TWI779566B - Anti-cheating method and electronic device - Google Patents

Abstract

An anti-cheating method and an electronic apparatus are provided. The anti-cheating method includes the following steps. Physical trajectory information of a mouse device on a touch sensing device is detected by using the touch sensing device. The mouse device moves on the touch sensing device. Mouse trajectory information for controlling a cursor is captured. A cheating operation is detected according to the physical trajectory information and the mouse trajectory information.

Description

Anti-cheating method and electronic device

The present invention relates to an electronic device, and in particular to an anti-cheating method using touch technology and the electronic device.

In today's esports gaming industry, what is often tested are skills that players have learned through practice. In this case, gaining an unfair advantage with additional software and hardware assistance is often one of the important factors that destroy the healthy competitive environment in the game. Therefore, if players who use the above cheating methods to play the game can be detected and found in a timely manner, the fairness of the game should be better guaranteed.

Generally speaking, a common cheating method is that the player plays the game with the help of an auxiliary operation script tool (script for short). Scripts can operate on the operating system of computer devices in the form of programs, so they can also be called plug-ins. Alternatively, players or other relevant personnel can set the script in the firmware inside the hardware device (such as a mouse device). With the assistance of the above-mentioned scripts, players can generate fake user operations, thereby destroying the balance of the original design of the game and also destroying the normal development of the game. Therefore, how to detect players playing games through unfair cheating behaviors is an important issue in the e-sports game industry.

In view of this, the present invention proposes an anti-cheating method and an electronic device, which can effectively determine whether a cheating operation occurs according to the moving track of the mouse device sensed by the touch sensing device.

An embodiment of the present invention provides an anti-cheating method suitable for an electronic device connected to a mouse device, which includes the following steps. The touch sensing device is used to detect the actual track information of the mouse device on the touch sensing device, wherein the mouse device moves on the touch sensing device. Retrieves the mouse track information used to control the cursor. Detect cheating operations based on actual trajectory information and mouse trajectory information.

An embodiment of the present invention provides an electronic device, which is connected to a touch sensing device and a mouse device and includes a storage device and a processor. The processor is connected to the storage device and is configured to execute the following steps. The touch sensing device is used to detect the actual track information of the mouse device on the touch sensing device, wherein the mouse device moves on the touch sensing device. Retrieves the mouse track information used to control the cursor. Detect cheating operations based on actual trajectory information and mouse trajectory information.

Based on the above, in the embodiment of the present invention, when the mouse device is moving on the touch sensing device, the electronic device can obtain the touch information of the mouse device according to the touch data provided by the touch sensing device. The actual trajectory information on the measuring device. Accordingly, according to the actual trajectory information and the mouse trajectory information used to control the cursor, the electronic device can effectively and instantly detect whether the user controls the electronic device to perform cheating operations.

In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail together with the accompanying drawings.

Parts of the embodiments of the present invention will be described in detail with reference to the accompanying drawings. For the referenced reference symbols in the following description, when the same reference symbols appear in different drawings, they will be regarded as the same or similar components. These embodiments are only a part of the present invention, and do not reveal all possible implementation modes of the present invention. Rather, these embodiments are merely examples of devices and methods within the scope of the present invention.

It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or other intervening elements may be present. In other words, unless otherwise specified, the terms "connected" and "coupled" include both direct and indirect connection and coupling of two elements.

FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the present invention, but this is only for convenience of description, and is not intended to limit the present invention. Firstly, FIG. 1 firstly introduces all the components and their configuration relationships in the electronic device, and the detailed functions and operations will be disclosed together with FIG. 2 .

Please refer to FIG. 1 , the electronic device 10 of this embodiment is, for example, a notebook computer, a smart phone, a tablet computer, an e-book, a game console, etc., which can be connected with a mouse device 20 and a touch sensing device 30. The invention is not limited thereto. The electronic device 10 includes a display 110 , a storage device 120 and a processor 130 . In some embodiments, the electronic device 10 can be used to run a game, and the mouse device 20 can allow the user to control/operate the above game in a mobile manner. In some embodiments, the electronic device 10 can be used to run an online quiz, and the mouse device 20 can allow the user to input answers to the online quiz in a moving manner.

The mouse device 20 can be connected to the electronic device 10 in a wired or wireless manner, which is not limited in the present invention. For example, the mouse device 20 can be a Bluetooth mouse or a wired mouse with a USB connector. In addition, according to different working principles of the mouse device 20 , the mouse device 20 may be a roller mouse or an optical mouse, which is not limited in the present invention.

The touch sensing device 30 can be used to sense the contact of an object on the touch sensing surface. The touch sensing device 30 can be connected to the electronic device 10 in a wired or wireless manner, which is not limited in the present invention. In the embodiment of the present invention, the mouse device 20 is moved on the touch sensing device 30 . In more detail, controlled by the user's operation, the mouse device 20 moves on the touch sensing surface of the touch sensing device 30, and the touch sensing device 30 can sense the mouse device 20 s contact. The touch sensing device 30 can be implemented as a touch panel, a touch screen, or a mouse pad with a touch sensing function, and the present invention is not limited thereto. The touch sensing device 30 may include, for example, a capacitive touch panel, a resistive touch panel, an electromagnetic touch panel, an optical touch panel, or a touch panel applying other touch sensing principles. In some embodiments, the touch sensing device 30 includes a plurality of touch sensing elements arranged in an array (such as capacitive sensing elements or resistive sensing elements, etc.) to perform touch sensing, to obtain information including A touch sensing image frame corresponding to the touch raw data of the touch sensing element.

The display 110 is, for example, a liquid crystal display (Liquid Crystal Display, LCD), a light-emitting diode (Light-Emitting Diode, LED) display, a field emission display (Field Emission Display, FED), an organic light-emitting diode (Organic Light-Emitting Diode) , OLED) or other types of display devices. In some embodiments, the display 110 is, for example, a screen that can be used to display the above-mentioned game screen or online quiz screen. In addition, in some embodiments, the display 110 may display a cursor controlled by the mouse device 20 . In other words, the cursor on the screen displayed on the display 110 will move correspondingly in response to the movement of the mouse device 20 .

The storage device 120 is used to store data such as touch data, instructions, program codes, software components, etc., which can be, for example, any type of fixed or removable random access memory (random access memory, RAM), read-only memory body (read-only memory, ROM), flash memory (flash memory), hard disk or other similar devices, integrated circuits and combinations thereof.

The processor 130 is coupled to the display 110 and the storage device 120, and is used to control the actions between the components of the electronic device 10, such as a central processing unit (Central Processing Unit, CPU), or other programmable general purpose or special Microprocessor (Microprocessor), Digital Signal Processor (Digital Signal Processor, DSP), Programmable Controller, Application Specific Integrated Circuits (Application Specific Integrated Circuits, ASIC), Programmable Logic Device (Programmable Logic Device) , PLD), graphics processing unit (Graphics Processing Unit, GPU or other similar devices or a combination of these devices. The processor 130 can execute the program codes, software modules, instructions, etc. recorded in the storage device 120 to realize the present invention An anti-cheating method using touch data in the embodiment.

However, in addition to the display 110, the storage device 120, and the processor 130, the electronic device 10 may also include other components not shown in FIG. 1, such as speakers, microphones, cameras, communication modules, keyboards, etc. The invention is not limited thereto.

Fig. 2 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Please refer to FIG. 2 , the method of this embodiment is applicable to the electronic device 10 in the above-mentioned embodiment, and the detailed steps of this embodiment will be described below with various components in the electronic device 10 .

In step S210 , the processor 130 uses the touch sensing device 30 to detect the actual track information of the mouse device 20 on the touch sensing device 30 . The mouse device 20 moves on the touch sensing device 30 . Specifically, the user places the mouse device 20 on the touch-sensing surface of the touch-sensing device 30, and the user can use the mouse device 20 by moving the mouse device 20 and pressing the buttons on the mouse device 20. Or command to the electronic device 10. It should be noted that since the touch sensing device 30 can sense the contact of the mouse device 20, the processor 130 can sense the movement of the mouse device 20 through the touch sensing device 30, and obtain the mouse device 20 The actual trajectory information on the touch sensing device 30 . The above-mentioned actual trajectory information may include at least two touch positioning coordinates.

In one embodiment, the processor 130 can acquire a plurality of touch sensing image frames through the touch sensing device 30 . Each touch sensing image frame may include a plurality of frame cells respectively corresponding to the touch sensing elements, and each frame cell in each touch sensing image frame has touch raw data . For example, assuming that the touch sensing device 30 has m*n touch sensing elements, each touch sensing image frame will include m*n image frames respectively corresponding to m*n pen touch raw data cell. In one embodiment, the processor 130 can also perform normalization processing on the raw touch data, so that the touch data of each frame cell in the normalized touch sensing frame can be between the predetermined Set the value range, for example, within 0 to 255.

It should be noted that, in one embodiment, in order to detect the actual trajectory information of the mouse device 20 on the touch sensing device 30 , the processor 130 obtains raw touch data that has not undergone any filtering process. The reason is that, compared with the touch of human fingers, the touch sensing signal generated by the touch sensing element can change greatly, and the touch of the mouse device 20 usually only makes the touch sensing signal generated by the touch sensing element There is a small change in the control sensing signal. If the touch raw data is filtered, the touch sensing image frame may not be able to represent the touch of the mouse device 20 . In one embodiment, the capacitive touch sensing element can undergo a small charge change in response to the proximity of metal elements inside the mouse device 20, and the raw touch data in the touch sensing frame can therefore be used To sense the touch of the mouse device 20 .

Further, FIG. 3A is a schematic diagram of a touch sensing device according to an embodiment of the present invention. FIG. 3B is a schematic diagram of a touch sensing frame according to an embodiment of the invention. Please refer to FIG. 3A first, the touch sensing device 30 may include a sensing element array 111 , a scan driving circuit 113 and a receiving sensing circuit 112 . The sensing element array 111 includes a plurality of touch sensing elements (such as touch sensing elements CS11 , CS12 , CS21 ) arranged in an array. The scanning driving circuit 113 applies driving signals to the touch sensing elements column by column through the scanning lines (such as the scanning lines 114 ). The receiving sensing circuit 112 receives the touch sensing signal provided by the touch sensing element through the sensing line (such as the sensing line 115 ) and outputs the touch raw data d1. The receiving sensing circuit 112 can use an analog-to-digital converter (ADC) to convert the touch sensing signal generated by the touch sensing element into digital touch raw data d1 for output.

Please refer to FIG. 3B again, the touch sensing frame F1 includes a plurality of frame cells (eg frame cell FC11 ) respectively corresponding to a plurality of touch sensing elements (eg touch sensing elements CS11, CS12, CS21). , FC12, FC21). Moreover, each image frame cell has corresponding touch original data. For example, the frame cell FC11 has touch raw data 'r1'; the frame cell FC12 has touch raw data 'r2'; the frame cell FC21 has touch raw data 'r3'. In other words, the touch sensing image frame F1 can also be regarded as an m*n data array, and the array elements in the data array are the original touch data.

Then, the processor 130 can input each touch sensing image frame into a machine learning model to obtain the actual trajectory information of the mouse device 20 on the touch sensing device 30 . Specifically, whenever the processor 130 inputs a touch sensing image frame into the machine learning model, the machine learning model can detect the mouse touch of the mouse device 20 from the touch sensing image frame. area.

In one embodiment, the machine learning model is constructed in advance by performing machine learning (such as deep learning) according to the set of training image frames, which can be stored in the storage device 120 . In other words, the model parameters of the trained machine learning model (such as the number of neural network layers and the weight of each neural network layer, etc.) have been determined by pre-training and stored in the storage device 120 . The machine learning model may be an object detection model used for object detection in a Convolution Neural Network (CNN) model, such as YOLO or SSD, and the present invention is not limited thereto. Alternatively, the machine learning model may be a Semantic Segmentation model in a convolutional neural network model, such as DeepLabv3+, etc., which is not limited in the present invention.

In one embodiment, the processor 130 may input each touch sensing image frame into the machine learning model to obtain an object box (bounding box) corresponding to the mouse device 20 in each touch sensing image frame. Then, the processor 130 can obtain actual trajectory information according to the position of the reference point in the object frame in each touch sensing image frame. Specifically, when the processor 130 applies the machine learning model belonging to the object detection model, the machine learning model may output the object frame corresponding to the mouse device 20 in the touch sensing image frame. Then, the processor 130 may take the coordinate position of a reference point in the object frame as the current touch positioning coordinate of the mouse device 20 . The aforementioned reference point is, for example, the center point of the object frame, but not limited thereto. In this way, by sequentially inputting multiple touch sensing image frames into the machine learning model, the processor 130 can obtain multiple touch positioning coordinates in the multiple touch sensing image frames, so as to obtain information including multiple touch sensing image frames. The actual trajectory information of the control positioning coordinates.

For example, FIG. 4A is a schematic diagram of using a machine learning model to obtain actual trajectory information according to an embodiment of the present invention. Please refer to FIG. 4A , by inputting the touch sensing image frame F2 provided by the touch sensing device 30 into the machine learning model, the processor 130 can obtain the object frame B1 corresponding to the mouse device 20, and use the object frame B1 The coordinate position of the central point P1 is positioned as the touch positioning coordinate of the mouse device 20 . By collecting a plurality of touch positioning coordinates in a plurality of touch sensing image frames, the processor 130 can obtain the moving track T1 (ie, actual track information) of the mouse device 20 on the touch sensing device 30 .

Alternatively, in one embodiment, the processor 130 may input each touch sensing image frame into the machine learning model to obtain the semantic segmentation region corresponding to the mouse device 20 in each touch sensing image frame. Next, the processor 130 can acquire actual trajectory information according to the boundaries of the semantically segmented regions in each touch sensing image frame. Specifically, when the processor 130 applies the machine learning model belonging to the semantic segmentation model, the machine learning model can classify each frame cell in the touch sensing image frame to obtain the corresponding cell in the touch sensing image frame. To the semantically segmented area of the mouse device 20. Next, the processor 130 may determine a reference point according to the boundary of the semantically segmented area, and use the coordinate position of the reference point as the current touch positioning coordinate of the mouse device 20 . In this way, by sequentially inputting multiple touch sensing image frames into the machine learning model, the processor 130 can obtain multiple touch positioning coordinates in the multiple touch sensing image frames, so as to obtain information including multiple touch sensing image frames. The actual trajectory information of the control positioning coordinates.

For example, FIG. 4B is a schematic diagram of using a machine learning model to obtain actual trajectory information according to an embodiment of the present invention. Please refer to FIG. 4B , by inputting the touch sensing image frame F3 provided by the touch sensing device 30 into the machine learning model, the processor 130 can segment the touch sensing image frame F3 into semantics corresponding to the mouse device 20 Divide zone Z1 from other zone Z2. In this example, the processor 130 can extract the four extreme points PL, PR, PB, and PU of the semantic segmentation area Z1 on the vertical axis and the horizontal axis, and obtain the center according to the extreme points PL, PR, PB, and PU. Reference point PC. Then, the processor 130 can locate the coordinate position of the central reference point PC1 as the touch positioning coordinate of the mouse device 20 . By collecting a plurality of touch positioning coordinates in a plurality of touch sensing image frames, the processor 130 can obtain the moving track T2 (ie, actual track information) of the mouse device 20 on the touch sensing device 30 .

Next, in step S220, the processor 130 retrieves the mouse track information for controlling the cursor. In one embodiment, the processor 130 can obtain the mouse track information for controlling the cursor from the operating system or the application program executed by the electronic device 10 . For example, the processor 130 can obtain the cursor positioning coordinates of the cursor on the screen or in a certain working window through the application program interface (such as GetCursorPos API, etc.) provided by the Microsoft Windows operating system, so as to obtain multiple cursor positioning coordinates. mouse track information for . Or, in other embodiments, the processor 130 can obtain the mouse track information for controlling the cursor by detecting the cursor on the screen displayed on the display 110 (such as a game screen or an application program screen) to obtain cursor positioning coordinates.

Therefore, in step S230, the processor 130 detects cheating operations according to the actual track information and the mouse track information. In detail, the actual trajectory information is generated in response to the real operation of the user controlling the mouse device 20 . Therefore, according to the actual track information and the mouse track information provided by the operating system or the application program, the processor 130 can determine whether the user uses an illegal script to control the cursor with forged user input information. For example, the processor 130 can know that the mouse device 20 is in a static state according to the actual track information, but the mouse track information used to control the cursor keeps changing, and the processor 130 can judge that the mouse device 20 is detected based on this. fraudulent operations. Or, the processor 130 can know the moving direction of the mouse device 20 according to the actual track information, but the mouse track information used to control the cursor indicates an inconsistent moving direction of the cursor, and the processor 130 can judge the detection To the user's cheating operation.

Accordingly, by using the touch data sensed by the touch sensing device 30 , the processor 130 can effectively determine whether the user controls the electronic device 10 to perform cheating operations, so as to ensure the fairness of e-sports games and online quizzes. It should be noted that the processor 130 can detect cheating operations in a variety of different ways according to the actual track information and the mouse track information, and examples will be described below.

Fig. 5 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Please refer to FIG. 5 , the method of this embodiment is applicable to the electronic device 10 in the above-mentioned embodiment, and the detailed steps of this embodiment will be described below with various elements in the electronic device 10 .

In step S510 , the processor 130 uses the touch sensing device 30 to detect the actual track information of the mouse device 20 on the touch sensing device 30 . In step S520, the processor 130 retrieves mouse track information for controlling the cursor. The implementation manners of step S510 to step S520 are the same as the embodiment illustrated in FIG. 2 , and will not be repeated here. It should be noted that in step S530, the processor 130 detects cheating operations according to the actual track information and the mouse track information. In this embodiment, step S530 can be implemented as step S531-step S533.

In step S531 , the processor 130 acquires actual movement data within a predetermined period of time according to the plurality of touch positioning coordinates in the actual trajectory information. The actual moving data may include an actual moving direction and an actual displacement. The aforementioned preset time period is, for example, 1 second or 3 seconds, etc., which can be configured according to actual needs, and the present invention is not limited thereto. In more detail, each touch positioning coordinate in the actual trajectory information corresponds to a positioning time point. The processor 130 may determine to take out two touch positioning coordinates based on the length of the preset time period, and calculate the actual moving direction and actual displacement within the preset time period according to the two touch positioning coordinates.

In step S532, the processor 130 acquires cursor movement data within a preset period of time according to a plurality of cursor positioning coordinates in the mouse track information. The cursor movement data may include the cursor movement direction and the cursor displacement amount. Specifically, each cursor positioning coordinate in the mouse track information may represent the coordinate position of the cursor on the screen at a certain point in time. The processor 130 may decide to take out two cursor positioning coordinates based on the length of the preset time period, and calculate the cursor moving direction and cursor displacement within the preset time period according to the two cursor positioning coordinates.

In step S533, the processor 130 compares the actual movement data with the cursor movement data to determine whether a cheating operation is detected. In one embodiment, the processor 130 may determine whether a cheating operation is detected according to the angle between the actual moving direction and the moving direction of the cursor. If the angle between the actual moving direction and the cursor moving direction is larger than the preset threshold value, it means that the direction in which the user moves the mouse device 20 is inconsistent with the moving direction of the cursor, and the processor 130 can determine that a cheating operation has been detected. On the contrary, if the angle between the actual moving direction and the cursor moving direction is not greater than the preset threshold, the processor 130 may determine that no cheating operation is detected. Alternatively, there should be a certain proportional relationship between the cursor displacement and the actual displacement without interference from other cheat scripts. Therefore, the processor 130 can determine whether a cheating operation is detected according to the ratio between the actual moving direction and the moving direction of the cursor. If the ratio between the actual moving direction and the cursor moving direction does not match the specific proportional relationship, the processor 130 may determine that a cheating operation is detected. On the contrary, if the ratio between the moving direction of the cursor and the moving direction of the cursor coincides with a certain ratio, the processor 130 can determine that no cheating operation is detected.

Fig. 6 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Please refer to FIG. 6 , the method of this embodiment is applicable to the electronic device 10 in the above-mentioned embodiment, and the detailed steps of this embodiment will be described below with various components in the electronic device 10 .

In step S610 , the processor 130 uses the touch sensing device 30 to detect the actual track information of the mouse device 20 on the touch sensing device 30 . In step S620, the processor 130 retrieves mouse track information for controlling the cursor. The implementation manners of step S610 to step S620 are the same as the embodiment illustrated in FIG. 2 , and will not be repeated here. It should be noted that in step S630, the processor 130 detects cheating operations according to the actual track information and the mouse track information. In this embodiment, step S630 can be implemented as step S631-step S633.

In step S631, the processor 130 acquires an actual trajectory image according to a plurality of touch positioning coordinates in the actual trajectory information. In step S632, the processor 130 acquires a cursor track image according to a plurality of cursor positioning coordinates in the mouse track information. In detail, by simultaneously presenting the touch positioning coordinates in the actual trajectory information in a single actual trajectory image, the actual trajectory image can present the moving trajectory of the mouse device 20 on the touch sensing device 30 . Similarly, by simultaneously displaying multiple cursor positioning coordinates in the mouse track information in a single cursor track image, the actual track image can present the moving track of the cursor on the screen.

In step S633, the processor 130 determines whether a cheating operation is detected according to the actual trajectory image and the cursor trajectory image. In other words, the processor 130 can compare the actual moving track in the actual track image with the cursor moving track in the cursor track image to determine whether a cheating operation is detected. In one embodiment, the processor 130 may input the actual trajectory image and the cursor trajectory image into the trained machine learning model, so as to determine whether a cheating operation is detected through the output of the machine learning model. Alternatively, in one embodiment, the processor 130 may perform image scaling or other image processing on the actual trajectory image or/and the cursor trajectory image, and then compare the trajectory shape of the moving trajectory in the two images after processing to determine whether a cheating operation has been detected.

Fig. 7 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Please refer to FIG. 7 , the method of this embodiment is applicable to the electronic device 10 in the above-mentioned embodiment, and the detailed steps of this embodiment will be described below with various components in the electronic device 10 .

In step S710 , the processor 130 uses the touch sensing device 30 to detect the actual track information of the mouse device 20 on the touch sensing device 30 . In step S720, the processor 130 retrieves mouse track information for controlling the cursor. The implementation manners of step S710 to step S720 are the same as the embodiment illustrated in FIG. 2 , and will not be repeated here. It should be noted that in step S730, the processor 130 detects cheating operations according to the actual track information and the mouse track information. In this embodiment, step S730 can be implemented as steps S731 to S733.

In step S731 , the processor 130 acquires actual movement related data according to a plurality of touch positioning coordinates in the actual trajectory information. The actual motion-related data may include actual displacement, actual moving direction, actual moving speed, actual moving acceleration, or statistics of the above-mentioned data, and the like.

In step S732, the processor 130 obtains cursor motion related data according to a plurality of cursor positioning coordinates in the mouse track information. The cursor movement related data may include cursor displacement, cursor movement direction, cursor movement speed, cursor movement acceleration, or statistics of the above information, and the like.

In step S733, the processor 130 inputs the actual movement-related data and the cursor movement-related data into the machine learning model, so that the machine learning model determines whether a cheating operation is detected. The processor 130 may input the actual motion-related data and the cursor motion-related data into the trained machine learning model, and judge whether a cheating operation is detected according to the output of the machine learning model. For example, the above machine learning model may be, for example, a support vector machine (support vector machine, SVM) classification model or a nearest neighbor algorithm (K-nearest neighbor algorithm, KNN) classification model, etc., but is not limited thereto. In one embodiment, the machine learning model may output, for example, the existence probability of the cheating operation, and the processor 130 may determine whether the cheating operation is detected according to the above existence probability.

To sum up, in the embodiment of the present invention, the actual track information of the mouse device can be detected through the touch sensing device, and the actual track information is compared with the mouse track information used to control the cursor. Therefore, according to the actual trajectory information based on the user's actual actions and the mouse trajectory information used to control the cursor, the existence of cheating operations that forge user operations can be effectively and accurately detected. In this way, it is possible to effectively grasp which players have improperly used scripts, thereby preventing players from cheating, and thus better maintaining the fairness of the game.

Although the present invention has been disclosed above with the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field may make some changes and modifications without departing from the spirit and scope of the present invention. The scope of protection of the present invention should be defined by the scope of the appended patent application.

10: Electronic device 110: Display 120: storage device 130: Processor 20:Mouse device 30: Touch sensing device 111: sensing element array CS11, CS12, CS21: touch sensing components 113: Scan driving circuit 112: Receive sensing circuit 114: scan line 115: Sensing line d1: touch original data FC11, FC12, FC21: picture frame cell F1, F2, F3: touch sensor frame T1, T2: moving track B1: Object Box P1: center point PL, PR, PB, PU: extreme points PC: Center reference point Z1: Semantic segmentation area Z2: other areas S210～S230, S510～S533, S610～S633, S710～S733: steps

FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the invention. Fig. 2 is a flow chart of an anti-cheating method according to an embodiment of the present invention. FIG. 3A is a schematic diagram of a touch sensing device according to an embodiment of the invention. FIG. 3B is a schematic diagram of a touch sensing frame according to an embodiment of the invention. FIG. 4A is a schematic diagram of acquiring actual trajectory information by using a machine learning model according to an embodiment of the present invention. FIG. 4B is a schematic diagram of acquiring actual trajectory information by using a machine learning model according to an embodiment of the present invention. Fig. 5 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Fig. 6 is a flow chart of an anti-cheating method according to an embodiment of the present invention. Fig. 7 is a flow chart of an anti-cheating method according to an embodiment of the present invention.

S210~S230: steps

Claims (16)

An anti-cheating method applicable to an electronic device connected to a mouse device, the method comprising: using a touch sensing device to detect the actual track information of the mouse device on the touch sensing device, wherein The mouse device moves over the touch sensing device; captures mouse track information used to control a cursor; and detects a cheat for forging user operations based on the actual track information and the mouse track information operate. The anti-cheating method as described in claim 1, wherein the step of using the touch sensing device to detect the actual trajectory information of the mouse device on the touch sensing device includes: using the touch sensing device Obtaining a plurality of touch sensing image frames; and inputting each of the touch sensing image frames into a machine learning model to obtain the actual trajectory information of the mouse device on the touch sensing device. The anti-cheating method as described in claim 2, wherein the step of inputting each of the touch-sensing image frames into the machine learning model to obtain the actual track information of the mouse device on the touch-sensing device includes : Input each of the touch sensing image frames into the machine learning model to obtain an object frame corresponding to the mouse device in each of the touch sensing image frames; and according to each of the touch sensing image frames The actual trajectory information is obtained from the position of a reference point within the object frame in the frame. The anti-cheating method as described in claim 2, wherein the step of inputting each of the touch-sensing image frames into the machine learning model to obtain the actual track information of the mouse device on the touch-sensing device includes : Input each of the touch sensing image frames into the machine learning model to obtain the semantic segmentation area corresponding to the mouse device in each of the touch sensing image frames; and according to each of the touch sensing image frames The actual trajectory information of the boundary of the semantically segmented region in the frame is acquired. The anti-cheating method as described in Claim 1, wherein the step of retrieving the mouse movement track used to control the cursor includes: obtaining the track used to control the cursor from an operating system or an application program executed by the electronic device The mouse track information. The anti-cheating method as described in claim 1, wherein the step of detecting the cheating operation according to the actual track information and the mouse track information includes: obtaining a preset according to a plurality of touch positioning coordinates in the actual track information An actual movement data within a time period; obtain a cursor movement data within the preset time period according to multiple cursor positioning coordinates in the mouse track information; and compare the actual movement data with the cursor movement data to determine whether to detect to the cheating operation. The anti-cheating method as described in Claim 1, wherein the step of detecting the cheating operation based on the actual track information and the mouse track information includes: Acquiring an actual trajectory image according to a plurality of touch positioning coordinates in the actual trajectory information; obtaining a cursor trajectory image according to a plurality of cursor positioning coordinates in the mouse trajectory information; and obtaining a cursor trajectory image according to the actual trajectory image and the cursor The trajectory image determines whether the cheating operation is detected. The anti-cheating method as described in claim 1, wherein the step of detecting the cheating operation according to the actual trajectory information and the mouse trajectory information includes: obtaining an actual movement according to a plurality of touch positioning coordinates in the actual trajectory information Relevant data; obtaining a cursor movement-related data according to multiple cursor positioning coordinates in the mouse track information; and inputting the actual movement-related data and the cursor movement-related data into a machine learning model, so as to be determined by the machine learning model Whether to detect this cheat operation. An electronic device connected to a mouse device and a touch sensing device, including: a storage device; and a processor, coupled to the touch sensing device and the storage device, configured to: utilize the touch sensing The detection device detects the actual trajectory information of the mouse device on the touch sensing device, wherein the mouse device moves on the touch sensing device; and retrieves the mouse trajectory information for controlling a cursor ;as well as A cheating operation of forging user operations is detected according to the actual track information and the mouse track information. The electronic device as described in claim 9, wherein the processor is further configured to: obtain a plurality of touch sensing image frames through the touch sensing device; and input each of the touch sensing image frames to a A machine learning model is used to obtain the actual trajectory information of the mouse device on the touch sensing device. The electronic device as described in claim 10, wherein the processor is further configured to: input each of the touch sensing image frames into the machine learning model to obtain each of the touch sensing image frames corresponding to the an object frame of the mouse device; and obtaining the actual trajectory information according to the position of a reference point in the object frame in each of the touch sensing image frames. The electronic device as described in claim 10, wherein the processor is further configured to: input each of the touch sensing image frames into the machine learning model to obtain each of the touch sensing image frames corresponding to the a semantically segmented area of the mouse device; and acquiring the actual trajectory information according to the boundary of the semantically segmented area in each of the touch sensing image frames. The electronic device as claimed in item 9, wherein the processor is further configured to: The mouse track information for controlling the cursor is obtained from an operating system or an application program executed by the electronic device. The electronic device as described in claim 9, wherein the processor is further configured to: obtain an actual movement data within a preset period of time according to a plurality of touch positioning coordinates in the actual trajectory information; according to the mouse trajectory information Obtaining a cursor movement data within the preset period of time at multiple cursor positioning coordinates; and comparing the actual movement data with the cursor movement data to determine whether the cheating operation is detected. The electronic device as described in claim 9, wherein the processor is further configured to: acquire an actual trajectory image according to a plurality of touch positioning coordinates in the actual trajectory information; obtain an actual trajectory image according to a plurality of cursors in the mouse trajectory information Locating coordinates to obtain a cursor track image; and judging whether the cheating operation is detected according to the actual track image and the cursor track image. The electronic device as described in claim 9, wherein the processor is further configured to: obtain an actual movement-related data according to a plurality of touch positioning coordinates in the actual trajectory information; Obtain a cursor motion-related data according to multiple cursor positioning coordinates in the mouse track information; and input the actual motion-related data and the cursor motion-related data into a machine learning model, so that the machine learning model determines whether to detect to the cheating operation.

Images