Method and device for determining touch position, electronic equipment and storage medium

Abstract

The invention relates to a method and device for determining a touch position, electronic equipment and a storage medium, and relates to the technical field of touch screens, and the method comprises the following steps: obtaining a touch signal collected on a touch screen of a terminal; inputting the touch signal into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used for performing enhancement value compensation on the touch signal, so that a signal value corresponding to each contact in a target area where the output target signal is located is within a preset signal value range; the signal values corresponding to the contacts in all directions from the area center of the target area to the area edge of the target area are gradually reduced; and according to the target signal, determining a touch position where the user touches the touch screen. Thus, the acquired touch signal can be subjected to enhanced value compensation through the signal processing model, the stability and accuracy of point reporting of the touch screen are guaranteed, and the experience of touch operation of a user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of touch screen technology, and in particular to a method, device, electronic device and storage medium for determining a touch position. Background Art

[0002] In actual application scenarios, the terminal device reports the collected touch signals to the system after coordinate calculation. The system responds to different touch events by calculating the coordinate position and touch status in combination with the touch interface. It can be seen that in the entire touch event response process, the accuracy and stability of touch coordinate calculation are particularly important.

[0003] In some scenarios, the touch screen will be in a floating state (Low Ground Mass in English; weak ground in Chinese; LGM in short). In the floating state, the floating effect will interfere with the touch signal, resulting in serious coordinate jitter and coordinate offset in the calculated touch coordinates, which will cause problems such as insensitive touch and disconnection, seriously affecting the user's operating experience. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a method, device, electronic device and storage medium for determining a touch position.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for determining a touch position is provided, the method comprising:

[0006] Acquire the touch signal collected on the touch screen of the terminal;

[0007] The touch signal is input into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend;

[0008] A touch position of the touch screen by a user is determined according to the target signal.

[0009] Optionally, the step of inputting the touch signal into a signal processing model to obtain a target signal output by the signal processing model includes:

[0010] When it is determined that the touch signal satisfies a preset signal condition, inputting the touch signal into the signal processing model to obtain a target signal output by the signal processing model;

[0011] Wherein, the preset signal condition includes:

[0012] There are at least a first preset number of negative signals in the touch signal;

[0013] The signal values ​​corresponding to the touch points in all directions from the center of the signal area where the touch signal is located to the edge of the signal area present a gradually increasing trend.

[0014] Optionally, determining a touch position of the touch screen by the user according to the target signal includes:

[0015] Obtaining signal weights corresponding to each contact point in the target area;

[0016] Determining the touch center coordinate information corresponding to the target signal through a preset touch algorithm according to the target signal and the signal weight;

[0017] The touch center coordinate information is used as the touch position where the user touches the touch screen.

[0018] Optionally, determining a touch position of the touch screen by the user according to the target signal includes:

[0019] Performing smoothing filtering on the target signal;

[0020] And according to the target signal after the smoothing filtering process, the touch position where the user touches the touch screen is determined.

[0021] Optionally, the signal processing model is pre-generated in the following manner:

[0022] A sample input set and a sample output set are obtained; the sample input set includes a plurality of first sample touch data satisfying a first preset condition, and the sample output set includes a plurality of second sample touch data satisfying a second preset condition; the first preset condition includes: at least a second preset number of negative signals exist in the first sample touch data; and the signal values ​​corresponding to the touch points in each direction from the center of the first sample data region where the first sample touch data is located to the edge of the first sample data region present a gradually increasing trend; the second preset condition includes: the signal values ​​corresponding to the touch points in the second sample data region where the second sample touch data is located are all within a preset sample signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the second sample data region to the edge of the second sample data region present a gradually decreasing trend;

[0023] Using the sample input set as input of a preset training model and using the sample output set as output of the preset training model to train the preset training model;

[0024] The trained preset training model is used as the signal processing model.

[0025] Optionally, the method further comprises:

[0026] For each of the first sample touch data, determining a first sample data area corresponding to the first sample touch data and a signal value corresponding to each touch point in the first sample data area;

[0027] determining first target touch data from a plurality of first sample touch data according to the first sample data region corresponding to each first sample touch data and the signal values ​​corresponding to each touch point in the first sample data region;

[0028] and using the first target touch data as a new sample input set;

[0029] The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises:

[0030] The new sample input set is used as the input of the preset training model, and the sample output set is used as the output of the preset training model to train the preset training model.

[0031] Optionally, determining the first target touch data from a plurality of the first sample touch data according to the first sample data area corresponding to each of the first sample touch data and the signal value corresponding to each touch point in the first sample data area comprises:

[0032] For each of the first sample touch data, if the area size of the first sample data area is within a preset area size range and / or the signal values ​​corresponding to each touch point in the first sample data area are within a preset threshold range, the first sample touch data is used as the first target touch data.

[0033] Optionally, the method further comprises:

[0034] According to a preset data processing method, performing data augmentation processing on the plurality of first sample touch data to obtain a plurality of second target touch data, and performing data augmentation processing on the plurality of second sample touch data to obtain a plurality of third target touch data;

[0035] Using the plurality of the second target touch data as a new sample input set, and using the plurality of the third target touch data as a new sample output set;

[0036] The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises:

[0037] The new sample input set is used as the input of the preset training model, and the new sample output set is used as the output of the preset training model to train the preset training model.

[0038] Optionally, the preset data processing method includes one or more of the following:

[0039] Crop the sample touch data according to the preset cropping size to obtain the target touch data;

[0040] Rotate the sample touch data according to a preset rotation angle to obtain target touch data;

[0041] The sample touch data is flipped according to a preset flip angle to obtain target touch data.

[0042] According to a second aspect of an embodiment of the present disclosure, a device for determining a touch position is provided, the device comprising:

[0043] A signal acquisition module is configured to acquire a touch signal collected on a touch screen of a terminal;

[0044] A signal processing module is configured to input the touch signal into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend;

[0045] The position determination module is configured to determine the touch position where the user touches the touch screen according to the target signal.

[0046] Optionally, the signal processing module is configured to input the touch signal into the signal processing model to obtain a target signal output by the signal processing model when it is determined that the touch signal meets a preset signal condition; wherein the preset signal condition includes: there are at least a first preset number of negative signals in the touch signal; and the signal values ​​corresponding to the touch points in all directions from the center of the signal area where the touch signal is located to the edge of the signal area show a gradually increasing trend.

[0047] Optionally, the position determination module is configured to obtain the signal weights corresponding to each touch point in the target area; determine the touch center coordinate information corresponding to the target signal through a preset touch algorithm based on the target signal and the signal weights; and use the touch center coordinate information as the touch position of the user touching the touch screen.

[0048] Optionally, the position determination module is configured to perform smoothing filtering on the target signal; and determine the touch position of the user touching the touch screen according to the target signal after the smoothing filtering.

[0049] Optionally, the signal processing model is pre-generated in the following manner:

[0050] A sample input set and a sample output set are obtained; the sample input set includes a plurality of first sample touch data satisfying a first preset condition, and the sample output set includes a plurality of second sample touch data satisfying a second preset condition; the first preset condition includes: at least a second preset number of negative signals exist in the first sample touch data; and the signal values ​​corresponding to the touch points in each direction from the center of the first sample data region where the first sample touch data is located to the edge of the first sample data region present a gradually increasing trend; the second preset condition includes: the signal values ​​corresponding to the touch points in the second sample data region where the second sample touch data is located are all within a preset sample signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the second sample data region to the edge of the second sample data region present a gradually decreasing trend;

[0051] Using the sample input set as input of a preset training model and using the sample output set as output of the preset training model to train the preset training model;

[0052] The trained preset training model is used as the signal processing model.

[0053] Optionally, the method further comprises:

[0054] For each of the first sample touch data, determining a first sample data area corresponding to the first sample touch data and a signal value corresponding to each touch point in the first sample data area;

[0055] determining first target touch data from a plurality of first sample touch data according to the first sample data region corresponding to each first sample touch data and the signal values ​​corresponding to each touch point in the first sample data region;

[0056] and using the first target touch data as a new sample input set;

[0057] The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises:

[0058] The new sample input set is used as the input of the preset training model, and the sample output set is used as the output of the preset training model to train the preset training model.

[0059] Optionally, determining the first target touch data from a plurality of the first sample touch data according to the first sample data area corresponding to each of the first sample touch data and the signal value corresponding to each touch point in the first sample data area comprises:

[0060] For each of the first sample touch data, if the area size of the first sample data area is within a preset area size range and / or the signal values ​​corresponding to each touch point in the first sample data area are within a preset threshold range, the first sample touch data is used as the first target touch data.

[0061] Optionally, the method further comprises:

[0062] According to a preset data processing method, performing data augmentation processing on the plurality of first sample touch data to obtain a plurality of second target touch data, and performing data augmentation processing on the plurality of second sample touch data to obtain a plurality of third target touch data;

[0063] Using the plurality of the second target touch data as a new sample input set, and using the plurality of the third target touch data as a new sample output set;

[0064] The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises:

[0065] The new sample input set is used as the input of the preset training model, and the new sample output set is used as the output of the preset training model to train the preset training model.

[0066] Optionally, the preset data processing method includes one or more of the following:

[0067] Crop the sample touch data according to the preset cropping size to obtain the target touch data;

[0068] Rotate the sample touch data according to a preset rotation angle to obtain target touch data;

[0069] The sample touch data is flipped according to a preset flip angle to obtain target touch data.

[0070] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to implement the steps of the touch position determination method provided in the first aspect of the present disclosure when calling the executable instructions stored on the memory.

[0071] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method for determining a touch position provided in the first aspect of the present disclosure are implemented.

[0072] The technical solution provided by the embodiment of the present disclosure may include the following beneficial effects: first, the touch signal collected on the touch screen of the terminal is obtained. Secondly, the touch signal is input into the signal processing model to obtain the target signal output by the signal processing model; the signal processing model is used to enhance the touch signal so that the signal values ​​corresponding to each contact point in the target area where the output target signal is located are all within the preset signal value range, and the signal values ​​corresponding to the contact points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend. Finally, according to the target signal, the touch position of the user touching the touch screen is determined. In the present disclosure, the signal processing model obtained by machine learning enhances the touch signal collected by the touch screen so that the signal values ​​corresponding to each contact point in the target area where the target signal output by the model is located are within the normal value range, and the signal values ​​corresponding to the contact points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend, that is, the signal value of the target area presents a convex shape as a whole. In other words, the data form of the target signal is made more stable, which conforms to the signal form formed by the actual user pressing the touch screen. Finally, the touch position is determined according to the target signal, which ensures the stability and accuracy of the touch screen reporting point, greatly improving the user's touch operation experience.

[0073] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0075] Figure 1 The figure is a flow chart of a method for determining a touch position according to an exemplary embodiment.

[0076] Figure 2is a schematic diagram of a touch signal according to an exemplary embodiment.

[0077] Figure 3 is a schematic diagram of a target signal according to an exemplary embodiment.

[0078] Figure 4 It is a block diagram of a device for determining a touch position according to an exemplary embodiment.

[0079] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0080] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0081] The terms "first", "second", etc. in the specification and claims of this application and the above drawings are used to distinguish similar objects and do not have to be understood as a specific order or sequence. In addition, in the description with reference to the drawings, the same symbols in different drawings represent the same elements.

[0082] In the description of the present disclosure, unless otherwise specified, "multiple" means two or more than two, and other quantifiers are similar thereto; "at least one item", "one item or multiple items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one item a can represent any number of a; for another example, one item or multiple items among a, b and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple; "and / or" is a kind of description of the association relationship of associated objects, indicating that there can be three kinds of relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " indicates that the associated objects before and after are in an "or" relationship.

[0083] Although operations or steps are described in a specific order in the drawings in the embodiments of the present disclosure, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or to perform all the operations or steps shown to obtain the desired results. In the embodiments of the present disclosure, these operations or steps can be performed in series; these operations or steps can also be performed in parallel; or some of these operations or steps can be performed.

[0084] Before introducing the touch position determination method, device, electronic device and storage medium provided by the present disclosure, the application scenarios involved in each embodiment of the present disclosure are first introduced. In some scenarios, the touch screen will be in a floating state. In the use scenario of the floating state, the floating effect will interfere with the touch signal, resulting in serious coordinate jitter, coordinate offset and other problems in the calculated touch coordinates, which will in turn cause problems such as insensitive touch and broken touch, seriously affecting the user's operating experience. Especially for terminal devices with mobile phone cases and tempered films, floating scenes are more likely to exist, that is, the touch signal is more likely to be interfered with, which will be very poor for the user's gaming experience and affect the user's gaming operation.

[0085] In some methods, the touch signal is compensated by the self-capacitance signal corresponding to the border area of ​​the touch screen. However, the interference degree of the touch signal in different floating states is different, and the level of the floating state is not taken into account in the process of compensating with the self-capacitance signal. In other words, no matter how much interference the current touch signal is subjected to, it is compensated in the same way, which is prone to over-compensation or under-compensation, resulting in unstable touch coordinates calculated in the end.

[0086] In other methods, problems such as coordinate jitter and coordinate offset in the floating state are solved by locking the reporting point. Specifically, if the area offset corresponding to the touch signal is less than the preset offset range, the coordinate position of the touch signal is locked, that is, it is considered that the current touch coordinates have not moved. Although this method can solve the problems of coordinate jitter and coordinate offset to a certain extent, at the same time, the coordinates are easily locked for the touch movement under normal user operation, which makes the user's touch movement very difficult, especially affecting the user's micro-operation during the game.

[0087] In order to solve the above technical problems, the present invention provides a method, device, electronic device and storage medium for determining the touch position. The signal processing model obtained by machine learning is used to enhance and compensate the touch signal collected by the touch screen, so that the signal value corresponding to each touch point in the target area where the target signal output by the model is located is within the normal value range, and the signal value corresponding to the touch point in each direction from the center of the target area to the edge of the target area presents a gradually decreasing trend, that is, the signal value of the target area presents a convex shape as a whole. In other words, the data form of the target signal is made more stable, which is consistent with the signal form formed by the actual user pressing the touch screen. Finally, the touch position is determined according to the target signal. In this way, the stability and accuracy of the touch screen reporting point can be guaranteed, which greatly improves the user's touch operation experience.

[0088] The specific implementation modes of the present invention are described in detail below with reference to the accompanying drawings.

[0089] Figure 1 This is a flow chart of a method for determining a touch position according to an exemplary embodiment. The method can be applied to a terminal, which can be any electronic device with a touch screen, such as a smart phone, tablet computer, smart TV, smart watch, PDA (Personal Digital Assistant), portable computer and other mobile terminals, or smart home devices, such as sweeping robots, air purifiers, air conditioners, lighting, speakers, robots, etc. Figure 1 As shown, the method may include the following steps:

[0090] In step S101, a touch signal collected on a touch screen of a terminal is acquired.

[0091] Taking a capacitive touch screen as an example, the touch screen usually includes multiple touch points. When a user touches the screen, a coupling capacitor is formed between the human body electric field, the finger and the conductor layer, and a touch signal is generated on the touch point. Then, the touch position of the user when touching the screen can be determined based on the touch signal. That is, the touch signal is the signal generated by the user pressing the touch screen.

[0092] In step S102 , the touch signal is input into a signal processing model to obtain a target signal output by the signal processing model.

[0093] Among them, the signal processing model can be pre-generated and used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in all directions from the center of the target area to the edge of the target area show a gradually decreasing trend.

[0094] In some usage scenarios, when the user does not hold the terminal or the terminal is covered with a thick protective shell, the grounding state of the terminal will be affected, and the touch screen of the terminal will be in a floating state. Affected by the floating effect, the touch signal triggered by the user on the touch screen will be disturbed, and the signal value will change accordingly. For example, Figure 2 As shown, Figure 2 There are two boxes in it, which respectively simulate the touch signals generated when the left and right thumbs of the user touch the touch screen. Figure 2 It can be seen that due to the influence of the floating ground effect, the signal value in the center area of ​​the left and right boxes is significantly smaller than that in the surrounding area, and the overall signal value presents a concave shape. When the touch screen is in normal working condition, there should not be too many negative signals in the area where the touch signal is located, and the overall signal value should present a convex shape, that is, the signal value in the center area is greater than that in the surrounding area. At the same time, under normal working conditions, the signal value of the contact point in the area not touched by the user is 0, or a value close to 0. But in Figure 2 Due to the floating effect, the two thumb touch areas will interfere with each other, causing more and larger negative signals to be generated in the area not touched by the user. Figure 2 There are large negative signals in the surrounding areas of the two boxes. For example, the touch points with signal values ​​of -357, -301, -343, -188 and -117 in the left box are all negative signals with large signal values, which will seriously affect the accuracy of subsequent determination of the touch position.

[0095] When determining the touch position, the touch center coordinates are determined based on the signal value of the touch signal corresponding to the touch point, and then the corresponding touch command is generated. Figure 2The touch signals in the two boxes are interfered with, causing the signal values ​​of each touch point to change. If the touch center coordinates are calculated directly based on the interfered touch signal, the calculated touch position will have a large offset or jitter, resulting in touch insensitivity, disconnection and other related problems, which seriously affects the user's touch operation experience. Therefore, in this step, the touch signal can be input into a pre-generated signal processing model, because the signal processing model has the ability to enhance and compensate the signal. Through the signal processing model, the touch signal is enhanced and compensated to ensure that the data form of the user's touch area is more stable, thereby improving the accuracy of subsequent touch position determination.

[0096] In order to more intuitively show the effect of model processing, Figure 3 As shown, a signal schematic diagram of a target signal output by a model is shown, such as Figure 3 As shown in the figure, the target signal processed by the signal processing model presents a convex shape in its overall form, that is, the signal value closer to the center is larger, the signal value closer to the edge is smaller, and the large negative signal around the signal no longer exists. The overall signal shape is more stable, and the area where the target signal is located is more consistent with the user's finger shape.

[0097] In addition, since the signal processing model is often a pre-generated local model, in order to facilitate use on the terminal, the signal processing model can be deployed to the terminal through the target model interface. In this way, during the application process, the touch signal can be sent to the target model interface first. Then, the signal processing model is called through the target model interface, and the touch signal is input into the pre-generated signal processing model to obtain the target signal output by the signal processing model. Among them, the target model interface can be, for example, a TF Lite model interface. By way of example, the signal processing model can be first converted into a TF Lite model that can be used by the terminal, and the TF Lite model file, the matching .so file, and the model call file can be deployed to the terminal, so that when the signal processing model needs to be used, the signal processing model can be called through the TF Lite model interface.

[0098] In step S103, the touch position of the touch screen by the user is determined according to the target signal.

[0099] In this step, the touch center coordinate information of the user touching the touch screen can be determined according to the target signal through a preset touch algorithm. The preset touch algorithm may be, for example but not limited to, an HTC (Host Touch Computing) algorithm. Specifically, the signal weights of each touch point in the target area corresponding to the target signal may be obtained first, and then the touch center coordinate information corresponding to the target signal may be determined according to the target signal and the signal weight through a preset touch algorithm, that is, the touch point where the user touches the touch screen may be determined. The touch center coordinate information is used as the touch position where the user touches the touch screen. After determining the touch position where the user touches the touch screen, the final touch position may be reported to the terminal system application end in order to generate a corresponding touch event.

[0100] Considering that there are some other interferences in the actual scene, in order to ensure the accuracy of the touch position determination, the target signal can also be smoothed and filtered to eliminate the noise mixed in the target signal. Then, the touch position of the user touching the touch screen can be determined based on the target signal after the smoothing and filtering.

[0101] The above method is used to enhance and compensate the touch signal collected by the touch screen through the signal processing model obtained by machine learning, so that the signal values ​​corresponding to each touch point in the target area where the target signal output by the model is located are within the normal value range, and the signal values ​​corresponding to the touch points in all directions from the center of the target area to the edge of the target area show a gradually decreasing trend, that is, the signal value of the target area presents a convex shape as a whole. In other words, the data form of the target signal is made more stable, which conforms to the signal form formed by the actual user pressing the touch screen. Finally, the touch position is determined according to the target signal. In this way, the stability and accuracy of the touch screen reporting point can be guaranteed, which greatly improves the user's touch operation experience.

[0102] In some embodiments, in order to improve the efficiency and accuracy of data processing and save computing power, it can be determined whether the current touch screen is in a floating state. Specifically, in the above step S102, inputting the touch signal into the signal processing model to obtain the target signal output by the signal processing model may include: when it is determined that the touch signal meets the preset signal condition, inputting the touch signal into the signal processing model to obtain the target signal output by the signal processing model.

[0103] The preset signal condition includes:

[0104] There are at least a first preset number of negative signals in the touch signal;

[0105] The signal values ​​corresponding to the touch points in all directions from the center of the signal area where the touch signal is located to the edge of the signal area present a gradually increasing trend.

[0106] Since a relatively large negative signal is easily generated between two touch positions when disturbed, for accurate identification, the negative signal may be a negative signal whose signal value is greater than or equal to a preset negative signal value.

[0107] Considering that in actual scenarios, when the touch screen is in a floating state, the touch signal will be disturbed. Figure 2 For example, the signal value of the central area will be significantly smaller than the signal value of the surrounding area, and the interference between the two touch areas causes the area that the user does not touch to generate a larger negative signal. According to the above characteristics, when the touch signal meets the preset signal conditions, it is determined that the current touch screen is in a floating state. At this time, the touch signal can be input into the signal processing model so that the signal processing model can enhance the touch signal. In the case where the touch signal does not meet the preset signal conditions, it can be indicated that the current touch screen is in a normal working state. At this time, there is no need to input the touch signal into the signal processing model. The touch position of the user touching the touch screen can be directly determined based on the acquired touch signal. In this way, the touch signal can be accurately enhanced and compensated, while saving the computing power of the terminal.

[0108] In some embodiments, the signal processing model may be pre-generated by:

[0109] S1, obtain the sample input set and sample output set.

[0110] The sample input set includes a plurality of first sample touch data satisfying a first preset condition, and the sample output set includes a plurality of second sample touch data satisfying a second preset condition.

[0111] The first preset condition includes: there are at least a second preset number of negative signals in the first sample touch data; and the signal values ​​corresponding to the touch points in all directions from the center of the first sample data area where the first sample touch data is located to the edge of the first sample data area present a gradually increasing trend.

[0112] The second preset condition includes: the signal values ​​corresponding to each contact point in the second sample data area where the second sample touch data is located are all within the preset sample signal value range, and the signal values ​​corresponding to the contact points in each direction from the area center of the second sample data area to the area edge of the second sample data area show a gradually decreasing trend.

[0113] In other words, the first sample touch data is a signal shape that meets the interference in the floating state, that is, the first sample data area where the signal is located presents a concave shape, and there are at least a second preset number of negative signals. Similarly, the negative signal can be a negative signal whose signal value is greater than or equal to the preset negative signal value. The second sample touch data is a signal shape that meets the normal working state and is generated when the user touches the touch screen, that is, the second sample data area where the signal is located presents a convex shape, and at the same time, there are no negative signals greater than the second preset number. Similarly, the negative signal can be a negative signal whose signal value is greater than or equal to the preset negative signal value.

[0114] S2: Use the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model.

[0115] The preset training model may be, for example but not limited to, a generative adversarial network (GAN).

[0116] S3, using the trained preset training model as the signal processing model.

[0117] For example, multiple second sample touch data can be used as a sample output set, and each sample output in the sample output set includes a second sample touch data. Multiple first sample touch data can be used as a sample input set, and each sample input in the sample input set includes a first sample touch data. The sample inputs in the sample input set correspond one-to-one with the sample outputs in the sample output set, that is, the first sample touch data included in the sample input, and the corresponding sample output is the second sample touch data corresponding to the first sample touch data. When training the preset training model, the sample input set can be used as the input of the preset training model, and the sample output set can be used as the output of the preset training model for training, so that when the preset training model inputs the sample input set, the output target sample touch data can match the sample output set.

[0118] Specifically, an initial generative adversarial network can be preselected (the parameters of the generative adversarial network can be selected according to specific needs). Any first sample touch data is used as the input of the initial generative adversarial network to obtain the target sample touch data corresponding to the first sample touch data output by the initial generative adversarial network. The target sample touch data is compared with the second sample touch data corresponding to the first sample touch data, so as to correct the parameters in the initial generative adversarial network. Repeat the above steps so that the initial generative adversarial network meets the preset conditions, and finally the initial generative adversarial network that meets the preset conditions is used as the signal processing model. Among them, the preset condition can be, for example, the minimum preset loss function.

[0119] In some embodiments, before training the model, in order to improve the training efficiency, the first sample touch data may be cleaned. Specifically, before S2, the following steps may be included:

[0120] S4, for each of the first sample touch data, determining a first sample data region corresponding to the first sample touch data and a signal value corresponding to each touch point in the first sample data region.

[0121] S5 , determining first target touch data from a plurality of first sample touch data according to a first sample data region corresponding to each first sample touch data and a signal value corresponding to each touch point in the first sample data region.

[0122] For example, for each first sample touch data, when the area size of the first sample data area is within a preset area size range and / or the signal value corresponding to each touch point in the first sample data area is within a preset threshold range, the first sample touch data is used as the first target touch data.

[0123] When the area size of the first sample data area is outside the preset area size range, it can be determined that the pressing area corresponding to the first sample touch data is inconsistent with the normal finger size. When the signal values ​​corresponding to each contact point in the first sample data area are outside the preset threshold range, it can be determined that the first sample touch data does not belong to the data abnormality caused by the floating effect. In this way, the first sample touch data that does not meet the training requirements can be deleted, thereby ensuring the validity and accuracy of the input first sample touch data.

[0124] S6, and taking the first target touch data as a new sample input set.

[0125] Correspondingly, in S2, using the sample input set as the input of the preset training model and using the sample output set as the output of the preset training model to train the preset training model may include: using the new sample input set as the input of the preset training model and using the sample output set as the output of the preset training model to train the preset training model.

[0126] In some other embodiments, before training the model, in order to increase the number of training samples, data augmentation processing may be performed on the first sample touch data and the second sample touch data. Specifically, before S2, the following may be included:

[0127] S7, performing data augmentation processing on the plurality of first sample touch data according to a preset data processing method to obtain a plurality of second target touch data, and performing data augmentation processing on the plurality of second sample touch data to obtain a plurality of third target touch data.

[0128] The preset data processing method may include, for example but not limited to, one or more of the following:

[0129] Crop the sample touch data according to the preset cropping size to obtain the target touch data;

[0130] Rotate the sample touch data according to a preset rotation angle to obtain target touch data;

[0131] The sample touch data is flipped according to a preset flip angle to obtain target touch data.

[0132] The preset cropping size, the preset rotation angle, and the preset flipping angle can be one or more. That is, the sample touch data can be cropped according to one or more sizes to obtain target touch data of different sizes; the sample touch data can also be rotated according to one or more rotation angles to obtain target touch data of different positions and directions in two-dimensional space; the sample touch data can also be flipped according to one or more flipping angles to obtain target touch data of different positions and directions in three-dimensional space.

[0133] By using a preset data processing method, data augmentation processing is performed on the first sample touch data and the second sample touch data, which can effectively increase the number of samples without consuming a lot of manpower and financial resources, thereby improving the accuracy of model learning.

[0134] S8, taking the plurality of second target touch data as a new sample input set, and taking the plurality of third target touch data as a new sample output set.

[0135] Correspondingly, in S2, using the sample input set as the input of the preset training model and using the sample output set as the output of the preset training model to train the preset training model may include: using the new sample input set as the input of the preset training model and using the new sample output set as the output of the preset training model to train the preset training model.

[0136] The above method is used to enhance and compensate the touch signal collected by the touch screen through the signal processing model obtained by machine learning, so that the signal values ​​corresponding to each touch point in the target area where the target signal output by the model is located are within the normal value range, and the signal values ​​corresponding to the touch points in all directions from the center of the target area to the edge of the target area show a gradually decreasing trend, that is, the signal value of the target area presents a convex shape as a whole. In other words, the data form of the target signal is made more stable, which conforms to the signal form formed by the actual user pressing the touch screen. Finally, the touch position is determined according to the target signal. In this way, the stability and accuracy of the touch screen reporting point can be guaranteed, which greatly improves the user's touch operation experience.

[0137] Figure 4 is a block diagram of a device for determining a touch position according to an exemplary embodiment. Figure 4 As shown, the device 200 includes:

[0138] The signal acquisition module 201 is configured to acquire a touch signal collected on the touch screen of the terminal;

[0139] The signal processing module 202 is configured to input the touch signal into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in all directions from the center of the target area to the edge of the target area show a gradually decreasing trend;

[0140] The position determination module 203 is configured to determine the touch position of the touch screen where the user touches according to the target signal.

[0141] Optionally, the signal processing module 202 is configured to input the touch signal into the signal processing model to obtain a target signal output by the signal processing model when it is determined that the touch signal satisfies a preset signal condition; wherein the preset signal condition includes: there are at least a first preset number of negative signals in the touch signal; and the signal values ​​corresponding to the touch points in all directions from the center of the signal area where the touch signal is located to the edge of the signal area show a gradually increasing trend.

[0142] Optionally, the position determination module 203 is configured to obtain the signal weights corresponding to each touch point in the target area; determine the touch center coordinate information corresponding to the target signal based on the target signal and the signal weights through a preset touch algorithm; and use the touch center coordinate information as the touch position of the user touching the touch screen.

[0143] Optionally, the position determination module 203 is configured to perform smoothing filtering on the target signal; and determine the touch position of the user touching the touch screen according to the target signal after the smoothing filtering.

[0144] Optionally, the signal processing model is pre-generated in the following manner:

[0145] A sample input set and a sample output set are obtained; the sample input set includes a plurality of first sample touch data satisfying a first preset condition, and the sample output set includes a plurality of second sample touch data satisfying a second preset condition; the first preset condition includes: at least a second preset number of negative signals exist in the first sample touch data; and signal values ​​corresponding to touch points in all directions from the center of a first sample data region where the first sample touch data is located to the edge of the first sample data region present a gradually increasing trend; the second preset condition includes: signal values ​​corresponding to all touch points in a second sample data region where the second sample touch data is located are all within a preset sample signal value range, and signal values ​​corresponding to touch points in all directions from the center of the second sample data region to the edge of the second sample data region present a gradually decreasing trend;

[0146] The sample input set is used as the input of a preset training model, and the sample output set is used as the output of the preset training model to train the preset training model;

[0147] The trained preset training model is used as the signal processing model.

[0148] Optionally, the method further comprises:

[0149] For each of the first sample touch data, determining a first sample data region corresponding to the first sample touch data and a signal value corresponding to each touch point in the first sample data region;

[0150] Determine first target touch data from a plurality of first sample touch data according to the first sample data region corresponding to each of the first sample touch data and the signal values ​​corresponding to each touch point in the first sample data region;

[0151] and taking the first target touch data as a new sample input set;

[0152] The step of using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model includes:

[0153] The new sample input set is used as the input of the preset training model, and the sample output set is used as the output of the preset training model to train the preset training model.

[0154] Optionally, determining the first target touch data from the plurality of first sample touch data according to the first sample data region corresponding to each of the first sample touch data and the signal value corresponding to each touch point in the first sample data region comprises:

[0155] For each first sample touch data, when the area size of the first sample data area is within a preset area size range and / or the signal values ​​corresponding to each touch point in the first sample data area are within a preset threshold range, the first sample touch data is used as the first target touch data.

[0156] Optionally, the method further comprises:

[0157] According to a preset data processing method, a plurality of the first sample touch data are subjected to data augmentation processing to obtain a plurality of second target touch data, and a plurality of the second sample touch data are subjected to data augmentation processing to obtain a plurality of third target touch data;

[0158] Using the plurality of second target touch data as a new sample input set, and using the plurality of third target touch data as a new sample output set;

[0159] The step of using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model includes:

[0160] The new sample input set is used as the input of the preset training model, and the new sample output set is used as the output of the preset training model to train the preset training model.

[0161] Optionally, the preset data processing method includes one or more of the following:

[0162] Crop the sample touch data according to the preset cropping size to obtain the target touch data;

[0163] Rotate the sample touch data according to a preset rotation angle to obtain target touch data;

[0164] The sample touch data is flipped according to a preset flip angle to obtain target touch data.

[0165] The above-mentioned device is used to enhance and compensate the touch signal collected by the touch screen through the signal processing model obtained by machine learning, so that the signal value corresponding to each touch point in the target area where the target signal output by the model is located is within the normal value range, and the signal value corresponding to the touch point in each direction from the center of the target area to the edge of the target area presents a gradually decreasing trend, that is, the signal value of the target area presents a convex shape as a whole. In other words, the data form of the target signal is made more stable, which conforms to the signal form formed by the actual user pressing the touch screen. Finally, the touch position is determined according to the target signal. In this way, the stability and accuracy of the touch screen reporting point can be guaranteed, which greatly improves the user's touch operation experience.

[0166] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0167] The present disclosure further provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method for determining a touch position provided by the present disclosure are implemented.

[0168] Figure 5 is a block diagram of an electronic device 300 according to an exemplary embodiment. For example, the electronic device 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0169] Reference Figure 5 , the electronic device 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output interface 312 , a sensor component 314 , and a communication component 316 .

[0170] The processing component 302 generally controls the overall operation of the electronic device 300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-mentioned touch position determination method. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0171] The memory 304 is configured to store various types of data to support operations on the electronic device 300. Examples of such data include instructions for any application or method operating on the electronic device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0172] The power supply component 306 provides power to the various components of the electronic device 300. The power supply component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 300.

[0173] The multimedia component 308 includes a screen that provides an output interface between the electronic device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front camera and / or a rear camera. When the electronic device 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0174] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), and when the electronic device 300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 304 or sent via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0175] The input / output interface 312 provides an interface between the processing component 302 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0176] The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the electronic device 300. For example, the sensor assembly 314 can detect the open / closed state of the electronic device 300, the relative positioning of components, such as the display and keypad of the electronic device 300, and the sensor assembly 314 can also detect the position change of the electronic device 300 or a component of the electronic device 300, the presence or absence of user contact with the electronic device 300, the orientation or acceleration / deceleration of the electronic device 300, and the temperature change of the electronic device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0177] The communication component 316 is configured to facilitate wired or wireless communication between the electronic device 300 and other devices. The electronic device 300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0178] In an exemplary embodiment, the electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned touch position determination method.

[0179] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, and the instructions can be executed by a processor 320 of an electronic device 300 to complete the above touch position determination method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0180] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above touch position determination method when executed by the programmable device.

[0181] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0182] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining a touch position, characterized in that: The method comprises: Acquire the touch signal collected on the touch screen of the terminal; The touch signal is input into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend; A touch position of the touch screen by a user is determined according to the target signal.

2. The method according to claim 1, characterized in that The step of inputting the touch signal into a signal processing model to obtain a target signal output by the signal processing model includes: When it is determined that the touch signal satisfies a preset signal condition, inputting the touch signal into the signal processing model to obtain a target signal output by the signal processing model; Wherein, the preset signal condition includes: There are at least a first preset number of negative signals in the touch signal; The signal values ​​corresponding to the touch points in all directions from the center of the signal area where the touch signal is located to the edge of the signal area present a gradually increasing trend.

3. The method according to claim 1, characterized in that Determining the touch position of the touch screen by the user according to the target signal includes: Obtaining signal weights corresponding to each contact point in the target area; Determining the touch center coordinate information corresponding to the target signal through a preset touch algorithm according to the target signal and the signal weight; The touch center coordinate information is used as the touch position where the user touches the touch screen.

4. The method according to claim 1, characterized in that: Determining the touch position of the touch screen by the user according to the target signal includes: Performing smoothing filtering on the target signal; And according to the target signal after the smoothing filtering process, the touch position where the user touches the touch screen is determined.

5. The method according to any one of claims 1 to 4, characterized in that The signal processing model is pre-generated in the following way: A sample input set and a sample output set are obtained; the sample input set includes a plurality of first sample touch data satisfying a first preset condition, and the sample output set includes a plurality of second sample touch data satisfying a second preset condition; the first preset condition includes: at least a second preset number of negative signals exist in the first sample touch data; and the signal values ​​corresponding to the touch points in each direction from the center of the first sample data region where the first sample touch data is located to the edge of the first sample data region present a gradually increasing trend; the second preset condition includes: the signal values ​​corresponding to the touch points in the second sample data region where the second sample touch data is located are all within a preset sample signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the second sample data region to the edge of the second sample data region present a gradually decreasing trend; Using the sample input set as input of a preset training model and using the sample output set as output of the preset training model to train the preset training model; The trained preset training model is used as the signal processing model.

6. The method according to claim 5, characterized in that The method further comprises: For each of the first sample touch data, determining a first sample data area corresponding to the first sample touch data and a signal value corresponding to each touch point in the first sample data area; determining first target touch data from a plurality of first sample touch data according to the first sample data region corresponding to each first sample touch data and the signal values ​​corresponding to each touch point in the first sample data region; and using the first target touch data as a new sample input set; The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises: The new sample input set is used as the input of the preset training model, and the sample output set is used as the output of the preset training model to train the preset training model.

7. The method according to claim 6, characterized in that The determining first target touch data from a plurality of first sample touch data according to the first sample data area corresponding to each first sample touch data and the signal value corresponding to each touch point in the first sample data area comprises: For each of the first sample touch data, if the area size of the first sample data area is within a preset area size range and / or the signal values ​​corresponding to each touch point in the first sample data area are within a preset threshold range, the first sample touch data is used as the first target touch data.

8. The method according to claim 5, characterized in that The method further comprises: According to a preset data processing method, performing data augmentation processing on the plurality of first sample touch data to obtain a plurality of second target touch data, and performing data augmentation processing on the plurality of second sample touch data to obtain a plurality of third target touch data; Using the plurality of the second target touch data as a new sample input set, and using the plurality of the third target touch data as a new sample output set; The using the sample input set as the input of a preset training model and the sample output set as the output of the preset training model to train the preset training model comprises: The new sample input set is used as the input of the preset training model, and the new sample output set is used as the output of the preset training model to train the preset training model.

9. The method according to claim 8, characterized in that The preset data processing method includes one or more of the following: Crop the sample touch data according to the preset cropping size to obtain the target touch data; Rotate the sample touch data according to a preset rotation angle to obtain target touch data; The sample touch data is flipped according to a preset flip angle to obtain target touch data.

10. A device for determining a touch position, characterized in that: The device comprises: A signal acquisition module is configured to acquire a touch signal collected on a touch screen of a terminal; A signal processing module is configured to input the touch signal into a signal processing model to obtain a target signal output by the signal processing model; the signal processing model is used to enhance and compensate the touch signal so that the signal values ​​corresponding to each touch point in the target area where the output target signal is located are all within a preset signal value range, and the signal values ​​corresponding to the touch points in each direction from the center of the target area to the edge of the target area show a gradually decreasing trend; The position determination module is configured to determine the touch position where the user touches the touch screen according to the target signal.

11. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the steps of the method described in any one of claims 1 to 9 when calling the executable instructions stored in the memory.

12. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.

Images