Touch area detection method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a touch area detection method and device, electronic equipment, a storage medium and a program product. The touch area detection method comprises the steps that first touch data obtained when a user conducts touch operation on a touch screen are obtained, and the first touch data at least comprise touch data of an intention touch area of the touch screen; based on the first touch data, touch area detection is conducted through a machine learning model, and coordinate information of an intention touch area corresponding to the first touch data is obtained. According to the scheme, the detection effect on the touch area of the touch screen is good.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of touch technology, and in particular, to a touch area detection method, device, electronic device, storage medium, and program product. Background Art

[0002] With the rapid popularization and continuous development of mobile devices such as smartphones, touch screens have become an indispensable part of them. Full-screen design has gradually become a major trend in mobile devices, which can bring users a better visual experience and usage experience. However, this design also brings new challenges. For example, due to the increase in the screen-to-body ratio, users are more likely to make accidental touches when holding the phone, such as but not limited to accidentally touching the edge of the screen with fingers or palms. These accidental touches may cause a series of negative situations that reduce the user experience. Therefore, how to accurately detect the touch area to suppress the negative situations caused by accidental touches and improve the user experience of using the touch screen has become an urgent problem to be solved. Summary of the invention

[0003] In view of this, embodiments of the present application provide a touch area detection method, device, electronic device, storage medium, and program product.

[0004] According to a first aspect of an embodiment of the present application, a touch area detection method is provided, including: obtaining first touch data obtained by a user performing a touch operation on a touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen; based on the first touch data, performing touch area detection through a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0005] In some optional embodiments, the first touch data includes touch data for an intended touch area of ​​the touch screen and touch data for an edge mis-touch area.

[0006] In some optional embodiments, the touch area detection is performed through a machine learning model based on the first touch data to obtain coordinate information of the intended touch area corresponding to the first touch data, including: transforming the first touch data according to reference touch data to obtain second touch data, wherein the reference touch data is data that has been determined to be able to perform touch area detection through the machine learning model to obtain coordinate information of the intended touch area corresponding to the reference touch data; and inputting the second touch data into the machine learning model for touch area detection to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0007] In some optional embodiments, the first touch data is transformed according to the reference touch data to obtain the second touch data, including: according to the reference touch data and preset transformation parameters, using an affine transformation algorithm or a second machine learning model to transform the first touch data to obtain the second touch data.

[0008] In some optional embodiments, the preset transformation parameters are predetermined in the following manner: obtaining registered touch data obtained by a user performing a touch operation on a touch screen, wherein the registered touch data at least includes touch data for an intended touch area of ​​the touch screen; performing at least one round of transformation processing on the registered touch data, and obtaining the preset transformation parameters from the processing results of the at least one round of transformation processing based on a relationship between the at least one round of transformation processing and a preset transformation termination condition.

[0009] In some optional embodiments, according to the relationship between the at least one round of transformation processing and the preset transformation termination condition, the preset transformation parameters are obtained from the processing results of the at least one round of transformation processing, including: for each round of transformation processing, determining whether the transformation result obtained by performing the transformation processing on the registered touch data in this round meets the similarity standard with the reference touch data; if the similarity standard is met, determining the transformation parameters of the transformation processing in this round as the preset transformation parameters; if the similarity standard is not met, iteratively updating the transformation parameters of the transformation processing based on the transformation result of this round of transformation processing, and using the updated transformation parameters to transform the registered touch data in the next round of transformation processing.

[0010] In some optional embodiments, the method also includes: if the number of processing times of the at least one transformation processing reaches a preset round and no transformation result whose similarity with the reference touch data satisfies the similarity standard is obtained, then the transformation parameters corresponding to the transformation result with the greatest similarity with the reference touch data are determined as the preset transformation parameters.

[0011] In some optional embodiments, the acquiring of first touch data obtained by a user performing a touch operation on the touch screen includes: acquiring capacitance enhancement data, wherein the capacitance enhancement data is used to characterize: capacitance data obtained by a user performing a touch operation on the touch screen after enhancing the capacitance data acquisition capability of an edge area of ​​the touch screen relative to the capacitance data acquisition capability of a middle area of ​​the touch screen; and determining the capacitance enhancement data as the first touch data.

[0012] In some optional embodiments, the touch screen includes a first edge area, a middle area, and a second edge area arranged along a first direction, and the touch screen includes a plurality of drive signal lines arranged sequentially in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge area, at least one second drive signal line among the plurality of drive signal lines is located in the second edge area, and at least one third drive signal line among the plurality of drive signal lines is located in the middle area; the capacitance data collection capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen in the following manner: the coding time of at least one first drive signal line and / or at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

[0013] In some optional embodiments, the method also includes: according to the touch technique selected by the user, displaying a given touch area corresponding to the touch technique on the touch screen to prompt the user to perform a touch operation in the given touch area, wherein the given touch area includes a given intended touch area and a given edge false touch area; obtaining registered touch data obtained by the user performing a touch operation in the given touch area on the touch screen; wherein the registered touch data is used to determine preset transformation parameters for the user, and the preset transformation parameters are used to transform the user's first touch data to obtain second touch data for input into the machine learning model for touch area detection.

[0014] In some optional embodiments, the given edge false touch area and the given intended touch area are configured with different visual effects.

[0015] According to a second aspect of an embodiment of the present application, a model training method is provided, comprising: obtaining training samples for training a machine learning model, wherein the training samples include target touch data samples obtained by a user performing a touch operation on a touch screen, and true values ​​of intended touch areas corresponding to the target touch data samples, and the target touch data samples include at least touch data samples for the intended touch area of ​​the touch screen; inputting the training samples into the machine learning model to train the machine learning model.

[0016] In some optional embodiments, the target touch data samples include touch data samples of the intended touch area and touch data samples of the edge false touch area; the training samples also include: the true value of the edge false touch area corresponding to the target touch data samples.

[0017] In some optional embodiments, the obtaining of training samples for training the machine learning model includes: obtaining multiple training samples for training the machine learning model, wherein: the multiple target touch data samples of the multiple training samples include multiple first touch data samples and multiple second touch data samples; the multiple first touch data samples are obtained by touching the touch screen through different preset standard touch techniques; the multiple second touch data samples are obtained by touching the touch screen through personalized touch techniques corresponding to different device manufacturers; the inputting of the training samples into the machine learning model to train the machine learning model includes: inputting the multiple training samples into the machine learning model, and performing supervised fine-tuning training on the machine learning model to obtain machine learning models for different device manufacturers.

[0018] In some optional embodiments, the target touch data samples obtained by the user in the training sample performing a touch operation on the touch screen are obtained by: obtaining original capacitance data samples, and the original capacitance data samples are used to characterize: capacitance data samples obtained by the user performing a touch operation on the touch screen after enhancing the capacitance data acquisition capability of the edge area of ​​the touch screen relative to the capacitance data acquisition capability of the middle area of ​​the touch screen; and determining the original capacitance data samples as the target touch data samples.

[0019] In some optional embodiments, the touch screen includes a first edge area, a middle area, and a second edge area arranged along a first direction, and the touch screen includes a plurality of drive signal lines arranged sequentially in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge area, at least one second drive signal line among the plurality of drive signal lines is located in the second edge area, and at least one third drive signal line among the plurality of drive signal lines is located in the middle area; the capacitance data collection capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen in the following manner: the coding time of at least one first drive signal line and / or at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

[0020] According to a third aspect of an embodiment of the present application, a touch area detection device is provided, including: a first acquisition module, used to acquire first touch data obtained by a user performing a touch operation on a touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen; a detection module, used to perform touch area detection through a machine learning model based on the first touch data, and obtain coordinate information of the intended touch area corresponding to the first touch data.

[0021] According to a fourth aspect of an embodiment of the present application, a model training device is provided, comprising: a second acquisition module, used to acquire training samples for training a machine learning model, wherein the training samples include target touch data samples obtained by a user performing a touch operation on a touch screen, and true values ​​of intended touch areas corresponding to the target touch data samples, and the target touch data samples at least include touch data samples for the intended touch area of ​​the touch screen; and a training module, used to input the training samples into the machine learning model to train the machine learning model.

[0022] According to the fifth aspect of the embodiments of the present application, there is provided an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store a computer program; and the processor is used to execute the method described in the first or second aspect above by running the computer program stored in the memory.

[0023] According to a sixth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0024] According to a seventh aspect of an embodiment of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method described in the first aspect or the second aspect.

[0025] According to the technical solution provided in the embodiment of the present application, since the first touch data obtained by the user's touch operation on the touch screen can be obtained, and the touch area detection is performed based on the first touch data through the machine learning model to obtain the coordinate information of the intended touch area corresponding to the first touch data, therefore, the machine learning model can be used to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is conducive to further suppressing the negative situations caused by accidental touches through accurate detection results, thereby improving the user experience of using the touch screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0027] Figure 1A A schematic diagram of defining an edge suppression area for a touch screen in the related art.

[0028] Figure 1B The present invention is a workflow diagram of a technical solution for touch area detection and edge false touch suppression in the related art.

[0029] Figure 2 A flow chart of the steps of a touch area detection method according to an embodiment of the present application.

[0030] Figure 3A A schematic diagram of an example user holding technique and its corresponding touch data.

[0031] Figure 3B FIG. 4 is a schematic diagram of another example of a user's holding gesture and its corresponding touch data.

[0032] Figure 4 A schematic diagram of different areas of an exemplary touch screen and a capacitance detection circuit network.

[0033] Figure 5 This is a flowchart of some optional steps of step S104 in an embodiment of the present application.

[0034] Figure 6 The present invention is a flowchart of some optional steps for predetermining the preset transformation parameters in the embodiments of the present application.

[0035] Figure 7 The following is a flowchart of some application scenario examples of the embodiments of the present application.

[0036] Figure 8 A flowchart of the steps of a model training method according to an embodiment of the present application.

[0037] Fig. 9 An example of a target touch data sample before and after annotation is shown.

[0038] Fig.10 FIG. 4 is a schematic diagram of a touch area detection device according to an embodiment of the present application.

[0039] Fig.11 A schematic diagram of a model training device according to an embodiment of the present application.

[0040] Fig.12 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0042] With the rapid popularization and continuous development of mobile devices such as smartphones, touch screens have become an indispensable part of them. Full-screen design has gradually become a major trend in mobile devices, which can bring users a better visual experience and usage experience. However, this design also brings new challenges. For example, due to the increase in the screen-to-body ratio, users are more likely to make accidental touches when holding the phone, such as but not limited to accidentally touching the edge of the screen with their fingers or palms. These accidental touches may cause a series of negative situations that reduce the user experience, such as but not limited to application misoperation, frequent typing errors, missending of messages, frequent screen wake-up, etc.

[0043] For example, to reduce the situation of false touch at the edge, some solutions in the related art mostly use edge false touch prevention algorithms to distinguish normal touch from false touch by extracting characteristic information such as touch shape, position, area and operation status. Figure 1A As shown, some manufacturers define the "edge suppression area" of the touch screen according to their own product requirements (it should be understood that Figure 1A The horizontal and vertical screens are only examples). In this area, it is necessary to distinguish between the user's real touch operations and accidental touch operations as much as possible. Figure 1A When a touch event occurs in the middle area (i.e., the white area), it is judged as a real touch; however, Figure 1A When a touch event occurs in the "edge suppression area" (i.e., gray area), the edge false touch prevention algorithm is used to determine whether the touch event is a real touch or a false touch based on a series of complex conditions. However, including but not limited to Figure 1A The solutions shown still have deficiencies in the accuracy of suppressing false touches and cannot fully meet the needs of users. In addition, the debugging efficiency of most solutions is not high, which is not conducive to maintenance and optimization, and R&D personnel need to invest a lot of time.

[0044] For example, refer to Figure 1B As shown, a flowchart of a technical solution for touch area detection and edge false touch suppression in the related art is shown. Figure 1BAs shown, in the technical solution of the related technology, taking the touch screen as a capacitive touch screen as an example, the capacitance data of the current frame can be obtained first, and then the touch frame corresponding to the touch area in the capacitance data is searched, and the corresponding coordinates are calculated, and then the touch frame state analysis and coordinate point state analysis are performed, and then the manufacturer's requirements (such as information on the edge suppression area, etc.) and the above analysis results are combined to suppress edge false touches and report the coordinates of the touch area. It can be seen from the introduction of the technical solution in the above-mentioned related technology that the edge false touch suppression of the technical solution needs to rely on multiple conditions (such as touch frame state, coordinate point state, and manufacturer requirements, etc.), and these conditions need to be combined and coordinated with each other to ensure the effectiveness of the solution, and the intervention of the above-mentioned multiple conditions makes the judgment logic of the solution itself extremely cumbersome. In addition, the solution involves a large number of preset thresholds, and each threshold requires careful selection by R&D personnel to improve the accuracy of the existing solution. However, the complexity of the solution can neither guarantee the accuracy of touch area detection and edge false touch suppression, nor is it conducive to later maintenance and further optimization. In addition, the requirements of the same manufacturer may change frequently. For example, manufacturers usually put forward a preliminary requirement for edge accidental touch suppression first, and then adjust these requirements during the development process. On the other hand, different manufacturers have different requirements for edge accidental touch suppression. This results in the above technical solution not being universal, because the addition, deletion or modification of the requirements of the same manufacturer, or the different requirements between different manufacturers, will cause the above technical solution to be modified or even reconstructed, consuming a lot of time and energy of R&D personnel, resulting in low development efficiency and difficulty in ensuring accuracy. It should be noted that the above Figure 1B The technical solutions of the related technologies shown may not be prior arts.

[0045] It should be understood that a new touch area detection scheme is provided in the embodiment of the present application, which can realize the detection of the user's intended touch area and the determination of coordinate information through a machine learning model, and at least improve the accuracy of touch area detection. The accurate results of the touch area detection can help to more effectively suppress the negative situations caused by false touches, and help to improve versatility, thereby improving the user experience of using the touch screen.

[0046] The specific implementation of the embodiment of the present application is further explained below in conjunction with the drawings of the embodiment of the present application.

[0047] Figure 2 A touch area detection method is provided according to a first aspect of the embodiment of the present application. Figure 2 As shown, the method includes steps S102 and S104, specifically:

[0048] S102: Acquire first touch data obtained by a user performing a touch operation on the touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen.

[0049] It should be noted that the touch area detection method in the embodiment of the present application can be applied to the touch area detection of any touch screen. For example, the touch screen can be a capacitive touch screen, a resistive touch screen, etc. For ease of explanation, the capacitive touch screen is taken as an example below, and the touch data collected is capacitive data.

[0050] Optionally, the touch area detection method in the embodiment of the present application can be used in the use phase of the touch screen, that is, the phase in which the touch screen is used after it has been manufactured and installed in a terminal device.

[0051] In the embodiment of the present application, the type of the first touch data can be determined according to the type of the touch screen. For example, taking the touch screen as a capacitive touch screen as an example, the first touch data can be capacitance data. The capacitance data here can be mutual capacitance data or self-capacitance data, which depends on whether the touch screen is based on the mutual capacitance principle or the self-capacitance principle. Taking the capacitance data as mutual capacitance data as an example, for example, each position on the touch screen can collect mutual capacitance data. When the user does not touch the touch screen, the mutual capacitance data collected at each position on the touch screen fluctuates very little, and when the user presses on a part of the touch screen to achieve touch or touch by mistake, the mutual capacitance data collected through the part of the area changes, so that the difference between the mutual capacitance data and the time when it is not touched or touched by mistake increases significantly. Therefore, it is possible to determine whether there is a touch or a false touch by detecting the difference in the mutual capacitance data (for example, it can be the difference with the reference value (for example, it can be 0)), so as to facilitate the determination of the user's intended touch area, accurately realize the touch area detection, and suppress the occurrence of false touches.

[0052] In the embodiment of the present application, the intended touch area can be the area that the user actually wants to touch on the touch screen, and can also be considered as the actual touch area. Generally speaking, when the user touches, if an accidental touch occurs at any position, the area that the accidental touch is not the area that the user actually wants to touch. It should be understood that in the embodiment of the present application, by obtaining the first touch data including at least the intended touch area for the touch area, it is convenient to accurately implement touch area detection according to the user's intention through the machine learning model in the subsequent process, that is, to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, and to further suppress the negative situations caused by the accidental touch through accurate detection results, so as to achieve accidental touch suppression, so as to improve the user's experience of using the touch screen.

[0053] In some optional embodiments, the first touch data includes touch data for an intended touch area of ​​the touch screen and touch data for an edge mis-touch area.

[0054] Based on this, in the embodiment of the present application, by acquiring first touch data including touch data for the intended touch area of ​​the touch screen and touch data for the edge mistouch area, it is possible to subsequently use a machine learning model to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, and to further suppress the negative situations caused by edge mistouch through accurate detection results, thereby suppressing the user's edge mistouch and improving the user's experience of using the touch screen.

[0055] Optionally, the touch screen is a capacitive touch screen, and the first touch data obtained in the embodiment of the present application can be capacitance data, for example, it can be original capacitance data collected by user touch, or it can be capacitance data after noise reduction processing of the original capacitance data. Using the noise-reduced data is beneficial to reducing detection errors.

[0056] In some optional embodiments, the touch screen is a capacitive touch screen, and the above step S102 includes: obtaining capacitance enhancement data, wherein the capacitance enhancement data is used to characterize: after enhancing the capacitance data acquisition capability of the edge area of ​​the touch screen relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, the capacitance data obtained by the user performing a touch operation on the touch screen is collected; and the capacitance enhancement data is determined as the first touch data.

[0057] In some cases, the user holds the edge area of ​​the touch screen in different ways, and the touch data (capacitive data) at the edge area of ​​the touch screen has little difference in form. Figure 3A In the left column of examples, the user's thumb is "continuously held" on the edge area of ​​the touch screen (such as Figure 3A As shown in the figure, both contacts are edge touches). Figure 3A The right column of is an example of the corresponding capacitance data (touch data). Figure 3B In the left column of examples, the user's thumb "continuously clicks" on the edge area (such as Figure 3B As shown in the figure, one contact is an intentional touch and one contact is an edge touch). Figure 3B The right column of is an example of its corresponding capacitance data (touch data). Figure 3A Right and Figure 3B In contrast, the user's thumb is constantly holding ( Figure 3A ) and click continuously ( Figure 3B ) are almost the same in the form of capacitance data (such as capacitance data difference, affected area, touch shape, etc.). In other words, some touch data itself cannot reflect the difference between certain holding techniques in the edge area, so it is impossible to distinguish the user's true intention (that is, it is impossible to determine whether it is an intentional touch or an edge accidental touch).

[0058] It should be understood that the above-mentioned optional embodiment in the embodiment of the present application, by obtaining capacitance enhancement data, and then determining the capacitance enhancement data as the first touch data, because the capacitance enhancement data is the capacitance data obtained by the user performing a touch operation on the touch screen after the capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, the data quality corresponding to the edge area in the first touch data is enhanced, so that the first touch data itself can better reflect the user's operation intention, which is conducive to the subsequent touch area detection with better effect through the machine learning model, so as to determine the coordinate information of the intended touch area, and facilitate the suppression of negative situations of accidental touches on the edge, thereby improving the user's experience of using the touch screen.

[0059] In the embodiment of the present application, the capacitance data collection capability of the edge area of ​​the touch screen can be enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen in any manner. Figure 4 Schematic diagram of different areas of an exemplary touch screen and a capacitance detection circuit network. In some optional embodiments, Figure 4 As shown in sub-figures a and b, the touch screen 100 includes a first edge area 101, a middle area 103 and a second edge area 102 arranged along a first direction F, and the touch screen 100 includes a plurality of drive signal lines arranged in sequence in the first direction F for collecting capacitance data, wherein at least one first drive signal line 1041 among the plurality of drive signal lines is located in the first edge area 101, at least one second drive signal line 1042 among the plurality of drive signal lines is located in the second edge area 103, and at least one third drive signal line 1043 among the plurality of drive signal lines is located in the middle area 103. Optionally, the capacitance data acquisition capability of the edge area of ​​the touch screen can be enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen in the following manner: the coding time of at least one first drive signal line 1041 and / or at least one second drive signal line 1042 is set to be greater than the coding time of each third drive signal line 1043, so that the capacitance data acquisition capability of the first edge area 101 and / or the second edge area 102 of the touch screen 100 is enhanced relative to the capacitance data acquisition capability of the middle area 103 of the touch screen 100.

[0060] For example Figure 4As shown in sub-figure a and sub-figure b, the touch screen 100 of this example includes multiple drivers TX0, TX1, ..., TXend, multiple receivers RX0, RX1, ..., RXend, each of the multiple drivers is connected to a drive signal line (also called a drive electrode), each of the multiple receivers is connected to a receive signal line (also called a receive electrode), and the multiple drive signal lines and the multiple receive signal lines form a capacitance detection circuit network (mutual capacitance). Taking the 5 drive signal lines and 5 receive signal lines in the figure as an example, the changes in capacitance data C11~C55 (only for example) caused by touch in various areas on the touch screen 100 can be detected and collected. It should be understood that Figure 4 The structural numbers and proportions are only used to facilitate illustration and understanding, which are not necessarily consistent with the actual situation and are not intended to limit the embodiments of the present application.

[0061] Optionally, the first direction F may be a width direction or a length direction of the touch screen 100. Figure 4 The width direction is taken as an example. It should be understood that the number of the first drive signal lines 1041 located in the first edge region 101 can be set as needed, the number of the second drive signal lines 1042 located in the second edge region 102 can be set as needed, and the number of the third drive signal lines 1043 located in the middle region 103 can be set as needed. As an example, Figure 4 As shown in sub-figure b, there is one first drive signal line 1041 in the first edge area 101, i.e., the drive signal line connected to the leftmost driver TX0 (which corresponds to the left edge of the touch screen); there is one second drive signal line 1042 in the second edge area 102, i.e., the drive signal line connected to the rightmost driver TXend (which corresponds to the right edge of the touch screen); there are three first drive signal lines 1043 in the middle area 103, i.e., the drive signal lines connected to the previous driver from the middle driver TX1 to TXend.

[0062] The coding time can be considered as the time for the drive signal line to collect capacitance data in one cycle. The greater the coding time of the drive signal line, the longer the time for its driver to send the drive signal, so that it can collect more and higher quality capacitance data. Therefore, by adjusting the coding time, the capacitance data collection capability of different areas of the touch screen can be changed. Therefore, in the embodiment of the present application, the coding time of at least one first drive signal line 1041 and / or at least one second drive signal line 1042 can be set to be greater than the coding time of each third drive signal line 1043, so that the capacitance data collection capability in the first edge area 101 and / or the second edge area 102 is enhanced relative to the capacitance data collection capability of the middle area 103 of the touch screen 100, so that the capacitance data quality collected by the first edge area 101 and / or the second edge area 102 is enhanced. Optionally, the coding time of each first drive signal line 1041 and each second drive signal line 1042 can be set to be greater than the coding time of each third drive signal line 1043. For example, as an example, the coding time of the third drive signal line 1043 can be set to 100us, and the coding time of the first drive signal line 1041 and the second drive signal line 1042 can be set to 200us. For example, assuming that the original coding time of each drive signal line is 100us, it can be equivalent to increasing the coding time of the first drive signal line 1041 and the second drive signal line 1042 from 100us to 200us, while the coding time of the third drive signal line 1043 remains unchanged. Or it can be set to other values ​​as needed, which are not specifically limited here.

[0063] Based on this, in the embodiment of the present application, the above-mentioned optional method is used to enhance the capacitance data acquisition capability of the edge area (i.e., the first edge area and / or the second edge area) of the touch screen relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, so that capacitance enhanced data can be effectively obtained. Therefore, the data quality corresponding to the edge area in the first touch data can be effectively enhanced, so that the first touch data itself can better reflect the user's operation intention, which is conducive to the subsequent touch area detection through the machine learning model with better effect, so as to determine the coordinate information of the intended touch area, and facilitate the suppression of negative situations of accidental touches on the edge, thereby improving the user's experience of using the touch screen.

[0064] For example, still Figure 3A and Figure 3B After adopting the above optional enhancement method, if Figure 3A As shown on the left, when a user holds the edge of the touch screen of a mobile phone with the palm thenar and thumb, the suspended area between the palm thenar and the thumb (such as Figure 3A The touch data (capacitive data) collected will also be reflected in the touch data (which is different from Figure 3A The example of touch data on the right side is different) because the distance between the suspended area and the edge of the touch screen is closer under this method, and after the capacitance data collection capability is enhanced, it can be collected and reflected. Figure 3B As shown on the left, when a user holds the edge of the touch screen of a mobile phone with the palm of the hand and clicks the edge of the touch screen with the thumb, the suspended area between the palm of the hand and the thumb pad (such as Figure 3B If the area is outlined with a double-dotted line, it will not be reflected in the touch data (capacitance data) because the distance between the suspended area and the edge of the touch screen is far. Figure 3A and Figure 3B The situation where the capacitance data (touch data) originally collected by the two different holding techniques were not obviously different now has obvious differences, which can better reflect the user's operation intention, so that the first touch data obtained based on data enhancement can be used to more accurately detect the touch area through the machine learning model, better suppress edge accidental touches, and improve the user experience of using the touch screen.

[0065] S104: Based on the first touch data, touch area detection is performed by using a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0066] In the embodiment of the present application, after obtaining the first touch data, touch area detection can be performed based on the first touch data through a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data. In this way, even if there are false touches on the touch screen (including but not limited to false touches on the edges), they can be accurately suppressed due to the reporting of the accurate coordinate information of the user's actual intended touch area.

[0067] Optionally, the coordinate information of the intended touch area can be the coordinates of the center point of the intended touch area (for example, if the intended touch area is an ellipse, it can be the coordinates of the center point of the elliptical area), or it can be the coordinates of each point on the outer contour of the intended touch area, or it can be the coordinates of each point within the intended touch area, or it can be any multiple of them, which can be selected and set as needed, and there is no single limitation here.

[0068] Based on this, in the embodiment of the present application, the touch area detection scheme through the above steps S102 to S104 can obtain the first touch data obtained by the user performing a touch operation on the touch screen, and based on the first touch data, the touch area detection is performed through the machine learning model to obtain the coordinate information of the intended touch area corresponding to the first touch data. Therefore, the machine learning model can be used to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is conducive to further suppressing the negative situations caused by accidental touches through accurate detection results, thereby improving the user experience of using the touch screen.

[0069] In addition, due to the use of machine learning models, it is not only convenient to use, but also has better development and debugging efficiency, is conducive to maintenance and optimization, has better versatility, and is also conducive to reducing the extra time and energy invested by R&D personnel before and after development is completed.

[0070] Since this solution can effectively suppress false touches, it can also better avoid false detection and reduce delay when pulling up or sliding down the menu during the use of the touch screen.

[0071] It should be understood that the machine learning model in the embodiment of the present application can be a pre-trained machine learning model. The machine learning model is implemented based on artificial intelligence technology. The machine learning model can be of any type. For example, it can be a convolutional neural network model (for example, including but not limited to AlexNet, Inception, VGG, ResNet, MobileNet, FCN, U-Net, DeepLab, BiSeNet, R-CNN, Yolo, SSD, RetinaNet and other models), a deep language model (for example, including but not limited to LSTM, GRU, BiLSTM, Transformer, MarianMT, BERT, RoBERTa, XLNet, GPT, T5, S4, Mamba and other models), or a hybrid variant model based on the above two (for example, including but not limited to ViT, DeiT, ConViT, SwinTransformer, TransUNet, Swin Unet, DETR, Deformable DETR, ConvS2S, ConvBERT and other models). Regarding the training process of the machine learning model, there is no limitation in the embodiment of the present application. For example, the model training method of the second aspect described below may be used for training. This part will be described in detail below and will not be elaborated here.

[0072] The implementation of step S104 is not limited in the present application. For example, in some optional embodiments, the first touch data can be directly input into the machine learning model for touch area detection, so as to obtain the coordinate information of the intended touch data corresponding to the first touch data.

[0073] In some other optional embodiments, refer to Figure 5 In the flowchart shown, step S104 includes steps S1042 and S1044, specifically:

[0074] S1042: transforming the first touch data according to the reference touch data to obtain the second touch data, wherein the reference touch data is data that has been determined to be capable of performing touch area detection through a machine learning model to obtain coordinate information of the intended touch area corresponding to the reference touch data.

[0075] For example, some touch data of typical hand shapes can be selected as reference touch data and stored in a storage unit (the storage unit can be set in the terminal device where the touch screen is installed, and can include but is not limited to a database, or any type of memory with storage function, etc.). These touch data of typical hand shapes can be obtained by touching the touch screen in different ways. When storing the reference touch data in the storage unit, it is necessary to ensure that the content in the database does not disappear after operations such as shutting down the device and cutting off the power. These touch data of typical hand shapes can come from the same person or from different people. It is necessary to ensure that the touch data of these typical hand shapes can be correctly recognized by the machine learning model, that is, the touch area detection can be performed through the machine learning model to obtain the data of the coordinate information of the corresponding intended touch area.

[0076] Since the trained machine learning model in the embodiment of the present application already has a certain degree of generalization, it can accurately detect touch areas and suppress edge false touches for more touch data. However, the machine learning model is still not sufficient to cover the hand shapes of all users. In order to adapt to such a situation, when using the machine learning model, the first touch data can be first transformed and processed according to the reference touch data to obtain the second touch data, so that the second touch data can better approach the reference touch data. Since the reference touch data can realize accurate touch area detection through the machine learning model, the second touch data can also realize accurate touch area detection through the machine learning model, thereby adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use of the touch screen.

[0077] The above step S1042 can be implemented in any suitable manner. In some optional embodiments, step S1042 can be implemented by an affine transformation algorithm or a second machine learning model. Optionally, step S1042 may include: according to the reference touch data and the preset transformation parameters, using the affine transformation algorithm or the second machine learning model, transforming the first touch data to obtain the second touch data.

[0078] Based on this, in the embodiment of the present application, the first touch data can be effectively transformed according to the reference touch data and preset transformation parameters through an affine transformation algorithm or a second machine learning model to obtain second touch data that can better approach the reference touch data, so that accurate touch area detection can be achieved for the second touch data through the subsequent machine learning model, thereby adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use of the touch screen.

[0079] For example, when using an affine transformation algorithm, the first touch data can be affine transformed using preset transformation parameters to obtain second touch data. The second touch data obtained at this time can be closer to the reference touch data, so as to facilitate subsequent input into the machine learning model for touch area detection.

[0080] For example, the affine transformation can be implemented as follows:

[0081]

[0082] Wherein, θ represents the rotation angle; sx and sy represent the scaling coefficients in the x and y directions respectively; tx and ty represent the translation amounts in the x and y directions respectively. The x and y directions may be the horizontal and vertical directions of the coordinate system. The first touch data is taken as an independent variable, and an affine transformation is performed through the above formula. The first touch data is affinely transformed according to preset transformation parameters (which may include at least one of θ, sx, sy, tx, and ty here), so that f(first touch data) = second touch data ≈ reference touch data.

[0083] The second machine learning model is another machine learning model different from the aforementioned machine learning model, which can be used to transform the first touch data. Alternatively, the second machine learning model can also be a part of other models (such as the aforementioned machine learning model). For the second machine learning model, the preset transformation parameters can be at least part of the model parameters of the second machine learning model. For example, the first touch data can be input into the second machine learning model, so that the first touch data can be transformed according to the preset transformation parameters by the second machine learning model to obtain the second touch data. The second touch data obtained at this time can better approach the reference touch data, so as to facilitate the subsequent input into the machine learning model for touch area detection.

[0084] The above-mentioned preset transformation parameters can be determined by any suitable method. For example, in one embodiment, specific values ​​can be set according to needs, experience, etc. In other optional embodiments, refer to Figure 6 As shown in the flowchart, the preset transformation parameters are predetermined by the following steps T102 to T104:

[0085] T102: Acquire registered touch data obtained by a user performing a touch operation on the touch screen, wherein the registered touch data at least includes touch data for an intended touch area of ​​the touch screen.

[0086] For example, operation instructions for user registration can be displayed in the display interface of the touch screen (for example, the system can automatically enter the interface when the terminal device equipped with the touch screen is turned on, or the user can actively control the terminal device to enter the interface). The user can follow the prompts in the operation instructions and use the same touch technique as the reference touch data to enter the registration touch data (which can be capacitive data), so that the user operation intentions of the reference touch data and the registration touch data are consistent.

[0087] Optionally, the registered touch data may include touch data for the intended control area of ​​the touch screen and touch data for the edge false touch area of ​​the touch screen, so as to more easily achieve edge false touch suppression.

[0088] Optionally, when implementing step T102, a given touch area can be displayed on the touch screen to prompt the user to perform a touch operation in the given touch area according to the touch method corresponding to the given touch area, wherein the given touch area includes a given intended touch area and a given edge mistouch area; and the registered touch data obtained by the user performing a touch operation in the given touch area on the touch screen is obtained. In this way, the registered touch data can be effectively obtained. (This part can be understood by referring to the relevant content below)

[0089] Optionally, the touch data for the intended touch area of ​​the touch screen included in the registered touch data may be: touch data for a given intended touch area of ​​the touch screen. Optionally, the touch data for the edge mis-touch area of ​​the touch screen included in the registered touch data may be: touch data for a given edge mis-touch area of ​​the touch screen.

[0090] Since different parts of the hand can cause edge mis-touch, optionally, in the given touch area displayed on the touch screen in the present application, there can be multiple given edge mis-touch areas. Of course, in some cases, there can also be one given edge mis-touch area.

[0091] Optionally, the given edge false touch area and the given intended touch area are configured with different visual effects. Thus, the visualization effect of different areas of the given touch area for the user can be improved, making it easier for the user to distinguish the given edge false touch area from the given intended touch area, thereby facilitating the user to accurately perform touch operations in the given edge false touch area and the given intended touch area, so as to accurately obtain registered touch data. (This part can be understood by referring to the relevant content below)

[0092] T104: performing at least one round of transformation processing on the registered touch data, and obtaining preset transformation parameters from the processing results of at least one round of transformation processing according to the relationship between the at least one round of transformation processing and the preset transformation termination condition.

[0093] Based on this, through the optional method of the above steps T102 to T104, the registered touch data obtained by the user performing a touch operation on the touch screen can be obtained, and at least one round of transformation processing can be performed on the registered touch data. According to the relationship between at least one round of transformation processing and the preset transformation termination condition, the preset transformation parameters with better effect can be effectively obtained from the processing results of at least one round of transformation processing, so that when using the preset transformation parameters, the first touch data can be effectively transformed by the preset transformation parameters, thereby effectively obtaining the second touch data that can better approach the reference touch data, so that the second touch data can be accurately detected by the machine learning model in the subsequent touch area detection, and the coordinate information of the intended touch area corresponding to the first touch data can be accurately obtained, so as to realize accurate and effective detection of the actual intended touch area of ​​the user's touch operation on the touch screen, thereby adapting to the touch area detection and edge false touch suppression requirements under the hand shape of the corresponding user, and effectively improving the use effect of the touch screen by the corresponding user.

[0094] It should be understood that the transformation termination condition in the embodiments of the present application can be set as needed. For example, in some optional embodiments, the transformation termination condition can be that the transformation rounds reach a preset round, the result of the transformation processing meets the similarity standard with the reference touch data, etc. Or it can also be other termination conditions.

[0095] In some optional embodiments, "obtaining preset transformation parameters from the processing results of at least one round of transformation processing based on the relationship between at least one round of transformation processing and the preset transformation termination condition" in step T104 includes: for each round of transformation processing, determining whether the transformation result obtained by performing that round of transformation processing on the registered touch data meets the similarity standard with the reference touch data.

[0096] If the similarity standard is met, the transformation parameters of this round of transformation processing are determined as preset transformation parameters.

[0097] If the similarity standard is not met, the transformation parameters of the transformation process are iteratively updated based on the transformation result of the current round of transformation process, and the registered touch data are transformed using the updated transformation parameters in the next round of transformation process.

[0098] Optionally, the similarity standard may be that the similarity is greater than a preset similarity threshold. The preset similarity threshold may be set as required, such as 90%, 95%, 98%, etc. Alternatively, other similarity standards may be used. The calculation of similarity may be implemented using any suitable similarity index. For example, the similarity may be calculated using at least one similarity index including but not limited to correlation NCC (Normalized Cross Correlation), structural similarity SSIM (structural similarity), mean square error MSE (mean-square error), cosine similarity, etc.

[0099] For example, taking the similarity standard as greater than a preset similarity threshold as an example, when the similarity between the transformation result of a certain round of transformation processing and the reference touch data is greater than the preset similarity threshold, it can be considered that the transformation result is basically consistent with the reference touch data, and at this time it can be considered that the transformation effect can meet the requirements, so the transformation parameters of this round of transformation processing can be determined as preset transformation parameters. The preset transformation parameters can be stored in the storage unit so that the first touch data can be directly obtained and transformed using the preset transformation parameters in the subsequent process.

[0100] For example, taking the similarity standard as being greater than a preset similarity threshold, when the similarity between the transformation result of a certain round of transformation processing and the reference touch data is less than the preset similarity threshold, it is considered that the transformation result is not similar enough to the reference touch data and the transformation effect cannot meet the requirements. Therefore, the transformation parameters of the transformation processing can be iteratively updated, and the next round of transformation processing can be continued using the updated transformation parameters, in the hope that the transformation results in subsequent rounds can gradually meet the similarity standard (such as being greater than the preset similarity threshold) with the reference touch data.

[0101] Optionally, the registered touch data entered by the user using the same technique can be used during iterative updating, and / or the registered touch data entered by the user using different techniques can also be used, so that the preset transformation parameters obtained subsequently can better adapt to the transformation processing of the first touch data collected when the user performs touch operations on the touch screen using different techniques.

[0102] Based on this, the above optional method in the embodiment of the present application sets a similarity standard, and in each round of transformation processing, determines whether the transformation result obtained by performing the transformation processing on the registered touch data in this round meets the similarity standard with the reference touch data, and when the similarity meets the similarity standard, determines the transformation parameters of this round of transformation processing as the preset transformation parameters, and when the similarity does not meet the similarity standard, iteratively updates the transformation parameters of the transformation processing based on the transformation result of this round of transformation processing, and uses the updated transformation parameters to process the registered touch data in the next round of transformation processing, thereby effectively obtaining a better effect. The preset transformation parameters can be used to effectively transform the first touch data through the preset transformation parameters when using the preset transformation parameters, so as to effectively obtain the second touch data that can better approach the reference touch data, so that the second touch data can be accurately detected through the machine learning model in the future, and the coordinate information of the intended touch area corresponding to the first touch data can be accurately obtained, so as to realize accurate and effective detection of the actual intended touch area of ​​the user's touch operation on the touch screen, thereby adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use of the touch screen.

[0103] In some optional embodiments, the touch area detection method in the embodiments of the present application further includes: if the number of processing times of at least one transformation process reaches a preset round and no transformation result whose similarity with the reference touch data satisfies the similarity standard is obtained, then the transformation parameters corresponding to the transformation result with the greatest similarity with the reference touch data are determined as the preset transformation parameters.

[0104] Based on this, it is possible to avoid performing multiple rounds of parameter iteration updates and multiple rounds of transformation processing when the transformation result that meets the similarity condition cannot be obtained, thereby improving processing efficiency, and adopting the transformation parameters corresponding to the transformation result with the greatest similarity to the reference touch data to determine as the preset transformation parameters. On the basis of the existing parameter data, the effect of the preset transformation parameters can be guaranteed to the greatest extent, so that when the preset transformation parameters are used, it is guaranteed to the greatest extent that the first touch data can be effectively transformed and processed by the preset transformation parameters, thereby effectively obtaining the second touch data that can better approach the reference touch data, so that the second touch data can be accurately detected through the machine learning model in the subsequent touch area detection, and the coordinate information of the intended touch area corresponding to the first touch data can be accurately obtained, so as to realize accurate and effective detection of the actual intended touch area of ​​the user's touch operation on the touch screen, thereby adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use of the touch screen.

[0105] For example, if the similarity standard is that the similarity between the transformation result and the reference touch data is greater than 95%, and the preset rounds are 100 rounds, the transformation parameters are iteratively updated in each round of transformation processing. Assuming that the similarity corresponding to the 80th round is 96%, which is greater than 95% and meets the similarity standard, the transformation parameters of the 80th round of transformation processing are determined as the preset transformation parameters; if the similarity is less than 95% after 100 rounds of transformation processing, and the largest similarity among these 100 rounds is 92% of the 99th round, the transformation parameters of the 99th round of transformation processing can be determined as the preset transformation parameters. It should be understood that this is used for ease of understanding and does not serve as any limitation to the embodiments of the present application.

[0106] It should be understood that in addition to the above-mentioned use of the affine transformation algorithm or the second machine learning model to implement the transformation processing, the transformation processing can also be performed by other feasible methods, which are not specifically limited in the embodiments of the present application.

[0107] S1044: Input the second touch data into the machine learning model to perform touch area detection to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0108] Based on this, in an embodiment of the present application, through the optional embodiment of the above steps S1042 to S1044, the first touch data is first transformed and processed according to the reference touch data to obtain the second touch data. After obtaining the second touch data, it can be input into the machine learning model for touch area detection. Since the second touch data can better approach the reference touch data, and the reference touch data can realize accurate touch area detection through the machine learning model, the second touch data can also realize accurate touch area detection through the machine learning model, and accurately obtain the coordinate information of the intended touch area corresponding to the first touch data, so as to realize accurate and effective detection of the actual intended touch area of ​​the user's touch operation on the touch screen, thereby better adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use effect of the touch screen.

[0109] In some optional embodiments, the touch area detection method of the embodiments of the present application also includes: displaying a given touch area on the touch screen to prompt the user to perform a touch operation in the given touch area according to the touch technique corresponding to the given touch area, wherein the given touch area includes a given intended touch area and a given edge false touch area; obtaining registered touch data obtained by the user performing a touch operation in the given touch area on the touch screen; wherein the registered touch data is used to determine preset transformation parameters for the user, and the preset transformation parameters are used to transform the user's first touch data to obtain second touch data for input into the machine learning model for touch area detection.

[0110] Based on this, in the present application, a given touch area including a given intended touch area and a given edge false touch area is displayed on the touch screen to prompt the user to perform a touch operation in the given touch area according to the touch technique corresponding to the given touch area, and then the registered touch data obtained by the user's touch operation in the given touch area is obtained, so as to determine the preset transformation parameters for the user, which is conducive to the subsequent use of the preset transformation parameters to transform the user's first touch data to obtain the second touch data, and then the second touch data can be used to input the machine learning model, which can facilitate accurate touch area detection for the user through the machine learning model, thereby adapting to the touch area detection and edge false touch suppression requirements under the user's hand shape, and effectively improving the user's use of the touch screen.

[0111] Optionally, the touch data for the intended touch area of ​​the touch screen included in the registered touch data may be: touch data for a given intended touch area of ​​the touch screen. Optionally, the touch data for the edge mis-touch area of ​​the touch screen included in the registered touch data may be: touch data for a given edge mis-touch area of ​​the touch screen.

[0112] Since different parts of the hand can cause edge mis-touch, optionally, in the given touch area displayed on the touch screen in the present application, there can be multiple given edge mis-touch areas. Of course, in some cases, there can also be one given edge mis-touch area.

[0113] For example, a user registration system function can be added to a terminal device (such as a mobile phone, etc.) equipped with a touch screen, and users using the device can register. For example, an operation guide for user registration can be displayed in the display interface of the touch screen (for example, the system can automatically enter when the terminal device equipped with the touch screen is powered on, or the user can actively control the terminal device to enter), and a given touch area can be displayed on the touch screen through the operation guide, prompting the user to use the touch method corresponding to the given touch area to perform a touch operation in the given touch area, and then the user can follow the prompt of the operation guide and use the touch method corresponding to the given touch area (for example, the touch method can use the "preset standard touch method" and "personalized touch method" mentioned below, which can be understood by referring to the relevant description of the model training method embodiment below, and will not be repeated here) to perform a touch operation in the given touch area, and the given intended touch area and the given edge false touch area in the given touch area are completely covered during the touch operation, so as to obtain the registered touch data. After that, it can be convenient to determine the preset transformation parameters for the user according to the registered touch data.

[0114] In the present application, the touch method corresponding to a given touch area can be the same as the touch method of a certain reference touch data, so that the user operation intention of the reference touch data is consistent with that of the registered touch data. The reference touch data is data that has been determined to be able to detect the touch area through a machine learning model to obtain the coordinate information of the intended touch area corresponding to the reference touch data.

[0115] Optionally, the user's first touch data can be transformed in the following manner to obtain second touch data: based on reference touch data and preset transformation parameters, an affine transformation algorithm or a second machine learning model is used to transform the first touch data to obtain second touch data.

[0116] Optionally, the preset transformation parameters may be determined by performing at least one round of transformation processing on the registered touch data, and obtaining the preset transformation parameters from the processing results of at least one round of transformation processing according to the relationship between the at least one round of transformation processing and the preset transformation termination condition.

[0117] Optionally, the above-mentioned obtaining preset transformation parameters from the processing results of at least one round of transformation processing according to the relationship between at least one round of transformation processing and the preset transformation termination condition may include: for each round of transformation processing, determining whether the transformation result obtained by performing that round of transformation processing on the registered touch data satisfies a similarity standard with the reference touch data; if the similarity standard is met, determining the transformation parameters of that round of transformation processing as the preset transformation parameters; if the similarity standard is not met, iteratively updating the transformation parameters of the transformation processing based on the transformation result of that round of transformation processing, and using the updated transformation parameters to transform the registered touch data in the next round of transformation processing.

[0118] Optionally, if at least one transformation process reaches a preset number of rounds and no transformation result is obtained whose similarity with the reference touch data satisfies the similarity standard, the transformation parameters corresponding to the transformation result with the greatest similarity with the reference touch data are determined as preset transformation parameters.

[0119] Optionally, the second touch data is input into a machine learning model to perform touch area detection, so as to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0120] It should be understood that the above optional contents related to the preset transformation parameters, the second touch data, the reference touch data, etc. have been described in detail in the previous text and will not be repeated here.

[0121] In some optional embodiments, the given edge false touch area and the given intended touch area can be configured with different visual effects. Thus, the visualization effect of different areas of the given touch area for the user can be improved, and it is convenient for the user to distinguish the given edge false touch area and the given intended touch area, so as to facilitate the user to accurately perform touch operations in the given edge false touch area and the given intended touch area, so as to accurately obtain registered touch data.

[0122] Optionally, the above-mentioned different visual effects can be embodied in any form, as long as the user can accurately distinguish between the given edge mistouch area and the given intended touch area. For example, the given edge mistouch area and the given intended touch area can be configured with different colors (for example, the given edge touch area can be configured as a blue area, and the given intended touch area can be configured as a red area; for another example, the given edge touch area can be configured as an area with a blue outline, and the given intended touch area can be configured as an area with a red outline; the blue and red here are also only examples, and different colors can be selected to achieve it), so as to achieve different visual effects. For another example, the given edge mistouch area and the given intended touch area can be configured with different text and / or pattern logos (for example, taking the text logo as an example, the given edge touch area can be configured with a text logo of "mistouch area", and the given edge touch area can be configured with a text logo of "actual touch area", the text here is only an example, and a more complex or simpler style can also be used), so as to achieve different visual effects. Or other implementation methods can also be used, which are not limited here.

[0123] Refer to the following Figure 7 The workflow of some application scenario examples of the embodiment of the present application is illustrated as shown. This workflow can be applied to the touch area detection in the edge false touch suppression scenario. Figure 7 As shown:

[0124] First, the first touch data of the current frame after noise reduction is obtained, and the first touch data may have an edge enhancement effect; for example, capacitance enhancement data may be obtained, and the capacitance enhancement data may be determined as the first touch data, and such first touch data may have an edge enhancement effect (refer to the above embodiment for understanding);

[0125] Afterwards, searching the touch frame in the first touch data;

[0126] Afterwards, it is determined whether there is a touch frame in the edge area of ​​the touch screen. If there is a touch frame in the edge area of ​​the touch screen, the first touch data is transformed to obtain the second touch data; for example, the first touch data can be transformed according to the reference touch data and the preset transformation parameters using an affine transformation algorithm or a second machine learning model to obtain the second touch data (refer to the previous embodiment for understanding);

[0127] Afterwards, the second touch data is input into the machine learning model to perform touch area detection, and coordinate information of the intended touch area corresponding to the first touch data is obtained;

[0128] Afterwards, the coordinate information of the intended touch area can be reported and the coordinates of the accidental touches can be suppressed.

[0129] It should be understood that the above Figure 7The workflow shown is not intended to be a limitation to the embodiments of the present application.

[0130] It is understandable that the above description of the touch area detection scheme is only used as some exemplary descriptions of the embodiments of the present application, and does not serve as any limitation to the embodiments of the present application.

[0131] To summarize, the touch area detection scheme provided in the embodiment of the present application can obtain the first touch data obtained by the user performing a touch operation on the touch screen, and based on the first touch data, perform touch area detection through a machine learning model to obtain the coordinate information of the intended touch area corresponding to the first touch data. Therefore, the machine learning model can be used to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is beneficial to further suppress the negative situations caused by false touches through accurate detection results, thereby improving the user experience of using the touch screen.

[0132] According to a second aspect of the embodiment of the present application, a model training method is provided, referring to Figure 8 As shown in the flowchart, the method includes the following steps S202 and S204, specifically:

[0133] S202: Obtain training samples for training the machine learning model, wherein the training samples include target touch data samples obtained by the user performing a touch operation on the touch screen, and true values ​​of the intended touch areas corresponding to the target touch data samples, and the target touch data samples include at least touch data samples for the intended touch areas of the touch screen.

[0134] Optionally, if the touch screen is a capacitive touch screen, the target touch data sample in the training sample may be a capacitive data sample. The capacitive data sample here may be mutual capacitance data or self capacitance data, depending on whether the touch screen is based on the mutual capacitance principle or the self capacitance principle. Optionally, the true value of the intended touch area corresponding to the target touch data sample may include annotation data for annotating the intended touch area in the target touch data sample.

[0135] In the embodiment of the present application, a machine learning model is trained by acquiring at least a target touch data sample including an intended touch area for the touch area and a true value of the intended touch area corresponding to the target touch data sample, so that the trained machine learning model can accurately detect the touch area according to the user's intention, that is, to achieve accurate and effective detection of the actual intended touch area of ​​the user's touch operation on the touch screen, and is conducive to further suppressing the negative situations caused by false touches through accurate detection results, thereby achieving false touch suppression and improving the user experience of using the touch screen.

[0136] In some optional embodiments, the target touch data samples include touch data samples of the intended touch area and touch data samples of the edge false touch area; the training samples also include: the true value of the edge false touch area corresponding to the target touch data samples.

[0137] Optionally, the true value of the edge false touch area corresponding to the target touch data sample may include labeling data for labeling the edge false touch area in the target touch data sample.

[0138] Based on this, in an embodiment of the present application, a target touch data sample including a touch data sample for the intended touch area of ​​the touch screen and a touch data sample for the edge mistouch area is obtained, and a machine learning model is trained using such target touch data samples, the true value of the intended touch area corresponding to the target touch data sample, and the true value of the edge mistouch area corresponding to the target touch data sample, so that the machine learning model that is subsequently trained can accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, and is conducive to further suppressing the negative situations caused by edge mistouches through accurate detection results, thereby suppressing the user's edge mistouches and improving the user's experience of using the touch screen.

[0139] After acquiring the touch data samples, the user can manually annotate them, or use a preset annotation model to annotate the target touch data samples to obtain the true value of the intended touch area and the true value of the edge false touch area. Fig. 9 As shown in FIG. 1 , an example of a target touch data sample before and after annotation is shown. Fig. 9 The left side shows the target touch data sample. Fig. 9 The right side is the target touch data sample after annotation. In this example, the touch data corresponding to the intended touch area is annotated as 200, and the touch data corresponding to the edge false touch area is annotated as 100. Of course, this example does not serve as any limitation to the embodiments of the present application.

[0140] The training samples obtained in the embodiment of the present application can be multiple training samples from different populations, so that after the machine learning model is trained with the training samples, the model can have better versatility.

[0141] In some optional embodiments, the touch screen is a capacitive touch screen. Optionally, the target touch data samples obtained by the user performing touch operations on the touch screen in the above training samples can be obtained in the following manner: obtaining original capacitance data samples, the original capacitance data samples are used to characterize: after the capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, the capacitance data samples obtained by the user performing touch operations on the touch screen are collected; the original capacitance data samples are determined as target touch data samples.

[0142] In some cases, the user holds the edge area of ​​the touch screen in different ways, and the touch data (capacitive data) at the edge area of ​​the touch screen has little difference in form. Figure 3A In the left column of examples, the user's thumb is "continuously held" on the edge area of ​​the touch screen (such as Figure 3A As shown in the figure, both contacts are edge touches). Figure 3A The right column of is an example of the corresponding capacitance data (touch data). Figure 3B In the left column of examples, the user's thumb "continuously clicks" on the edge area (such as Figure 3B As shown in the figure, one contact is an intentional touch and one contact is an edge touch). Figure 3B The right column of is an example of its corresponding capacitance data (touch data). Figure 3A Right and Figure 3B In contrast, the user's thumb is constantly holding ( Figure 3A ) and click continuously ( Figure 3B ) are almost the same in the form of capacitance data (such as capacitance data difference, affected area, touch shape, etc.). In other words, some touch data itself cannot reflect the difference between certain holding techniques in the edge area, so it is impossible to distinguish the user's true intention (that is, it is impossible to determine whether it is an intentional touch or an edge accidental touch).

[0143] It should be understood that the above-mentioned optional embodiment in the embodiment of the present application obtains the original capacitance data sample and then determines the original capacitance data sample as the target touch data sample. Since the original capacitance data sample is the capacitance data sample obtained by the user performing a touch operation on the touch screen after the capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, the data quality corresponding to the edge area in the target touch data sample is enhanced, so that the target touch data sample itself can better reflect the user's operation intention. After the machine learning model is trained with such target touch data samples, it is beneficial for the subsequent machine learning model completed by training to perform better touch area detection, and it is convenient to suppress the negative situation of edge mis-touches, thereby improving the user experience of using the touch screen.

[0144] In the embodiment of the present application, the capacitance data collection capability of the edge area of ​​the touch screen can be enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen by any method. Figure 4As shown, the touch screen 100 includes a first edge area 101, a middle area 103 and a second edge area 102 arranged along a first direction F, and the touch screen 100 includes a plurality of drive signal lines arranged in sequence in the first direction F for collecting capacitance data, wherein at least one first drive signal line 1041 among the plurality of drive signal lines is located in the first edge area 101, at least one second drive signal line 1042 among the plurality of drive signal lines is located in the second edge area 103, and at least one third drive signal line 1043 among the plurality of drive signal lines is located in the middle area 103. Optionally, the capacitance data acquisition capability of the edge area of ​​the touch screen can be enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen in the following manner: the coding time of at least one first drive signal line 1041 and / or at least one second drive signal line 1042 is set to be greater than the coding time of each third drive signal line 1043, so that the capacitance data acquisition capability of the first edge area 101 and / or the second edge area 102 of the touch screen 100 is enhanced relative to the capacitance data acquisition capability of the middle area 103 of the touch screen 100.

[0145] It should be understood that the relevant content of this part has been described in detail in the above embodiment of the touch area detection method, so it will not be repeated here. Please refer to the above for details.

[0146] Based on this, in the embodiment of the present application, the above-mentioned optional method is used to enhance the capacitance data acquisition capability of the edge area (i.e., the first edge area and / or the second edge area) of the touch screen relative to the capacitance data acquisition capability of the middle area of ​​the touch screen, so that the original capacitance data sample can be effectively obtained, and thus the data quality corresponding to the edge area in the target touch data sample can be effectively enhanced, so that the target touch data sample itself can better reflect the user's operation intention. After the machine learning model is trained with such a target touch data sample, it is beneficial for the subsequent machine learning model completed through training to perform better touch area detection, and facilitate the suppression of negative situations of accidental touches on the edge, thereby improving the user experience of using the touch screen.

[0147] S204: Input the training samples into the machine learning model to train the machine learning model.

[0148] After obtaining the training samples, they can be input into the machine learning model to train the machine learning model until the training end condition is reached, thereby completing the training of the machine learning model. The training end condition can be set as needed, for example, the training can be ended after the training rounds reach a predetermined training round (for example, 1000 times, 5000 times, 10000 times, etc.), or the training can be ended after the loss value of the loss function of the machine learning model is less than a certain threshold.

[0149] In the embodiment of the present application, the machine learning model is implemented based on artificial intelligence technology. The machine learning model can be of any type. For example, it can be a convolutional neural network model (for example, including but not limited to AlexNet, Inception, VGG, ResNet, MobileNet, FCN, U-Net, DeepLab, BiSeNet, R-CNN, Yolo, SSD, RetinaNet and other models), a deep language model (for example, including but not limited to LSTM, GRU, BiLSTM, Transformer, MarianMT, BERT, RoBERTa, XLNet, GPT, T5, S4, Mamba and other models), or a hybrid variant model based on the above two (for example, including but not limited to ViT, DeiT, ConViT, Swin Transformer, TransUNet, Swin Unet, DETR, Deformable DETR, ConvS2S, ConvBERT and other models).

[0150] Based on this, in the embodiment of the present application, through the model training scheme of the above steps S202 to S204, training samples for training the machine learning model can be obtained, and the training samples include the target touch data samples obtained when the user performs a touch operation on the touch screen, the true value of the intended touch area corresponding to the target touch data samples, and the target touch data samples at least include touch data samples for the intended touch area of ​​the touch screen, and the training samples are input into the machine learning model to train the machine learning model. Therefore, after the model training is completed, a machine learning model that can accurately detect the user's intended touch area can be obtained, which facilitates the subsequent use of the machine learning model to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is beneficial to further suppress the negative situations caused by false touches through accurate detection results, thereby improving the user's experience of using the touch screen.

[0151] In addition, since the machine learning model trained by the above-mentioned model training method can be used subsequently, the machine learning model is not only convenient to use, but also has better development and debugging efficiency, is conducive to maintenance and optimization, has better versatility, and is also conducive to reducing the extra time and energy invested by R&D personnel before and after the development is completed.

[0152] In some optional embodiments, the above step S202 includes: obtaining multiple training samples for training the machine learning model, wherein: the multiple target touch data samples of the multiple training samples include multiple first touch data samples and multiple second touch data samples.

[0153] In the embodiment of the present application, the plurality of first touch data samples are obtained by touching the touch screen using different preset standard touch techniques.

[0154] In an embodiment of the present application, the preset standard touch technique may be a touch technique commonly used by various equipment manufacturers, and may also be referred to as a "common technique". The preset standard touch technique may be pre-set. For example, taking the touch data sample including the touch data sample corresponding to the intended touch area and the touch data sample corresponding to the edge touch area as an example, some examples of preset touch techniques may include but are not limited to: the thenar of the palm and the middle finger, ring finger, and little finger of one hand simultaneously hold the edge of the touch screen, and the thumb of the holding hand draws a line or clicks in the middle area of ​​the touch screen; the thenar of the palm and the thumb of one hand simultaneously hold the edge of the touch screen, and the fingers of the other hand draw a line or click in the middle area of ​​the touch screen; the five fingers of one hand clamp the edge of the touch screen at the same time, and the fingers of the other hand draw a line or click in the middle area of ​​the touch screen, and so on.

[0155] For example, when collecting the first touch data sample, different groups of people (such as different men, women, the elderly, children, etc.) can be asked to use various preset standard touch techniques to collect data, so as to cover the operating habits of "common techniques" of users with various hand shapes as much as possible, and mark the collected first touch data samples to obtain the corresponding true value.

[0156] Optionally, after obtaining multiple training samples including the first touch data sample, the machine learning model can be trained through the multiple training samples. The trained machine learning model will have overall better performance in touch area detection and edge false touch suppression under the operation of preset standard touch techniques of different users.

[0157] In the embodiment of the present application, the plurality of second touch data samples are obtained by touching the touch screen using personalized touch techniques corresponding to different device manufacturers.

[0158] In the embodiment of the present application, the personalized touch technique may be a touch technique dedicated to a certain device manufacturer, which may also be referred to as a "non-common technique" and depends on the unique and personalized needs of different manufacturers. Therefore, in the embodiment of the present application, the specific circumstances of the personalized touch technique are not specifically limited.

[0159] For example, when collecting the second touch data sample, different groups of people (such as different men, women, the elderly, children, etc.) can be allowed to use personalized touch techniques of various device manufacturers to collect data, so as to cover the operating habits of users with various hand shapes for "non-common techniques" as much as possible, and adapt to the special needs of touch area detection and edge false touch suppression of different device manufacturers, and mark the collected second touch data samples to obtain the corresponding true value.

[0160] Optionally, the above step S204 may include: inputting multiple training samples into the machine learning model, and performing supervised fine-tuning training on the machine learning model to obtain machine learning models for different equipment manufacturers.

[0161] It should be understood that by inputting multiple training samples including the first touch data sample and the second touch data sample into the machine learning model for supervised fine-tuning training in the above manner, after the model fine-tuning training is completed, a machine learning model that can accurately detect the user's intended touch area can be obtained, and the machine learning model can effectively adapt to the special needs of touch area detection and edge false touch suppression of different equipment manufacturers, so that the machine learning model can be used in the future to accurately and effectively detect the actual intended touch area of ​​the user's touch operation using the touch screen of different equipment manufacturers, which is conducive to further suppressing the negative situations caused by false touches through accurate detection results, thereby improving the user experience of using touch screens of different equipment manufacturers, and can further effectively improve the generalization and versatility of the machine learning model.

[0162] It should be understood that the above description of the model training scheme is merely an exemplary description of the embodiments of the present application and does not constitute any limitation to the embodiments of the present application.

[0163] It can be seen from the technical solutions of the above embodiments of the present application that the present technical solution starts from improving the quality of the touch screen edge data to ensure the quality of the screen edge data, and then pre-trains a machine learning model with strong generalization. The machine learning model can theoretically approximate any function, so it is no longer up to the developer to design a complex process. Finally, the user's special hand shape is also considered to further improve the versatility of the technical solution. The technical details considered are more complete, which helps to improve the accuracy. At the same time, because the machine learning model is used, the developer's investment can be reduced, which helps to save development manpower. In addition, the system solution is implemented using a machine learning model, which benefits from the universal approximation principle of artificial intelligence technology and has a certain degree of versatility. It only needs to collect additional data according to the manufacturer's needs, and then retrain or fine-tune the general machine learning model. In other words, the technical solution can ensure the performance of the overall solution without investing too many R&D personnel, and quickly respond to changes in the needs of equipment manufacturers or different needs of different equipment manufacturers, which can effectively save labor costs, ensure the accuracy of the touch area detection and edge false touch suppression of the solution, and improve efficiency.

[0164] Reference Fig.10 As shown, according to a third aspect of an embodiment of the present application, a touch area detection device 1000 is provided, comprising:

[0165] A first acquisition module 1002 is used to acquire first touch data obtained by a user performing a touch operation on the touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen;

[0166] The detection module 1004 is used to perform touch area detection based on the first touch data through a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0167] In the embodiment of the present application, through the above-mentioned touch area detection scheme, since the first acquisition module 1002 can obtain the first touch data obtained by the user's touch operation on the touch screen, and the detection module 1004 can perform touch area detection based on the first touch data through a machine learning model to obtain the coordinate information of the intended touch area corresponding to the first touch data, therefore, the machine learning model can be used to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is conducive to further suppressing the negative situations caused by accidental touches through accurate detection results, thereby improving the user experience of using the touch screen.

[0168] In some optional embodiments, the first touch data includes touch data for an intended touch area of ​​the touch screen and touch data for an edge mis-touch area.

[0169] In some optional embodiments, the detection module 1004 is specifically used to: transform the first touch data according to reference touch data to obtain second touch data, wherein the reference touch data is data that has been determined to be able to perform touch area detection through the machine learning model to obtain coordinate information of the intended touch area corresponding to the reference touch data; input the second touch data into the machine learning model for touch area detection to obtain coordinate information of the intended touch area corresponding to the first touch data.

[0170] In some optional embodiments, the detection module 1004 is specifically used to: transform the first touch data according to the reference touch data and preset transformation parameters using an affine transformation algorithm or a second machine learning model to obtain the second touch data.

[0171] In some optional embodiments, the preset transformation parameters are predetermined in the following manner: obtaining registered touch data obtained by a user performing a touch operation on a touch screen, wherein the registered touch data at least includes touch data for an intended touch area of ​​the touch screen; performing at least one round of transformation processing on the registered touch data, and obtaining the preset transformation parameters from the processing results of the at least one round of transformation processing based on a relationship between the at least one round of transformation processing and a preset transformation termination condition.

[0172] In some optional embodiments, according to the relationship between the at least one round of transformation processing and the preset transformation termination condition, the preset transformation parameters are obtained from the processing results of the at least one round of transformation processing, including: for each round of transformation processing, determining whether the transformation result obtained by performing the transformation processing on the registered touch data in this round meets the similarity standard with the reference touch data; if the similarity standard is met, determining the transformation parameters of the transformation processing in this round as the preset transformation parameters; if the similarity standard is not met, iteratively updating the transformation parameters of the transformation processing based on the transformation result of this round of transformation processing, and using the updated transformation parameters to transform the registered touch data in the next round of transformation processing.

[0173] In some optional embodiments, the method for determining the preset transformation parameters also includes: if the number of processing times of the at least one transformation process reaches a preset number of rounds, and no transformation result is obtained whose similarity with the reference touch data satisfies the similarity standard, then the transformation parameters corresponding to the transformation result with the greatest similarity with the reference touch data are determined as the preset transformation parameters.

[0174] In some optional embodiments, the first acquisition module 1002 is specifically used to: acquire capacitance enhancement data, wherein the capacitance enhancement data is used to characterize: capacitance data acquired by a user performing a touch operation on the touch screen after the capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen; and the capacitance enhancement data is determined as the first touch data.

[0175] In some optional embodiments, the touch screen includes a first edge area, a middle area, and a second edge area arranged along a first direction, and the touch screen includes a plurality of drive signal lines arranged sequentially in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge area, at least one second drive signal line among the plurality of drive signal lines is located in the second edge area, and at least one third drive signal line among the plurality of drive signal lines is located in the middle area; the capacitance data collection capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen in the following manner: the coding time of the at least one first drive signal line and / or the at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

[0176] In some optional embodiments, the touch area detection device 1000 is further used to: display a given touch area on the touch screen to prompt the user to perform a touch operation in the given touch area according to the touch technique corresponding to the given touch area, wherein the given touch area includes a given intended touch area and a given edge false touch area; obtain registered touch data obtained by the user performing a touch operation in the given touch area on the touch screen; wherein the registered touch data is used to determine preset transformation parameters for the user, and the preset transformation parameters are used to transform the user's first touch data to obtain second touch data for input into the machine learning model for touch area detection.

[0177] In some optional embodiments, the given edge false touch area and the given intended touch area are configured with different visual effects.

[0178] The touch area detection device 1000 and its optional embodiments in the embodiment of the present application have been described in detail in the aforementioned touch area detection method embodiment, so their related contents and beneficial effects can be understood by referring to the contents of the various optional embodiments of the aforementioned method, and will not be repeated here.

[0179] Reference Fig.11 As shown, according to a fourth aspect of an embodiment of the present application, a model training device 1100 is provided, including:

[0180] A second acquisition module 1102 is used to acquire training samples for training the machine learning model, wherein the training samples include target touch data samples obtained by a user performing a touch operation on the touch screen and true values ​​of intended touch areas corresponding to the target touch data samples, and the target touch data samples at least include touch data samples for intended touch areas of the touch screen;

[0181] The training module 1104 is used to input the training samples into the machine learning model to train the machine learning model.

[0182] The embodiment of the present application uses the above-mentioned model training scheme. Since the second acquisition module 1102 can obtain training samples for training the machine learning model, the training samples include the target touch data samples obtained when the user performs a touch operation on the touch screen, the true value of the intended touch area corresponding to the target touch data samples, and the target touch data samples at least include the touch data samples for the intended touch area of ​​the touch screen, and the training module 1104 can input the training samples into the machine learning model to train the machine learning model. Therefore, after the model training is completed, a machine learning model that can accurately detect the user's intended touch area can be obtained, which is convenient for the subsequent use of the machine learning model to accurately and effectively detect the actual intended touch area of ​​the user's touch operation on the touch screen, which is conducive to further suppressing the negative situations caused by false touches through accurate detection results, thereby improving the user's experience of using the touch screen.

[0183] In some optional embodiments, the target touch data samples include touch data samples of the intended touch area and touch data samples of the edge false touch area; the training samples also include: the true value of the edge false touch area corresponding to the target touch data samples.

[0184] In some optional embodiments, the second acquisition module 1102 is specifically used to: acquire multiple training samples for training a machine learning model, wherein: the multiple target touch data samples of the multiple training samples include multiple first touch data samples and multiple second touch data samples; the multiple first touch data samples are obtained by touching the touch screen through different preset standard touch techniques; the multiple second touch data samples are obtained by touching the touch screen through personalized touch techniques corresponding to different device manufacturers; the training module 1104 is specifically used to: input the multiple training samples into the machine learning model, and perform supervised fine-tuning training on the machine learning model to obtain machine learning models for different device manufacturers.

[0185] In some optional embodiments, the second acquisition module 1102 is specifically used to: acquire original capacitance data samples, where the original capacitance data samples are used to characterize: capacitance data samples acquired by a user performing a touch operation on the touch screen after the capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen; and determine the original capacitance data samples as the target touch data samples.

[0186] In some optional embodiments, the touch screen includes a first edge area, a middle area, and a second edge area arranged along a first direction, and the touch screen includes a plurality of drive signal lines arranged sequentially in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge area, at least one second drive signal line among the plurality of drive signal lines is located in the second edge area, and at least one third drive signal line among the plurality of drive signal lines is located in the middle area; the capacitance data collection capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen in the following manner: the coding time of the at least one first drive signal line and / or the at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

[0187] The model training device 1100 and its optional embodiments in the embodiment of the present application have been described in detail in the aforementioned model training method embodiment. Therefore, their relevant contents and beneficial effects can be understood by referring to the contents of the various optional embodiments of the above-mentioned method and will not be repeated here.

[0188] According to the fifth aspect of the embodiments of the present application, there is provided an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store a computer program; the processor is used to execute the touch area detection method described in the first aspect or the model training method described in the third aspect by running the computer program stored in the memory.

[0189] Fig.12 1200 is a block diagram of an optional electronic device in an embodiment of the present application. The present application embodiment does not limit the specific implementation of the electronic device 1200. Fig.12 The electronic device 1200 provided in the embodiment of the present application includes: a processor 1202, a communication interface 1204, a memory 1206, and a communication bus 1208. Among them:

[0190] The processor 1202 , the communication interface 1204 , and the memory 1206 communicate with each other via a communication bus 1208 .

[0191] The communication interface 1204 is used to communicate with other electronic devices or servers.

[0192] The processor 1202 is used to execute the computer program 1210, and specifically can execute the relevant steps in any of the aforementioned touch area detection methods or model training method embodiments.

[0193] Specifically, the computer program 1210 may include program codes including computer operation instructions.

[0194] The processor 1202 may be a CPU, or a GPU (Graphic Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0195] The memory 1206 is used to store the computer program 1210. The memory 1206 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0196] The computer program 1210 can be specifically used to enable the processor 1202 to execute the touch area detection method or model training method in any of the aforementioned embodiments.

[0197] The specific implementation of each step in the computer program 1210 can refer to the corresponding description of the corresponding steps and units in any of the above-mentioned touch area detection method or model training method embodiments, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiments, which will not be repeated here.

[0198] The electronic device 1200 in the embodiment of the present application has been described in detail in the aforementioned touch area detection method or model training method embodiment, so its related content and beneficial effects can be understood with reference to the above-mentioned method embodiment and will not be repeated here.

[0199] According to the sixth aspect of the embodiments of the present application, the embodiments of the present application further provide a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, the touch area detection method or model training method described in any of the aforementioned multiple method embodiments is implemented. The computer storage medium includes but is not limited to: a compact disc read-only memory (CD-ROM), a random access memory (RAM), a floppy disk, a hard disk or a magneto-optical disk, etc.

[0200] According to the seventh aspect of the embodiments of the present application, the embodiments of the present application also provide a computer program product, including a computer program, which, when executed by a processor, implements the touch area detection method or model training method as described in any one of the above-mentioned multiple method embodiments.

[0201] The touch area detection device 1000 / model training device 1100 / electronic device 1200 / computer storage medium / computer program product embodiments in the embodiments of the present application have been described in detail in the aforementioned touch area detection method and model training method embodiments, so their related contents and beneficial effects can be understood with reference to the above-mentioned method embodiments and will not be repeated here.

[0202] It should be understood that the various drawings of the embodiments of the present application are for the convenience of illustrating the structures, and the size ratios of the various structures are not necessarily drawn according to the actual ratios.

[0203] In addition, it should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used to train the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0204] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0205] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA)). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., a random access memory (RAM), a read-only memory (ROM), a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown here.

[0206] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for specific applications, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0207] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A touch area detection method, comprising: Acquire first touch data obtained by a user performing a touch operation on the touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen; Based on the first touch data, touch area detection is performed through a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data.

2. The method according to claim 1, wherein: The first touch data includes touch data for an intended touch area of ​​the touch screen and touch data for an edge mis-touch area.

3. The method according to claim 1 or 2, wherein: The step of performing touch area detection based on the first touch data by using a machine learning model to obtain coordinate information of an intended touch area corresponding to the first touch data includes: According to reference touch data, transforming the first touch data to obtain second touch data, wherein the reference touch data is data that has been determined to be capable of performing touch area detection through the machine learning model to obtain coordinate information of an intended touch area corresponding to the reference touch data; The second touch data is input into the machine learning model to perform touch area detection to obtain coordinate information of the intended touch area corresponding to the first touch data.

4. The method according to claim 3, wherein: The step of transforming the first touch data according to the reference touch data to obtain the second touch data includes: According to the reference touch data and the preset transformation parameters, an affine transformation algorithm or a second machine learning model is used to transform the first touch data to obtain the second touch data.

5. The method according to claim 4, wherein: The preset transformation parameters are predetermined in the following manner: Acquire registered touch data obtained by a user performing a touch operation on the touch screen, wherein the registered touch data at least includes touch data for an intended touch area of ​​the touch screen; At least one round of transformation processing is performed on the registered touch data, and according to the relationship between the at least one round of transformation processing and the preset transformation termination condition, the preset transformation parameters are obtained from the processing results of the at least one round of transformation processing.

6. The method according to claim 5, wherein: The obtaining of preset transformation parameters from the processing result of the at least one round of transformation processing according to the relationship between the at least one round of transformation processing and the preset transformation termination condition includes: For each round of transformation processing, determining whether a transformation result obtained by performing the transformation processing on the registered touch data in the round satisfies a similarity standard with the reference touch data; If the similarity standard is met, the transformation parameters of the round of transformation processing are determined as the preset transformation parameters; If the similarity standard is not met, based on the transformation result of this round of transformation processing, the transformation parameters of the transformation processing are iteratively updated, and in the next round of transformation processing, the registered touch data are transformed using the updated transformation parameters.

7. The method according to claim 6, wherein: The method further comprises: If the at least one transformation process is processed a preset number of times and no transformation result is obtained whose similarity with the reference touch data satisfies the similarity standard, the transformation parameters corresponding to the transformation result with the greatest similarity with the reference touch data are determined as the preset transformation parameters.

8. The method according to claim 1 or 2, wherein: The acquiring of first touch data obtained by a user performing a touch operation on the touch screen includes: Acquiring capacitance enhancement data, wherein the capacitance enhancement data is used to represent: capacitance data collected by a user performing a touch operation on the touch screen after enhancing the capacitance data collection capability of the edge area of ​​the touch screen relative to the capacitance data collection capability of the middle area of ​​the touch screen; The capacitance enhancement data is determined as the first touch data.

9. The method according to claim 8, wherein: The touch screen comprises a first edge region, a middle region, and a second edge region arranged along a first direction, and the touch screen comprises a plurality of drive signal lines arranged in sequence in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge region, at least one second drive signal line among the plurality of drive signal lines is located in the second edge region, and at least one third drive signal line among the plurality of drive signal lines is located in the middle region; The capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen by: The coding time of at least one first drive signal line and / or at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

10. The method according to claim 1 or 2, wherein: The method further comprises: Displaying a given touch area on the touch screen to prompt the user to perform a touch operation in the given touch area according to a touch technique corresponding to the given touch area, wherein the given touch area includes a given intended touch area and a given edge mistouch area; Acquire registered touch data obtained by the user performing a touch operation on a given touch area on the touch screen; Among them, the registered touch data is used to determine the preset transformation parameters for the user, and the preset transformation parameters are used to transform the user's first touch data to obtain the second touch data for input into the machine learning model for touch area detection.

11. The method according to claim 10, wherein: The given edge false touch area and the given intended touch area are configured with different visual effects.

12. A model training method, comprising: Acquire training samples for training a machine learning model, wherein the training samples include target touch data samples obtained by a user performing a touch operation on a touch screen, and true values ​​of intended touch areas corresponding to the target touch data samples, and the target touch data samples at least include touch data samples for intended touch areas of the touch screen; The training samples are input into a machine learning model to train the machine learning model.

13. The method according to claim 12, wherein: The target touch data samples include touch data samples of the intended touch area and touch data samples of the edge mis-touch area; The training sample also includes: a true value of the edge mis-touch area corresponding to the target touch data sample.

14. The method according to claim 12 or 13, wherein: The obtaining of training samples for training the machine learning model comprises: obtaining a plurality of training samples for training the machine learning model, wherein: The multiple target touch data samples of the multiple training samples include multiple first touch data samples and multiple second touch data samples; The plurality of first touch data samples are obtained by touching the touch screen using different preset standard touch techniques; The plurality of second touch data samples are obtained by touching the touch screen using personalized touch techniques corresponding to different equipment manufacturers; The step of inputting the training samples into the machine learning model and training the machine learning model includes: inputting the multiple training samples into the machine learning model and performing supervised fine-tuning training on the machine learning model to obtain machine learning models for different equipment manufacturers.

15. The method according to claim 12 or 13, wherein: The target touch data samples obtained by the user performing touch operation on the touch screen in the training samples are obtained in the following manner: Acquire original capacitance data samples, where the original capacitance data samples are used to characterize: capacitance data samples collected by a user performing a touch operation on the touch screen after enhancing the capacitance data collection capability of the edge area of ​​the touch screen relative to the capacitance data collection capability of the middle area of ​​the touch screen; The original capacitance data sample is determined as the target touch data sample.

16. The method according to claim 15, wherein: The touch screen comprises a first edge region, a middle region, and a second edge region arranged along a first direction, and the touch screen comprises a plurality of drive signal lines arranged in sequence in the first direction for collecting capacitance data, wherein at least one first drive signal line among the plurality of drive signal lines is located in the first edge region, at least one second drive signal line among the plurality of drive signal lines is located in the second edge region, and at least one third drive signal line among the plurality of drive signal lines is located in the middle region; The capacitance data acquisition capability of the edge area of ​​the touch screen is enhanced relative to the capacitance data acquisition capability of the middle area of ​​the touch screen by: The coding time of at least one first drive signal line and / or at least one second drive signal line is set to be greater than the coding time of each of the third drive signal lines, so that the capacitance data collection capability of the first edge area and / or the second edge area of ​​the touch screen is enhanced relative to the capacitance data collection capability of the middle area of ​​the touch screen.

17. A touch area detection device, comprising: A first acquisition module, configured to acquire first touch data obtained by a user performing a touch operation on the touch screen, wherein the first touch data at least includes touch data for an intended touch area of ​​the touch screen; A detection module is used to perform touch area detection based on the first touch data through a machine learning model to obtain coordinate information of the intended touch area corresponding to the first touch data.

18. A model training device, comprising: A second acquisition module is used to acquire training samples for training the machine learning model, wherein the training samples include target touch data samples obtained by a user performing a touch operation on the touch screen, and true values ​​of intended touch areas corresponding to the target touch data samples, and the target touch data samples at least include touch data samples for intended touch areas of the touch screen; The training module is used to input the training samples into the machine learning model to train the machine learning model.

19. An electronic device comprising: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 17 by running the computer program stored in the memory.

20. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 17.

21. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 17.

Images