CN113806174A - Method and system for monitoring game state of mobile phone - Google Patents
Method and system for monitoring game state of mobile phone Download PDFInfo
- Publication number
- CN113806174A CN113806174A CN202111098974.4A CN202111098974A CN113806174A CN 113806174 A CN113806174 A CN 113806174A CN 202111098974 A CN202111098974 A CN 202111098974A CN 113806174 A CN113806174 A CN 113806174A
- Authority
- CN
- China
- Prior art keywords
- training
- mobile phone
- picture
- monitoring application
- game
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of computers, in particular to a method and a system for monitoring a game state of a mobile phone. The method comprises the following steps: a monitoring application is installed in the mobile phone; the mobile phone runs a game, records a game video, processes the recorded game video into picture data, and uploads the picture data to a training server by a monitoring application; the training server is provided with at least one pre-training model, the pre-training model trains the received picture data to form an optimal model, and the training server sends the optimal model to the file updating server for storage; the monitoring application downloads the optimal model stored in the file updating server through the network, when the mobile phone runs a game or the monitoring application, the monitoring application intercepts the screen picture of the mobile phone, the optimal model carries out scene recognition on the screen picture, and when the recognition result is scene switching or game state change, the monitoring application generates state change information and displays the state change information through the mobile phone. The customized mobile phone game state monitoring is automatically formulated.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a system for monitoring a game state of a mobile phone.
Background
When a user operates a mobile phone to run a game, the mobile phone needs to monitor the game so as to judge the game state, and due to the fact that the games in the current mobile phone market are various and the requirements of the user for obtaining the game state are different, customized game monitoring application or the monitoring function of the game cannot meet the requirements of all users.
In the prior art, an engineer is required to design a suitable monitoring application for each game by accurately monitoring each game, so that a specific game can be accurately monitored, and when the specific monitoring application is applied to monitoring other games, an accurate monitoring effect cannot be achieved or even a monitoring effect cannot be achieved completely.
Under the current large background that deep learning image recognition is prevalent and stably developed, the application of the image recognition technology on the mobile phone end is used for monitoring the game state of the mobile phone end, the method is a feasible scheme, meanwhile, an automatic platform is built, a user uploads game data to be recognized, a model for monitoring the game state is automatically generated, and then the model is combined with a mobile phone of the user through a thermal updating system and loaded and used by the game state monitoring application, so that customized mobile phone game state monitoring is realized.
In summary, the technical problem actually solved by the present invention is how to automatically implement customized mobile game state monitoring.
Disclosure of Invention
In order to overcome the above technical defects, an object of the present invention is to provide a method for monitoring a game state of a mobile phone, which tries to implement automatic customized monitoring of a game state of a mobile phone.
The invention discloses a method for monitoring the game state of a mobile phone, which comprises the following steps:
s1: a monitoring application is installed in the mobile phone;
s2: the mobile phone runs the game, records the game video, processes the recorded game video into picture data, and uploads the picture data to the training server through the monitoring application;
s3: the training server is provided with at least one pre-training model, training the received picture data through the pre-training model to form an optimal model, and sending the optimal model to the file updating server for storage;
s4: the monitoring application downloads the optimal model stored in the file updating server through the network, when the mobile phone runs a game or the monitoring application, the monitoring application intercepts the screen picture of the mobile phone, the optimal model identifies the scene of the screen picture, and when the identification result is scene switching or game state change, the monitoring application generates state change information and displays the state change information through the mobile phone.
Preferably, step S1 specifically includes:
s101: downloading the monitoring application into the mobile phone through a network;
s102: and the downloaded monitoring application is installed on the mobile phone after being authorized.
Preferably, step S2 specifically includes:
s201: recording a game video through a mobile phone, and framing the recorded game video into pictures according to two pictures per second;
s202: classifying the framed pictures into picture sets according to the progress of the game;
s203: setting training parameters for each type of picture set to form picture data, wherein the training parameters at least comprise time thresholds;
s204: the picture data is uploaded to the training server over a network with the monitoring application.
Preferably, step S3 specifically includes:
s301: at least one pre-training model is set in the training server;
s302: the training server receives the picture data and then judges the quantity of each picture set;
s303: randomly selecting one picture set with the largest number of pictures, and expanding the selected pictures to other picture sets to ensure that the number of the pictures in each picture set is equal;
s304: dividing the pictures in each picture set after the amplification into a training set, a verification set and a test set according to the ratio of 20:1: 1;
s305: converting each picture set into a pre-trained data format;
s306: starting training scripts in parallel, training the picture set in the step S305 by using different pre-training models to obtain different training models, comparing each training model, and selecting an optimal model;
s307: generating training parameters set by a user and information of a model into a configuration file;
s308: and sending the configuration file generated in the step S307 and the optimal model compared in the step S306 to a file updating server for storage.
Preferably, step S4 specifically includes:
s401: a user downloads the configuration file and the optimal model through a monitoring application installed on a mobile phone;
s402: the user runs games or monitoring applications in parallel, and the monitoring applications intercept the mobile phone screen pictures at intervals of a threshold value;
s403: the optimal model carries out scene recognition on the intercepted mobile phone screen picture, and when a game scene is switched or the game state is changed, the monitoring application generates state change information.
In view of the above, another objective of the present invention is to provide a system for monitoring game status of a mobile phone, comprising:
installing a module: the mobile phone is used for installing the monitoring application on the mobile phone;
a data acquisition module: the system comprises a training server, a video server and a video server, wherein the training server is used for recording mobile phone game videos, processing the recorded game videos into picture data and uploading the picture data to the training server through a monitoring application;
a data training module: training picture data by a pre-training model in a training server, selecting an optimal model, and sending the optimal model to a file updating server for storage;
a monitoring module: the monitoring application downloads the optimal model stored in the file updating server through the network, intercepts the mobile phone screen picture when the mobile phone runs a game or the monitoring application, performs scene recognition by the optimal model, and generates state change information and displays the state change information through the mobile phone when the scene switching or the game state change is recognized.
Preferably, the installation module comprises:
a downloading module: downloading the monitoring application into the mobile phone through a network;
an authorization module: and the monitoring application is authorized by the mobile phone and is allowed to be installed, and then the monitoring application is installed on the mobile phone.
Preferably, the data acquisition module comprises:
a recording processing module: recording a game video by the mobile phone, and framing the recorded game video into pictures according to two pictures per second;
a classification processing module: classifying the framed pictures into picture sets according to the progress of the game;
a parameter setting module: setting training parameters for each type of picture set to form picture data, wherein the training parameters at least comprise time thresholds;
a network uploading module: and uploading the picture data to a training server through the monitoring application.
Preferably, the data training module comprises:
presetting a module: the training server at least comprises a pre-training model;
a judging module: the training server receives the picture data and judges the number of pictures in each picture set;
an augmentation module: randomly selecting one picture set with the largest number of pictures, and increasing the selected pictures to other picture sets to ensure that the number of the pictures in each picture set is equal;
splitting the module: the images in each image set after the amplification are divided into a training set, a verification set and a test set according to the ratio of 20:1: 1;
an adjusting module: each picture set format is converted into a pre-training data format;
a selecting module: the training scripts are started in parallel, different pre-training models are used for training the format-converted picture set to obtain different training models, and the optimal models are selected after each training model is compared;
a generation module: generating training parameters and model information into a configuration file;
a storage module: and sending the configuration file and the optimal model to a file updating server for storage.
Preferably, the monitoring module comprises:
an update module: downloading configuration files and optimal models by a monitoring application;
an intercepting module: the game or the monitoring application runs in parallel, and the monitoring application intercepts the screen picture of the mobile phone after a time threshold;
a reminding module: the optimal model carries out scene recognition on the intercepted mobile phone screen picture, and when a game scene is switched or the game state is changed, the monitoring application generates state change information.
After the technical scheme is adopted, compared with the prior art, the invention has the beneficial effects that: the customized mobile game state monitoring is automatically formulated, and the picture data is randomly augmented by optimizing the picture data, so that the training is more stable, and the training effect is better; by setting a plurality of pre-training models, the optimal model can be obtained more easily, the model and the configuration file can be automatically formed according to the picture data without manual intervention, and the application can record videos by monitoring games according to the needs of users and then monitor the videos.
Drawings
FIG. 1 is a flow chart of a method and a system for monitoring a game status of a mobile phone according to the present invention;
FIG. 2 is a schematic diagram of a method and system for monitoring a game state of a mobile phone according to the present invention;
fig. 3 is a schematic diagram of a mobile phone end flow of a method and a system for monitoring a game state of a mobile phone according to the present invention.
Detailed Description
The advantages of the invention are further illustrated in the following description of specific embodiments in conjunction with the accompanying drawings.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
Referring to fig. 1, the present embodiment provides a method for monitoring a game status of a mobile phone, including the following steps:
s1: the monitoring application is installed in the mobile phone. When the mobile phone is provided with the monitoring application, the next step is directly carried out, if the monitoring application is not available in the mobile phone, the monitoring application is downloaded through the network and then carried out, and the monitoring application is mainly used for data transmission and real-time monitoring.
S2: when the mobile phone opens the game to run, the mobile phone records the video when the game is run, the recorded game video is processed to obtain picture data, and the picture data is uploaded to a training server for training through a monitoring application.
S3: at least one pre-training model is arranged in a training server, after the training server receives the processed picture data in the steps, the picture data are trained through the pre-training models, the same picture data are trained through different pre-training models to obtain different training models, then the training models trained by the same picture data through different pre-training models are compared to obtain an optimal model, and then the optimal model obtained after comparison is sent to a file updating server by the training server to be stored and to wait for downloading.
S4: the monitoring application is installed on the mobile phone, so when an optimal model is formed after training is completed, the monitoring application downloads the optimal model in the storage and file updating server through the network, when the mobile phone runs a game or the monitoring application, the monitoring application intercepts a mobile phone screen picture and performs scene recognition on the intercepted mobile phone screen picture through the downloaded optimal model, when the result of the optimal model recognition is scene switching or game state change, the monitoring application generates state change information and displays the state change information through the mobile phone, and a user can visually watch a display result through the mobile phone screen.
It should be noted that the monitoring application is manually stopped by the user or the monitoring application is stopped when the game is ended.
Referring to the foregoing embodiment, the present embodiment provides the specific steps of the step S1, including:
s101: if the mobile phone is internally used for downloading the monitoring application, the monitoring application is downloaded into the mobile phone through the network;
s102: the downloaded monitoring application is authorized and then installed on the mobile phone through the mobile phone, so that the mobile phone can directly read the mobile phone file.
Referring to the foregoing embodiment, the present embodiment provides the specific steps of the step S2, including:
s201: after a game is started by the mobile phone, recording a game video during game running through the mobile phone, and framing the recorded game video into pictures according to two pictures per second through a framing tool;
s202: framing the game video into pictures by a framing tool, and then classifying the pictures into a picture set according to the progress of the game; the classification may include: starting a game interface picture set, loading a game interface picture set, a hall game interface picture set, a game running interface picture set, a game settlement interface picture set, a game ending interface picture set and the like.
S203: setting training parameters for each classified picture set to form picture data; the training parameters include the area to be identified for each picture, the name of the game, the interval time threshold between each screen capture, and the like.
S204: and uploading the picture data with the set training parameters to a training server through a monitoring application and a network.
It should be noted that, when the training parameters are set, specifically, whether the whole picture needs to be identified or not is set, or a certain area in the picture may be selected for identification, and meanwhile, information such as an abbreviation or a full name of the game, a package name of the game, and the like is filled in for subsequent judgment when the monitoring application runs.
Referring to the foregoing embodiment, the present embodiment provides the specific steps of the step S3, including:
s301: at least one pre-training model is arranged in a training server, and different pre-training models can be obtained after training pictures in each picture set;
s302: the training server firstly judges the number of the received picture sets, judges whether the number of the pictures in each picture set is equal or not, and directly runs the step 304 if the number of the pictures is equal, and carries out the next step if the number of the pictures is not equal.
S303: and judging that the pictures in each picture set are not equal, judging the picture set with the largest number of pictures, randomly selecting the pictures in the picture set, and increasing the randomly selected pictures to the picture sets with the number of the other pictures smaller than that of the picture set, and running the next step until the number of the pictures in each picture set is equal.
S304: when the number of the pictures in each picture set is equal, dividing each picture set into three sets according to the ratio of 20:1:1, wherein the three sets comprise a training set, a verification set and a test set;
s305: uniformly converting the format of each classified picture set to ensure that the data formats of the picture sets are the same, thereby accelerating the precision and progress of training in the subsequent training;
s306: after the format is adjusted in step S305, three training scripts are started in parallel, a training set, a verification set, and a test set are trained at the same time, each picture set needs to be trained by a different pre-training model, then different training models are obtained after training by different pre-training models, then the training server compares all obtained training models, and an optimal model is selected after comparison;
s307: generating the set training parameters and the information of the model into configuration files, and packaging the formats of the configuration files into a ZIP format;
s308: and sending the ZIP format of the configuration file generated in the step S307 and the optimal model selected in the step S306 after comparison to a file updating server for storing and waiting for downloading of the user.
With reference to the foregoing embodiments, the present embodiment provides the specific steps of step S4, including:
s401: the configuration file and the optimal model are downloaded through a monitoring application installed on the mobile phone by using a network, and a user can open the configuration file and check whether the training parameters set by the user are matched with the information of the model;
s402: simultaneously running the game and the monitoring application, and intercepting the mobile phone screen picture once after each time threshold value by the monitoring application;
s403: after the monitoring application intercepts the mobile phone picture, scene identification is carried out through the downloaded optimal model, and when the identification result is scene switching or the game state changes, the monitoring application generates change information.
The invention also includes a monitoring system for the game state of the mobile phone, which comprises:
installing a module: the mobile phone monitoring system is used for installing the monitoring application on the mobile phone, and when the monitoring application is already on the mobile phone, the monitoring application is not downloaded;
a data acquisition module: the mobile phone game system is used for recording mobile phone game videos when a mobile phone runs games, processing the recorded game videos into picture data and uploading the picture data to a training server through the monitoring application;
a data training module: training picture data by a pre-training model in a training server, selecting an optimal model, and sending the optimal model to a file updating server for storage;
a monitoring module: the monitoring application downloads the optimal model stored in the file updating server through the network, when the mobile phone runs a game or the monitoring application, the monitoring application intercepts the mobile phone screen picture and performs scene recognition by the optimal model, and when the scene switching or the game state change is recognized, the monitoring application generates state change information and displays the state change information through the mobile phone.
The installation module includes:
a downloading module: downloading the monitoring application into the mobile phone through a network;
an authorization module: and the monitoring application is authorized by the mobile phone and is allowed to be installed, and then the monitoring application is installed on the mobile phone.
The data acquisition module comprises:
a recording processing module: recording a game video by the mobile phone, and framing the recorded game video into pictures according to two pictures per second;
a classification processing module: classifying the framed pictures into picture sets according to the progress of the game;
a parameter setting module: setting training parameters for each type of picture set to form picture data, wherein the training parameters at least comprise time thresholds;
a network uploading module: and uploading the picture data to a training server through the monitoring application.
The data training module comprises:
presetting a module: the training server at least comprises a pre-training model;
a judging module: the training server receives the picture data and judges the number of pictures in each picture set;
an augmentation module: randomly selecting one picture set with the largest number of pictures, and increasing the selected pictures to other picture sets to ensure that the number of the pictures in each picture set is equal;
splitting the module: the images in each image set after the amplification are divided into a training set, a verification set and a test set according to the ratio of 20:1: 1;
an adjusting module: each picture set format is converted into a pre-training data format;
a selecting module: the training scripts are started in parallel, different pre-training models are used for training the format-converted picture set to obtain different training models, and the optimal models are selected after each training model is compared;
a generation module: generating training parameters and model information into a configuration file;
a storage module: and sending the configuration file and the optimal model to a file updating server for storage.
The monitoring module includes:
an update module: downloading configuration files and optimal models by a monitoring application;
an intercepting module: the game or the monitoring application runs in parallel, and the monitoring application intercepts the screen picture of the mobile phone after a time threshold;
a reminding module: the optimal model carries out scene recognition on the intercepted mobile phone screen picture, and when a game scene is switched or a game state is changed, the monitoring application generates state change information.
In summary, referring to fig. 3, the embodiment provided by the foregoing embodiment is specifically implemented by installing a monitoring application, recording a video of a game running by a mobile phone when the mobile phone runs the game, then framing the recorded game video according to two pictures per second to obtain pictures, classifying the obtained pictures according to a running process of the game, setting training parameters for the pictures in each classification after classification, training by a training server to obtain an optimal model, downloading the optimal model into the monitoring application, capturing the pictures when the mobile phone plays the game by the monitoring application, recognizing scenes of the captured pictures by the optimal model, and determining a game process, a scene and a state at that time after recognition.
Referring to fig. 2, the invention mainly includes two parts, one part is a user side, the other part is a server side, the user side needs to collect data of a game requiring a game state to be identified, and uploads data from a mobile phone to a chemical training server, the training server performs model training according to training parameters of a user after receiving a new training request of the user, uploads an obtained model to a file updating server, the file updating server stores the received model and waits for downloading of the user, the user mobile phone side plays the game after opening a monitoring application, the monitoring application downloads a corresponding model from the file updating server according to a game and a user ID, and the game is identified and monitored after loading.
The smart terminal may be implemented in various forms. For example, the terminal described in the present invention may include an intelligent terminal such as a mobile phone, a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, etc., and a fixed terminal such as a digital TV, a desktop computer, etc. In the following, it is assumed that the terminal is a smart terminal. However, it will be understood by those skilled in the art that the configuration according to the embodiment of the present invention can be applied to a fixed type terminal in addition to elements particularly used for moving purposes.
It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.
Claims (10)
1. A method for monitoring the game state of a mobile phone is characterized by comprising the following steps:
s1: a monitoring application is installed in the mobile phone;
s2: the mobile phone runs games, records game videos, processes the recorded game videos into picture data, and uploads the picture data to a training server through the monitoring application;
s3: the training server is provided with at least one pre-training model, training the received picture data through the pre-training model to form an optimal model, and sending the optimal model to the file updating server for storage;
s4: the monitoring application downloads the optimal model stored in the file updating server through a network, when a mobile phone runs a game or the monitoring application, the monitoring application intercepts a mobile phone screen picture, carries out scene recognition on the screen picture by the optimal model, and generates state change information and displays the state change information through the mobile phone when the recognition result is scene switching or game state change.
2. The monitoring method according to claim 1, wherein the step S1 specifically includes:
s101: downloading the monitoring application into the mobile phone through a network;
s102: and the downloaded monitoring application is installed on the mobile phone after being authorized.
3. The monitoring method according to claim 1, wherein the step S2 specifically includes:
s201: recording a game video through a mobile phone, and framing the recorded game video into pictures according to two pictures per second;
s202: classifying the framed pictures into picture sets according to the progress of the game;
s203: setting training parameters for each type of picture set to form picture data, wherein the training parameters at least comprise time thresholds;
s204: uploading the picture data to the training server through a network by the monitoring application.
4. The monitoring method according to claim 1, wherein the step S3 specifically includes:
s301: at least one pre-training model is set in the training server;
s302: the training server receives the picture data and then judges the quantity of each picture set;
s303: randomly selecting one picture set with the largest number of pictures, and expanding the selected pictures to other picture sets to ensure that the number of the pictures in each picture set is equal;
s304: dividing the pictures in each picture set after the amplification into a training set, a verification set and a test set according to the ratio of 20:1: 1;
s305: converting each picture set into a pre-trained data format;
s306: starting training scripts in parallel, training the picture set in the step S305 by using different pre-training models to obtain different training models, comparing each training model, and selecting an optimal model;
s307: generating the set training parameters and the information of the model into a configuration file;
s308: and sending the configuration file generated in the step S307 and the optimal model compared in the step S306 to a file updating server for storage.
5. The monitoring method according to claim 1, wherein the step S4 specifically includes:
s401: downloading the configuration file and the optimal model through a monitoring application installed on a mobile phone;
s402: running games or monitoring applications in parallel, and intercepting mobile phone screen pictures after the monitoring applications are subjected to threshold values every time;
s403: the optimal model carries out scene recognition on the intercepted mobile phone screen picture, and when a game scene is switched or a game state is changed, the monitoring application generates state change information.
6. A system for monitoring game status of a mobile phone, the system comprising:
installing a module: the mobile phone is used for installing the monitoring application on the mobile phone;
a data acquisition module: the mobile phone game system is used for recording mobile phone game videos when a mobile phone runs games, processing the recorded game videos into picture data and uploading the picture data to a training server through the monitoring application;
a data training module: training picture data by a pre-training model in a training server, selecting an optimal model, and sending the optimal model to a file updating server for storage;
a monitoring module: the monitoring application downloads the optimal model stored in the file updating server through the network, when the mobile phone runs a game or the monitoring application, the monitoring application intercepts the mobile phone screen picture and performs scene recognition by the optimal model, and when the scene switching or the game state change is recognized, the monitoring application generates state change information and displays the state change information through the mobile phone.
7. The monitoring system of claim 6, wherein the mounting module comprises:
a downloading module: downloading the monitoring application into the mobile phone through a network;
an authorization module: and the monitoring application is authorized by the mobile phone and is allowed to be installed, and then the monitoring application is installed on the mobile phone.
8. The monitoring system of claim 6, wherein the data acquisition module comprises:
a recording processing module: recording a game video by the mobile phone, and framing the recorded game video into pictures according to two pictures per second;
a classification processing module: classifying the framed pictures into picture sets according to the progress of the game;
a parameter setting module: setting training parameters for each type of picture set to form picture data, wherein the training parameters at least comprise time thresholds;
a network uploading module: and uploading the picture data to a training server through the monitoring application.
9. The monitoring system of claim 6, wherein the data training module comprises:
presetting a module: the training server at least comprises a pre-training model;
a judging module: the training server receives the picture data and judges the number of pictures in each picture set;
an augmentation module: randomly selecting one picture set with the largest number of pictures, and increasing the selected pictures to other picture sets to ensure that the number of the pictures in each picture set is equal;
splitting the module: the images in each image set after the amplification are divided into a training set, a verification set and a test set according to the ratio of 20:1: 1;
an adjusting module: each picture set format is converted into a pre-training data format;
a selecting module: the training scripts are started in parallel, different pre-training models are used for training the format-converted picture set to obtain different training models, and the optimal models are selected after each training model is compared;
a generation module: generating training parameters and model information into a configuration file;
a storage module: and sending the configuration file and the optimal model to a file updating server for storage.
10. The monitoring system of claim 6, wherein the monitoring module comprises:
an update module: downloading configuration files and optimal models by a monitoring application;
an intercepting module: the game or the monitoring application runs in parallel, and the monitoring application intercepts the screen picture of the mobile phone after a time threshold;
a reminding module: the optimal model carries out scene recognition on the intercepted mobile phone screen picture, and when a game scene is switched or a game state is changed, the monitoring application generates state change information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098974.4A CN113806174A (en) | 2021-09-18 | 2021-09-18 | Method and system for monitoring game state of mobile phone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098974.4A CN113806174A (en) | 2021-09-18 | 2021-09-18 | Method and system for monitoring game state of mobile phone |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113806174A true CN113806174A (en) | 2021-12-17 |
Family
ID=78939648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111098974.4A Pending CN113806174A (en) | 2021-09-18 | 2021-09-18 | Method and system for monitoring game state of mobile phone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113806174A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100255906A1 (en) * | 2009-04-03 | 2010-10-07 | Academia Sinica | Graphical representation of gaming experience |
| CN109189648A (en) * | 2018-07-26 | 2019-01-11 | 深圳市沃特沃德股份有限公司 | Game monitor method and device |
| CN110337005A (en) * | 2019-07-09 | 2019-10-15 | 南京雷鲨信息科技有限公司 | Record screen method, system, intelligent terminal and the computer readable storage medium of intelligent terminal |
| CN111723673A (en) * | 2020-05-25 | 2020-09-29 | 西安交通大学 | Intelligent high-speed rail people counting method based on computer vision |
| CN112348089A (en) * | 2020-11-10 | 2021-02-09 | 中南民族大学 | Working state identification method, server, storage medium and device |
| CN112784269A (en) * | 2021-01-15 | 2021-05-11 | 鹏城实验室 | Malicious software detection method and device and computer storage medium |
-
2021
- 2021-09-18 CN CN202111098974.4A patent/CN113806174A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100255906A1 (en) * | 2009-04-03 | 2010-10-07 | Academia Sinica | Graphical representation of gaming experience |
| CN109189648A (en) * | 2018-07-26 | 2019-01-11 | 深圳市沃特沃德股份有限公司 | Game monitor method and device |
| CN110337005A (en) * | 2019-07-09 | 2019-10-15 | 南京雷鲨信息科技有限公司 | Record screen method, system, intelligent terminal and the computer readable storage medium of intelligent terminal |
| CN111723673A (en) * | 2020-05-25 | 2020-09-29 | 西安交通大学 | Intelligent high-speed rail people counting method based on computer vision |
| CN112348089A (en) * | 2020-11-10 | 2021-02-09 | 中南民族大学 | Working state identification method, server, storage medium and device |
| CN112784269A (en) * | 2021-01-15 | 2021-05-11 | 鹏城实验室 | Malicious software detection method and device and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107229402B (en) | Dynamic screen capturing method and device of terminal and readable storage medium | |
| EP3937073A1 (en) | Method for video classification, method and device for model training, and storage medium | |
| CN106791958B (en) | Position mark information generation method and device | |
| US20150281710A1 (en) | Distributed video processing in a cloud environment | |
| EP3040878A1 (en) | Information processing device and information processing method | |
| US9141190B2 (en) | Information processing apparatus and information processing system | |
| CN104811756B (en) | Display device and and its control method | |
| CN112188267B (en) | Video playing method, device and equipment and computer storage medium | |
| US20190342428A1 (en) | Content evaluator | |
| CN105847413A (en) | Camera parameter processing method, apparatus and system, and server | |
| US10531051B2 (en) | Method and apparatus for managing provisioning of an imaging system | |
| CN102905102A (en) | Screen capturing video player and screen capturing method | |
| CN115396705A (en) | Screen projection operation verification method, platform and system | |
| CA3102425C (en) | Video processing method, device, terminal and storage medium | |
| CN106326328B (en) | Picture transmitter device, image sending method and recording medium | |
| CN113806174A (en) | Method and system for monitoring game state of mobile phone | |
| CN111667602A (en) | Image sharing method and system for automobile data recorder | |
| CN110913279B (en) | Processing method for augmented reality and augmented reality terminal | |
| CN111274449A (en) | Video playing method and device, electronic equipment and storage medium | |
| CN111698444B (en) | Classroom-oriented data processing method, device, terminal and system | |
| US8824854B2 (en) | Method and arrangement for transferring multimedia data | |
| CN107818469A (en) | Data processing method, device and computer-readable recording medium | |
| CN113938707A (en) | Video processing method, recording and playing box and computer readable storage medium | |
| KR101093492B1 (en) | User Creative Contents Edit and Service Method | |
| CN106257461B (en) | Data storage method and device |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230310 Address after: 518055 1501, Building 1, Chongwen Park, Nanshan Zhiyuan, No. 3370, Liuxian Avenue, Fuguang Community, Taoyuan Street, Nanshan District, Shenzhen, Guangdong Province Applicant after: Shenzhen Grey Shark Technology Co.,Ltd. Address before: 210022 Room 601, block a, Chuangzhi building, 17 Xinghuo Road, Jiangbei new district, Nanjing City, Jiangsu Province Applicant before: Nanjing Thunder Shark Information Technology Co.,Ltd. |