the overall response sensitivity of the region. In an exemplary embodiment, the average capacitance change amplitude can be obtained by taking the arithmetic mean of the continuous sampling data. Further, the average capacitance change amplitude can be used in clustering operations to achieve preliminary partitioning. The capacitance change amplitude peak value can be the maximum instantaneous change in capacitance response of a sub-region under pressure, which can be used to represent the dynamic bearing capacity and non-linear boundary of the region. For example, the capacitance change amplitude peak value can be obtained by extracting the maximum value from the dynamic signal sequence. Further, the capacitance change amplitude peak value can be used together with the average value as a clustering characteristic variable.

[0077] The clustering operation can be a pattern classification operation on sub-regions based on the average and peak values of the capacitance change amplitude. Further, the clustering operation can be implemented by introducing a weighted distance metric to highlight the influence of key features, thereby improving grouping consistency and automatically merging regions with similar response characteristics. The capacitance response grouping result can be a preliminary functional region division formed after clustering based on the capacitance change amplitude characteristics, which can be used to form a region set with similar dynamic response characteristics. In this embodiment, the capacitance response grouping result is used as the input basis for subsequent coordinate offset correction. For example, the capacitance response grouping result can include one or more of a high response group, a standard response group, a delayed response group, etc.

[0078] The touch point coordinate offset data corresponding to each sub-region is obtained, the preset positioning tolerance threshold is compared with the coordinate offset data, and the capacitance response grouping result is refined and adjusted based on the comparison result to obtain a multi-perception region layout.

[0079] The touch point coordinate offset data can be a spatial deviation value between an actual touch position and a system-recognized position, and can be used to evaluate positioning accuracy. In one specific embodiment, the touch point coordinate offset data can be obtained by recording a real touch point through a high-precision external positioning device and comparing the result with a system output. Further, the touch point coordinate offset data can be used to verify and correct the capacitive response grouping result. The preset positioning tolerance threshold can be a maximum allowable coordinate recognition error limit value, and can be used to determine whether the positioning performance meets the requirements. For example, the preset positioning tolerance threshold can be set as a fixed value or an adaptive variable value according to the accuracy requirements of the application scenario. Further, the preset positioning tolerance threshold can be compared with the coordinate offset data to trigger the partition adjustment mechanism. The refinement adjustment can be a process of comparing the coordinate offset data with the preset positioning tolerance threshold to determine whether the preliminary partition boundary needs to be modified. Further, the refinement adjustment can be achieved by separately splitting or reclassifying the regions exceeding the tolerance threshold to a higher-precision group, so as to ensure that the final partition meets the positioning accuracy requirements.

[0080] For example, in the scenario of a flexible screen gesture control device, the self-made glass sensor capacitive grid layout optimization method of the embodiment can be used to improve the edge touch control accuracy when performing multi-finger pressure zoom operation on a curved flexible display screen. The system first constructs a complexity matrix based on electrode density and signal-to-noise ratio, generates a perception directed graph to reveal the signal attenuation path of the edge and center regions, and preliminarily divides the regions into a high-response center region and a low-response edge region by clustering the response amplitudes of the regions obtained by applying uniform pressure. Then, the system detects that there is a significant coordinate offset in the edge region, which exceeds the preset tolerance threshold, and further subdivides the edge region into a compensation correction sub-region. Finally, the multi-perception region layout formed realizes the effective improvement of the edge touch control accuracy.

[0081] The embodiment constructs a layout complexity quantization matrix by obtaining the electrode density, unit capacitance base value, mutual coupling coefficient and signal-to-noise ratio of each sub-region in the capacitive grid layout, establishes a perception directed graph based on the matrix, and performs clustering operation by combining the mean and peak values of the capacitive change amplitudes under pressure load to realize preliminary partitioning. Then, the embodiment uses the comparison result of the touch point coordinate offset data and the preset positioning tolerance threshold to refine the capacitive response grouping result, enhances the physical basis of region division through multi-dimensional electrical characteristic modeling, merges sub-regions with consistent response behavior by using clustering method, and optimizes the partition boundary through actual positioning error feedback mechanism, so as to achieve the technical effect that the final multi-perception region layout simultaneously considers dynamic response consistency and spatial positioning accuracy.

[0082] In one of the embodiments, the base capacitance response threshold includes a baseline capacitance value, a dynamic range lower limit value, and a saturation upper limit value; the coordinate positioning accuracy threshold includes a minimum distinguishable distance and a linearity error limit; the pressure change rate perception threshold includes a minimum perceivable rate gradient and a maximum following rate.

[0083] In one of the embodiments, the base capacitance response threshold includes a baseline capacitance value, a dynamic range lower limit value, and a saturation upper limit value; the coordinate positioning accuracy threshold includes a minimum distinguishable distance and a linearity error limit; the pressure change rate perception threshold includes a minimum perceivable rate gradient and a maximum following rate.

[0084] In one of the embodiments, determining the base capacitance response threshold, the coordinate positioning accuracy threshold, and the pressure change rate perception threshold of each sensing area layout according to the sensing feature database includes:

[0085] extracting baseline capacitance sampling values of the layout of each sensing area in a touchless state, capacitance saturation values under different pressures, and non-linear distortion points from the perception feature database, and fitting a static response curve of capacitance-pressure through Gaussian process regression to determine baseline capacitance values, lower limit values of dynamic range, and upper limit values of saturation of the layout of each sensing area;

[0086] In the embodiment, the baseline capacitance sampling values can be the capacitance values in a stable state obtained by performing multiple capacitance measurements on the capacitance grid under no external force, as a reference. Further, the baseline capacitance sampling values can be the basic input data for fitting the static response curve of capacitance-pressure through Gaussian process regression. The capacitance saturation values can be the maximum capacitance response values that the sensing area of the capacitance grid can reach under the action of the maximum pressure, and can be used to determine the upper limit value of saturation in the basic capacitance response threshold. In the embodiment, the capacitance saturation values can be the capacitance values recorded in the state where the capacitance changes tend to be stable by applying gradually increasing pressure. Further, the capacitance saturation values can participate in the modeling of the capacitance-pressure response curve together with the non-linear distortion points. The non-linear distortion points can be the inflection points in the capacitance-pressure response curve deviating from the linear relationship, and can be used to define the effective working interval between the lower limit value of dynamic range and the upper limit value of saturation. In the embodiment, the non-linear distortion points can be identified by analyzing the curve of capacitance change with pressure. Further, the non-linear distortion points can participate in the setting of the capacitance response threshold together with the capacitance saturation values. Gaussian process regression can be a non-parametric regression method for inferring function distribution from limited samples, which can be used to fit the static response curve of capacitance-pressure, and improve the accuracy of threshold setting. In the embodiment, Gaussian process regression can be based on the Bayesian framework, and the similarity between samples is calculated through kernel function to construct the confidence interval of the capacitance-pressure relationship. Further, Gaussian process regression can act on the baseline capacitance sampling values, capacitance saturation values, and non-linear distortion points to generate a response model.

[0087] The extraction of baseline capacitance sampling values can be achieved by screening capacitance data in a touchless state from a perception feature database. Further, the extraction of baseline capacitance sampling values can be achieved by setting a time window to screen stable state data, excluding transient interference, so that reliable baseline capacitance values can be obtained. The extraction of capacitance saturation values and nonlinear distortion points can be achieved by screening capacitance response data in a high pressure state from the database and identifying nonlinear feature points. Further, the extraction of capacitance saturation values and nonlinear distortion points can be achieved by using a curve inflection point detection algorithm to identify nonlinear distortion points, so that the effective dynamic range of the capacitance response can be defined. Gaussian process regression fitting can be achieved by constructing a nonlinear response model based on historical capacitance-pressure data. Further, Gaussian process regression fitting can improve fitting accuracy by selecting appropriate kernel functions, so that a high-precision capacitance-pressure static response curve can be generated.

[0088] Extracting multiple coordinate sampling data of each perception area layout on standard test points from the perception feature database, calculating the root mean square error and linear fitting residual of the theoretical coordinates, and determining the minimum resolvable distance and linearity error limit of each perception area layout through confidence interval estimation;

[0089] The standard test points can be preset known coordinate positions for evaluating the positioning performance of the capacitance grid. In the embodiment, the standard test points can be achieved by applying a standard pressure at a fixed position and collecting the corresponding capacitance response and coordinate output. Further, the standard test points can include, but are not limited to, one or more of center test points, edge test points, diagonal test points, etc. The root mean square error can be the square root of the square mean of the deviation between the measured coordinates and the theoretical coordinates, and can be used to evaluate the repeatability and stability of coordinate positioning. In the embodiment, the root mean square error can be achieved by squaring the difference between the multiple measurement results and the theoretical value and then taking the average. Further, the root mean square error can be combined with the linear fitting residual to determine the positioning accuracy threshold through confidence interval estimation. The linear fitting residual can be the deviation between the measured coordinates and the ideal linear model, and can be used to evaluate the systematic deviation of coordinate positioning. In the embodiment, the linear fitting residual can be achieved by fitting the relationship between the theoretical coordinates and the measured coordinates using the least squares method to calculate the residual distribution. Further, the linear fitting residual can be used together with the root mean square error to set the positioning accuracy threshold. Confidence interval estimation can be a statistical method for quantifying the uncertainty range of parameter estimates, which can be used to determine a reasonable range for the minimum resolvable distance and linearity error limit. In the embodiment, the confidence interval estimation can be used to calculate the upper and lower limits of the parameters to reflect the reliability of the estimated value. Further, the confidence interval estimation can be used to generate the coordinate positioning accuracy threshold based on the root mean square error and the linear fitting residual.

[0090] The standard test point coordinate data can be extracted by retrieving multiple coordinate sampling results of preset test points from a database. Further, the standard test point coordinate data can be extracted by classifying the data according to test point numbers to support regionalized analysis, thereby providing a data basis for positioning accuracy evaluation. The root mean square error and linear fitting residual can be calculated by statistically analyzing the measured coordinates and the theoretical coordinates. Further, the root mean square error and linear fitting residual can be calculated by using the least square method for linear fitting, thereby quantifying the repeatability and systematic error of coordinate positioning. The confidence interval estimation can be based on statistical methods for interval estimation of positioning error. Further, the confidence interval estimation can be improved by using the Bootstrap method to improve the estimation stability, thereby setting a reasonable minimum resolvable distance and linearity error limit.

[0091] The capacitance response delay data and rate tracking error of each sensing area layout under the preset pressure ramp signal are extracted from the perception feature database, and the Kalman filter is used to smooth the measurement noise and identify the system response bandwidth to determine the minimum perceptible rate gradient and the maximum following rate of each sensing area layout.

[0092] The pressure ramp signal can be a pressure input signal that changes linearly over time, which can be used to test the dynamic performance of the capacitance response. In the embodiment, the pressure ramp signal can be achieved by controlling the device to apply a continuously changing pressure to the capacitance grid, simulating dynamic touch behavior. Further, the pressure ramp signal can be used together with the capacitance response delay data and rate tracking error to set the pressure rate perception threshold. The capacitance response delay data can be the time lag of capacitance change relative to pressure input, which can be used to evaluate the real-time performance of pressure rate perception. In the embodiment, the capacitance response delay data can record the time difference between pressure input and capacitance response, reflecting the system response speed. Further, the capacitance response delay data can be used together with the rate tracking error to set the pressure rate perception threshold. The rate tracking error can be the deviation between the perceived pressure change rate and the actual rate of the system, which can be used to evaluate the accuracy of pressure dynamic response. In the embodiment, the rate tracking error can be calculated by comparing the slope of the pressure input with the slope of the capacitance response. Further, the rate tracking error can be used together with the capacitance response delay data to set the pressure rate perception threshold.

[0093] The Kalman filter can be a recursive algorithm used to estimate the system state from noisy measurement data, which can be used to extract the effective signal components in pressure rate perception. In this embodiment, the Kalman filter can be a smoothing process for measurement noise through a prediction-update mechanism to improve signal stability. Further, the Kalman filter can be applied to the capacitance response delay data and rate tracking error to identify the system response bandwidth. The system response bandwidth can be the frequency range that the system can accurately track the changes of the input signal, which can be used to determine the limit capability of pressure change rate perception. In this embodiment, the system response bandwidth can be achieved by analyzing the filtered capacitance response data to identify its frequency response characteristics. Further, the system response bandwidth can be used as a basis for setting the minimum perceptible rate gradient and the maximum following rate. Extracting pressure ramp signal response data can be achieved by retrieving the capacitance response records under the preset pressure ramp from the database. Further, extracting pressure ramp signal response data can be achieved by grouping data by pressure change rate to support multi-rate analysis, thereby providing basic data for dynamic response analysis. Kalman filter processing can be achieved by noise smoothing and state estimation on capacitance response data. Further, Kalman filter processing can be achieved by dynamically adjusting filter parameters to adapt to different pressure change rates, thereby improving the signal-to-noise ratio and accuracy of pressure rate perception. Identifying the system response bandwidth can be achieved by analyzing the frequency response characteristics of the filtered data. Further, identifying the system response bandwidth can be achieved by using a spectrum analysis method to identify the upper limit of the response bandwidth, thereby determining the dynamic limit of pressure rate perception.

[0094] Taking an industrial-grade high-precision pressure plotting device as an example, the self-made glass sensor capacitance grid layout optimization method of the embodiment can be that on a professional plotting board, the user uses a pressure-sensitive pen to draw fine lines, and the system automatically identifies whether the current pen pressure is within the dynamic range through the preset capacitance-pressure response curve in the perception feature database. When it is detected that the pressure is close to the upper limit of the saturation value, the system triggers the Gaussian process regression model to re-fit the local response curve, and optimizes the capacitance response data through the Kalman filter to prevent signal distortion. At the same time, the system continuously monitors the minimum resolvable distance and linearity error limit to ensure that the pen touch coordinates remain high-precision positioning in complex gesture operations.

[0095] In one of the embodiments, based on the perception feature database, the influence of the grid parameter change in the layout of each perception area on the multi-touch point pressure perception accuracy is analyzed to obtain the grid parameter sensitivity of each perception area layout, including:

[0096] The historical touch point coordinate data, the historical pressure change rate data, and the corresponding historical grid parameter change record of each sensing area layout are extracted from the sensing feature database as training samples to train the time series convolution network to obtain a response model representing the dynamic correlation between the grid parameter change and the multi-dimensional sensing performance in each sensing area layout.

[0097] The time series convolution network can be a deep neural network structure specially processing time series data, extracting local features in the sequence through a convolution layer and modeling the time series dependence relationship, and can be used to model the dynamic correlation between the grid parameter change and the multi-dimensional sensing performance. In the embodiment, the time series convolution network extracts features of the input sequence by stacking multiple convolution layers and activation functions in combination with a sliding window mechanism in the time dimension. Further, the time series convolution network can be used to train the response model in cooperation with the sensing feature database. For example, the time series convolution network can include one or more of a one-dimensional time series convolution network, an expanded time series convolution network, a residual time series convolution network, etc. The response model can be a mathematical model representing the dynamic mapping relationship between the grid parameter change and the multi-dimensional sensing performance in each sensing area layout, and can be used to predict the influence of a specific parameter change on the sensing performance. In the embodiment, the response model is obtained by training the time series convolution network based on the training samples (historical touch point coordinate data, historical pressure change rate data, and historical grid parameter change record). For example, the response model can be used to provide prediction output for parameter-performance correlation strength analysis.

[0098] Training the time series convolution network can be to use the historical touch point coordinate data, the historical pressure change rate data, and the historical grid parameter change record as input and output pairs to train the network model to capture the dynamic relationship between the parameter change and the sensing performance. Further, the training of the time series convolution network can be implemented by using a sliding window to construct training samples, introducing regularization to prevent overfitting, using cross-validation to select the optimal model, etc., so that a high-precision response model can be constructed for performance prediction.

[0099] Based on the response model, the coordinate positioning error change and the pressure rate tracking error change caused by a specific grid parameter change in each sensing area layout under a preset pressure mode sequence are calculated, and the error change is analyzed according to the pressure change rate interval to obtain the parameter-performance correlation strength index of each sensing area layout.

[0100] The parameter-performance correlation strength indicator can be a comprehensive score quantifying the influence degree of a specific grid parameter change on multi-dimensional perceptual performance, and can be used to reflect the sensitivity of the parameter to the performance. In the embodiment, the parameter-performance correlation strength indicator is based on the response model prediction result, and the coordinate positioning error variation and the pressure rate tracking error variation caused by the parameter change under the preset pressure mode sequence are counted, and the Spearman rank correlation analysis is used to obtain the parameter-performance correlation strength indicator. Further, the parameter-performance correlation strength indicator can be used as the input basis of the sensitivity classification table. The statistical error variation can be the variation of the coordinate positioning error and the pressure rate tracking error caused by a specific parameter change under the preset pressure mode sequence based on the response model simulation. Further, the statistical error variation can be achieved by setting multiple groups of parameter perturbation experiments, recording error responses, and classifying and counting the error responses according to the pressure change rate interval, so as to quantify the specific influence of the parameter change on the perceptual performance. The Spearman rank correlation analysis can be a non-parametric correlation analysis on the ordering relationship between the error variation and the parameter variation. Further, the Spearman rank correlation analysis can be achieved by calculating the rank correlation coefficient and evaluating the monotonic relationship strength between the parameter and the performance indicator, so as to exclude the linear hypothesis limitation and reveal the nonlinear correlation strength between the parameter and the performance.

[0101] The preset functional weight of each perceptual area layout in the global perceptual task is used to weight and fuse the corresponding parameter-performance correlation strength indicators, and the interval of the fusion result is divided according to the preset sensitivity classification threshold, so as to obtain the grid parameter sensitivity classification table to quantitatively determine the grid parameter sensitivity of each perceptual area layout.

[0102] The sensitivity grading threshold can be a numerical boundary for dividing the parameter-performance correlation intensity index into different sensitivity levels, and can be used to quantitatively grade the sensitivity of the grid parameters. In this embodiment, the sensitivity grading threshold is set according to the overall performance requirement of the system, and is used to divide the interval of the fused index. For example, the sensitivity grading threshold can be combined with the parameter-performance correlation intensity index to generate a sensitivity grading table. The grid parameter sensitivity grading table can be a query table that records the sensitivity levels of different grid parameters in each sensing area layout, and can be used to provide parameter priority basis for subsequent optimization. In this embodiment, the grid parameter sensitivity grading table is generated by weighted fusion and interval division of the parameter-performance correlation intensity index. For example, the grid parameter sensitivity grading table can guide the generation of the set of grid parameters to be optimized. The weighted fusion can be a weighted average of the parameter-performance correlation intensity index according to the functional importance of each sensing area in the global task. Further, the weighted fusion can be achieved by using a task priority weight allocation strategy, such as assigning a higher weight to the central area, so as to improve the global consistency of the sensitivity evaluation. The interval division can be to divide the fused index into different level intervals according to the preset sensitivity grading threshold. Further, the interval division can be achieved by using an equal-width, equal-frequency or adaptive division strategy based on the distribution, so as to realize the visualization and operable expression of the sensitivity.

[0103] For example, in the scenario of multi-point pressure interaction in touch display screen game playing, the self-made glass sensor grid layout optimization method of the embodiment can be that the user uses double fingers to quickly and alternately press to control the character movement and attack in competitive games, and the system senses the pressure intensity and change rate of each point in real time through the self-made glass sensor. When the pressure sensing error of a certain area increases due to continuous and rapid clicking, the system calls the response model to predict the error change after adjusting the parameters of the area, and determines the key influencing parameters through Spearman rank correlation analysis. Combining the functional weight of the area in the interaction task, the system weightedly fuses the parameter-performance correlation intensity index, and determines that it belongs to a high sensitivity area according to the sensitivity grading table, so as to trigger the fine adjustment mechanism, quickly restore the sensing accuracy, and ensure the stability and accuracy of the operation response.

[0104] In one embodiment, based on the perception feature database, the multiple correlations between the capacitance response, coordinate positioning and pressure rate sensing of each sensing area layout are analyzed, and the grid parameters are extracted from the grid parameter adjustment table according to the multiple correlations for perception importance calculation to generate the set of grid parameters to be optimized for each sensing area layout, including:

[0105] extracting historical capacitance response sequences, historical coordinate positioning data and historical perception performance evaluation data of each sensing area layout under different pressure change rates from the perception feature database, and calculating the sensing behavior similarity under different pressure scenarios through a dynamic time warping algorithm, to cluster the sensing area layouts according to the similarity calculation results, and obtain a typical pressure sensing scenario set;

[0106] The historical capacitance response sequence can be the capacitance value time series data of each sensing area of the capacitance grid changing with time under different pressure change rates, and can be used to represent the time domain adaptability of the capacitance response to dynamic pressure. In the embodiment, the historical capacitance response sequence can be obtained by recording the continuous fluctuation trajectory of the inter-electrode capacitance during the touch process through a high sampling rate sensor circuit. For example, the historical capacitance response sequence can be used to construct the sensing behavior features together with the historical coordinate positioning data and the historical perception performance evaluation data. The historical coordinate positioning data can be the two-dimensional space coordinate time series record of the touch point output by the system under different pressure loads, and can be used to evaluate the positioning stability and trajectory tracking consistency. In an exemplary embodiment, the historical coordinate positioning data can be based on the spatial solution of the electrode signal peak value through the capacitance difference algorithm to generate a continuous frame coordinate sequence. Further, the historical coordinate positioning data can be used for sensing behavior similarity calculation together with the historical capacitance response sequence. The historical perception performance evaluation data can be a comprehensive score or label for the capacitance response, coordinate accuracy and pressure rate tracking effect in the historical touch event, and can be used as a supervision signal or reference benchmark for pressure scenario clustering. In a specific embodiment, the historical perception performance evaluation data can be obtained by expert annotation or multi-index weighted performance score synthesis to reflect the pros and cons of the perception quality. Further, the historical perception performance evaluation data can be used to guide the rationality of the scenario classification results after dynamic time warping.

[0107] The dynamic time warping algorithm can be a sequence matching method for aligning time series data of different lengths or speeds to calculate their similarity, which can be used to eliminate the interference of stress change rate difference on the comparison of perceptual behavior. In the embodiment, the dynamic time warping algorithm can minimize the cumulative distance between two sets of time series data by nonlinear stretching or compressing the time axis. For example, the dynamic time warping algorithm can introduce a weighted Euclidean distance or Mahalanobis distance to enhance the robustness to abnormal fluctuations, or combine a sliding window segmentation matching to improve the local pattern recognition capability, so as to realize the semantic alignment of perceptual behavior under different stress rhythms and eliminate the interference of time asynchrony. The stress scene clustering can be a classification of historical stress events into several typical interaction modes according to the similarity of perceptual behavior, which can be used to identify typical stress interaction types with high frequency and high impact. In the embodiment, the stress scene clustering can use a clustering algorithm to group the behavior feature vectors after dynamic time warping. For example, the stress scene clustering can use K-means algorithm, hierarchical clustering algorithm, DBSCAN algorithm or Gaussian mixture model, so as to extract representative typical interaction modes and reduce the complexity of subsequent modeling. For example, the stress scene clustering can include one or more of a light touch and slide scene, a heavy pressure click scene, and a multi-finger pressure alternation scene.

[0108] The mean, variance, extreme value and covariance matrix of the capacitance response characteristic value, coordinate stability index and rate tracking accuracy in each set of typical stress perception scenes are calculated to construct a multi-modal perception feature tensor, and a partial least squares regression method is used to quantify the complex correlation between the layout grid parameters and the multi-modal perception performance indicators, to obtain a multi-element coupling relationship matrix of the layout of each perception area;

[0109] The multimodal sensing feature tensor can be a three-dimensional structured data volume composed of statistics of three types of indicators: capacitance response, coordinate stability, and rate tracking accuracy. It can be used to comprehensively characterize the statistical distribution and variable relationships of sensing performance under various scenarios. In this embodiment, the multimodal sensing feature tensor can calculate the mean, variance, extreme values, and covariance matrices of each indicator within each typical pressure scenario set and stack them into a tensor. Furthermore, the multimodal sensing feature tensor can introduce a sliding statistical window to dynamically update the variance and covariance, or embed higher-order moment features to enhance nonlinear expressive power, thereby forming a high-dimensional performance descriptor that can be analyzed by a regression model. The multivariate coupling relationship matrix can be a weight matrix describing the nonlinear dependence between grid parameters and multimodal sensing performance indicators, and can be used to reveal the synergistic influence path of parameters on multi-target performance. In this embodiment, the multivariate coupling relationship matrix can be achieved by fitting the latent variable relationship between the grid parameter vector and the multimodal sensing feature tensor using partial least squares regression. For example, multivariate coupling relationship matrices can introduce cross-validation to select the optimal latent variable dimension, or combine sparse constraints to avoid overfitting, thereby revealing the synergistic driving mechanism of parameters on multi-objective performance and breaking through the limitations of univariate analysis.

[0110] Candidate adjustment parameters are extracted from the grid parameter adjustment table of each sensing area based on the multivariate coupling relationship matrix. The contribution of the extracted candidate grid parameters to the overall sensing performance improvement is quantified by the random forest algorithm. The sensing importance of the extracted candidate grid parameters is quantified based on the contribution. Candidate grid parameters whose importance calculation results exceed the importance threshold are selected to form the set of grid parameters to be optimized for each sensing area.

[0111] The candidate adjustment parameters can be a subset of adjustable parameters that may affect perception performance, initially selected from the grid parameter adjustment table. This can be used to narrow the optimization search space and avoid interference from irrelevant parameters. In this embodiment, candidate adjustment parameters can be obtained by filtering based on all operable parameters in the adjustment table and significant related terms in the multivariate coupling relationship matrix. Furthermore, candidate adjustment parameters can serve as the input feature set for the random forest algorithm. Perception importance can be a quantitative score that measures the contribution of candidate grid parameters to the overall improvement of perception performance, and can be used to determine which parameters are most worthy of optimization. In this embodiment, perception importance can be achieved by calculating the information gain or Gini importance of each parameter in the regression tree split using the random forest algorithm. For example, perception importance can be enhanced by using permutation importance or SHAP value to improve interpretability, or by combining multiple sampling to improve stability, thereby achieving a nonlinear, interactive contribution assessment of the parameter's impact and avoiding linear assumption bias. The set of grid parameters to be optimized can be a set of parameters identified as high-value optimization targets after being screened by perception importance. This can be used to accurately focus optimization resources and improve parameter reconstruction efficiency. In this embodiment, the set of grid parameters to be optimized can be formed by selecting candidate parameters whose importance exceeds a preset threshold. Furthermore, the set of grid parameters to be optimized can be configured with a dynamic threshold mechanism to adaptively adjust the selection criteria based on the current system load or scene activity, thereby ensuring that optimization resources are concentrated on the most promising parameters and improving system response efficiency and convergence speed.

[0112] Taking multi-pressure level interaction with a touchscreen stylus as an example, the self-made glass sensor capacitive grid layout optimization method in this embodiment allows users to perform calligraphy writing with a pressure-sensitive pen, rapidly switching between light, medium, and heavy pressure, while simultaneously using multi-finger assisted positioning. The system collects the capacitance timing, coordinate trajectory, and performance score during this process. By dynamically warping the behavior patterns under different writing speeds, it clusters and identifies typical scenarios such as "rapid heavy pressure stroke" and "continuous light swipe transition." A multimodal feature tensor is constructed for each scenario, and partial least squares regression is used to find that electrode spacing and edge capacitance coupling have the greatest impact on pressure rate tracking. Random forest further confirms that only three parameters significantly contribute to the overall perception quality, while the remaining parameters can be frozen. Finally, an optimization set containing only these three parameters is generated, enabling the system to complete local reconstruction within milliseconds, ensuring that the thickness of the handwriting and ink smudges change naturally with pressure, without delay or distortion.

[0113] In one of the embodiments, the sensitivity of each grid parameter is grouped according to the sensitivity of each sensing area layout to obtain a multi-level sensitivity layout area, and a mapping relationship between the grid parameter adjustment amount of each level sensitivity layout area and the multi-touch point pressure sensing performance improvement amount is constructed by a regression tree to generate a progressive layout adjustment rule to optimize the set of grid parameters to be optimized of each sensing area layout, and after the parameterized reconstruction of the layout of the self-made glass sensor capacitive grid based on the optimization result, including:

[0114] The performance index time series data of the self-made glass sensor after layout parameter optimization under multiple pressure change rate test modes is obtained, and the performance index time series data is used as input features to train a conditional generative adversarial network to generate real-time high-fidelity virtual pressure touch signals and simulate sensor responses through the trained network to obtain virtual sensing response data.

[0115] In this embodiment, the performance index time series data can be a dynamic performance sequence data output by the sensor after layout optimization under multiple pressure change rate test modes, which can be used as a conditional input to drive the generation of a generative adversarial network training to simulate the sensing behavior under extreme conditions. In this embodiment, the performance index time series data can be a continuous data stream of capacitive response, coordinate offset, pressure rate tracking error, etc. collected by a high sampling rate sensing circuit over time. Further, the performance index time series data can be the input features of the conditional generative adversarial network, and the virtual sensing response data constitutes a training closed loop. The conditional generative adversarial network can be a deep generative model that can generate realistic time series data according to input conditions, and can be used to generate high-fidelity virtual pressure touch signals and sensor responses without physical testing conditions. In one exemplary embodiment, the conditional generative adversarial network can be trained by an adversarial network to make the generator learn the distribution characteristics of the performance index time series data, and the discriminator can distinguish between real and generated data. Further, the conditional generative adversarial network can enhance time series dependency modeling by using a time series encoder, and introduce an attention mechanism to focus on pressure mutation segments, so that high-fidelity virtual extension of sensor behavior under extreme pressure rates can be achieved.

[0116] Virtual sensing response data can be sensor output signals generated by a conditional generative adversarial network in a simulated pressure touch scenario, which can be used to expand the extreme condition data set for boundary analysis and parameter scanning. In one specific embodiment, the virtual sensing response data can be a capacitive, coordinate, and rate response sequence corresponding to the pressure change rate generated based on the performance index time series data. Further, the virtual sensing response data can be the input basis for parameter tolerance boundary calculation and virtual layout simulation.

[0117] The parameter tolerance boundary can be obtained by imposing a limit on the rate of change of pressure in the virtual perception response data to identify a performance collapse threshold. Illustratively, the parameter tolerance boundary can be obtained by detecting an error jump inflection point using a sliding window statistical method, defined as the tolerance boundary, so that a physical feasibility constraint before manufacturing can be established to avoid the design entering an unstable region.

[0118] The virtual layout simulation environment can be a digital simulation platform containing a four-dimensional parameter space of electrode width, pitch, shape factor, and interlayer coverage area, which can be used to support large-scale virtual iteration before multi-parameter collaborative optimization. In this embodiment, the virtual layout simulation environment can be constructed by a parameterized modeling tool to adjust the electrode geometry, and coupled with electromagnetic field and mechanical stress simulation engines. Further, the virtual layout simulation environment can automatically switch the geometry configuration by using a parameterized script, combined with a grid adaptive algorithm to improve simulation efficiency, so that large-scale, high-degree-of-freedom virtual parameter space exploration can be achieved.

[0119] The optimization objective is to minimize the comprehensive accuracy weighted sum of multi-touch point pressure perception, and the comprehensive accuracy includes coordinate error, pressure value error, and rate tracking error. The multi-objective Bayesian optimization is used to collaboratively optimize the virtual grid parameters of each perception area layout in the virtual layout simulation environment, to obtain a Pareto optimal virtual parameter combination set of each perception area layout.

[0120] The comprehensive accuracy weighted sum can be a comprehensive performance evaluation index of the weighted fusion of the three types of errors, which can be used as a unified objective function of multi-objective optimization to balance multi-dimensional performance requirements. In this embodiment, the comprehensive accuracy weighted sum can be linearly weighted and summed by setting weight coefficients according to the priority of the perception task. Further, the comprehensive accuracy weighted sum can be the optimization objective of the multi-objective Bayesian optimization to drive the virtual parameter combination search. The multi-objective Bayesian optimization can search for a Pareto optimal solution set in the virtual layout simulation environment with the comprehensive accuracy weighted sum as the optimization objective. Illustratively, the multi-objective Bayesian optimization can balance exploration and development by using the expected improvement and Pareto front update strategy, and introduce a Gaussian process proxy model to accelerate convergence, so that a multi-objective balance point can be efficiently located in a high-dimensional parameter space, and the number of simulations can be reduced. The Pareto optimal virtual parameter combination set can be a parameter set that cannot further optimize the comprehensive accuracy without deteriorating the performance of other dimensions, which can be used to provide an optimal parameter candidate scheme before manufacturing. In this embodiment, the Pareto optimal virtual parameter combination set can be searched in a four-dimensional parameter space by a multi-objective Bayesian optimization algorithm to obtain a non-dominated solution set. Further, the Pareto optimal virtual parameter combination set can be the input basis for high-precision electromagnetic-structure coupled simulation and final reconstruction.

[0121] Based on the virtual perception response data, parameter tolerance boundaries of each perception area layout under extreme pressure change rate are obtained as stability constraint conditions, and a virtual layout simulation environment including four groups of virtual grid parameters of electrode width, spacing, shape factor and interlayer coverage area is constructed through parameterized scanning;

[0122] With the comprehensive precision weighted sum of multi-touch point pressure perception as the optimization objective, the comprehensive precision including coordinate error, pressure value error and rate tracking error is optimized by multi-objective Bayesian optimization, and a Pareto optimal virtual parameter combination set of each perception area layout is obtained.

[0123] Based on each Pareto optimal virtual parameter combination set, high-precision electromagnetic-structure coupling simulation is performed on the capacitor grid, and when the perception performance index data obtained by simulation is stable in the preset performance target interval, the final parameterized reconstruction and output of the layout of the self-made glass sensor capacitor grid before manufacturing are controlled according to the optimized virtual parameter combination set.

[0124] In the embodiment, the high-precision electromagnetic-structure coupling simulation can be a multi-physics field simulation that simultaneously simulates the influence of electrode geometric structure on electric field distribution and mechanical deformation, and can be used to verify the feasibility of the virtual optimization result in the real physical environment. In the embodiment, the high-precision electromagnetic-structure coupling simulation can be importing the virtual parameter combination into a finite element simulation platform to solve the coupling equation of capacitive coupling and stress distribution. Further, the high-precision electromagnetic-structure coupling simulation can monitor the cooperative response of capacitive fluctuation and structural deformation by setting a multi-working-condition pressure loading path, so as to ensure that the virtual optimization result still meets the performance target under real physical constraints. The final parameterized reconstruction and output can be generating a manufacturing layout design file according to the Pareto optimal combination obtained by coupling simulation. Exemplarily, the final parameterized reconstruction and output can output a GDSII format file and embed parameter tolerance boundary annotations for mask manufacturing and yield analysis, so as to realize seamless connection from virtual optimization to physical manufacturing and reduce trial and error risk.

[0125] In addition, the embodiment of the present application also proposes a storage medium, and the storage medium stores a self-made glass sensor capacitor grid layout optimization program. When the self-made glass sensor capacitor grid layout optimization program is executed by a processor, the steps of the self-made glass sensor capacitor grid layout optimization method described above are realized.

[0126] In addition, with reference to Figure 3 , the embodiment of the present application also proposes a self-made glass sensor capacitor grid layout optimization device, and the self-made glass sensor capacitor grid layout optimization device comprises:

[0127] The data acquisition module 10 is used for dividing the layout structure of the self-made glass sensor capacitive grid by a multi-dimensional perception analysis method to obtain a multi-perception area layout, and collecting historical capacitive change data, historical touch point coordinate data and corresponding historical pressure change rate data of each perception area layout under a plurality of pressure loads to construct a perception feature database.

[0128] The parameter perception module 20 is used for determining a basic capacitive response threshold, a coordinate positioning accuracy threshold and a pressure change rate perception threshold of each perception area layout according to the perception feature database, and analyzing the influence of grid parameter changes in each perception area layout on multi-touch point pressure perception accuracy based on the perception feature database to obtain a grid parameter sensitivity of each perception area layout.

[0129] The adjustment generation module 30 is used for acquiring real-time capacitive change data, real-time touch point coordinate data and real-time pressure change rate data of each perception area layout, and generating a grid parameter adjustment table of each perception area layout when the corresponding basic capacitive response threshold, coordinate positioning accuracy threshold or pressure change rate perception threshold is exceeded.

[0130] The correlation analysis module 40 is used for analyzing the multiple correlations among capacitive response, coordinate positioning and pressure rate perception of each perception area layout based on the perception feature database, and performing perception importance calculation on grid parameters extracted from the grid parameter adjustment table according to the multiple correlations to generate a set of to-be-optimized grid parameters of each perception area layout.

[0131] The parameter adjustment module 50 is used for grouping each perception area layout according to the grid parameter sensitivity to obtain a multi-level sensitivity layout area, constructing a mapping relationship between the grid parameter adjustment amount and the multi-touch point pressure perception performance improvement amount of each level sensitivity layout area by a regression tree, generating a gradual layout adjustment rule to optimize the set of to-be-optimized grid parameters of each perception area layout, and controlling the parameterized reconstruction of the layout of the self-made glass sensor capacitive grid based on the optimization result.

[0132] Other embodiments or specific implementations of the self-made glass sensor capacitive grid layout optimization device can refer to the above-mentioned method embodiments, which will not be described here.

[0133] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0134] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments. In the module claims in which several devices are listed, several of the devices can be embodied by the same hardware item. The use of the words first, second, and third, etc. does not represent any order, and the words can be interpreted as names.

[0135] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, and of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a Read Only Memory image (ROM) / Random Access Memory (RAM), a magnetic disk, or an optical disk) and includes a number of instructions for making an end user device (which can be a mobile phone, a computer, a server, an air conditioner, or a network user device) execute the methods described in the various embodiments of the present application.

[0136] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for optimizing the capacitive grid layout of a self-made glass sensor, characterized in that, The method includes: The layout structure of the capacitor grid of the self-made glass sensor is divided into regions by multi-dimensional sensing analysis method to obtain a multi-sensing region layout. Historical capacitance change data, historical touch point coordinate data and corresponding historical pressure change rate data of each sensing region layout under various pressure loads are collected to construct a sensing feature database. Based on the perception feature database, the basic capacitance response threshold, coordinate positioning accuracy threshold, and pressure change rate perception threshold of each perception area are determined. Based on the perception feature database, the influence of grid parameter changes on the multi-touch point pressure perception accuracy of each perception area is analyzed to obtain the grid parameter sensitivity of each perception area. The system acquires real-time capacitance change data, real-time touch point coordinate data, and real-time pressure change rate data for each of the sensing area maps. When the corresponding basic capacitance response threshold, coordinate positioning accuracy threshold, or pressure change rate sensing threshold is exceeded, a grid parameter adjustment table for each of the sensing area maps is generated. Based on the perception feature database, the multiple correlations between capacitance response, coordinate positioning and pressure rate perception of each perception area are analyzed, and the grid parameters are extracted from the grid parameter adjustment table according to the multiple correlations to calculate the perception importance, so as to generate a set of grid parameters to be optimized for each perception area. Based on the sensitivity of each grid parameter, the layout of each sensing region is grouped by sensitivity to obtain a multi-level sensitivity layout region. A regression tree is used to construct a mapping relationship between the grid parameter adjustment amount and the improvement amount of multi-touch point pressure sensing performance of each level of sensitivity layout region. A progressive layout adjustment rule is generated to optimize the set of grid parameters to be optimized in each sensing region layout. Based on the optimization results, the layout of the self-made glass sensor capacitor grid is parametrically reconstructed. The method of dividing the layout structure of the self-made glass sensor capacitor grid into regions using a multi-dimensional sensing analysis method to obtain a multi-sensing region layout includes: The electrode density, cell capacitance base value, mutual coupling coefficient and signal-to-noise ratio of each sub-region in the capacitor grid layout are obtained to construct the layout complexity quantization matrix of each sub-region. Based on the complex quantification matrix of each of the aforementioned layouts, a perceptual directed graph is established, and clustering operation is performed on the mean and peak values ​​of capacitance change amplitude of each of the aforementioned sub-regions under pressure load to perform preliminary partitioning of each of the aforementioned sub-regions and obtain capacitance response grouping results. The touch point coordinate offset data corresponding to each sub-region is obtained, and the coordinate offset data is compared with the preset positioning tolerance threshold. The capacitive response grouping results are then refined and adjusted according to the comparison results to obtain a multi-sensing region map.

2. The method for optimizing the capacitor grid layout of a self-made glass sensor as described in claim 1, characterized in that, The basic capacitance response threshold includes the baseline capacitance value, the lower limit of the dynamic range, and the upper limit of saturation; the coordinate positioning accuracy threshold includes the minimum resolvable distance and the linearity error limit; the pressure change rate sensing threshold includes the minimum perceptible rate gradient and the maximum following rate.

3. The method for optimizing the capacitive grid layout of a self-made glass sensor as described in claim 2, characterized in that, The determination of the basic capacitance response threshold, coordinate positioning accuracy threshold, and pressure change rate sensing threshold for each of the sensing regions based on the sensing feature database includes: The baseline capacitance sampling value, capacitance saturation value and nonlinear distortion point of each sensing area in the non-touch state are extracted from the sensing feature database. The static response curve of capacitance-pressure is fitted by Gaussian process regression to determine the baseline capacitance value, lower limit of dynamic range and upper limit of saturation of each sensing area. Extract multiple coordinate sampling data of standard test points for each of the sensing area maps from the sensing feature database, calculate the root mean square error and linear fitting residual between the data and the theoretical coordinates, and determine the minimum resolvable distance and linearity error limit of each of the sensing area maps by confidence interval estimation. Capacitive response delay data and rate tracking error of each sensing region under a preset pressure ramp signal are extracted from the sensing feature database. The measurement noise is smoothed by a Kalman filter and the system response bandwidth is identified to determine the minimum perceptible rate gradient and maximum following rate of each sensing region.

4. The method for optimizing the capacitive grid layout of a self-made glass sensor as described in claim 1, characterized in that, The analysis of the impact of grid parameter changes on the multi-touch point pressure sensing accuracy in each sensing area based on the sensing feature database, to obtain the grid parameter sensitivity of each sensing area, includes: Historical touch point coordinate data, historical pressure change rate data and corresponding historical grid parameter change records of each of the perception area maps are extracted from the perception feature database and used as training samples to train the temporal convolutional network to obtain a response model that represents the dynamic relationship between grid parameter changes and multi-dimensional perception performance in each of the perception area maps. Based on the response model, the coordinate positioning error change and pressure rate tracking error change caused by the change of specific grid parameters in each of the sensing area maps under the preset pressure mode sequence are statistically analyzed. Spearman rank correlation analysis is performed on the error change according to the pressure change rate interval to obtain the parameter-performance correlation strength index of each of the sensing area maps. The corresponding parameter-performance correlation strength index is weighted and fused using the preset functional weights of each perception region map in the global perception task. The fusion result is then divided into intervals according to the preset sensitivity grading threshold to obtain a grid parameter sensitivity grading table to quantitatively determine the grid parameter sensitivity of each perception region map.

5. The method for optimizing the capacitor grid layout of a self-made glass sensor as described in claim 1, characterized in that, The process involves analyzing the multiple correlations between capacitive response, coordinate positioning, and pressure rate sensing of each sensing region based on the sensing feature database, and extracting grid parameters from the grid parameter adjustment table according to these multiple correlations to calculate sensing importance, thereby generating a set of grid parameters to be optimized for each sensing region. This includes: Historical capacitance response sequences, historical coordinate positioning data, and historical sensing performance evaluation data of each sensing region map under different pressure change rates are extracted from the sensing feature database. The similarity of sensing behavior under different pressure scenarios is calculated by dynamic time warping algorithm. Based on the similarity calculation results, each sensing region map is clustered for pressure scenarios to obtain a set of typical pressure sensing scenarios. The mean, variance, extreme values, and covariance matrix of the capacitive response characteristic values, coordinate stability index, and rate tracking accuracy within each set of typical pressure sensing scenarios are calculated to construct a multimodal sensing feature tensor. The partial least squares regression method is used to quantify the complex correlation between the layout mesh parameters and the multimodal sensing performance index, thereby obtaining the multivariate coupling relationship matrix of each sensing area layout. Based on the multivariate coupling relationship matrix, candidate adjustment parameters are extracted from the grid parameter adjustment table of each of the sensing regions. The contribution of the extracted candidate grid parameters to the overall sensing performance improvement is quantified by the random forest algorithm. The sensing importance of the extracted candidate grid parameters is quantified based on the contribution measure. Candidate grid parameters whose importance calculation results exceed the importance threshold are selected to form the set of grid parameters to be optimized for each of the sensing regions.

6. The method for optimizing the capacitive grid layout of a self-made glass sensor as described in claim 1, characterized in that, The process involves grouping the sensor area layout according to the sensitivity of each grid parameter to obtain multi-level sensitivity layout regions. A regression tree is then used to construct a mapping relationship between the grid parameter adjustment amount and the improvement in multi-touch point pressure sensing performance for each level of sensitivity layout region. A progressive layout adjustment rule is generated to optimize the set of grid parameters to be optimized for each sensor area layout. Based on the optimization results, the layout of the self-made glass sensor capacitor grid is then parametrically reconstructed. This process includes: The performance index time series data of the self-made glass sensor with optimized layout parameters are obtained under various pressure change rate test modes. The performance index time series data is used as input features to train the conditional generative adversarial network. The trained network is used to generate high-fidelity virtual pressure touch signals in real time and simulate sensing response to obtain virtual perception response data. Based on the virtual sensing response data, the parameter tolerance boundary of each sensing area layout under extreme pressure change rate is obtained as a stability constraint condition, and a virtual layout simulation environment containing four sets of virtual mesh parameters including electrode width, spacing, shape factor and interlayer coverage area is constructed by parametric scanning method. The optimization objective is to minimize the weighted sum of the comprehensive accuracy of multi-touch pressure sensing, which includes coordinate error, pressure value error, and rate tracking error. Multi-objective Bayesian optimization is used to collaboratively optimize the virtual mesh parameters of each sensing region in the virtual landscape simulation environment to obtain the Pareto optimal set of virtual parameter combinations for each sensing region. High-precision electromagnetic-structural coupling simulation is performed on the capacitor grid based on each Pareto optimal virtual parameter combination set. When the sensing performance index data obtained from the simulation is stable within the preset performance target range, the layout of the self-made glass sensor capacitor grid is controlled according to the optimized virtual parameter combination set for final parameterization reconstruction and output before manufacturing.

7. A self-made glass sensor capacitance grid layout optimization device, characterized in that, The self-made glass sensor capacitance grid layout optimization device includes: The data acquisition module is used to divide the layout structure of the capacitor grid of the self-made glass sensor into regions using a multi-dimensional perception analysis method, obtain a multi-sensor region layout, and collect historical capacitance change data, historical touch point coordinate data and corresponding historical pressure change rate data of each sensing region layout under various pressure loads, so as to construct a sensing feature database. The parameter sensing module is used to determine the basic capacitance response threshold, coordinate positioning accuracy threshold, and pressure change rate sensing threshold of each sensing area based on the sensing feature database, and to analyze the impact of grid parameter changes on the multi-touch point pressure sensing accuracy based on the sensing feature database, thereby obtaining the grid parameter sensitivity of each sensing area. The adjustment generation module is used to obtain real-time capacitance change data, real-time touch point coordinate data and real-time pressure change rate data of each of the sensing area maps, and generate a grid parameter adjustment table for each of the sensing area maps when the corresponding basic capacitance response threshold, coordinate positioning accuracy threshold or pressure change rate sensing threshold is exceeded. The correlation analysis module is used to analyze the multiple correlations between the capacitance response, coordinate positioning and pressure rate perception of each of the sensing regions based on the sensing feature database, and extract grid parameters from the grid parameter adjustment table according to the multiple correlations to calculate the perception importance, so as to generate a set of grid parameters to be optimized for each of the sensing regions. The parameter adjustment module is used to group the layout of each sensing region according to the sensitivity of each grid parameter to obtain a multi-level sensitivity layout region. The module constructs a mapping relationship between the grid parameter adjustment amount and the improvement amount of multi-touch point pressure sensing performance of each level sensitivity layout region through a regression tree, generates progressive layout adjustment rules to optimize the set of grid parameters to be optimized in each sensing region layout, and controls the parameterized reconstruction of the layout of the self-made glass sensor capacitor grid based on the optimization results. The method of dividing the layout structure of the self-made glass sensor capacitor grid into regions using a multi-dimensional sensing analysis method to obtain a multi-sensing region layout includes: The electrode density, cell capacitance base value, mutual coupling coefficient and signal-to-noise ratio of each sub-region in the capacitor grid layout are obtained to construct the layout complexity quantization matrix of each sub-region. Based on the complex quantification matrix of each of the aforementioned layouts, a perceptual directed graph is established, and clustering operation is performed on the mean and peak values ​​of capacitance change amplitude of each of the aforementioned sub-regions under pressure load to perform preliminary partitioning of each of the aforementioned sub-regions and obtain capacitance response grouping results. The touch point coordinate offset data corresponding to each sub-region is obtained, and the coordinate offset data is compared with the preset positioning tolerance threshold. The capacitive response grouping results are then refined and adjusted according to the comparison results to obtain a multi-sensing region map.

8. A self-made glass sensor capacitance grid layout optimization device, characterized in that, The self-made glass sensor capacitance grid layout optimization device includes: a memory, a processor, and a self-made glass sensor capacitance grid layout optimization program stored in the memory and executable on the processor. The self-made glass sensor capacitance grid layout optimization program is configured to implement the steps of the self-made glass sensor capacitance grid layout optimization method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a self-made glass sensor capacitor grid layout optimization program, which, when executed by a processor, implements the steps of the self-made glass sensor capacitor grid layout optimization method as described in any one of claims 1 to 6.

Images