CN109409427A - A kind of key detecting method and device - Google Patents
A kind of key detecting method and device Download PDFInfo
- Publication number
- CN109409427A CN109409427A CN201811249475.9A CN201811249475A CN109409427A CN 109409427 A CN109409427 A CN 109409427A CN 201811249475 A CN201811249475 A CN 201811249475A CN 109409427 A CN109409427 A CN 109409427A
- Authority
- CN
- China
- Prior art keywords
- coordinate value
- key
- characteristic information
- class probability
- button operation
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Abstract
The embodiment of the invention discloses a kind of key detecting method and devices, comprising: obtains the coordinate value of multiple button operations on the display screen, and determines characteristic information according to the coordinate value;The characteristic information is input in the prediction model trained and is predicted, determines the class probability of the characteristic information;According to the class probability, the keystroke categories of the multiple button operation are determined.Using the embodiment of the present invention, the accuracy of key detection can be improved, improve detection efficiency.
Description
Technical field
The present invention relates to electronic technology field more particularly to a kind of key detecting methods and device.
Background technique
In many game, analogue-key supplementary mode can be used to realize automatic operation, it is, for example, possible to use press
Key assists position of touch and automatically clicking to identify interface, very high game point is completed, if other player's craft
Operation is generally extremely difficult to, and is done a lot of damage to game balance, is needed to identify and handle this behavior.Existing detection
The method of client simulation key not can guarantee the accuracy of detection, and low efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of key detecting method and device.The accuracy of key detection can be improved, improve
Detection efficiency.
In a first aspect, the embodiment of the invention provides a kind of key detecting methods, comprising:
The coordinate value of multiple button operations on the display screen is obtained, and characteristic information is determined according to the coordinate value;
The characteristic information is input in the prediction model trained and is predicted, determines the classification of the characteristic information
Probability;
According to the class probability, the keystroke categories of the multiple button operation are determined.
Wherein, described according to the class probability, determine that the keystroke categories of the multiple button operation include:
When the class probability is greater than preset threshold, determine that the keystroke categories are analogue-key;
When the class probability is not more than the preset threshold, determine the keystroke categories for manual key.
Wherein, it is described when the class probability be greater than preset threshold when, determine the keystroke categories be analogue-key after,
Further include:
When determining the keystroke categories is the analogue-key, warning message, the warning letter are sent to user equipment
Breath is for reminding user to stop the game operation behavior of the analogue-key.
Wherein, the coordinate value of the multiple button operations of the acquisition on the display screen, and determined according to the coordinate value
Characteristic information includes:
The multiple button operation is grouped to obtain multiple button operation groupings;
According to the coordinate value of each button operation in button operation grouping each in the grouping of the multiple button operation, really
The characteristic information of fixed each button operation grouping.
Wherein, the described characteristic information is input in the prediction model trained is predicted, determines the feature
The class probability of information includes:
The characteristic information of each button operation grouping is input in the prediction model trained and is predicted, is determined
Dispersion in each button operation grouping between the coordinate value of multiple button operations;
According to the dispersion, the class probability is determined.
Wherein, the coordinate value of the multiple button operations of the acquisition on the display screen, and determined according to the coordinate value
Before characteristic information, further includes:
It obtains the first coordinate value of multiple analogue-keys and fisrt feature is determined according to first coordinate value, obtain multiple
Second coordinate value of artificial key simultaneously determines second feature according to second coordinate value;
The fisrt feature and the second feature are input to be trained to obtain the prediction in training pattern
Model.
Second aspect, the embodiment of the invention provides a kind of key detection devices, comprising:
Module is obtained, for obtaining the coordinate value of multiple button operations on the display screen, and according to the coordinate value
Determine characteristic information;
Prediction module is predicted for the characteristic information to be input in the prediction model trained, described in determination
The class probability of characteristic information;
Processing module, for determining the keystroke categories of the multiple button operation according to the class probability.
Wherein, the processing module is also used to determine the keystroke categories when the class probability is greater than preset threshold
For analogue-key;When the class probability is not more than the preset threshold, determine the keystroke categories for manual key.
Wherein, described device further include:
Sending module, for being set to user when the processing module determines that the keystroke categories are the analogue-key
Preparation send warning message, the game operation behavior that the warning message is used to that user to be reminded to stop the analogue-key.
Wherein, the processing module is also used to be grouped to obtain to the multiple button operation multiple button operations point
Group;According to the coordinate value of each button operation in button operation grouping each in the grouping of the multiple button operation, institute is determined
State the characteristic information of each button operation grouping.
Wherein, the prediction module is also used to for the characteristic information of each button operation grouping being input to and train
Prediction model in predicted, determine discrete between the coordinate value of multiple button operations in each button operation grouping
Degree;According to the dispersion, the class probability is determined.
Wherein, the acquisition module is also used to obtain the first coordinate value of multiple analogue-keys and sits according to described first
Scale value determines fisrt feature, obtains the second coordinate value of multiple artificial keys and determines the second spy according to second coordinate value
Sign;
The processing module, be also used to for the fisrt feature and the second feature being input to in training pattern into
Row training obtains the prediction model.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, comprising: processor, memory, communication interface and
Bus;
The processor, the memory are connected by the bus with the communication interface and complete mutual lead to
Letter;
The memory stores executable program code;
The processor is run by reading the executable program code stored in the memory can be performed with described
The corresponding program of program code, for executing above-mentioned performed method.
Correspondingly, the embodiment of the present application provides a kind of storage medium, wherein the storage medium applies journey for storing
Sequence, the application program for executing a kind of key detecting method disclosed in the embodiment of the present application first aspect at runtime.
Correspondingly, the embodiment of the present application provides a kind of application program, wherein the application program for holding at runtime
A kind of key detecting method disclosed in row the embodiment of the present application first aspect.
Implement the embodiment of the present invention, obtains the coordinate value of multiple button operations on the display screen first, and according to institute
It states coordinate value and determines characteristic information;Then the characteristic information is input in the prediction model trained and is predicted, determined
The class probability of the characteristic information;Finally according to the class probability, the keystroke categories of the multiple button operation are determined.It is logical
It crosses prediction model to predict the classification of button operation, to improve the accuracy of key detection, improves detection efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for this field
For those of ordinary skill, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of structural schematic diagram for key detection system that the embodiment of the present application proposes;
Fig. 2 is a kind of flow diagram of key detecting method provided by the embodiments of the present application;
Fig. 3 is the flow diagram of another key detecting method provided by the embodiments of the present application;
Fig. 4 is a kind of structural schematic diagram of key detection device provided by the embodiments of the present application;
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present application proposes.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.
Referring to FIG. 1, Fig. 1 is a kind of structural schematic diagram for key detection system that the embodiment of the present application proposes.The system
Including user equipment 101 and server 102, wherein user equipment 101 can refer to the voice and/or number for providing and arriving user
According to the equipment of connection, also may be connected to laptop computer or desktop computer etc. calculating equipment or its can
To be the autonomous device of such as personal digital assistant (Personal Digital Assistant, PDA) etc., such as hand is mechanical, electrical
Depending on machine etc..Server 102 can be the server, such as data server, Analysis server etc. for being capable of providing data analysis
Deng.In the embodiment of the present application, user equipment directly can carry out key detection by prediction model.Server also can receive
The coordinate value for the button operation that user equipment is sent carries out key detection by prediction model, and will test result and be sent to use
Family equipment.The present invention is without limitation.Based on above system, the embodiment of the present application provides following solution.
Referring to FIG. 2, Fig. 2 is a kind of flow diagram of key detecting method provided by the embodiments of the present application.As schemed
Show, the step in the embodiment of the present application includes:
S201 obtains the coordinate value of multiple button operations on the display screen, and determines feature according to the coordinate value
Information.Wherein, characteristic information can standard deviation between multiple coordinate values.
In the specific implementation, can be monitored to user's game behavior, when monitoring every innings of game over, user is obtained
The coordinate value of all button operations in game process.Or it can obtain according to the preset time interval on the display screen
Multiple button operations coordinate value.Then coordinate value can be standardized, due to showing the difference of screen, key
The coordinate value of operation is also different, each coordinate value pair can be calculated by coordinate value divided by the height or width of display screen
The standard value answered.Finally calculate the standard deviation between multiple standard values.
Further, the multiple button operation can be grouped to obtain multiple button operation groupings;Then basis
The coordinate value of each button operation in the grouping of the multiple button operation in each button operation grouping, determine it is described each by
The characteristic information of key operation grouping.For example, multiple button operations can be divided into N number of button operation grouping, each key behaviour
Make the coordinate value that grouping may include 10 button operations, calculates separately the seat of 10 button operations in each button operation grouping
Standard deviation between scale value, to obtain N number of standard deviation.
The characteristic information is input in the prediction model trained and predicts by S202, determines the characteristic information
Class probability.
In the specific implementation, the characteristic information of each button operation grouping can be input to the prediction model trained
In predicted, determine the dispersion in each button operation grouping between the coordinate value of multiple button operations;Then root
According to the dispersion, the class probability is determined.Dispersion is bigger, then illustrates that keystroke categories are that the class probability of artificial key is got over
Greatly;Dispersion is smaller, then illustrates that the class probability that keystroke categories are analogue-key is bigger.
Wherein, available more before being input to the characteristic information and being predicted in the prediction model trained
First coordinate value of a analogue-key simultaneously determines fisrt feature according to first coordinate value, obtains the second of multiple artificial keys
Coordinate value simultaneously determines second feature according to second coordinate value;By the fisrt feature and the second feature be input to
It is trained to obtain the prediction model in training pattern.
For example, game can be carried out using analogue-key tool first, and the coordinate of record is denoted as coordinate set A;Hand
Work operation carries out normal game, and the coordinate of record is denoted as coordinate set B.Secondly, by coordinate set A and coordinate set B
Coordinate sequence distinguish standardization.Then coordinate set A and coordinate set B are grouped respectively, every 10 coordinates point
For 1 group of feature, in coordinates computed set A in a standard deviation of every group of feature and coordinate set B every group of feature a mark
It is quasi- poor.Finally by coordinate set A corresponding multiple standard deviation a1, a2, a3 ... and the corresponding multiple standards of coordinate set B
Poor b1, b2, b3 ..., be separately input into and be trained to obtain prediction model M to training pattern.It should be understood that since key assists
The coordinate value of click generally compares concentration, and coordinate value is fixed on certain several point, and normal manual operation coordinate value compare from
It dissipates, therefore two kinds of features can relatively accurately be distinguished by machine learning model.
Wherein, prediction model can be convolutional neural networks (Convolutional Neural Networks, CNN) point
Class model.The CNN disaggregated model includes input layer, convolutional layer, pond layer, full articulamentum and output layer.Wherein, convolutional layer and pond
The combination for changing layer can occur repeatedly in hidden layer.It include that trained model parameter, the model have been joined in CNN disaggregated model
Number includes convolution kernel, the bias matrix of each convolutional layer and the weight matrix of full articulamentum and full articulamentum of each convolutional layer
Bias vector etc..During prediction, characteristic information can be input in prediction module first, then in each convolution
On layer, convolution operation and maximum Chi Huacao are carried out to each pending area using the convolution kernel and bias matrix of each convolutional layer
Make, extracts data characteristics of the characteristic information on each convolutional layer.Then, using the weight matrix and bias vector of full articulamentum
Game data is handled, class probability is obtained.In the embodiment of the present application, by way of machine learning or deep learning
Game data is predicted, the accuracy of game data judgement can be improved.
S203 determines the keystroke categories of the multiple button operation according to the class probability.
In the specific implementation, working as institute in the case where prediction model is mainly for identifying whether user's operation is analogue-key
When stating class probability greater than preset threshold, determine that the keystroke categories are analogue-key;When the class probability is no more than described
When preset threshold, determine the keystroke categories for manual key.Certainly, prediction model mainly for identification user's operation whether
In the case where for manual key, when the class probability be greater than the preset threshold when, determine the keystroke categories for by hand by
Key determines that the keystroke categories are analogue-key when the class probability is not more than preset threshold.Wherein, preset threshold can
Think 0.5 or 0.6 etc..
In the embodiment of the present application, user equipment obtains the coordinate value of multiple button operations on the display screen first,
And characteristic information is determined according to the coordinate value;Then the characteristic information is input in the prediction model trained and is carried out in advance
It surveys, determines the class probability of the characteristic information;Finally according to the class probability, the key of the multiple button operation is determined
Classification.It is predicted by classification of the prediction model to button operation, to improve the accuracy of key detection, improves detection effect
Rate.
Referring to FIG. 3, Fig. 3 is the flow diagram of another key detecting method provided by the embodiments of the present application.Such as figure
Shown, the step in the embodiment of the present application includes:
S301, user equipment send the coordinate value of multiple button operations on the display screen to server.
In the specific implementation, user equipment can be monitored user's game behavior, when monitoring every innings of game over,
Obtain the coordinate value of all button operations of the user in game process.Alternatively, can obtain according to the preset time interval
Show the coordinate value of multiple button operations on screen.Then server is reported to according to predetermined period.
S302, server determine characteristic information according to the coordinate value.
In the specific implementation, server can be standardized coordinate value, due to showing the difference of screen, key behaviour
The coordinate value of work is also different, it is corresponding that each coordinate value can be calculated by coordinate value divided by the height or width of display screen
Standard value.Finally calculate the standard deviation between multiple standard values.
Further, the multiple button operation can be grouped to obtain multiple button operation groupings;Then basis
The coordinate value of each button operation in the grouping of the multiple button operation in each button operation grouping, determine it is described each by
The characteristic information of key operation grouping.For example, multiple button operations can be divided into N number of button operation grouping, each key behaviour
Make the coordinate value that grouping may include 10 button operations, calculates separately the seat of 10 button operations in each button operation grouping
Standard deviation between scale value, to obtain N number of standard deviation.
The characteristic information is input in the prediction model trained and predicts by S303, server, determines the spy
The class probability of reference breath.
In the specific implementation, the characteristic information of each button operation grouping can be input to the prediction model trained
In predicted, determine the dispersion in each button operation grouping between the coordinate value of multiple button operations;Then root
According to the dispersion, the class probability is determined.Dispersion is bigger, then illustrates that keystroke categories are that the class probability of artificial key is got over
Greatly;Dispersion is smaller, then illustrates that the class probability that keystroke categories are analogue-key is bigger.
Wherein, available more before being input to the characteristic information and being predicted in the prediction model trained
First coordinate value of a analogue-key simultaneously determines fisrt feature according to first coordinate value, obtains the second of multiple artificial keys
Coordinate value simultaneously determines second feature according to second coordinate value;By the fisrt feature and the second feature be input to
It is trained to obtain the prediction model in training pattern.
For example, game can be carried out using analogue-key tool first, and the coordinate of record is denoted as coordinate set A;Hand
Work operation carries out normal game, and the coordinate of record is denoted as coordinate set B.Secondly, by coordinate set A and coordinate set B
Coordinate sequence distinguish standardization.Then coordinate set A and coordinate set B are grouped respectively, every 10 coordinates point
For 1 group of feature, in coordinates computed set A in a standard deviation of every group of feature and coordinate set B every group of feature a mark
It is quasi- poor.Finally by coordinate set A corresponding multiple standard deviation a1, a2, a3 ... and the corresponding multiple standards of coordinate set B
Poor b1, b2, b3 ..., be separately input into and be trained to obtain prediction model M to training pattern.It should be understood that since key assists
The coordinate value of click generally compares concentration, and coordinate value is fixed on certain several point, and normal manual operation coordinate value compare from
It dissipates, therefore two kinds of features can relatively accurately be distinguished by machine learning model.
Wherein, prediction model can be convolutional neural networks (Convolutional Neural Networks, CNN) point
Class model.The CNN disaggregated model includes input layer, convolutional layer, pond layer, full articulamentum and output layer.Wherein, convolutional layer and pond
The combination for changing layer can occur repeatedly in hidden layer.It include that trained model parameter, the model have been joined in CNN disaggregated model
Number includes convolution kernel, the bias matrix of each convolutional layer and the weight matrix of full articulamentum and full articulamentum of each convolutional layer
Bias vector etc..During prediction, characteristic information can be input in prediction module first, then in each convolution
On layer, convolution operation and maximum Chi Huacao are carried out to each pending area using the convolution kernel and bias matrix of each convolutional layer
Make, extracts data characteristics of the characteristic information on each convolutional layer.Then, using the weight matrix and bias vector of full articulamentum
Game data is handled, class probability is obtained.In the embodiment of the present application, by way of machine learning or deep learning
Game data is predicted, the accuracy of game data judgement can be improved.
S304, server determine the keystroke categories of the multiple button operation according to the class probability.
In the specific implementation, working as institute in the case where prediction model is mainly for identifying whether user's operation is analogue-key
When stating class probability greater than preset threshold, determine that the keystroke categories are analogue-key;When the class probability is no more than described
When preset threshold, determine the keystroke categories for manual key.Certainly, prediction model mainly for identification user's operation whether
In the case where for manual key, when the class probability be greater than the preset threshold when, determine the keystroke categories for by hand by
Key determines that the keystroke categories are analogue-key when the class probability is not more than preset threshold.Wherein, preset threshold can
Think 0.5 or 0.6 etc..
S305, server send warning message when determining the keystroke categories is the analogue-key, to user equipment,
The game operation behavior that the warning message is used to that user to be reminded to stop the analogue-key.
Wherein, warning message may include the punishment such as the consequence operated using analogue-key, such as title, suspension.
User equipment receives warning message, can show the warning message.There are analogue-keys determining the user equipment for server
The case where after, detection cycle can be shortened, detection is re-started to the game data of the user equipment, avoid remind user
The case where still having analogue-key later.
In the embodiment of the present application, server can receive multiple keys behaviour on the display screen of user equipment transmission
The coordinate value of work, and characteristic information is determined according to the coordinate value;Then the characteristic information is input to the prediction trained
It is predicted in model, determines the class probability of the characteristic information;Finally according to the class probability, determine it is the multiple by
The keystroke categories of key operation.It is predicted by classification of the prediction model to button operation, to improve the accurate of key detection
Degree improves detection efficiency.
Referring to FIG. 4, Fig. 4 is a kind of structural schematic diagram of key detection device provided by the embodiments of the present application.The application
Key detection device in embodiment includes obtaining module 401, prediction module 402, processing module 403 and sending module 404,
Wherein:
Module 401 is obtained, for obtaining the coordinate value of multiple button operations on the display screen, and according to the coordinate
It is worth and determines characteristic information.
In the specific implementation, can be monitored to user's game behavior, when monitoring every innings of game over, user is obtained
The coordinate value of all button operations in game process.Or it can obtain according to the preset time interval on the display screen
Multiple button operations coordinate value.Then coordinate value can be standardized, due to showing the difference of screen, key
The coordinate value of operation is also different, each coordinate value pair can be calculated by coordinate value divided by the height or width of display screen
The standard value answered.Finally calculate the standard deviation between multiple standard values.
Further, the multiple button operation can be grouped to obtain multiple button operation groupings;Then basis
The coordinate value of each button operation in the grouping of the multiple button operation in each button operation grouping, determine it is described each by
The characteristic information of key operation grouping.For example, multiple button operations can be divided into N number of button operation grouping, each key behaviour
Make the coordinate value that grouping may include 10 button operations, calculates separately the seat of 10 button operations in each button operation grouping
Standard deviation between scale value, to obtain N number of standard deviation.
Prediction module 402 is predicted for the characteristic information to be input in the prediction model trained, and determines institute
State the class probability of characteristic information.
In the specific implementation, the characteristic information of each button operation grouping can be input to the prediction model trained
In predicted, determine the dispersion in each button operation grouping between the coordinate value of multiple button operations;Then root
According to the dispersion, the class probability is determined.Dispersion is bigger, then illustrates that keystroke categories are that the class probability of artificial key is got over
Greatly;Dispersion is smaller, then illustrates that the class probability that keystroke categories are analogue-key is bigger.
Wherein, available more before being input to the characteristic information and being predicted in the prediction model trained
First coordinate value of a analogue-key simultaneously determines the second of fisrt feature and multiple artificial keys according to first coordinate value
Coordinate value simultaneously determines second feature according to second coordinate value;By the fisrt feature and the second feature be input to
It is trained to obtain the prediction model in training pattern.
For example, game can be carried out using analogue-key tool first, and the coordinate of record is denoted as coordinate set A;Hand
Work operation carries out normal game, and the coordinate of record is denoted as coordinate set B.Secondly, by coordinate set A and coordinate set B
Coordinate sequence distinguish standardization.Then coordinate set A and coordinate set B are grouped respectively, every 10 coordinates point
For 1 group of feature, in coordinates computed set A in a standard deviation of every group of feature and coordinate set B every group of feature a mark
It is quasi- poor.Finally by coordinate set A corresponding multiple standard deviation a1, a2, a3 ... and the corresponding multiple standards of coordinate set B
Poor b1, b2, b3 ..., be separately input into and be trained to obtain prediction model M to training pattern.It should be understood that since key assists
The coordinate value of click generally compares concentration, and coordinate value is fixed on certain several point, and normal manual operation coordinate value compare from
It dissipates, therefore two kinds of features can relatively accurately be distinguished by machine learning model.
Wherein, prediction model can be convolutional neural networks (Convolutional Neural Networks, CNN) point
Class model.The CNN disaggregated model includes input layer, convolutional layer, pond layer, full articulamentum and output layer.Wherein, convolutional layer and pond
The combination for changing layer can occur repeatedly in hidden layer.It include that trained model parameter, the model have been joined in CNN disaggregated model
Number includes convolution kernel, the bias matrix of each convolutional layer and the weight matrix of full articulamentum and full articulamentum of each convolutional layer
Bias vector etc..During prediction, characteristic information can be input in prediction module first, then in each convolution
On layer, convolution operation and maximum Chi Huacao are carried out to each pending area using the convolution kernel and bias matrix of each convolutional layer
Make, extracts data characteristics of the characteristic information on each convolutional layer.Then, using the weight matrix and bias vector of full articulamentum
Game data is handled, class probability is obtained.In the embodiment of the present application, by way of machine learning or deep learning
Game data is predicted, the accuracy of game data judgement can be improved.
Processing module 403, for determining the keystroke categories of the multiple button operation according to the class probability.
In the specific implementation, working as institute in the case where prediction model is mainly for identifying whether user's operation is analogue-key
When stating class probability greater than preset threshold, determine that the keystroke categories are analogue-key;When the class probability is no more than described
When preset threshold, determine the keystroke categories for manual key.Certainly, prediction model mainly for identification user's operation whether
In the case where for manual key, when the class probability be greater than the preset threshold when, determine the keystroke categories for by hand by
Key determines that the keystroke categories are analogue-key when the class probability is not more than preset threshold.Wherein, preset threshold can
Think 0.5 or 0.6 etc..
Optionally, sending module 404 are used for when processing module 403 determines that the keystroke categories are analogue-key, Xiang Yong
Family equipment sends warning message, the game operation behavior that the warning message is used to that user to be reminded to stop the analogue-key.Its
In, warning message may include the punishment such as the consequence operated using analogue-key, such as title, suspension.User equipment connects
Warning message is received, can show the warning message.Server after the case where determining the user equipment there are analogue-keys,
Detection cycle can be shortened, detection is re-started to the game data of the user equipment, avoid still depositing after reminding user
The analogue-key the case where.
Referring to FIG. 5, Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present application proposes.As shown, should
Electronic equipment may include: at least one processor 501, such as CPU, at least one communication interface 502, at least one processor
503, at least one bus 504.Wherein, bus 504 is for realizing the connection communication between these components.Wherein, the application is real
The communication interface 502 for applying electronic equipment in example is wired sending port, or wireless device, for example including antenna assembly,
For carrying out the communication of signaling or data with other node devices.Memory 503 can be high speed RAM memory, be also possible to
Non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.Memory 503 is optional
It can also be that at least one is located remotely from the storage device of aforementioned processor 501.Batch processing code is stored in memory 503,
And processor 501 is used to call the program code stored in memory, for performing the following operations:
The coordinate value of multiple button operations on the display screen is obtained, and characteristic information is determined according to the coordinate value;
The characteristic information is input in the prediction model trained and is predicted, determines the classification of the characteristic information
Probability;
According to the class probability, the keystroke categories of the multiple button operation are determined.
Wherein, processor 501 is also used to perform the following operations step:
When the class probability is greater than preset threshold, determine that the keystroke categories are analogue-key;
When the class probability is not more than the preset threshold, determine the keystroke categories for manual key.
Wherein, processor 501 is also used to perform the following operations step:
When determining the keystroke categories is analogue-key, warning message is sent to user equipment, the warning message is used
In the game operation behavior for reminding user to stop the analogue-key.
Wherein, processor 501 is also used to perform the following operations step:
The multiple button operation is grouped to obtain multiple button operation groupings;
According to the coordinate value of each button operation in button operation grouping each in the grouping of the multiple button operation, really
The characteristic information of fixed each button operation grouping.
Wherein, processor 501 is also used to perform the following operations step:
The characteristic information of each button operation grouping is input in the prediction model trained and is predicted, is determined
Dispersion in each button operation grouping between the coordinate value of multiple button operations;
According to the dispersion, the class probability is determined.
Wherein, processor 501 is also used to perform the following operations step:
It obtains the first coordinate value of multiple analogue-keys and fisrt feature is determined according to first coordinate value, obtain multiple
Second coordinate value of artificial key simultaneously determines second feature according to second coordinate value;
The fisrt feature and the second feature are input to be trained to obtain the prediction in training pattern
Model.
It should be noted that the embodiment of the present application also provides a kind of storage medium simultaneously, the storage medium is for storing
Application program, the application program are held for executing electronic equipment in Fig. 2 and a kind of key detecting method shown in Fig. 3 at runtime
Capable operation.
It should be noted that the embodiment of the present application also provides a kind of application program simultaneously, the application program is for transporting
The operation that electronic equipment executes in Fig. 2 and a kind of key detecting method shown in Fig. 3 is executed when row.
It should be noted that for simple description, therefore, it is stated as a systems for each embodiment of the method above-mentioned
The combination of actions of column, but those skilled in the art should understand that, the application is not limited by the described action sequence, because
For according to the application, certain some step be can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily this Shen
It please be necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in some embodiment
Part, reference can be made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: flash disk, read-only memory (English: Read-Only Memory, abbreviation: ROM), random access device (English
Text: Random Access Memory, referred to as: RAM), disk or CD etc..
Content download method provided by the embodiment of the present application and relevant device, system are described in detail above,
Specific examples are used herein to illustrate the principle and implementation manner of the present application, and the explanation of above embodiments is only used
The present processes and its core concept are understood in help;At the same time, for those skilled in the art, according to the application's
Thought, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as
Limitation to the application.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of application
Type.
Claims (10)
1. a kind of key detecting method, which is characterized in that the described method includes:
The coordinate value of multiple button operations on the display screen is obtained, and characteristic information is determined according to the coordinate value;
The characteristic information is input in the prediction model trained and is predicted, determines that the classification of the characteristic information is general
Rate;
According to the class probability, the keystroke categories of the multiple button operation are determined.
2. the method as described in claim 1, which is characterized in that it is described according to the class probability, determine the multiple key
The keystroke categories of operation include:
When the class probability is greater than preset threshold, determine that the keystroke categories are analogue-key;
When the class probability is not more than the preset threshold, determine the keystroke categories for manual key.
3. method according to claim 2, which is characterized in that it is described when the class probability is greater than preset threshold, it determines
The keystroke categories is after analogue-keys, further includes:
When determining the keystroke categories is the analogue-key, warning message is sent to user equipment, the warning message is used
In the game operation behavior for reminding user to stop the analogue-key.
4. the method as described in claim 1, which is characterized in that the seat of the multiple button operations of the acquisition on the display screen
Scale value, and determine that characteristic information includes: according to the coordinate value
The multiple button operation is grouped to obtain multiple button operation groupings;
According to the coordinate value of each button operation in button operation grouping each in the grouping of the multiple button operation, institute is determined
State the characteristic information of each button operation grouping.
5. method as claimed in claim 4, which is characterized in that described that the characteristic information is input to the prediction mould trained
It is predicted in type, determines that the class probability of the characteristic information includes:
The characteristic information of each button operation grouping is input in the prediction model trained and is predicted, described in determination
Dispersion in each button operation grouping between the coordinate value of multiple button operations;
According to the dispersion, the class probability is determined.
6. the method according to claim 1 to 5, which is characterized in that the multiple keys of the acquisition on the display screen
The coordinate value of operation, and before determining characteristic information according to the coordinate value, further includes:
It obtains the first coordinate value of multiple analogue-keys and fisrt feature is determined according to first coordinate value, obtain multiple artificial
Second coordinate value of key simultaneously determines second feature according to second coordinate value;
The fisrt feature and the second feature are input to be trained to obtain the prediction model in training pattern.
7. a kind of key detection device, which is characterized in that described device includes:
Module is obtained, is determined for obtaining the coordinate value of multiple button operations on the display screen, and according to the coordinate value
Characteristic information;
Prediction module is predicted for the characteristic information to be input in the prediction model trained, and determines the feature
The class probability of information;
Processing module, for determining the keystroke categories of the multiple button operation according to the class probability.
8. device as claimed in claim 7, which is characterized in that
The processing module, be also used to when the class probability be greater than preset threshold when, determine the keystroke categories for simulation by
Key;When the class probability is not more than the preset threshold, determine the keystroke categories for manual key.
9. a kind of electronic equipment characterized by comprising processor, memory, communication interface and bus;
The processor, the memory are connected by the bus with the communication interface and complete mutual communication;
The memory stores executable program code;
The processor is run and the executable program by reading the executable program code stored in the memory
The corresponding program of code, for executing key detecting method as claimed in any one of claims 1 to 6.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has a plurality of finger
It enables, described instruction is suitable for being loaded by processor and executing key detecting method as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811249475.9A CN109409427A (en) | 2018-10-25 | 2018-10-25 | A kind of key detecting method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811249475.9A CN109409427A (en) | 2018-10-25 | 2018-10-25 | A kind of key detecting method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409427A true CN109409427A (en) | 2019-03-01 |
Family
ID=65469165
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811249475.9A Pending CN109409427A (en) | 2018-10-25 | 2018-10-25 | A kind of key detecting method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409427A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113069757A (en) * | 2021-02-24 | 2021-07-06 | 广州点云科技有限公司 | Cloud game automatic acceleration method and device and computer readable storage medium |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070149279A1 (en) * | 2005-12-22 | 2007-06-28 | Lucent Technologies Inc. | Acorn: providing network-level security in P2P overlay architectures |
CN101025775A (en) * | 2007-01-19 | 2007-08-29 | 华为技术有限公司 | Method, system and device for preventing network game from extenally hanging software |
CN101256673A (en) * | 2008-03-18 | 2008-09-03 | 中国计量学院 | Method for tracing arm motion in real time video tracking system |
CN201205454Y (en) * | 2008-05-22 | 2009-03-11 | 中山新宏达日用制品有限公司 | Electric remote control car with inflatable mold |
CN101833619A (en) * | 2010-04-29 | 2010-09-15 | 西安交通大学 | Method for judging identity based on keyboard-mouse crossed certification |
CN103605697A (en) * | 2013-11-06 | 2014-02-26 | 北京掌阔移动传媒科技有限公司 | Method for judging cheat clicking of mobile phone advertising |
CN104679246A (en) * | 2015-02-11 | 2015-06-03 | 华南理工大学 | Wearable type equipment based on interactive interface human hand roaming control and interactive interface human hand roaming control method |
CN104869638A (en) * | 2015-05-28 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Detection method and device for GPS coordinate cheating |
CN105573639A (en) * | 2014-10-17 | 2016-05-11 | 国际商业机器公司 | Triggered application display method and system |
CN105677221A (en) * | 2015-12-30 | 2016-06-15 | 广州优视网络科技有限公司 | Method and device for improving application data detecting accuracy and equipment |
CN105868991A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method and device for identifying machine assisted cheating |
CN106694878A (en) * | 2015-11-15 | 2017-05-24 | 罗天珍 | Group scanning calibration and auxiliary heating method for laser sintering or curing 3D forming machine |
CN107506073A (en) * | 2017-08-08 | 2017-12-22 | 维沃移动通信有限公司 | Detection method of touch screen, device, mobile terminal and computer-readable recording medium |
CN207203437U (en) * | 2017-07-18 | 2018-04-10 | 深圳市冠和信业科技有限公司 | A kind of game paddle back splint |
CN107943825A (en) * | 2017-10-19 | 2018-04-20 | 阿里巴巴集团控股有限公司 | Data processing method, device and the electronic equipment of page access |
-
2018
- 2018-10-25 CN CN201811249475.9A patent/CN109409427A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070149279A1 (en) * | 2005-12-22 | 2007-06-28 | Lucent Technologies Inc. | Acorn: providing network-level security in P2P overlay architectures |
CN101025775A (en) * | 2007-01-19 | 2007-08-29 | 华为技术有限公司 | Method, system and device for preventing network game from extenally hanging software |
CN101256673A (en) * | 2008-03-18 | 2008-09-03 | 中国计量学院 | Method for tracing arm motion in real time video tracking system |
CN201205454Y (en) * | 2008-05-22 | 2009-03-11 | 中山新宏达日用制品有限公司 | Electric remote control car with inflatable mold |
CN101833619A (en) * | 2010-04-29 | 2010-09-15 | 西安交通大学 | Method for judging identity based on keyboard-mouse crossed certification |
CN103605697A (en) * | 2013-11-06 | 2014-02-26 | 北京掌阔移动传媒科技有限公司 | Method for judging cheat clicking of mobile phone advertising |
CN105573639A (en) * | 2014-10-17 | 2016-05-11 | 国际商业机器公司 | Triggered application display method and system |
CN105868991A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method and device for identifying machine assisted cheating |
CN104679246A (en) * | 2015-02-11 | 2015-06-03 | 华南理工大学 | Wearable type equipment based on interactive interface human hand roaming control and interactive interface human hand roaming control method |
CN104869638A (en) * | 2015-05-28 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Detection method and device for GPS coordinate cheating |
CN106694878A (en) * | 2015-11-15 | 2017-05-24 | 罗天珍 | Group scanning calibration and auxiliary heating method for laser sintering or curing 3D forming machine |
CN105677221A (en) * | 2015-12-30 | 2016-06-15 | 广州优视网络科技有限公司 | Method and device for improving application data detecting accuracy and equipment |
CN207203437U (en) * | 2017-07-18 | 2018-04-10 | 深圳市冠和信业科技有限公司 | A kind of game paddle back splint |
CN107506073A (en) * | 2017-08-08 | 2017-12-22 | 维沃移动通信有限公司 | Detection method of touch screen, device, mobile terminal and computer-readable recording medium |
CN107943825A (en) * | 2017-10-19 | 2018-04-20 | 阿里巴巴集团控股有限公司 | Data processing method, device and the electronic equipment of page access |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113069757A (en) * | 2021-02-24 | 2021-07-06 | 广州点云科技有限公司 | Cloud game automatic acceleration method and device and computer readable storage medium |
CN113069757B (en) * | 2021-02-24 | 2024-03-26 | 广州点云科技有限公司 | Cloud game automatic acceleration method, cloud game automatic acceleration equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI788529B (en) | Credit risk prediction method and device based on LSTM model | |
CN106021403B (en) | Client service method and device | |
CN109304034A (en) | A kind of game cheat detection method and relevant device | |
CN110399238B (en) | Disk fault early warning method, device, equipment and readable storage medium | |
CN107526964A (en) | Secure data aggregation and business intelligence for web application | |
CN109453514A (en) | A kind of game cheat detection method and device | |
CN108573358A (en) | A kind of overdue prediction model generation method and terminal device | |
US10977106B2 (en) | Tree-based anomaly detection | |
CN108021505A (en) | Data loading method, device and computer equipment | |
CN109726764A (en) | A kind of model selection method, device, equipment and medium | |
CN106598379A (en) | Method and device for managing application program | |
CN110313010A (en) | The structuring of electronic information responds summary | |
CN116401339A (en) | Data processing method, device, electronic equipment, medium and program product | |
CN106776757A (en) | User completes the indicating means and device of Net silver operation | |
CN109409427A (en) | A kind of key detecting method and device | |
US9636582B2 (en) | Text entry by training touch models | |
Aven et al. | On how to understand and express enterprise risk | |
CN113935788B (en) | Model evaluation method, device, equipment and computer readable storage medium | |
CN105227410A (en) | Based on the method and system that the server load of adaptive neural network detects | |
CN115983210A (en) | Table data enhancement method, device, equipment and medium | |
CN116304251A (en) | Label processing method, device, computer equipment and storage medium | |
CN109119157A (en) | A kind of prediction technique and system of infant development | |
US20210125068A1 (en) | Method for training neural network | |
CN114445147A (en) | Electronic ticket issuing method, electronic ticket issuing device, electronic ticket issuing apparatus, and electronic ticket issuing medium | |
CN113706019A (en) | Service capability analysis method, device, equipment and medium based on multidimensional data |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20191125 Address after: Room 105-53811, No. 6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Applicant after: Zhuhai Leopard Technology Co.,Ltd. Address before: 519070, No. 10, main building, No. six, science Road, Harbour Road, Tang Wan Town, Guangdong, Zhuhai, 601F Applicant before: Zhuhai Juntian Electronic Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |
|
RJ01 | Rejection of invention patent application after publication |