Methods, apparatus, devices, and storage media for identifying touch-sensitive objects

Abstract

This application relates to the field of touch recognition technology, and discloses a method for identifying touch objects, applied to infrared touch devices. As a touch object enters the touch detection area of ​​the screen and gradually approaches until it makes contact with the screen, occlusion signals of the touch object are periodically collected. These collected occlusion signals are sequentially combined to form a touch timing signal. By analyzing the touch timing signal, the variation pattern of the occlusion signal is determined. Since the variation pattern of the occlusion signal differs when using different types of touch objects, and the variation pattern of the occlusion signal corresponding to a touch object is only affected by the material of the touch object, the type of touch object can be determined more accurately based on the variation pattern of the occlusion signal corresponding to the touch object, thereby improving recognition accuracy. This application also discloses a device and equipment for identifying touch objects, and a storage medium.

Description

Technical Field

[0001] This application relates to the field of touch recognition technology, such as a method, apparatus, device, and storage medium for recognizing touch objects. Background Technology

[0002] Currently, when interacting with infrared touch devices, users typically use their fingers or styluses to perform touch operations on the screen surface. To enhance the user experience, infrared touch devices can recognize different types or materials of touch objects, thus providing different touch feedback or displaying different touch response interfaces when different types of touch objects touch the screen.

[0003] To identify different types of touch objects, related technologies use infrared touch devices to determine the type of touch object based on the difference in the area of ​​infrared light blocked when different objects touch the screen of the infrared touch device. Specifically, when a touch object touches the screen of the infrared touch device, the infrared touch device acquires the area of ​​the touch object blocking the screen and determines the type of touch object based on the comparison result of the blocking area and an area threshold.

[0004] However, since different touch objects may have similar occlusion areas when touching the screen of an infrared touch device, or the same touch object may have different occlusion areas when touching different positions on the screen, the accuracy of identifying the type of touch object based on the occlusion area in related technologies is relatively low. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This application provides a method, apparatus, device, and storage medium for identifying touch objects. When a touch object is touched on the screen of an infrared touch device, the type of touch object can be identified more accurately, thereby improving the recognition accuracy.

[0007] In a first aspect, embodiments of this application provide a method for identifying a touch-sensitive object, applied to an infrared touch-sensitive device, the method comprising:

[0008] The occlusion signal of the touch object is periodically collected during the preset period to obtain multiple occlusion signals. The preset period starts when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease.

[0009] Multiple occlusion signals are combined sequentially to form a touch timing signal;

[0010] Identify touch timing signals to extract target features of the touch timing signals;

[0011] The type of the touched object is determined based on the target characteristics of the touch timing signal;

[0012] The occlusion signal includes the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time; the target feature is used to characterize the change pattern of the occlusion area of ​​the touch object with the distance between the touch object and the screen and the acquisition time during the preset period.

[0013] Optionally, identifying touch timing signals to extract target features of the touch timing signals includes: inputting the touch timing signals into a recurrent neural network model so that the recurrent neural network model can identify the changing patterns of multiple occlusion signals in the touch timing signals and obtain the target features of the touch timing signals.

[0014] Optionally, identifying touch timing signals to extract target features of the touch timing signals includes: inputting the touch timing signals into a convolutional neural network model to enable the convolutional neural network model to identify the touch timing signals and extract spatial features of the touch timing signals; inputting the spatial features of the touch timing signals into a recurrent neural network model to enable the recurrent neural network model to identify the variation patterns of multiple occlusion signals in the touch timing signals based on the spatial features of the touch timing signals, thereby obtaining the temporal features of the touch timing signals; and using the spatial features and temporal features as target features.

[0015] Optionally, multiple occlusion signals are combined sequentially to form a touch timing signal, including: obtaining a contact occlusion signal from multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal; the contact occlusion signal is the occlusion signal generated when the distance between the touch object and the screen is zero; and combining the contact occlusion signals in chronological order to form a touch timing signal.

[0016] Optionally, multiple occlusion signals are combined sequentially to form a touch timing signal, including: determining abnormal occlusion signals from multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal; filtering out abnormal occlusion signals from multiple occlusion signals to obtain a target occlusion signal; and combining the target occlusion signals in chronological order to form a touch timing signal.

[0017] Optionally, before identifying the touch timing signal to extract the target features of the touch timing signal, the method further includes: obtaining occlusion signals from multiple occlusion signals of the touch timing signal where the distance between the touch object and the screen is within a preset distance range, and obtaining occlusion signals to be merged; and performing merging processing on the occlusion signals to be merged in the touch timing signal.

[0018] Secondly, embodiments of this application provide a device for identifying touch-sensitive objects, integrated into an infrared touch device, the device comprising:

[0019] The acquisition module is used to periodically acquire occlusion signals of the touch object during a preset period, and obtain multiple occlusion signals. The preset period starts when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease. The occlusion signals include the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time.

[0020] The combination module is used to combine multiple occlusion signals sequentially to form touch timing signals;

[0021] The recognition module is used to identify touch timing signals in order to extract target features from the touch timing signals. The target features are used to characterize the change pattern of the occlusion area of ​​the touch object with the distance between the touch object and the screen and the acquisition time during a preset period.

[0022] The determination module determines the type of the touch object based on the target characteristics of the touch timing signal.

[0023] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing program instructions, wherein the processor is configured to execute the method for recognizing a touch object as described in the first aspect when running the program instructions.

[0024] Fourthly, embodiments of this application provide a storage medium storing program instructions, which, when executed, perform the method for identifying touch objects as described in the first aspect.

[0025] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method for recognizing a touch object as described in the first aspect.

[0026] The method, apparatus, device, and storage medium for recognizing touch-sensitive objects provided in the embodiments of this application can achieve the following technical effects:

[0027] When identifying the type of touch object, an infrared touch device can periodically collect occlusion signals generated by the touch object within the screen during a preset period. That is, starting when the touch object enters the touch detection area of ​​the screen, occlusion signals are periodically collected, resulting in multiple occlusion signals corresponding to multiple collection cycles. Collection of occlusion signals stops when the touch object makes contact with the screen. These multiple occlusion signals are then sequentially combined to form a touch timing signal. The occlusion signal includes the occlusion area affected by the touch object within the screen, the distance between the touch object and the screen, and the time of occlusion signal collection. By identifying the touch timing signal, target features can be extracted to characterize the changing patterns of multiple occlusion signals. These changing patterns refer to the variation of the occlusion area with the distance between the touch object and the screen and the collection time. Specifically, when a user touches the infrared touch device with a touch object, the touch object gradually approaches the screen after entering the touch detection area until it makes contact. Thus, the occlusion area of ​​the touch object changes continuously as the distance between the touch object and the screen decreases, and the occlusion area also changes continuously over time, as does the distance between the touch object and the screen. Therefore, by identifying the touch timing signal, target features that characterize the above-mentioned changing patterns can be obtained.

[0028] It should be noted that, within the preset period, the change patterns of the occlusion signals generated by different types of touch objects at the instant they contact the screen are different. Taking a finger or stylus as an example, the contact between a finger and the screen is elastic, meaning that the finger deforms the instant it touches the screen, and this deformation changes the occlusion area in the occlusion signal. The contact between a stylus and the screen is rigid; the stylus does not deform after contacting the screen, and the occlusion area in the occlusion signal does not change. Therefore, in this embodiment, by identifying the touch timing signal, the distance change between the touch object and the screen can be obtained to determine whether the touch object has contacted the screen. Furthermore, at the instant the touch object contacts the screen, the change in the occlusion area in the occlusion signal over time can be obtained to determine the type of touch object. Compared to schemes that only identify the type of touch object based on the occlusion area and area threshold, this method can more accurately identify the type of touch object, thereby improving recognition accuracy.

[0029] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0030] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are considered similar elements. The drawings do not constitute a limitation of scale, and wherein:

[0031] Figure 1 This is a schematic diagram of an infrared touchscreen;

[0032] Figure 2 This is a flowchart of a method for recognizing touch-sensitive objects provided in an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the touch detection area of ​​an infrared touch screen provided in an embodiment of this application;

[0034] Figure 4 This is an example diagram of a finger touch control provided in an embodiment of this application;

[0035] Figure 5 This is a flowchart of another method for recognizing touch objects provided in an embodiment of this application;

[0036] Figure 6 This is a schematic diagram of a device for recognizing touch-sensitive objects provided in an embodiment of this application;

[0037] Figure 7 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0038] The terms "first," "second," etc., used in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0039] Unless otherwise stated, the term "multiple" means two or more.

[0040] In this embodiment, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0041] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0042] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0043] To provide a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0044] Combination Figure 1 The diagram illustrates an infrared touchscreen. Corresponding infrared transmitters 11 and receivers 12 are deployed on the screen's bezel. The infrared transmitters 11 can be deployed on the top and right bezels, while the receivers 12 can be deployed on the bottom and left bezels. The infrared transmitters 11 emit infrared rays 13 to the receivers 12, forming a horizontally and vertically intersecting infrared matrix on the screen surface. When a user touches the screen, the object being touched blocks the infrared rays 13 passing through the touch location 14 in the infrared matrix. The infrared touchscreen determines whether a touch has occurred by scanning the infrared matrix to see if any infrared rays 13 are blocked. If a touch has occurred, the touch location is determined based on the blocked infrared rays 13 in the infrared matrix, thus achieving touch detection and positioning.

[0045] The aforementioned infrared touchscreens are typically integrated into infrared touch devices. Users can control these devices by performing touch operations on the infrared touchscreen. When interacting with an infrared touch device, users usually use their fingers or styluses to perform touch operations on the screen surface. To enhance the user experience, infrared touch devices can recognize different types or materials of touch objects, thus providing different touch feedback or displaying different touch response interfaces when users use different types of touch objects to touch the screen.

[0046] To identify different types of touch objects, related technologies utilize infrared touch devices to determine the type of touch object based on the difference in the area of ​​infrared light blocked when different objects touch the screen. Specifically, when a touch object touches the screen, the infrared touch device acquires the area blocked by the touch object on the screen and determines the type of touch object by comparing the blocked area with an area threshold. Taking a finger and a stylus as examples, since the blocking area formed by a finger on the touch screen is larger than that formed by the stylus tip, the touch object can be identified as a finger when its blocking area is greater than or equal to the area threshold; and as a stylus when its blocking area is less than the area threshold.

[0047] However, different touch objects may have similar occlusion areas when used on the screen of an infrared touch device. For example, some styluses can also be used for touch operations at their tips. When using the tip of a stylus to touch the screen, because the tip of the stylus and the finger are similar in thickness, the occlusion area is similar. Alternatively, the occlusion area may differ depending on the location of the same touch object on the screen. For instance, when the touch object is located in the center of the screen, it will block multiple infrared rays in the infrared matrix, while when the touch object is located at the edge of the screen, it may only block a smaller number of infrared rays. Because the number of infrared rays blocked differs, the affected occlusion area also differs. Therefore, due to the instability of the occlusion area affected by touch objects, the accuracy of methods for identifying touch object types based on occlusion area in related technologies is relatively low.

[0048] Therefore, this application provides a scheme for identifying touch objects. This scheme periodically collects occlusion signals of the touch object on the screen as it enters the touch detection area and gradually approaches the screen until it makes contact. These occlusion signals are then sequentially combined to form a touch timing signal. By analyzing the touch timing signal, the changing pattern of the occlusion signal during the touch object's contact with the screen can be determined. Since different types of touch objects exhibit different patterns of occlusion signal change during screen contact, the type of touch object can be determined based on these patterns. Furthermore, the variation of the occlusion signal during screen contact is only affected by the material of the touch object itself. Therefore, this scheme can more accurately identify the type of touch object, thereby improving recognition accuracy.

[0049] The scheme for identifying touch objects provided in this application is applicable to infrared touch devices that integrate infrared touch technology. For example, the infrared touch device can be an interactive device such as a smart interactive flat panel, a commercial display, or a smart blackboard.

[0050] Combination Figure 2 As shown in the figure, this application provides a method for identifying touch objects, which can be applied to the above-mentioned infrared touch device. The method includes the following steps:

[0051] S21, periodically collect occlusion signals of the touch object during a preset period to obtain multiple occlusion signals.

[0052] In step S21, the preset period begins when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease. Figure 1 and Figure 3 As shown, the touch detection area 31 of the screen refers to the infrared detection area formed by the infrared rays 13 emitted from the infrared emitter 11 to the infrared receiver 12 above the screen. When the user touches the screen with a touch object 32, the touch object 32 first enters the touch detection area 31 of the screen. When the touch object 32 enters the touch detection area 31 (i.e., when...), the touch detection area 31 is activated. Figure 3 (As shown in the touch state), the infrared touch device can detect that infrared light 13 is blocked by the touch object 32, indicating that a touch has occurred. Subsequently, as the touch object 32 falls and comes into contact with the screen, the screen can detect the pressure of the touch object 32 on the screen surface. As the touch object 32 presses down on the screen surface, the pressure detected by the screen gradually increases. When the screen detects that the pressure of the touch object 32 remains constant, it indicates that the touch object 32 has been firmly pressed onto the screen surface, and that the touch object 32 has completed the downward touch operation. Alternatively, when the screen detects that the pressure of the touch object 32 decreases, it indicates that after the touch object 32 has completed the downward touch operation, it begins to lift off the screen surface. In this embodiment, the infrared touch device can determine the type of touch object solely based on the blocking signal when the user performs a downward touch operation on the screen using the touch object.

[0053] In step S21, the acquired occlusion signal includes the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time. The occlusion area refers to the area where the infrared matrix formed above the screen is blocked after the touch object enters the touch detection area of ​​the screen. The infrared touch device scans the infrared matrix on the screen to determine the blocked infrared light, and determines the contour coordinates of the touch object based on the blocked infrared light. The shape or area of ​​the touch object is calculated based on the contour coordinates, thereby determining the occlusion area of ​​the touch object. The distance between the touch object and the screen can also be calculated from the blocked infrared light. The acquisition time refers to the moment the occlusion signal is acquired.

[0054] In step S21, when collecting the occlusion signal of the touch object, the interval of the period can be 4 milliseconds, and this embodiment of the application does not specifically limit this.

[0055] S22 combines multiple occlusion signals sequentially to form a touch timing signal.

[0056] In step S22, the multiple occlusion signals collected are combined sequentially according to time order or according to the collection time to form a touch timing signal.

[0057] S23, identify the touch timing signal to extract the target features of the touch timing signal.

[0058] In step S23, the target features can reflect the changing patterns of multiple occlusion signals in the touch timing signal during a preset period, specifically including: the changes in the occlusion area as the distance between the touch object and the screen decreases, and the changes in the occlusion area as the acquisition time progresses, wherein the changes in the occlusion area can include changes in the area and / or size of the occlusion area.

[0059] S24, determine the type of the touched object based on the target characteristics of the touch timing signal.

[0060] In step S24, since the target characteristics of the touch timing signal reflect the changes in multiple occlusion signals in the touch timing signal, and the changes in occlusion signals generated by different types of touch objects are different, the type of touch object can be determined based on the target characteristics of the touch timing signal. For example, the type of touch object can be a finger or a stylus, etc.

[0061] Using the method for identifying touch objects provided in this application, when identifying the type of touch object, the infrared touch device can periodically collect occlusion signals generated by the touch object within the screen during a preset period. That is, starting from when the touch object enters the touch detection area of ​​the screen, the occlusion signal of the touch object is periodically collected, resulting in multiple occlusion signals corresponding to multiple collection cycles. Collection of occlusion signals stops when the touch object contacts the screen. The collected multiple occlusion signals are then sequentially combined to form a touch timing signal. The occlusion signal includes the occlusion area affected by the touch object within the screen, the distance between the touch object and the screen, and the time of occlusion signal collection. By identifying the touch timing signal, target features can be extracted to characterize the changing patterns of multiple occlusion signals in the touch timing signal. The changing patterns of multiple occlusion signals refer to the changing patterns of the occlusion area with the distance between the touch object and the screen and the collection time. Specifically, when a user touches the infrared touch device with a touch object, the touch object gradually approaches the screen after entering the touch detection area until it contacts the screen. Thus, the occlusion area of ​​the touch object changes continuously as the distance between the touch object and the screen decreases, and the occlusion area also changes continuously over time, as does the distance between the touch object and the screen. Therefore, by identifying the touch timing signal, target features that characterize the above-mentioned changing patterns can be obtained.

[0062] It should be noted that, within the preset period, specifically at the moment a touch object touches the screen, the changing patterns of the occlusion signal produced by different types of touch objects are different. Combined with... Figure 4 As shown, taking a finger as an example of a touch object, the contact between the finger and the screen is elastic, meaning that the finger deforms the instant it touches the screen, and this deformation changes the occlusion area in the occlusion signal. Taking a stylus as an example, the contact between the stylus and the screen is rigid; the stylus does not deform after touching the screen, and the occlusion area in the occlusion signal does not change. Therefore, in this embodiment, by identifying the touch timing signal, the distance change between the touch object and the screen can be obtained to determine whether the touch object has touched the screen. At the instant the touch object touches the screen, the change in the occlusion area in the occlusion signal over time is obtained to determine the type of touch object based on this change. Compared to schemes that only identify the type of touch object based on the occlusion area and area threshold, this method can more accurately identify the type of touch object, thereby improving recognition accuracy.

[0063] In addition, in this embodiment, since the type of touch object can be identified based on the occlusion signal generated at the moment the touch object touches the screen, the "touch object type contact recognition" is realized. That is, the type of touch object can be identified when the touch object touches the screen, thereby ensuring the immediacy of touch object type identification.

[0064] Optionally, in step S22 above, combining multiple occlusion signals sequentially to form a touch timing signal includes: obtaining a contact occlusion signal from the multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal. The contact occlusion signal is the occlusion signal generated when the distance between the touch object and the screen is zero. The contact occlusion signals are combined in chronological order to form the touch timing signal.

[0065] When determining the type of touch object, it is mainly determined by the occlusion signal generated at the moment the touch object contacts the screen. Therefore, in this embodiment, the touch timing signal can be composed of occlusion signals generated after the touch object contacts the screen. Specifically, the multiple occlusion signals periodically collected within a preset period are actually divided into two categories: one category refers to the occlusion signal when the touch object enters the touch detection area but does not contact the screen, and the other category refers to the occlusion signal generated at the moment the touch object contacts the screen. Since the distance between the touch object and the screen is zero at the moment of contact, the occlusion signal with a distance of zero can be selected from the multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal, and used as the contact occlusion signal. Combining the contact occlusion signals in chronological order can form the touch timing signal.

[0066] In this embodiment, only the occlusion signal generated at the moment the touch object comes into contact with the screen is selected from multiple occlusion signals to generate the touch timing signal. This reduces the number of occlusion signals in the touch timing signal, thereby improving the efficiency of identifying the touch timing signal and thus improving the efficiency of identifying the type of touch object.

[0067] In this embodiment, when a user touches the screen with a touch object, the touch object may hover or jitter as it approaches the screen. If the occlusion signal generated during hovering or jittering is used to generate the touch timing signal, it will result in distorted occlusion signals in the touch timing signal. Furthermore, identifying the type of touch object by recognizing touch timing signals containing distorted occlusion signals will affect the recognition accuracy. Therefore, in this embodiment, occlusion signals generated during hovering or jittering can be excluded when generating the touch timing signal. Specifically, when generating the touch timing signal, abnormal occlusion signals can be determined from multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal. After filtering out the abnormal occlusion signals from the multiple occlusion signals, the target occlusion signal is obtained. The target occlusion signal is then combined in chronological order to form the touch timing signal.

[0068] Among them, abnormal occlusion signal refers to the occlusion signal generated when the touch object is hovering or shaking.

[0069] Normally, as a touch object approaches the screen, the distance between the touch object and the screen should gradually decrease. That is, as the acquisition cycle or acquisition time progresses, the distance between the touch object and the screen in the acquired occlusion signal should also decrease. However, when the touch object hovers or shakes, the distance between the touch object and the screen may become abnormal; that is, the distance between the touch object and the screen may suddenly increase or remain unchanged. Therefore, by judging the change in the distance between the touch object and the screen in the occlusion signal between two adjacent acquisition cycles, abnormal occlusion signals can be identified. Specifically, by judging whether the distance between the touch object and the screen in the occlusion signal acquired in the first acquisition cycle is greater than or equal to the distance between the touch object and the screen in the occlusion signal acquired in the second acquisition cycle, it can be determined whether the occlusion signal acquired in the first acquisition cycle is abnormal. Here, the first acquisition cycle is the next acquisition cycle after the second acquisition cycle. Specifically, if the distance between the touch object and the screen in the occlusion signal acquired in the first acquisition cycle is less than the distance between the touch object and the screen in the occlusion signal acquired in the second acquisition cycle, the occlusion signal acquired in the first acquisition cycle is considered normal. If the distance between the touch object and the screen in the occlusion signal acquired in the first acquisition cycle is greater than or equal to the distance between the touch object and the screen in the occlusion signal acquired in the second acquisition cycle, the occlusion signal acquired in the first acquisition cycle is considered abnormal. After filtering out the abnormal occlusion signals from multiple occlusion signals, the remaining occlusion signals can be called target occlusion signals, which can be considered normal occlusion signals. The target occlusion signals are combined in chronological order to form the touch timing signal.

[0070] In this embodiment, when generating touch timing signals based on multiple collected occlusion signals, abnormal occlusion signals caused by hovering or shaking of the touch object are filtered out from the multiple occlusion signals. This avoids using distorted occlusion signals to generate touch timing signals, thereby avoiding the inclusion of distorted touch timing signals in the touch timing signals, and thus ensuring the accuracy of identifying the type of touch object based on the touch timing signals.

[0071] Optionally, in step S23 above, identifying the touch timing signal to extract the target features of the touch timing signal includes: inputting the touch timing signal into a recurrent neural network model so that the recurrent neural network model can identify the changing patterns of multiple occlusion signals in the touch timing signal and obtain the target features of the touch timing signal.

[0072] In this implementation, a recurrent neural network (RNN) model can be used to identify touch timing signals, thereby identifying target features that reflect the changing patterns of multiple occlusion signals. These target features can be temporal features. The RNN model takes sequential data (such as touch timing signals) as input, recursively processes the sequence in its evolution direction, and all nodes (recurrent units) are connected in a chain-like manner. The RNN model can utilize the temporal dependencies in the sequential data to extract the temporal features of the touch timing signals. Specifically, the RNN model can be a Long Short-Term Memory (LSTM) network model.

[0073] In this implementation, a recurrent neural network model can capture the long-term dependencies of various occlusion signals in the touch timing signal and identify nonlinear relationships within it. This allows for a deeper analysis and identification of the touch timing signal, leading to a more accurate and comprehensive extraction of temporal features reflecting the changing patterns of multiple occlusion signals as target features. Based on these accurate and comprehensive temporal features, the type of touched object can be determined more precisely, improving the accuracy of touch object type identification.

[0074] In this embodiment, when extracting target features from touch timing signals, a Convolutional Neural Network (CNN) model can be used based on the above implementation method. The CNN model is a feedforward neural network with convolutional computation and a deep structure, mainly including convolutional layers, pooling layers, and fully connected layers. The convolutional layer is the core component of the CNN model, used to extract local features from the input data. The pooling layer is usually located after the convolutional layer and is used to downsample the output of the convolutional layer, reducing the dimensionality of the data and the computational cost. The fully connected layer is located at the end of the CNN, integrating the features extracted by the convolutional and pooling layers for tasks such as classification or regression. Thus, feature information of the touch timing signals can be automatically extracted through the convolutional, pooling, and fully connected layers. Optionally, identifying the touch timing signals to extract target features includes: inputting the touch timing signals into the CNN model so that the CNN model can identify the touch timing signals to extract the spatial features of the touch timing signals. The spatial features of the touch timing signal are input into a recurrent neural network model, enabling the model to identify the variation patterns of multiple occlusion signals within the touch timing signal based on these spatial features, thus obtaining the temporal features of the touch timing signal. Both spatial and temporal features are used as target features.

[0075] Unlike the previous implementation, this implementation utilizes a convolutional neural network model to identify touch timing signals and extract their spatial features. Instead of using the touch timing signals as input, the recurrent neural network model uses the spatial features output by the convolutional neural network model as input, capturing the changing patterns of multiple occlusion signals within the touch timing signals to obtain their temporal features. These spatial and temporal features are then used as target features.

[0076] In this implementation, convolutional neural network and recurrent neural network models can be used to extract spatial and temporal features of the touch timing signal, making the acquired touch timing signal features more comprehensive. By analyzing these more comprehensive features, the type of touch object can be determined more accurately, thereby improving the accuracy of touch object type identification.

[0077] Optionally, in step S24 above, a fully connected neural network (FCNN) model can be used to analyze the target features and output the type of the touched object.

[0078] When a fully connected neural network model outputs the type of a touched object, it can either directly output the type of the touched object or output the classification result. The classification result represents the probability distribution of the touched object belonging to each type. From the classification results, the type corresponding to the highest probability distribution value is selected as the type of the touched object.

[0079] Combination Figure 5 As shown in the figure, this application provides another method for identifying touch objects. This method can be applied to the infrared touch device in the above embodiments. The method includes the following steps:

[0080] S51 periodically collects occlusion signals of the touch object during a preset period to obtain multiple occlusion signals.

[0081] S52 combines multiple occlusion signals sequentially to form a touch timing signal.

[0082] S53, from multiple occlusion signals of the touch timing signal, obtain the occlusion signal where the distance between the touch object and the screen is within a preset distance range, and obtain the occlusion signal to be merged;

[0083] S54 performs merging processing on the occlusion signals to be merged in the touch timing signals.

[0084] S55 identifies touch timing signals to extract target features of the touch timing signals.

[0085] S56, determine the type of the touched object based on the target characteristics of the touch timing signal.

[0086] In this application embodiment, the specific implementation methods of steps S51 to S52 and steps S55 to S56 have been described in the foregoing embodiments. The specific implementation methods and technical effects can be referred to in the foregoing embodiments, and will not be repeated here.

[0087] Optionally, in steps S53 and S54 above, during the user's touch operation on the screen using a touch object, the touch object is prone to hovering or shaking due to the user's influence just before it touches the screen, resulting in unstable or distorted occlusion signals. Therefore, in this embodiment, before recognizing the touch timing signal, occlusion signals that are relatively close to the screen can be merged based on a preset distance range to reduce unstable or distorted occlusion signals. The lower limit of the preset distance range is set to a value close to zero, while the upper limit can be set according to requirements; for example, the upper limit can be set to 3mm. This embodiment does not specifically limit this value.

[0088] It should be noted that the lower limit of the preset distance range is not directly set to zero because when the distance between the touch object and the screen is zero, it indicates that the touch object is in contact with the screen. However, in this embodiment, the type of touch object is determined primarily by utilizing the changing pattern of the occlusion signal generated when the touch object is in contact with the screen. Therefore, if the lower limit of the preset distance range is set to zero, the occlusion signal generated when the touch object is in contact with the screen will be treated as an occlusion signal to be merged. The merged occlusion signal will not reflect the changing pattern when the touch object is in contact with the screen, and thus the type of touch object cannot be determined. Therefore, the lower limit of the preset distance range cannot be directly set to zero.

[0089] In this embodiment, by merging the occlusion signals within a preset distance range in the touch timing signal, the stability of the touch timing signal can be improved, and the unstable or distorted occlusion signals in the touch timing signal can be reduced, thereby improving the quality of the touch timing signal. As a result, when identifying the type of touch object based on the high-quality touch timing signal, the recognition accuracy can be guaranteed.

[0090] Combination Figure 6 As shown, this application provides a device for identifying touch-sensitive objects. This device can be integrated into the infrared touch device described in the foregoing embodiments. The device includes a data acquisition module 601, a combination module 602, an identification module 603, and a determination module 604. Wherein:

[0091] The acquisition module 601 is used to periodically acquire occlusion signals of the touch object during a preset period to obtain multiple occlusion signals. The preset period starts when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease. The occlusion signals include the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time.

[0092] The combination module 602 is used to combine multiple occlusion signals sequentially to form a touch timing signal;

[0093] The recognition module 603 is used to recognize touch timing signals to extract target features of the touch timing signals; the target features are used to characterize the change pattern of the occlusion area of ​​the touch object with the distance between the touch object and the screen and the acquisition time during a preset period.

[0094] The determination module 604 determines the type of the touch object based on the target characteristics of the touch timing signal.

[0095] Optionally, the recognition module 603 recognizes the touch timing signal to extract the target features of the touch timing signal. Specifically, it inputs the touch timing signal into a recurrent neural network model so that the recurrent neural network model can recognize the changing patterns of multiple occlusion signals in the touch timing signal and obtain the target features of the touch timing signal.

[0096] Optionally, the recognition module 603, in recognizing the touch timing signal to extract target features of the touch timing signal, specifically performs the following steps: Inputting the touch timing signal into a convolutional neural network model to enable the convolutional neural network model to recognize the touch timing signal and extract its spatial features; inputting the spatial features of the touch timing signal into a recurrent neural network model to enable the recurrent neural network model to identify the changing patterns of multiple occlusion signals in the touch timing signal based on the spatial features, thereby obtaining the temporal features of the touch timing signal; and using the spatial and temporal features as target features.

[0097] Optionally, when combining multiple occlusion signals sequentially to form a touch timing signal, the combination module 602 is specifically used to: obtain a contact occlusion signal from the multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal; the contact occlusion signal is the occlusion signal generated when the distance between the touch object and the screen is zero. The contact occlusion signals are then combined in chronological order to form the touch timing signal.

[0098] Optionally, when combining multiple occlusion signals sequentially to form a touch timing signal, the combination module 602 is specifically used to: determine abnormal occlusion signals from the multiple occlusion signals based on the distance between the touch object and the screen in each occlusion signal; after filtering out the abnormal occlusion signals from the multiple occlusion signals, the target occlusion signal is obtained; and the target occlusion signal is combined in time sequence to form the touch timing signal.

[0099] Optionally, before identifying the variation pattern of multiple occlusion signals in the touch timing signal, the combination module 602 is further configured to: obtain occlusion signals from the multiple occlusion signals of the touch timing signal whose distance between the touch object and the screen is within a preset distance range, thus obtaining occlusion signals to be merged; and perform merging processing on the occlusion signals to be merged in the touch timing signal.

[0100] The device for identifying touch objects provided in this application embodiment can perform the actions of the infrared touch device in the aforementioned embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0101] Combination Figure 7As shown, this application provides an electronic device 700, including a processor 701 and a memory 702. Optionally, the electronic device 700 may further include a communication interface 703 and a bus 704. The processor 701, communication interface 703, and memory 702 can communicate with each other via the bus 704. The communication interface 703 can be used for information transmission. The processor 701 can call logical instructions in the memory 702 to execute the method for recognizing touch-sensitive objects described in the above embodiments.

[0102] Furthermore, the logic instructions in the aforementioned memory 702 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0103] The memory 702, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 701 executes functional applications and data processing by running the program instructions / modules stored in the memory 702, that is, it implements the method for recognizing touch objects in the above embodiments.

[0104] The memory 702 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 702 may include high-speed random access memory and may also include non-volatile memory.

[0105] This application provides a storage medium storing computer-executable instructions configured to perform the method for recognizing touch objects described in the above embodiments.

[0106] The aforementioned storage medium can be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0107] The technical solutions of this application embodiment can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this application embodiment. The aforementioned storage medium can be a non-transitory storage medium, including: USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0108] This application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for recognizing touch objects described in the above embodiments.

[0109] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0110] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0111] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for identifying touch-sensitive objects, characterized in that, Applied to infrared touch devices, the method includes: The occlusion signal of the touch object is periodically collected during a preset period to obtain multiple occlusion signals; the preset period starts when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease. The multiple occlusion signals are combined sequentially to form a touch timing signal; Identify the touch timing signal to extract the target features of the touch timing signal; The type of the touch object is determined based on the target characteristics of the touch timing signal; The occlusion signal includes the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time; the target feature is used to characterize the variation of the occlusion area of ​​the touch object with the distance between the touch object and the screen and the acquisition time during the preset period.

2. The method according to claim 1, characterized in that, Identifying the touch timing signal to extract target features of the touch timing signal includes: The touch timing signal is input into a recurrent neural network model so that the recurrent neural network model can identify the changing patterns of multiple occlusion signals in the touch timing signal and obtain the target features of the touch timing signal.

3. The method according to claim 1, characterized in that, Identifying the touch timing signal to extract target features of the touch timing signal includes: The touch timing signal is input into a convolutional neural network model so that the convolutional neural network model can recognize the touch timing signal and extract the spatial features of the touch timing signal; The spatial features of the touch timing signal are input into a recurrent neural network model, so that the recurrent neural network model can identify the variation pattern of multiple occlusion signals in the touch timing signal based on the spatial features of the touch timing signal, and obtain the temporal features of the touch timing signal. The spatial features and the temporal features are used as the target features.

4. The method according to claim 1, characterized in that, The multiple occlusion signals are combined sequentially to form a touch timing signal, including: Based on the distance between the touch object and the screen in each of the occlusion signals, a contact occlusion signal is obtained from the plurality of occlusion signals; the contact occlusion signal is the occlusion signal generated when the distance between the touch object and the screen is zero; The touch occlusion signals are combined in chronological order to form the touch timing signal.

5. The method according to claim 1, characterized in that, The multiple occlusion signals are combined sequentially to form a touch timing signal, including: Based on the distance between the touch object and the screen in each of the occlusion signals, an abnormal occlusion signal is determined from the plurality of occlusion signals; After filtering out the abnormal occlusion signals from the multiple occlusion signals, the target occlusion signal is obtained; The target occlusion signals are combined in chronological order to form the touch timing signal.

6. The method according to claim 1, characterized in that, Before identifying the touch timing signal to extract the target features of the touch timing signal, the method further includes: From the multiple occlusion signals of the touch timing signal, obtain the occlusion signal where the distance between the touch object and the screen is within a preset distance range, and obtain the occlusion signal to be merged; The occlusion signals to be merged in the touch timing signals are merged.

7. A device for recognizing touch-sensitive objects, characterized in that, Integrated into an infrared touch device, the device includes: The acquisition module is used to periodically acquire occlusion signals of the touch object during a preset period, thereby obtaining multiple occlusion signals. The preset period starts when the touch object enters the touch detection area of ​​the screen and ends when the touch object contacts the screen and the screen detects that the pressure of the touch object remains unchanged or begins to decrease. The occlusion signal includes the occlusion area of ​​the touch object, the distance between the touch object and the screen, and the acquisition time. A combination module is used to sequentially combine multiple occlusion signals to form a touch timing signal; The identification module is used to identify the touch timing signal to extract the target features of the touch timing signal; the target features are used to characterize the change pattern of the occlusion area of ​​the touch object with the distance between the touch object and the screen and the acquisition time during the preset period. The determination module determines the type of the touch object based on the target features of the touch timing signal.

8. An electronic device comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to perform the method for identifying a touch object as described in any one of claims 1 to 6 when executing the program instructions.

9. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the method for identifying touch objects as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the method for identifying a touch-sensitive object as described in any one of claims 1 to 6.

Images