A method for recognizing a continuous touch signal, a control device, and a storage medium

Abstract

A method for recognizing continuous touch signals, a control device and a storage medium, wherein the method comprises: acquiring a plurality of touch signals generated by touch actions; performing signal waveform form feature analysis and signal cross-correlation feature analysis on the plurality of touch signals; when it is analyzed that the signal waveform form feature and the signal cross-correlation feature both conform to the signal features corresponding to the continuous touch actions, performing a touch response operation corresponding to the plurality of touch signals, thereby improving the accuracy of recognizing continuous touch signals.

Description

Technical Field

[0001] This article relates to touch technology, and more particularly to a method, control device, and storage medium for recognizing continuous touch signals. Background Technology

[0002] Traditional methods for identifying continuous touch signals primarily involve analyzing the amplitude and time difference of multiple touch signals collected by a sensor. If the amplitude and time difference of multiple touch signals meet their respective preset thresholds, then the collected touch signals are determined to be continuous touch signals. This method is prone to false positives, reducing the accuracy of continuous touch signal identification and affecting the user's touch operation experience. Summary of the Invention

[0003] This application provides a method, control device, and storage medium for identifying continuous touch signals, which can improve the accuracy of continuous touch signal identification.

[0004] The continuous touch signal recognition method provided in this application includes: Acquire multiple touch signals generated by a touch action; The waveform morphology and cross-correlation characteristics of the multiple touch signals are analyzed. When the signal waveform morphology and cross-correlation characteristics are found to match the signal characteristics corresponding to continuous touch actions, the touch response operation corresponding to the multiple touch signals is executed.

[0005] In one exemplary embodiment, the plurality of touch signals include a plurality of raw touch signals acquired by a sensor or a preprocessed signal obtained by preprocessing the plurality of raw touch signals, wherein: The preprocessing of the plurality of original touch signals includes: Calculate the short-time energy values ​​of the multiple original touch signals as the preprocessed signal; or, The short-time energy value signals of the multiple original touch signals are calculated, and the short-time energy value signals are combined and smoothed to serve as the preprocessed signal. The combined smoothing process includes multiple individual smoothing operations.

[0006] In one exemplary embodiment, the combined smoothing process includes: The N-point mean smoothing, M-point mean smoothing, and reverse K-point median smoothing are performed in a preset order, where N, M, and K are all positive integers.

[0007] In one exemplary embodiment, signal waveform morphology feature analysis is performed on multiple touch signals, including one or more of the following methods: Method 1: Perform two-endpoint verification on each of the aforementioned touch signals; Method 2: For the multiple touch signals, analyze the total number of peak points where the analyzed value is greater than the preset baseline Ta, and analyze the duration T1 of each touch signal being greater than or equal to the baseline Ta; Method 3: Analyze the duration T2 of each touch signal being greater than or equal to a preset baseline Tc, where the preset baseline Tc is greater than the preset baseline Ta; Method 4: For the multiple touch signals, the total duration T3 of the analyzed value being greater than the preset baseline Tb, where the preset baseline Tb is determined based on the average of the multiple touch signals; Method 5: Analyze the relationship between the duration T1, the duration T2, and the total duration T3; Method 6: Analyze the time difference between the peak points of two adjacent touch signals; Method 7: Analyze the frequency corresponding to the median spectral energy of each touch signal; Method 8: Analyze the sum of all frequency energies less than or equal to a preset frequency threshold F in the multiple touch signals, where 0Hz < F ≤ 25Hz; Method 9: Analyze the average energy ratio of the multiple touch signals across multiple preset frequency bands, including: [190 Hz, 1200 Hz], [1600 Hz - 2000 Hz].

[0008] In an exemplary embodiment, the preset baseline Ta is: NIS is the maximum value of the noise component in the plurality of touch signals, and e and f are hyperparameters; The preset baseline Tc is: P is the peak value of each touch signal.

[0009] In an exemplary embodiment, based on the method of analyzing the signal waveform morphology features of multiple touch signals, the signal waveform morphology features corresponding to continuous touch actions refer to the signal waveform morphology features of the multiple touch signals satisfying one or more of the following conditions: Condition 1: Each of the touch signals contains two endpoints; Condition 2: For the plurality of touch signals, the total number of peak points with values ​​greater than the preset baseline Ta is the same as the number of the plurality of touch signals; the duration T1 is within the first preset time range; Condition 3: The duration T2 is within the second preset time range; Condition 4: The duration T3 is within the third preset time range; Condition 5: The duration T1 is less than the duration T2, and the duration T2 is less than the duration T3; Condition 6: The time difference between the peak points of two adjacent touch signals is within a preset time range; Condition 7: The frequency corresponding to the median spectral energy of each touch signal is within a preset frequency range, which is [80Hz, 2000Hz]. Condition 8: The energy of all frequencies less than or equal to a preset frequency threshold F among the plurality of touch signals and the energy less than the preset energy and threshold. Condition 9: The average energy of all the multiple touch signals in the first frequency band is greater than the average energy of all the signals in the second frequency band, and the maximum value of the frequency amplitude in the first frequency band is greater than the maximum value of the frequency amplitude in the second frequency band.

[0010] In one exemplary embodiment, signal cross-correlation feature analysis is performed on multiple touch signals, including one or more of the following methods: Method 1: Analyze the Pearson correlation coefficient of two adjacent touch signals in at least one of the time or frequency domains; Method 2: Analyze the mutual information of two adjacent touch signals in at least one of the time or frequency domains.

[0011] In an exemplary embodiment, based on the method of performing signal cross-correlation feature analysis on multiple touch signals, the signal cross-correlation feature corresponding to the signal feature of continuous touch action means that the signal cross-correlation feature of the multiple touch signals satisfies one or more of the following conditions: Condition 1: The Pearson correlation coefficient is greater than or equal to a preset coefficient value A, where 0.4 ≤ A ≤ 0.5; Condition 2: The mutual information is greater than 0.

[0012] The non-transient computer-readable storage medium provided in this application stores one or more program instructions, which can be executed by one or more processors to implement the continuous touch signal recognition method as described in any of the preceding embodiments.

[0013] The control device provided in this application includes: Memory is configured to store computer program instructions that can be executed on a processor; The processor is configured to execute the computer program instructions to implement the continuous touch signal recognition method as described in any of the preceding embodiments.

[0014] The waveform morphology features of the signal can reflect the basic attributes and inherent laws of the signal; the cross-correlation features of the signal can reflect the similarity between different signals; the technical solution described in the embodiments of this application considers continuous touch signals from two aspects: the waveform morphology features of each touch signal and the cross-correlation features between different touch signals, which expands the dimensions of consideration and can improve the accuracy of continuous touch signal recognition.

[0015] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the embodiments described in the description and the accompanying drawings. Attached Figure Description

[0016] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0017] Figure 1 A flowchart illustrating the continuous touch signal recognition method provided in this application embodiment; Figure 2 A schematic diagram of multiple raw touch signals provided in an embodiment of this application; Figure 3 The embodiments provided in this application provide for the Figure 2 A schematic diagram of the signal after short-time energy calculation; Figure 4 The embodiments provided in this application provide for the Figure 3 A schematic diagram of the signal after combined smoothing processing; Figure 5 This is a block diagram of a control device provided in an embodiment of this application. Detailed Implementation

[0018] This application describes several embodiments, but these descriptions are exemplary and not limiting, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0019] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application can also be combined with any conventional features or elements to form unique inventive solutions. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution. Therefore, it should be understood that any feature shown and / or discussed in this application can be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes can be made within the scope of the appended claims.

[0020] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0021] This application provides a method for recognizing continuous touch signals, such as... Figure 1 As shown, the method includes: Step S100: Acquire multiple touch signals generated by the touch action; Step S101: Perform waveform morphology analysis and cross-correlation analysis on multiple touch signals; Step S102: When the signal waveform morphology and cross-correlation characteristics are found to match the signal characteristics corresponding to continuous touch actions, execute the touch response operation corresponding to the multiple touch signals.

[0022] The waveform morphology features of the signal can reflect the basic attributes and inherent laws of the signal; the cross-correlation features of the signal can reflect the similarity between different signals; the technical solution described in the embodiments of this application considers continuous touch signals from two aspects: the waveform morphology features of each touch signal and the cross-correlation features between different touch signals, which expands the dimensions of consideration and can improve the accuracy of continuous touch signal recognition.

[0023] In one exemplary embodiment, the method further includes: After acquiring multiple touch signals generated by a touch action, before performing waveform morphology and cross-correlation analysis on these signals, the multiple touch signals can be treated as a single signal to calculate their characteristic values. If the characteristic value is greater than a preset characteristic threshold, then the waveform morphology and cross-correlation analysis on the multiple touch signals can be performed. If the characteristic value is less than the preset characteristic threshold, it can be directly determined as an invalid tap.

[0024] The feature value includes at least one of peak-to-peak value and root mean square value. The feature value being greater than a preset feature threshold includes at least one of the following: the peak-to-peak value being greater than its corresponding preset threshold, and the root mean square value being greater than its corresponding preset threshold.

[0025] In this embodiment, the touch signals are first screened using the magnitude of feature values, which can quickly eliminate invalid tap signals, reduce the workload of subsequent feature analysis, and lower unnecessary data processing costs.

[0026] In an exemplary embodiment, the plurality of touch signals include a plurality of raw touch signals acquired by a sensor or a preprocessed signal obtained by preprocessing the plurality of raw touch signals; the sensor may be an accelerometer or an elastic wave sensor; the type of the accelerometer may be piezoelectric, piezoresistive, capacitive or servo, and the passband of the accelerometer may be 0Hz-2kHz; the passband of the elastic wave sensor may be 0Hz-2kHz; the interaction surface between the sensitive element of the sensor and the touch action is arranged as horizontally or nearly horizontally as possible.

[0027] In one exemplary embodiment, the method of preprocessing the plurality of raw touch signals includes: The short-time energy values ​​of the multiple original touch signals are calculated. For example, the multiple original touch signals can be segmented by framing or windowing, and the energy value in each segment can be calculated to obtain the short-time energy values ​​of the multiple original touch signals. Correspondingly, the preprocessed signal is the short-time energy value signal of the multiple original touch signals.

[0028] For example, the original touch signal is windowed, and the window length of each window is N. Then the short-time energy value in the nth window is... The calculation method is as follows ,in, This represents the value of the original touch signal at the m-th sampling point within the n-th window.

[0029] Assuming the data frame length of the multiple raw touch signals collected by the sensor is 1000, meaning there are 1000 sampled signals, and each window has a window length N of 25 and a window sliding step size of 5, then the number of windows is 196. The sum of squares of the 1st to 25th sampled signals is E1; the sum of squares of the 6th to 30th sampled signals is E2; and so on, until E is calculated. 196 .

[0030] The original touch signal is often non-stationary. Calculating the short-time energy value of the original touch signal can adapt to its time-varying characteristics, more sensitively detect changes in the original touch signal, and better analyze its characteristics. The short-time energy value signal can also suppress background noise in the original touch signal, improving the signal-to-noise ratio. This application's embodiments calculate the short-time energy values ​​of multiple original touch signals, which helps in subsequent signal waveform morphology feature analysis and signal cross-correlation feature analysis, improving the accuracy of the feature analysis results.

[0031] In another exemplary embodiment, the method of preprocessing the plurality of raw touch signals includes: The short-time energy values ​​of the multiple original touch signals are calculated, and the short-time energy values ​​are then combined and smoothed. This combined smoothing process includes multiple individual smoothing operations. Correspondingly, the preprocessed signal is the combined and smoothed signal.

[0032] The technical solution described in this application, after calculating the short-time energy value of the multiple original touch signals, performs combined smoothing processing, which can further improve the signal quality, reduce or eliminate noise and unwanted fluctuations, and facilitate more accurate feature analysis of the touch signals.

[0033] In one exemplary embodiment, the combined smoothing process includes: The following steps are performed sequentially according to a preset order: N-point mean smoothing, M-point mean smoothing, and reverse K-point median smoothing. N, M, and K are all positive integers, and N, M, and K can be the same or different. For example, 3-point mean smoothing, 6-point mean smoothing, and reverse 5-point median smoothing are performed sequentially.

[0034] Figure 2 A schematic diagram of multiple original touch signals is given. Figure 3 To Figure 2 The diagram shows the signal after short-time energy value calculation of the original touch signal. Figure 4 To Figure 3 The diagram shows the signal after combined smoothing. From... Figures 2-4 It can be seen from this that Figure 3 The short-time energy value signal shown is relatively Figure 2The original touch signal shown is smoother, while Figure 4 The smoothed signal shown is relatively Figure 3 The short-time energy value signal shown further reduces signal glitches.

[0035] In one exemplary embodiment, signal waveform morphology feature analysis is performed on multiple touch signals, including one or more of the following methods: Method 1: Perform two-endpoint verification on each of the aforementioned touch signals; Method 2: For the multiple touch signals, analyze the total number of peak points where the analyzed value is greater than a preset baseline Ta, and analyze the duration T1 for each touch signal that is greater than or equal to the baseline Ta; for example, the preset baseline Ta is: NIS is the maximum value of the noise component in the plurality of touch signals, and e and f are hyperparameters; Method 3: Analyze the duration T2 of each touch signal being greater than or equal to a preset baseline Tc, where the preset baseline Tc is greater than the preset baseline Ta; for example, the preset baseline Tc is: P represents the peak value of each touch signal; Method 4: For the multiple touch signals, the total duration T3 of the analyzed value being greater than the preset baseline Tb, where the preset baseline Tb is determined based on the average of the multiple touch signals; Figure 4 The figure shown illustrates the relationship between Tc, Ta, and Tb. Method 5: Analyze the relationship between the durations T1, T2, and T3. Method 6: Analyze the time difference between the peak points of two adjacent touch signals; Method 7: Analyze the frequency corresponding to the median spectral energy of each touch signal; Method 8: Analyze the sum of all frequency energies less than or equal to a preset frequency threshold F in the multiple touch signals, where 0 Hz < F ≤ 25 Hz; Method 9: Analyze the energy ratio of the multiple touch signals in multiple preset frequency bands, including: [190 Hz, 1200 Hz], [1600 Hz - 2000 Hz].

[0036] In an exemplary embodiment, based on the method of analyzing the signal waveform morphology features of multiple touch signals, the signal waveform morphology features corresponding to continuous touch actions refer to the signal waveform morphology features of the multiple touch signals satisfying one or more of the following conditions: Condition 1: Each of the touch signals contains two endpoints; Condition 2: For the plurality of touch signals, the total number of peak points with values ​​greater than the preset baseline Ta is the same as the number of the plurality of touch signals; and the duration T1 is within the first preset time range; Condition 3: The duration T2 is within the second preset time range; Condition 4: The duration T3 is within the second preset time range; The first, second, and third preset time ranges mentioned above can be estimated based on experience. Condition 5: The duration T1 is less than the duration T2, and the duration T2 is less than the duration T3; Condition 6: The time difference between the peak points of two adjacent touch signals is within a preset time range; Condition 7: The frequency corresponding to the median spectral energy of each touch signal is within a preset frequency range, which is [80Hz, 2000Hz]. Condition 8: Among the multiple touch signals, the energy of all frequencies less than the preset frequency threshold F and the energy less than the preset threshold are 0 Hz ≤ F ≤ 25 Hz; Condition 9: The average energy of all the multiple touch signals in the first frequency band is greater than the average energy of all the signals in the second frequency band, and the maximum amplitude of the frequency in the first frequency band is greater than the maximum amplitude of the frequency in the second frequency band.

[0037] The following is based on Figure 4 Taking the diagram shown as an example, we will illustrate how the waveform characteristics of multiple touch signals correspond to the signal characteristics of continuous touch actions.

[0038] Method 1 involves analyzing the signal waveform morphology characteristic 1, specifically performing dual-endpoint verification on each touch signal: each valid touch signal should have a start point and an end point; after verification, Figure 4 The touch signals shown have the following numbers of start points, end points, and indices for the start and end points of each touch signal: 2, 2, 50, 76, 286, 312.

[0039] Method 2: Analyze the signal waveform morphology feature 2, and analyze the total number of peak points above the preset baseline Ta, and the duration T1 of each touch signal being greater than or equal to the preset baseline Ta; In the middle, e and f are set to 5 and 3 respectively, and NIS takes... Figure 4 The maximum value of the first 5 sampling points of the signal shown is 0.86; the Ta value is 19.3. Figure 4The touch signals shown have a total of 2 peak points above the preset baseline Ta, and the duration of each touch signal being greater than or equal to the preset baseline Ta is T11=5ms and T12=5ms.

[0040] Method 3: Analyze the signal waveform morphology feature 3, and analyze the duration of each touch signal that is greater than or equal to the preset baseline Tc, i.e., the duration T2 of each touch signal; for the first touch signal, Tc1 = Ta + (P1 - Ta) / 2 = 19.3 + (57.6 - 19.3) / 2 = 38.5, and the duration T21 that is greater than or equal to Tc1 is 3ms; for the second touch signal, Tc2 = Ta + (P2 - Ta) / 2 = 19.3 + (67.2 - 19.3) / 2 = 43.3, and the duration T22 that is greater than or equal to Tc2 is 3ms; P1 and P2 are the peak values ​​of the first touch signal and the second touch signal, respectively.

[0041] Method 4: Analyze the signal waveform morphology feature 4, and analyze the total duration T3 of multiple touch signals that is greater than the preset baseline Tb.

[0042] Method 5: Analyze the signal waveform morphology feature 5, and analyze the relationship between the duration T1, the duration T2, and the total duration T3; for continuous touch signals, each touch signal must satisfy T1-T2 > threshold a, T2 / T1 < threshold b, that is, each touch signal satisfies the damping attenuation feature, and multiple touch signals satisfy T3-T1 > threshold c.

[0043] Method 6: Analyze the signal waveform morphology feature 6, and analyze the time difference between the peak points of two adjacent touch signals; the time difference should not be too small or too large, and should meet the preset time condition, which can be obtained through experiments; Figure 4 In the test, the time difference between the two peaks P1 and P2 was 236ms, which met the preset time conditions.

[0044] Method 7: Analyze the signal waveform morphology feature 7, and analyze the frequency corresponding to the median spectral energy of each touch signal; sum the spectral amplitude of each touch signal and multiply it by one-half to calculate the frequency value corresponding to the median spectral energy. The median spectral energy of the effective touch signal is approximately in the range of 80Hz-2kHz.

[0045] Method 8 involves analyzing the signal waveform morphology feature 8, analyzing the sum of the frequencies less than or equal to a preset frequency threshold F in multiple touch signals, where 0Hz < F ≤ 25Hz; this feature focuses on the sum of the frequencies of the low-frequency channels in multiple touch signals, and if the multiple touch signals are valid touch signals, the sum of the frequencies of their low-frequency channels must be less than the preset energy and threshold.

[0046] Method 9 involves analyzing the signal waveform morphology characteristics 9, specifically the ratio of the average energy of all multiple touch signals in the [1600Hz, 2000Hz] frequency band to the average energy of all multiple touch signals in the [190Hz, 1200Hz] frequency band. If the multiple touch signals are valid touch signals, the average energy of all multiple touch signals in the [1600Hz, 2000Hz] frequency band is less than the average energy of all multiple touch signals in the [190Hz, 1200Hz] frequency band, and the maximum frequency amplitude of the multiple touch signals in the [1600Hz, 2000Hz] frequency band is less than the maximum frequency amplitude of the multiple touch signals in the [190Hz, 1200Hz] frequency band.

[0047] In one exemplary embodiment, signal cross-correlation feature analysis is performed on multiple touch signals, including one or more of the following methods: Method 1: Analyze the Pearson correlation coefficient of two adjacent touch signals in at least one of the time or frequency domains; the Pearson correlation coefficient measures the degree of linear correlation between the two touch signals; the value of the Pearson correlation coefficient is between -1 and 1, where a Pearson correlation coefficient of 1 indicates a perfect positive correlation; a Pearson correlation coefficient of -1 indicates a perfect negative correlation; and a Pearson correlation coefficient of 0 indicates no linear correlation. Method 2 involves analyzing the mutual information of two adjacent touch signals in at least one of the time or frequency domains; the mutual information (MI) can be used to quantify the degree of interdependence between the two touch signals. If the two touch signals are completely independent, their mutual information is 0; if one touch signal can completely determine the other touch signal, their mutual information reaches its maximum.

[0048] by Figure 4 For example, at least one of the Pearson correlation coefficient and mutual information of the original time-domain signals of the two touches can be calculated; or at least one of the Pearson correlation coefficient and mutual information of the short-time energy value signals of the two touches can be calculated; or at least one of the Pearson correlation coefficient and mutual information of the frequency-domain signals of the two touches can be calculated.

[0049] In an exemplary embodiment, based on the method of performing signal cross-correlation feature analysis on multiple touch signals, the signal cross-correlation feature corresponding to the signal feature of continuous touch action means that the signal cross-correlation feature of the multiple touch signals satisfies one or more of the following conditions: Condition 1: The Pearson correlation coefficient is greater than or equal to the preset coefficient value A, 0.4≤A≤0.5. This means that for continuous touch actions, multiple touch signals must have at least a moderate degree of cross-correlation. Condition 2: The mutual information is greater than 0.

[0050] This application also provides a non-transient computer-readable storage medium that stores one or more program instructions, which can be executed by one or more processors to implement the continuous touch signal recognition method as described in any of the preceding embodiments.

[0051] This application also provides a control device, such as... Figure 5 As shown, the device includes: The memory 501 is configured to store computer program instructions that can be executed on the processor 502; The processor 502 is configured to execute the computer program instructions to implement the continuous touch signal recognition method as described in any of the preceding embodiments.

[0052] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for recognizing continuous touch signals, the method comprising: Acquire multiple touch signals generated by a touch action; The waveform morphology and cross-correlation characteristics of the multiple touch signals are analyzed. When the signal waveform morphology and cross-correlation characteristics are found to match the signal characteristics corresponding to continuous touch actions, the touch response operation corresponding to the multiple touch signals is executed.

2. The method according to claim 1, characterized in that, The multiple touch signals include multiple raw touch signals collected by sensors or preprocessed signals obtained by preprocessing the multiple raw touch signals, wherein: The preprocessing of the plurality of original touch signals includes: Calculate the short-time energy values ​​of the multiple original touch signals as the preprocessed signal; or, The short-time energy value signals of the multiple original touch signals are calculated, and the short-time energy value signals are combined and smoothed to serve as the preprocessed signal. The combined smoothing process includes multiple individual smoothing operations.

3. The method according to claim 2, characterized in that, The combined smoothing process includes: The N-point mean smoothing, M-point mean smoothing, and reverse K-point median smoothing are performed in a preset order, where N, M, and K are all positive integers.

4. The method according to claim 1, characterized in that, Analyze the waveform morphology characteristics of multiple touch signals, including one or more of the following methods: Method 1: Perform two-endpoint verification on each of the aforementioned touch signals; Method 2: For the multiple touch signals, analyze the total number of peak points where the analyzed value is greater than the preset baseline Ta, and analyze the duration T1 of each touch signal being greater than or equal to the baseline Ta; Method 3: Analyze the duration T2 of each touch signal being greater than or equal to a preset baseline Tc, where the preset baseline Tc is greater than the preset baseline Ta; Method 4: For the multiple touch signals, the total duration T3 of the analyzed value being greater than the preset baseline Tb, where the preset baseline Tb is determined based on the average of the multiple touch signals; Method 5: Analyze the relationship between the duration T1, the duration T2, and the total duration T3; Method 6: Analyze the time difference between the peak points of two adjacent touch signals; Method 7: Analyze the frequency corresponding to the median spectral energy of each touch signal; Method 8: Analyze the sum of all frequency energies less than or equal to a preset frequency threshold F in the multiple touch signals, where 0Hz < F ≤ 25Hz; Method 9: Analyze the average energy ratio of the multiple touch signals across multiple preset frequency bands, including: [190 Hz, 1200 Hz], [1600 Hz - 2000 Hz].

5. The method according to claim 4, characterized in that, The preset baseline Ta is: NIS is the maximum value of the noise component in the plurality of touch signals, and e and f are hyperparameters; The preset baseline Tc is: P is the peak value of each touch signal.

6. The method according to claim 4, characterized in that, Based on the method of analyzing the waveform morphology characteristics of multiple touch signals, the signal waveform morphology characteristics corresponding to continuous touch actions refer to the signal waveform morphology characteristics of the multiple touch signals satisfying one or more of the following conditions: Condition 1: Each of the touch signals contains two endpoints; Condition 2: For the plurality of touch signals, the total number of peak points with values ​​greater than the preset baseline Ta is the same as the number of the plurality of touch signals; the duration T1 is within the first preset time range; Condition 3: The duration T2 is within the second preset time range; Condition 4: The duration T3 is within the third preset time range; Condition 5: The duration T1 is less than the duration T2, and the duration T2 is less than the duration T3; Condition 6: The time difference between the peak points of two adjacent touch signals is within a preset time range; Condition 7: The frequency corresponding to the median spectral energy of each touch signal is within a preset frequency range, wherein the preset frequency range is [80Hz, 2000Hz]. Condition 8: The energy of all frequencies less than or equal to a preset frequency threshold F among the plurality of touch signals and the energy less than the preset energy and threshold. Condition 9: The average energy of all the multiple touch signals in the first frequency band is greater than the average energy of all the signals in the second frequency band, and the maximum value of the frequency amplitude in the first frequency band is greater than the maximum value of the frequency amplitude in the second frequency band.

7. The method according to claim 1, characterized in that, Perform cross-correlation feature analysis on multiple touch signals, including one or more of the following methods: Method 1: Analyze the Pearson correlation coefficient of two adjacent touch signals in at least one of the time or frequency domains; Method 2: Analyze the mutual information of two adjacent touch signals in at least one of the time or frequency domains.

8. The method according to claim 7, characterized in that, Based on the method of analyzing the cross-correlation characteristics of multiple touch signals, the signal cross-correlation characteristics corresponding to continuous touch actions mean that the signal cross-correlation characteristics of the multiple touch signals satisfy one or more of the following conditions: Condition 1: The Pearson correlation coefficient is greater than or equal to a preset coefficient value A, where 0.4 ≤ A ≤ 0.5; Condition 2: The mutual information is greater than 0.

9. A non-transient computer-readable storage medium storing one or more program instructions that can be executed by one or more processors to implement the method as described in any one of claims 1-8.

10. A control device, characterized in that, The device includes: Memory is configured to store computer program instructions that can be executed on a processor; A processor configured to execute the computer program instructions to implement the method as described in any one of claims 1-8.

Images