CN113209628A - AI-based image processing method and device - Google Patents
AI-based image processing method and device Download PDFInfo
- Publication number
- CN113209628A CN113209628A CN202110518184.0A CN202110518184A CN113209628A CN 113209628 A CN113209628 A CN 113209628A CN 202110518184 A CN202110518184 A CN 202110518184A CN 113209628 A CN113209628 A CN 113209628A
- Authority
- CN
- China
- Prior art keywords
- display frame
- game display
- game
- abnormal
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/70—Game security or game management aspects
- A63F13/75—Enforcing rules, e.g. detecting foul play or generating lists of cheating players
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
- A63F2300/55—Details of game data or player data management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- General Business, Economics & Management (AREA)
- Controls And Circuits For Display Device (AREA)
- Display Devices Of Pinball Game Machines (AREA)
- Pinball Game Machines (AREA)
Abstract
The application provides an image processing method and device based on AI, the method comprises: acquiring a game display frame; the game display frame is a game screen image displayed to a first user; inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame; and when the game display frame is judged to be abnormal according to the detection result, carrying out frame supplementing processing on the game display frame. The method and the device can detect and stop the behavior of cheating by a user using the plug-in, and maintain the fairness of the game.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an AI-based image processing method and apparatus.
Background
More and more game items enrich daily life of people, but some bad phenomena such as use of game plug-ins also occur along with the game items. The game cheating program is a cheating program which can help users to obtain benefits by modifying games, and the main principle is that the capabilities of game characters are changed by modifying normal codes or data of the games. The fairness of the game is damaged when the user uses the plug-in, so that the behavior of the user for detecting and stopping cheating by using the plug-in is very important.
Disclosure of Invention
The application provides an AI-based image processing method and device, which can detect and terminate cheating behavior of a user using a plug-in and maintain fairness of games.
In a first aspect, the present application provides an AI-based image processing method, including:
acquiring a game display frame; the game display frame is a game screen image displayed to a first user;
inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame;
and when the game display frame is judged to be abnormal according to the detection result, carrying out frame supplementing processing on the game display frame.
According to the method, the abnormal degree of the game display frame is detected through the first model, and when the game display frame is judged to be abnormal according to the detection result output by the first model, the frame supplementing processing is carried out on the game display frame, so that the behavior of cheating by a user using a plug-in can be detected in time, the behavior of cheating by the user using the plug-in is stopped through the frame supplementing mode, and the fairness of the game is maintained.
In a possible implementation manner, the performing frame complementing processing on the game display frame includes:
acquiring a game map corresponding to the game display frame;
and repairing the game display frame according to the game map.
In one possible implementation manner, the repairing the game display frame according to the game map includes:
dividing the game display frame and the game map into a plurality of pixel areas respectively;
and for the pixel area in the game display frame, repairing the pixel area of the game display frame according to the pixel area at the same position in the game map.
In one possible implementation manner, the method further includes:
when the game display frame is judged to be abnormal, recording the game display frame as the abnormal game display frame of the first user;
when the game of the first user is detected to be finished, inputting the abnormal game display frame of the first user into a second model to obtain a detection result output by the second model aiming at the abnormal game display frame; the second model is used for detecting the abnormal degree of the game display frame;
and judging whether the abnormal game display frame is abnormal or not according to the detection result output by the second model aiming at the abnormal game display frame.
In a possible implementation manner, after detecting that the game of the first user ends, before inputting the abnormal game display frame of the first user into the second model, the method further includes:
acquiring a game time point of an abnormal game display frame of the first user;
and determining that the proportion of the abnormal game display frame at the specified time point in the abnormal game display frame of the first user reaches a preset first threshold value.
In a second aspect, an embodiment of the present application provides an AI-based image processing apparatus, including:
an acquisition unit configured to acquire a game display frame; the game display frame is a game screen image displayed to a first user;
the first detection unit is used for inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame;
and the processing unit is used for performing frame supplementing processing on the game display frame when the game display frame is judged to be abnormal according to the detection result.
In a possible implementation manner, the processing unit is specifically configured to: acquiring a game map corresponding to the game display frame; and repairing the game display frame according to the game map.
In a possible implementation manner, the processing unit is specifically configured to: dividing the game display frame and the game map into a plurality of pixel areas respectively; and for the pixel area in the game display frame, repairing the pixel area of the game display frame according to the pixel area at the same position in the game map.
In one possible implementation manner, the method further includes:
the recording unit is used for recording the game display frame as the abnormal game display frame of the first user when judging that the game display frame is abnormal;
the second detection unit is used for detecting that the game of the first user is ended, inputting the abnormal game display frame of the first user into a second model and obtaining a detection result output by the second model aiming at the abnormal game display frame; the second model is used for detecting the abnormal degree of the game display frame;
and the judging unit is used for judging whether the abnormal game display frame is abnormal or not according to the detection result output by the second model aiming at the abnormal game display frame.
In a possible implementation manner, the second detection unit is further configured to: acquiring a game time point of an abnormal game display frame of the first user; and determining that the proportion of the abnormal game display frame at the specified time point in the abnormal game display frame of the first user reaches a preset first threshold value.
In a third aspect, an embodiment of the present application provides a Central Processing Unit (CPU), where the CPU includes the obtaining unit of any one of the second aspects and the first detecting unit.
In a fourth aspect, an embodiment of the present application provides a Digital Signal Processor (DSP) including the processing unit of any one of the second aspects.
In a fifth aspect, an embodiment of the present application provides an electronic device, including:
one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions which, when executed by the apparatus, cause the apparatus to perform the method of any of the first aspects.
In a sixth aspect, embodiments of the present application provide a computer-readable storage medium, in which a computer program is stored, which, when run on a computer, causes the computer to perform the method of any one of the first aspect.
In a seventh aspect, the present application provides a computer program for performing the method of the first aspect when the computer program is executed by a computer.
In a possible design, the program in the seventh aspect may be stored in whole or in part on a storage medium packaged with the processor, or in part or in whole on a memory not packaged with the processor.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a view of a scene to which the AI-based image processing method of the present application is applied;
FIG. 2 is a flowchart of an embodiment of an AI-based image processing method of the present application;
FIG. 3 is a diagram illustrating an example of a division of pixel regions of a game display frame and a game map of the present application;
FIG. 4 is a flowchart illustrating an AI-based image processing method according to another embodiment of the present application;
FIG. 5 is a flowchart illustrating an AI-based image processing method according to another embodiment of the present application;
FIG. 6 is a flowchart illustrating an AI-based image processing method according to another embodiment of the present application;
FIG. 7 is a block diagram of an embodiment of an AI-based image processing apparatus according to the present application;
FIG. 8 is a block diagram of another embodiment of an AI-based image processing apparatus according to the subject application;
FIG. 9 is a block diagram of an embodiment of an electronic device of the present application.
Detailed Description
The terminology used in the description of the embodiments section of the present application is for the purpose of describing particular embodiments of the present application only and is not intended to be limiting of the present application.
The terms referred to in the embodiments of the present application will be described by way of illustration and not limitation:
artificial Intelligence (AI) is a new technical science to study and develop theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.
And (3) AI cultivation: in AI cultivation in the field of artificial intelligence, a suitable neural network architecture and optimal structural parameters of a neural network are found by using a large number of devices which can provide computing power, such as a Graphics Processing Unit (GPU) or a Central Processing Unit (CPU), and the network can complete specific work. Colloquially, a machine is "fed" with a large amount of data to learn to identify and differentiate objects.
Mapping: the pictures are named in game engineering.
Game mapping: after the art designing modeling is finished, using a tool to spread UV, namely flattening a 3D model to 2D to draw a picture, wherein the obtained picture can be attached to the model in a specific mode in the game running process to bring colors to the model for rendering and manufacturing, and the picture of the picture can be called as a game map; in some games, such as hand games, without modeling, the game map may be a game screen image that the game displays for the user.
Game display frame: and game picture images displayed to the user on the game client during the game playing process of the user. The game display frame can be a game map called by the user based on the operation of the user, or can be an image obtained by externally hanging the game map called by the user.
Frame supplementing refers to: and one or more display frames are additionally displayed between two adjacent display frames to be displayed.
The application provides an image processing method and device based on AI, which can detect and terminate the behavior of using plug-ins by users and maintain the fairness of games.
Fig. 1 is a schematic view of an applicable scene of the AI-based image processing method of the present application, as shown in fig. 1, the method may include: a number of electronic devices 110 and a server 120, wherein,
the electronic device 110 may have a game client installed therein, and a user may log in a game from the game client in the electronic device 110, and the electronic device 110 displays a game interface for the user through the game client, and the user may perform a game operation in the game interface. The electronic device 110 may include, but is not limited to: mobile phones, computers, laptops, tablet computers, and the like.
The server 120 may be a single server or a cluster of servers for providing game-based interaction services for game clients in the electronic device 110. Data communication may be performed between the electronic device 110 and the server 120.
The AI-based image processing method according to the embodiment of the present application can be applied to the electronic device 110.
Fig. 2 is a flowchart of an embodiment of an AI-based image processing method according to the present application, which can be applied to an electronic device, as shown in fig. 2, and the method can include:
step 201: the electronic equipment acquires a game display frame; the game display frame is a game screen image displayed to the first user.
Step 202: the electronic equipment inputs the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame.
The first model can be obtained by breeding an AI model in an AI breeding mode. Specifically, the first model may be obtained by "feeding" a large number of training samples, for example, more than one thousand training samples, to the AI machine, and calculating, by the AI machine, optimal network architecture and neural network architecture parameters for detecting the degree of abnormality of the game display frame according to the relationship characteristics between the data of the training samples.
Alternatively, the first model may be an AI-aware neural network consisting of an AI-aware neural network accelerator and a Recurrent Neural Network (RNN).
In one possible implementation, the specific training method of the first model may include: obtaining a training sample, wherein the training sample is a game map in a game; and inputting the training sample into a preset model for training to obtain a first model. The first model and the game may correspond to each other, the training sample of the first model may be a game map of a certain game, and accordingly, the trained first model may be used to detect whether a game display frame in the certain game is abnormal. In the process of training the first model by using the game maps, the model learns the relationship characteristics between the image data of the game maps, such as the brightness, color, texture and the like of the picture, so as to train the final first model.
For example, the following AI base model may be used as an initial model of the first model: AX + BY + CZ ═ U, where X is luminance, Y is color, Z is texture, A, B, C are weights to be weighted corresponding to the respective image features, and U is the first model. By training through the training sample, the weighting number corresponding to the image features, namely the value of A, B, C, can be obtained through final training, so as to obtain the first model.
The input of the first model may be a game display frame, and the output detection result may be: the game display frames are probability values of the game map. The higher the probability value is, the higher the probability that the game display frame is a game map is, and the lower the probability that the game display frame is a game picture image obtained by plug-in processing is; conversely, the lower the probability value, the lower the probability that the game display frame is a game map, and the higher the probability that the game display frame is a game screen image obtained by plug-in processing.
In another possible implementation manner, the specific training method of the first model may include: acquiring a training sample, wherein the training sample is a game map divided into pixel areas; and inputting the training sample into a preset model for training to obtain a first model. The first model and the game can be corresponding, the training sample of the first model can be a game map of a certain game, the game map is divided into pixel areas, correspondingly, the trained first model can be used for detecting whether each pixel area in a game display frame in the game is abnormal or not, and the fact that whether the game display frame is abnormal or not is known after the fact that whether each pixel area in the game display frame is abnormal or not is known. In the process of training the first model by using the game maps, the model learns the relationship characteristics between the image data of the pixel regions of the game maps, such as the brightness, color, texture and the like of the picture, so as to train the final first model.
For example, the following AI base model may be used as an initial model of the first model: AX + BY + CZ ═ U, where X is luminance, Y is color, Z is texture, A, B, C are weights to be weighted corresponding to the respective image features, and U is the first model. By training through the training sample, the weighting number corresponding to the image features, namely the value of A, B, C, can be obtained through final training, so as to obtain the first model.
The input of the first model may be a game display frame dividing a pixel area, and the output detection result may be: each pixel region in the game display frame is a probability value of the game map. The higher the probability value is, the higher the possibility that the pixel area of the game display frame is the pixel area of the game map is, and the lower the possibility that the pixel area of the game display frame is the pixel area of the game picture image obtained by plug-in processing is; conversely, the lower the probability value, the lower the probability that the pixel area of the game display frame is the pixel area of the game map, and the higher the probability that the pixel area of the game display frame is the pixel area of the game screen image obtained by the plug-in processing.
In order to make the processing of the first model more accurate, the pixel regions are divided for the game display frame and the pixel regions are divided for the game map as the training sample, and both may perform the division of the pixel regions according to the same division rule. For example, the game display frame 31 and the game map 32 shown in fig. 3 are each equally divided into 5 x 5 grids, each grid being a pixel area.
Step 203: and when the electronic equipment judges that the game display frame is abnormal according to the detection result, the electronic equipment performs frame supplementing processing on the game display frame.
In one possible implementation, if the detection result output by the first model in step 202 is: the game display frame is a probability value of the game map, a first probability threshold value can be preset in the electronic equipment, and at the moment, the electronic equipment judges whether the game display frame is abnormal or not according to a detection result, and the method can be realized by the following steps:
the electronic equipment judges whether the probability value in the detection result exceeds a first probability threshold value or not;
if the probability value in the detection result exceeds a first probability threshold value, judging that the game display frame is not abnormal;
and if the probability value in the detection result does not exceed the first probability threshold, judging that the game display frame is abnormal.
The specific value of the first probability threshold is not limited in this application. Generally, the higher the value of the first probability threshold is, the higher the detection accuracy of the electronic device on whether the game display frame is abnormal is.
In another possible implementation manner, if the detection result output by the first model in step 202 is a probability value that each pixel area in the game display frame is a pixel area of the game map, a second probability threshold and a first threshold may be preset in the electronic device, at this time, the electronic device may determine whether the game display frame is abnormal according to the detection result by the following steps:
the electronic equipment judges whether the probability value of each pixel area in the detection result exceeds a second probability threshold value or not; if the probability value of the pixel area exceeds a second probability threshold, judging that the pixel area is abnormal, and if the probability value of the pixel area does not exceed the second probability threshold, judging that the pixel area is not abnormal;
the electronic equipment counts the number of abnormal pixel areas in the game display frame and judges whether the number of the abnormal pixel areas in the game display frame exceeds a first threshold value or not; if the number of the abnormal pixel areas in the game display frame exceeds a first threshold value, the game display frame is abnormal; and if the number of the abnormal pixel areas in the game display frame does not exceed the first threshold value, the game display frame is not abnormal.
The second probability threshold and the specific value of the first threshold are not limited in this application, and generally, the higher the second probability threshold is, the lower the first threshold is, and the higher the detection accuracy of the electronic device on whether the game display frame is abnormal is.
A specific implementation of the frame interpolation processing for the game display frame in this step will be described below.
In one possible implementation manner, the electronic device performs frame complementing processing on the game display frame, and may include:
the electronic equipment acquires a game map corresponding to the game display frame;
the electronic device displays the game map.
After the electronic equipment displays the game map, the next frame of game display frame of the game display frame can be displayed, so that through the processing, one frame of game map can be added between the current game display frame and the next frame of game display frame, and therefore frame supplement is achieved.
In another possible implementation manner, the electronic device performs frame complementing processing on the game display frame, and may include:
the electronic equipment acquires a game map corresponding to the game display frame;
and the electronic equipment repairs the game display frame according to the game map.
After the electronic equipment finishes repairing the game display frame according to the game map, the obtained game display frame is the repaired frame of the game display frame before repair.
After the electronic equipment displays the repaired game display frame, the next game display frame of the game display frame can be displayed, so that the repaired game display frame can be added between the current game display frame and the next game display frame through the processing, and the frame supplement is realized.
The frame complementing process for the game display frame in this step can be completed by the display driver of the electronic device.
Optionally, in the two implementation manners, the obtaining, by the electronic device, the game map corresponding to the game display frame may include: the electronic equipment acquires the game map number corresponding to the game display frame, sends the game map number to the server, and receives the game map corresponding to the game map number sent by the server. The game map received by the electronic equipment from the server is the game map which should be displayed to the user by the game client of the electronic equipment under the condition that the plug-in is not used.
In one possible implementation, if the detection result output by the first model in step 202 is: the game display frame is a probability value of the game map, and at this time, the electronic device repairs the game display frame according to the game map, which may include:
the electronic equipment divides the game display frame and the game map into a plurality of pixel areas respectively;
for the pixel area in the game display frame, the electronic equipment repairs the pixel area of the game display frame according to the pixel area at the same position in the game map.
When the game display frame and the game map are divided into several pixel regions, respectively, the division may be performed in a manner as shown in fig. 3. The game display frame and the game map can be divided into pixel areas in the same manner, and at this time, the pixel areas of the game display frame and the game map can be in one-to-one correspondence according to the positions. For example, for the pixel area in the ith row and the jth column of the game display frame 31 in fig. 3, the pixel area in the ith row and the jth column of the game map 32 has the same position, i may have a value of 1, 2, 3, 4, or 5, and j may have a value of 1, 2, 3, 4, or 5.
Alternatively, the electronic device may repair only the pixel region where the abnormality occurs. In this case, for the pixel area in the game display frame, the repairing, by the electronic device, the pixel area in the game display frame according to the pixel area at the same position in the game map may include:
the electronic equipment determines a pixel area needing to be repaired in a game display frame;
and for the pixel area needing to be repaired in the game display frame, the electronic equipment repairs the pixel area of the game display frame according to the pixel area at the same position in the game map.
Optionally, the electronic device determining a pixel area in the game display frame that needs to be repaired may include: the electronic equipment respectively compares the pixel areas at the same positions in the game display frame and the game map, if the comparison results corresponding to the pixel areas of the game display frame are the same, the pixel areas of the game display frame do not need to be repaired, and if the comparison results corresponding to the pixel areas of the game display frame are different, the pixel areas of the game display frame need to be repaired.
Optionally, the method for the electronic device to compare whether the two pixel regions are the same may be implemented by calculating image similarity of the two pixel regions, and the specific image similarity calculation method is not limited in this application. At this time, the electronic device may preset a similarity threshold, and if the similarity of the two pixel regions with the same position exceeds the similarity threshold, the comparison result is that the two pixel regions are the same, otherwise, the comparison result is that the two pixel regions are different.
Still taking fig. 3 as an example, if the electronic device compares the pixel area in the 2 nd row and the 3 rd column in the game display frame with the pixel area in the 2 nd row and the 3 rd column in the game map, and finds that the two are different, it is determined that the pixel area in the 2 nd row and the 3 rd column in the game display frame is a pixel area to be repaired, and the sub device may repair the pixel area in the game display frame according to the pixel area in the 2 nd row and the 3 rd column in the game map. The processing of the other pixel regions is similar and will not be further described.
In another possible implementation, if the detection result output by the first model in step 202 is: each pixel area in the game display frame is a probability value of a pixel area of the game map, and since the electronic device has already divided the pixel area of the game display frame, at this time, the electronic device repairs the game display frame according to the game map, which may include:
for the pixel area in the game display frame, the electronic equipment repairs the pixel area of the game display frame according to the pixel area at the same position in the game map.
Alternatively, the electronic device may repair only the pixel region where the abnormality occurs. In this case, for the pixel area in the game display frame, the repairing, by the electronic device, the pixel area in the game display frame according to the pixel area at the same position in the game map may include:
the electronic equipment determines a pixel area needing to be repaired in a game display frame;
and for the pixel area needing to be repaired in the game display frame, the electronic equipment repairs the pixel area of the game display frame according to the pixel area at the same position in the game map.
Optionally, since the detection result output by the first model in step 202 is the probability value that each pixel area in the game display frame is the pixel area of the game map, when the electronic device determines whether the game display frame is abnormal according to the detection result, it is already known whether each pixel area in the game display frame is abnormal, and therefore, when the electronic device determines the pixel area in the game display frame that needs to be repaired, it is sufficient to directly obtain the determination result whether each pixel area in the game display frame is abnormal in the previous step.
In the method shown in fig. 2, the electronic device may use the first model to detect whether the game display frame is abnormal in real time, and perform frame supplementing processing on the game display frame when it is determined that the game display frame is abnormal, so as to detect the cheating action of the user using the plug-in time, terminate the cheating action of the user using the plug-in a frame supplementing manner, and maintain fairness of the game.
Fig. 4 is a flowchart of another embodiment of the AI-based image processing method according to the present application, and as shown in fig. 4, compared to the AI-based image processing method shown in fig. 2, the method shown in fig. 4 may further include, after step 203:
step 401: the electronic equipment reports the first information to the server.
The first information is used for indicating that the game display frame of the first user is abnormal to the server.
Compared with the method shown in fig. 2, in the method shown in fig. 3, the electronic device reports the information that the game display frame of the first user is abnormal to the server, so that a game operator can know the information of the user who may use the plug-in, so as to take possible processing measures for the user and maintain the fairness of the game.
In the game process, the electronic device uses the first model to detect the abnormal degree of each game display frame, and due to the large data processing amount, the first model may have errors in the detection result of the abnormal degree of the game display frame, that is, the situation that the user does not use the cheating-on-plug-in electronic device but detects that the game display frame of the user is abnormal may occur. For this reason, the embodiment of the present application also provides another embodiment of the AI-based image processing method, as shown in fig. 5, which further includes the following steps 501 to 504, compared with the method shown in fig. 2. Wherein the content of the first and second substances,
step 501: and when the electronic equipment judges that the game display frame is abnormal according to the detection result, recording the abnormal game display frame as the abnormal game display frame of the first user.
The execution order between step 501 and step 203 is not limited.
Step 502: the electronic equipment detects that the game of the first user is finished, inputs the abnormal game display frame of the first user into the second model, and obtains a detection result output by the second model aiming at the abnormal game display frame; the second model is used to detect the degree of abnormality of the game display frame.
In this step, the implementation of the second model may refer to the related description of the first model, which is not described herein.
It should be noted that the second model may be the same as or different from the first model. If the second model is not the same as the first model, the detection accuracy of the second model may be greater than that of the first model, e.g., the number of samples used to train the second model may be greater than the number of samples used to train the first model.
The number of the abnormal game display frames of the first user may be 1 or more, and if the number of the abnormal game display frames is more than one, each abnormal game display frame may be input into the second model, so as to obtain a detection result of the second model for each abnormal game display frame.
Step 503: and the electronic equipment judges whether the abnormal game display frame is abnormal according to the detection result output by the second model aiming at the abnormal game display frame, and obtains a judgment result.
The implementation of this step can refer to the description of step 203 for determining whether the game display frame is abnormal according to the detection result, which is not described herein again.
Step 504: the electronic equipment determines that the abnormal game display frame with the abnormal judgment result exists in the abnormal game display frames, and reports the first information to the server.
In order to reduce the data processing amount of the electronic device, the present application also provides another embodiment of an AI-based image processing method, which is different from the method shown in fig. 5, in which the electronic device re-detects the abnormal game display frame after the game of the first user is finished, and further defines the triggering condition for the abnormal game display frame re-detection, as shown in fig. 6, the method replaces step 502 in the method shown in fig. 5 with the following steps 601 to 602. In particular, the method comprises the following steps of,
step 601: the electronic equipment detects that the game of the first user is finished, and obtains the game time point of the abnormal game display frame of the first user.
The game time point may be represented by the user's status in the game, for example, the game time point may include but is not limited to: the users and teammates do not kill, the users kill themselves, the teammates of the users kill, the users are killed, and the like.
Step 602: the electronic equipment determines that the proportion of the abnormal game display frames at the game time point in the abnormal game display frames of the first user reaches a preset first threshold value.
The designated time point may be a game time point that is critical to the user, or a game time point at which the user has a relatively high possibility of using the cheating program in the game, for example, a game time point at which the user clicks on the cheating program, the user is clicked on the cheating program, or the user is clicked on the cheating program in the foregoing example.
If the proportion of the abnormal game display frames of which the game time points are the designated time points in the abnormal game display frames reaches a preset first threshold, the game time points of which the abnormal game display frames appear for the first user are mostly designated time points, and at the moment, the possibility that the first user uses plug-in cheating is relatively higher, so that the abnormal game display frames of the first user can be re-detected to obtain an accurate detection result, and whether the first user uses plug-in cheating is accurately determined.
It is to be understood that some or all of the steps or operations in the above-described embodiments are merely examples, and other operations or variations of various operations may be performed by the embodiments of the present application. Further, the various steps may be performed in a different order presented in the above-described embodiments, and it is possible that not all of the operations in the above-described embodiments are performed.
Fig. 7 is a block diagram of an embodiment of an AI-based image processing apparatus according to the present application, and as shown in fig. 7, the apparatus 70 may include:
an acquisition unit 71 for acquiring a game display frame; the game display frame is a game screen image displayed to a first user;
the first detection unit 72 is used for inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame;
and the processing unit 73 is configured to perform frame compensation processing on the game display frame when it is determined that the game display frame is abnormal according to the detection result.
Optionally, the processing unit 73 may be specifically configured to: acquiring a game map corresponding to the game display frame; and repairing the game display frame according to the game map.
Optionally, the processing unit 73 may be specifically configured to: dividing the game display frame and the game map into a plurality of pixel areas respectively; and for each pixel area in the game display frame, repairing the pixel area of the game display frame according to the pixel area at the same position in the game map.
Optionally, as shown in fig. 8, the apparatus 70 may further include:
a recording unit 81, configured to record the game display frame as an abnormal game display frame of the first user when it is determined that the game display frame is abnormal;
a second detecting unit 82, configured to detect that the game of the first user is ended, input the abnormal game display frame of the first user into a second model, and obtain a detection result output by the second model for the abnormal game display frame; the second model is used for detecting the abnormal degree of the game display frame;
a judging unit 83, configured to judge whether the abnormal game display frame is abnormal according to a detection result output by the second model for the abnormal game display frame.
Optionally, the second detecting unit 82 may be further configured to: acquiring a game time point of an abnormal game display frame of the first user; and determining that the proportion of the abnormal game display frame at the specified time point in the abnormal game display frame of the first user reaches a preset first threshold value.
The embodiments shown in fig. 7 and 8 provide an apparatus 70 that can be used to implement the technical solutions of the method embodiments shown in fig. 2 to 6 of the present application, and the implementation principles and technical effects thereof can be further referred to the related descriptions in the method embodiments.
It should be understood that the above division of the units of the apparatus shown in fig. 7 is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these units can be implemented entirely in software, invoked by a processing element; or may be implemented entirely in hardware; part of the units can also be realized in the form of software called by a processing element, and part of the units can be realized in the form of hardware. For example, the first detection unit may be a separately established processing element, or may be implemented by being integrated into a chip of the electronic device. The other units are implemented similarly. In addition, all or part of the units can be integrated together or can be independently realized. In implementation, the steps of the method or the units above may be implemented by hardware integrated logic circuits in a processor element or instructions in software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors (DSPs), one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, these modules may be integrated together and implemented in the form of a System-On-a-Chip (SOC).
For example, the above-described acquisition unit and the first detection unit may be implemented by a Central Processing Unit (CPU). The processing unit may be implemented by a Digital Signal Processor (DSP).
Block diagram of an electronic device of the present application for example, as shown in fig. 9, an electronic device 900 includes a processor 910 and a transceiver 920. Optionally, the electronic device 900 may also include a memory 930. The processor 910, the transceiver 920 and the memory 930 may communicate with each other via internal connection paths to transmit control and/or data signals, the memory 930 may be used for storing a computer program, and the processor 910 may be used for calling and running the computer program from the memory 930.
The memory 930 may be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a Random Access Memory (RAM), or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disc storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, etc.
Optionally, the electronic device 900 may further include an antenna 940 for transmitting the wireless signal output by the transceiver 920.
The processor 910 and the memory 930 may be combined into a single processing device, or more generally, separate components, and the processor 910 is configured to execute the program code stored in the memory 930 to implement the functions described above. In particular implementations, the memory 930 may be integrated with the processor 910 or may be separate from the processor 910.
The electronic device 900 may also include a display unit 950. The display unit 950 may include a display screen, among others.
It should be understood that the electronic device 900 shown in fig. 9 is capable of implementing the processes of the methods provided by the embodiments shown in fig. 2-6 of the present application. The operations and/or functions of the respective modules in the electronic device 900 are respectively for implementing the corresponding flows in the above-described method embodiments. Specifically, reference may be made to the description of the method embodiment shown in fig. 2 to 6 of the present application, and a detailed description is appropriately omitted herein to avoid redundancy.
The present application further provides an electronic device, where the device includes a storage medium and a central processing unit, the storage medium may be a non-volatile storage medium, a computer executable program is stored in the storage medium, and the central processing unit is connected to the non-volatile storage medium and executes the computer executable program to implement the method provided in the embodiment shown in fig. 2 to fig. 6 of the present application.
An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is enabled to execute the method provided by the embodiment shown in fig. 2 to 6 of the present application.
Embodiments of the present application further provide a computer program product, which includes a computer program, when the computer program runs on a computer, the computer executes the method provided by the embodiments shown in fig. 2 to fig. 6 of the present application.
In the embodiments of the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, and means that there may be three relationships, for example, a and/or B, and may mean that a exists alone, a and B exist simultaneously, and B exists alone. Wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.
Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, any function, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present disclosure, and all the changes or substitutions should be covered by the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. An AI-based image processing method, comprising:
acquiring a game display frame; the game display frame is a game screen image displayed to a first user;
inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame;
and when the game display frame is judged to be abnormal according to the detection result, carrying out frame supplementing processing on the game display frame.
2. The method of claim 1, wherein the frame-filling the game display frame comprises:
acquiring a game map corresponding to the game display frame;
and repairing the game display frame according to the game map.
3. The method of claim 2, wherein the repairing the game display frame according to the game map comprises:
dividing the game display frame and the game map into a plurality of pixel areas respectively;
and for the pixel area in the game display frame, repairing the pixel area of the game display frame according to the pixel area at the same position in the game map.
4. The method of any of claims 1 to 3, further comprising:
when the game display frame is judged to be abnormal, recording the game display frame as the abnormal game display frame of the first user;
when the game of the first user is detected to be finished, inputting the abnormal game display frame of the first user into a second model to obtain a detection result output by the second model aiming at the abnormal game display frame; the second model is used for detecting the abnormal degree of the game display frame;
and judging whether the abnormal game display frame is abnormal or not according to the detection result output by the second model aiming at the abnormal game display frame.
5. The method of claim 4, wherein after detecting the end of the game of the first user and before entering the abnormal game display frame of the first user into the second model, further comprising:
acquiring a game time point of an abnormal game display frame of the first user;
and determining that the proportion of a first abnormal game display frame in the abnormal game display frames of the first user reaches a preset first threshold, wherein the first abnormal game display frame is an abnormal game display frame of which the game time point is a designated time point.
6. An AI-based image processing apparatus, comprising:
an acquisition unit configured to acquire a game display frame; the game display frame is a game screen image displayed to a first user;
the first detection unit is used for inputting the game display frame into a preset first model to obtain a detection result output by the first model; the first model is used for detecting the abnormal degree of the game display frame;
and the processing unit is used for performing frame supplementing processing on the game display frame when the game display frame is judged to be abnormal according to the detection result.
7. The apparatus according to claim 6, wherein the processing unit is specifically configured to: acquiring a game map corresponding to the game display frame; and repairing the game display frame according to the game map.
8. The apparatus according to claim 7, wherein the processing unit is specifically configured to: dividing the game display frame and the game map into a plurality of pixel areas respectively; and for the pixel area in the game display frame, repairing the pixel area of the game display frame according to the pixel area at the same position in the game map.
9. The apparatus of any one of claims 6 to 8, further comprising:
the recording unit is used for recording the game display frame as the abnormal game display frame of the first user when judging that the game display frame is abnormal;
the second detection unit is used for detecting that the game of the first user is ended, inputting the abnormal game display frame of the first user into a second model and obtaining a detection result output by the second model aiming at the abnormal game display frame; the second model is used for detecting the abnormal degree of the game display frame;
and the judging unit is used for judging whether the abnormal game display frame is abnormal or not according to the detection result output by the second model aiming at the abnormal game display frame.
10. The apparatus of claim 9, wherein the second detection unit is further configured to: acquiring a game time point of an abnormal game display frame of the first user; and determining that the proportion of the abnormal game display frame at the specified time point in the abnormal game display frame of the first user reaches a preset first threshold value.
11. A central processing unit CPU, characterized in that it comprises the acquisition unit and the first detection unit of claim 6.
12. A digital signal processor, DSP, characterized in that said DSP comprises the processing unit as claimed in claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518184.0A CN113209628B (en) | 2021-05-12 | 2021-05-12 | AI-based image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518184.0A CN113209628B (en) | 2021-05-12 | 2021-05-12 | AI-based image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113209628A true CN113209628A (en) | 2021-08-06 |
| CN113209628B CN113209628B (en) | 2022-09-06 |
Family
ID=77095316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518184.0A Active CN113209628B (en) | 2021-05-12 | 2021-05-12 | AI-based image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113209628B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101082951A (en) * | 2007-07-11 | 2007-12-05 | 成都金山互动娱乐科技有限公司 | Technology for providing network game anti external hanging image origin by 3D technology |
| CN103020415A (en) * | 2011-09-28 | 2013-04-03 | 盛趣信息技术（上海）有限公司 | Method, device and system for preventing game cheating |
| CN107308645A (en) * | 2017-06-07 | 2017-11-03 | 浙江无端科技股份有限公司 | A kind of method and game client of the plug-in detection of perspective of playing |
| CN109589608A (en) * | 2018-12-19 | 2019-04-09 | 网易（杭州）网络有限公司 | The method and apparatus for protecting game data |
| CN110152303A (en) * | 2019-05-24 | 2019-08-23 | 江苏亨通工控安全研究院有限公司 | The plug-in method and system of protected network game off line |
| CN110909630A (en) * | 2019-11-06 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Abnormal game video detection method and device |
| CN110942031A (en) * | 2019-11-27 | 2020-03-31 | 上海米哈游网络科技股份有限公司 | Game picture abnormity detection method and device, electronic equipment and storage medium |
| CN110992448A (en) * | 2019-11-28 | 2020-04-10 | 网易（杭州）网络有限公司 | Animation processing method and device, electronic equipment and storage medium |
| US20200114265A1 (en) * | 2018-10-16 | 2020-04-16 | Kakao Games Corp. | Method for detecting abnormal game play |
| CN111054080A (en) * | 2019-12-06 | 2020-04-24 | 腾讯科技（深圳）有限公司 | Method, device and equipment for intelligently detecting perspective plug-in and storage medium thereof |
-
2021
- 2021-05-12 CN CN202110518184.0A patent/CN113209628B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101082951A (en) * | 2007-07-11 | 2007-12-05 | 成都金山互动娱乐科技有限公司 | Technology for providing network game anti external hanging image origin by 3D technology |
| CN103020415A (en) * | 2011-09-28 | 2013-04-03 | 盛趣信息技术（上海）有限公司 | Method, device and system for preventing game cheating |
| CN107308645A (en) * | 2017-06-07 | 2017-11-03 | 浙江无端科技股份有限公司 | A kind of method and game client of the plug-in detection of perspective of playing |
| US20200114265A1 (en) * | 2018-10-16 | 2020-04-16 | Kakao Games Corp. | Method for detecting abnormal game play |
| CN109589608A (en) * | 2018-12-19 | 2019-04-09 | 网易（杭州）网络有限公司 | The method and apparatus for protecting game data |
| CN110152303A (en) * | 2019-05-24 | 2019-08-23 | 江苏亨通工控安全研究院有限公司 | The plug-in method and system of protected network game off line |
| CN110909630A (en) * | 2019-11-06 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Abnormal game video detection method and device |
| CN110942031A (en) * | 2019-11-27 | 2020-03-31 | 上海米哈游网络科技股份有限公司 | Game picture abnormity detection method and device, electronic equipment and storage medium |
| CN110992448A (en) * | 2019-11-28 | 2020-04-10 | 网易（杭州）网络有限公司 | Animation processing method and device, electronic equipment and storage medium |
| CN111054080A (en) * | 2019-12-06 | 2020-04-24 | 腾讯科技（深圳）有限公司 | Method, device and equipment for intelligently detecting perspective plug-in and storage medium thereof |
Non-Patent Citations (1)
| Title |
|---|
| 游戏程序员刘宇: "帧同步游戏开发小结", 《HTTPS://WWW.CNBLOGS.COM/XIAOHUTU/P/12402399.HTML》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113209628B (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3719708A1 (en) | Model test method and device | |
| CN109118470B (en) | Image quality evaluation method and device, terminal and server | |
| US7076101B2 (en) | Method and apparatus for local image quantification verification | |
| US11068746B2 (en) | Image realism predictor | |
| WO2023071121A1 (en) | Multi-model fusion-based object detection method and apparatus, device and medium | |
| CN109272016A (en) | Target detection method, device, terminal equipment and computer readable storage medium | |
| CN101533472A (en) | Information processing apparatus, method, and program | |
| CN113887408B (en) | Method, device, equipment and storage medium for detecting activated face video | |
| US8644625B2 (en) | Object detection device, method and program | |
| CN107844803B (en) | Picture comparison method and device | |
| CN111881706B (en) | Living body detection, image classification and model training method, device, equipment and medium | |
| US20190370996A1 (en) | Image processing apparatus | |
| CN111803956B (en) | Method and device for determining game plug-in behavior, electronic equipment and storage medium | |
| US11640711B2 (en) | Automated artifact detection | |
| CN112206541B (en) | Game plug-in identification method and device, storage medium and computer equipment | |
| CN113822160A (en) | Evaluation method, system and equipment of deep forgery detection model | |
| CN113209628B (en) | AI-based image processing method and device | |
| CN111784660B (en) | Method and system for analyzing frontal face degree of face image | |
| JP2010271921A (en) | Skin area extraction method, skin area extraction device, and skin area extracting program | |
| CN110342363A (en) | Test method, apparatus, terminal device and the storage medium of elevator safety performance | |
| US20240020873A1 (en) | Image generation system, image generation method, and recording medium | |
| CN114917590A (en) | Virtual reality's game system | |
| CN111461971B (en) | Image processing method, device, equipment and computer readable storage medium | |
| US20220292706A1 (en) | Object number estimation device, control method, and program | |
| CN109583500A (en) | A kind of aesthetic images quality prediction system and method based on depth drift-diffusion method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |