CN106815451A - A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model - Google Patents
A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model Download PDFInfo
- Publication number
- CN106815451A CN106815451A CN201510836491.8A CN201510836491A CN106815451A CN 106815451 A CN106815451 A CN 106815451A CN 201510836491 A CN201510836491 A CN 201510836491A CN 106815451 A CN106815451 A CN 106815451A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior
- based control
- control characteristic
- characteristic model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of anti-external hanging of online game system of Behavior-based control characteristic model, the system is from game server end and client while evidence of fetching, result after analysis according to circumstances can be fed back to analyzer tuning by the data that will be obtained by exporting desired result after pretreatment, feature extraction, analysis, classification during analysis.The anti-external hanging of online game system of Behavior-based control characteristic model of the present invention only needs to operation team and carries out the definition and configuration of plug-in behavioural characteristic, you can all of doubtful plug-in in rapid positioning game, and is closed.
Description
Technical field
The present invention relates to a kind of anti-external store system, specifically a kind of anti-external hanging of online game system of Behavior-based control characteristic model.
Background technology
By the high speed development of 10 years, client network game comes into the relative growth rate for developing a slower stage, it is more and more weaker that the cake of client network game is cooked big trend again, each online game manufacturer need to do is to become more meticulous share of the service of itself in the existing cake more than point amount of exhausting, this required online game for service that player provides be more refine, it is exquisiter, more targeted.The lean operation requirement of online game is also required to provide the service for becoming more meticulous for the anti-plug-in technology that online game security balance operation escorts.And the traditional anti-plug-in technology detected with client Initiative Defense combination real-time online, it is still and is free on the traditional safe practice outside game content and solves game security issues with a kind of.Because the type of different game is different, feature is also different, therefore plug-in behavioural characteristic is also different, existing technology is caused not possess specific aim at the plug-in aspect of strike, anti- plug-in solution and game feature combination defective tightness, therefore prior art no longer adapts to the requirement that game becomes more meticulous to plug-in strike, also cannot ground exquisite effectively support for game operation is provided.
The content of the invention
It is an object of the invention to provide a kind of anti-external hanging of online game system of Behavior-based control characteristic model, to solve the problems, such as to be proposed in above-mentioned background technology.
To achieve the above object, the present invention provides following technical scheme:
A kind of anti-external hanging of online game system of Behavior-based control characteristic model, the system is from game server end and client while evidence of fetching, result after analysis according to circumstances can be fed back to analyzer tuning by the data that will be obtained by exporting desired result after pretreatment, feature extraction, analysis, classification during analysis.
As further scheme of the invention:The feature extraction includes:A. packaging group method filters class method for maximum variance with class method, packaging group method is filtered to cluster;B. dimension reduction method:Principal Component Analysis, Laplacian Eigenmaps and Locally linear embedding;C. unsupervised multi-cluster Feature Selection:The embedded cluster analysis of spectrum, study sparse coefficient and Feature Selection;D. unsupervised Feature Selection PCA:Choose and two benches CSSP subspace;
The algorithm of the classification is as follows:Decision tree:ID3 algorithms, calculate entropy Entropy (s)=- p+log2p+-p-log2p-;Calculate income:Wherein, V (A) is the codomain of attribute A, and S is sample set, SvIt is that value is equal to the sample set of V on attribute A in S;Classified according to Gain (S, A);
Bayes's classification:A given envelope mail, determines whether spam;
Svm classifier:Choose ωTX+b=0, choosing method is spaced using geometry, further according to hyperplane ωTX+b classifies.
As further scheme of the invention:Result after the analysis includes:A) whether the user is normal game player;B) if not normal game player, which the user played and aid in software or the user have opened how many client using;C) if the user is not normal game player, this pair user takes that following which kind of mode is punished:Close a period of time;Beat strange, activity, task income halve/without income;Do not punish;Prohibit speech.
As further scheme of the invention:The data include the data pushed after the data of game server active record and system client fixed point module record.
As further scheme of the invention:The type of the data includes User Status and user behavior.
As further scheme of the invention:The pretreatment is comprised the following steps:Successively data include with data summarization, data scrubbing, data integration, data conversion, wherein data rule operation, data summarization, will data acquisition module convergence to together;Wherein data scrubbing, i.e., by filling in vacancy value, isolated point is deleted in smooth noise data, identification, and solves the inconsistent purpose to clear up data to reach standardized format, abnormal data removing, error correcting, the removing of repeated data.
As further scheme of the invention:The treatment strategy of the vacancy value include ignoring tuple, it is artificial fill in vacancy value, using fixed value, use attribute average value and use most possible value.
As further scheme of the invention:The strategy of smooth noise data is smooth by case average value, and this needs to make branch mailbox before this and processes, the data for having same number in the different case of the depth representing of case;The interval of the width means of case each bin values is a constant.
As further scheme of the invention:Recognize that the strategy for deleting isolated point is:First pass through the methods such as cluster and find out isolated point, the information that these isolated points may include, artificial review these isolated points.
Compared with prior art, the beneficial effects of the invention are as follows:It is not rapid enough for the plug-in treatment for newly going out, because the condition code for obtain plug-in program, finding plug-in program is extracted, writes detection program, is dealt into client scan, can just detect corresponding plug-in, and these steps are required for the time, therefore can not quickly be closed and be hit.It is of the invention then only need to run team and carry out the definition and configuration of plug-in behavioural characteristic, you can all of doubtful plug-in in rapid positioning game, and closed.
Brief description of the drawings
Fig. 1 is the structured flowchart of the anti-external hanging of online game system of Behavior-based control characteristic model;
Fig. 2 is the flow chart pre-processed in the anti-external hanging of online game system of Behavior-based control characteristic model.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made belongs to the scope of protection of the invention.
Refer to Fig. 1~2, in the embodiment of the present invention, a kind of anti-external hanging of online game system of Behavior-based control characteristic model, the system is from game server end and client while evidence of fetching, result after analysis according to circumstances can be fed back to analyzer tuning by the data that will be obtained by exporting desired result after pretreatment, feature extraction, analysis, classification during analysis.
The feature extraction includes:A. packaging group method filters class method for maximum variance with class method, packaging group method is filtered to cluster;B. dimension reduction method:Principal Component Analysis, Laplacian Eigenmaps and Locally linear embedding;C. unsupervised multi-cluster Feature Selection:The embedded cluster analysis of spectrum, study sparse coefficient and Feature Selection;D. unsupervised Feature Selection PCA:Choose and two benches CSSP subspace;
The algorithm of the classification is as follows:Decision tree:ID3 algorithms, calculate entropy Entropy (s)=- p+log2p+-p-log2p-:Calculate income:Wherein, V (A) is the codomain of attribute A, and S is sample set, SvIt is that value is equal to the sample set of V on attribute A in S;Classified according to Gain (S, A);
Bayes's classification:A given envelope mail, determines whether spam;
Svm classifier:Choose ωTX+b=0, choosing method is spaced using geometry, further according to hyperplane ωTX+b classifies.
Result after the analysis includes:A) whether the user is normal game player;B) if not normal game player, which the user played and aid in software or the user have opened how many client using;C) if the user is not normal game player, this pair user takes that following which kind of mode is punished:Close a period of time;Beat strange, activity, task income halve/without income;Do not punish;Prohibit speech.
The data include the data pushed after the data of game server active record and system client fixed point module record.
The type of the data includes User Status and user behavior.
The pretreatment is comprised the following steps:Successively data include with data summarization, data scrubbing, data integration, data conversion, wherein data rule operation, data summarization, will data acquisition module convergence to together;Wherein data scrubbing, i.e., by filling in vacancy value, isolated point is deleted in smooth noise data, identification, and solves the inconsistent purpose to clear up data to reach standardized format, abnormal data removing, error correcting, the removing of repeated data.
The treatment strategy of the vacancy value include ignoring tuple, it is artificial fill in vacancy value, using fixed value, use attribute average value and use most possible value.
The strategy of smooth noise data is smooth by case average value, and this needs to make branch mailbox before this and processes, the data for having same number in the different case of the depth representing of case;The interval of the width means of case each bin values is a constant.
Recognize that the strategy for deleting isolated point is:First pass through the methods such as cluster and find out isolated point, the information that these isolated points may include, artificial review these isolated points.
User Status includes:Blood volume and the upper limit, method force value and the upper limit, present level, current occupation, currently equip, supplement amount, gold coin number, yuanbao, good friend's quantity, pet ID, energy value, muscle power value with money.
User behavior:Map where recently, recently where copy, last sale ID lists, kill recently strange ID lists, kill for a period of time recently strange number, recently a period of time obtain gold coin number, nearest chat buddies ID, recently release technical ability ID, nearest hematopoietic status, mend blue state recently, be recently completed task ID, using stage property ID quantity, nearest store buy stage property ID recently.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, and without departing from the spirit or essential characteristics of the present invention, can in other specific forms realize the present invention.Therefore, no matter from the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is limited by appended claims rather than described above, it is intended that all changes fallen in the implication and scope of the equivalency of claim are included in the present invention.Any reference in claim should not be considered as the claim involved by limitation.
In addition, it should be understood that, although the present specification is described in terms of embodiments, but not each implementation method only includes an independent technical scheme, this narrating mode of specification is only for clarity, those skilled in the art should using specification an as entirety, technical scheme in each embodiment can also through appropriately combined, formed it will be appreciated by those skilled in the art that other embodiment.
Claims (9)
1. a kind of anti-external hanging of online game system of Behavior-based control characteristic model, it is characterised in that the system is from game services
Device end and client are fetched evidence simultaneously, and the data that will be obtained are desired by output after pretreatment, feature extraction, analysis, classification
Result, the result after analysis according to circumstances can be fed back into analyzer tuning during analysis.
2. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 1, it is characterised in that institute
Stating feature extraction includes:A. packaging group method and filtering class method, packaging group method is cluster, and filtering class method is most generous
Difference;B. dimension reduction method:Principal Component Analysis, Laplacian Eigenmaps and Locally linear
embedding;C. unsupervised multi-cluster Feature Selection:The embedded cluster analysis of spectrum, study sparse coefficient and Feature Selection;d.
Unsupervised Feature Selection PCA:Choose and two benches CSSP subspace;
The algorithm of the classification is as follows:Decision tree:ID3 algorithms, calculate entropy Entropy (s)=- p+log2p+-p-log2p-;
Calculate income: Wherein, V (A) is the codomain of attribute A,
S is sample set, SvIt is that value is equal to the sample set of V on attribute A in S;Classified according to Gain (S, A);
Bayes's classification:Prior distribution π (θ)+sample informationPosterior distrbutionp π (θ | χ), an envelope mail is given,
Determine whether spam;
Svm classifier:Choose ωTX+b=0, choosing method is spaced using geometry, further according to hyperplane ωTX+b classifies.
3. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 1, it is characterised in that institute
Stating the result after analysis includes:A) whether the user is normal game player;B) if not normal game player,
Which the user played and aid in software or the user have opened how many client using;C) if the user is not normal
Game player, this pair user takes that following which kind of mode is punished:Close a period of time;Strange, activity, task income is played to subtract
Half/without income;Do not punish;Prohibit speech.
4. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 1, it is characterised in that institute
State the data pushed after data and system client fixed point module record of the data including game server active record.
5. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 1, it is characterised in that institute
The type for stating data includes User Status and user behavior.
6. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 1, it is characterised in that institute
Pretreatment is stated to comprise the following steps:Successively data include data summarization, data scrubbing, data integration, data conversion,
Data rule is operated, wherein data summarization, will data acquisition module convergence to together;Wherein data scrubbing, i.e.,
By filling in vacancy value, isolated point is deleted in smooth noise data, identification, and solves inconsistent to clear up data to reach form
Standardization, abnormal data removing, error correcting, the purpose of the removing of repeated data.
7. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 6, it is characterised in that institute
State the treatment strategy of vacancy value include ignoring tuple, it is artificial fill in vacancy value, using fixed value, using attribute average value and make
With most possible value.
8. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 6, it is characterised in that flat
The strategy of sliding noise data is smooth by case average value, and this needs to make branch mailbox before this and processes, in the different case of the depth representing of case
There are the data of same number;The interval of the width means of case each bin values is a constant.
9. the anti-external hanging of online game system of Behavior-based control characteristic model according to claim 6, it is characterised in that know
Not Shan Chu the strategy of isolated point be:First pass through the methods such as cluster and find out isolated point, the information that these isolated points may include,
Artificial these isolated points of review.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510836491.8A CN106815451A (en) | 2015-11-27 | 2015-11-27 | A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510836491.8A CN106815451A (en) | 2015-11-27 | 2015-11-27 | A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106815451A true CN106815451A (en) | 2017-06-09 |
Family
ID=59101873
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510836491.8A Pending CN106815451A (en) | 2015-11-27 | 2015-11-27 | A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106815451A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108654091A (en) * | 2018-05-14 | 2018-10-16 | 网易(杭州)网络有限公司 | Method, medium, device and computing device for verification of practising fraud in game |
CN108875817A (en) * | 2018-06-06 | 2018-11-23 | 网易(杭州)网络有限公司 | Identify plug-in method and device, storage medium, electronic device |
CN109858549A (en) * | 2019-01-30 | 2019-06-07 | 腾讯科技(深圳)有限公司 | Training method, device and the medium of application identification and its identification model |
CN111265883A (en) * | 2019-12-24 | 2020-06-12 | 武汉勾勾互娱科技有限公司 | Anti-plug-in system and method for PC game |
CN111382329A (en) * | 2020-02-17 | 2020-07-07 | 山东外事职业大学 | Data mining method and system for big data analysis |
CN111744204A (en) * | 2020-06-18 | 2020-10-09 | 网易(杭州)网络有限公司 | Game plug-in detection method and device, computer storage medium and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101187959A (en) * | 2006-11-17 | 2008-05-28 | 中兴通讯股份有限公司 | Game cheat detection method based on decision tree |
CN102163251A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机系统有限公司 | Method and device for recognizing game cheating |
CN103825780A (en) * | 2014-02-26 | 2014-05-28 | 珠海市君天电子科技有限公司 | Tag-on program identification method, service and system |
-
2015
- 2015-11-27 CN CN201510836491.8A patent/CN106815451A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101187959A (en) * | 2006-11-17 | 2008-05-28 | 中兴通讯股份有限公司 | Game cheat detection method based on decision tree |
CN102163251A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机系统有限公司 | Method and device for recognizing game cheating |
CN103825780A (en) * | 2014-02-26 | 2014-05-28 | 珠海市君天电子科技有限公司 | Tag-on program identification method, service and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108654091A (en) * | 2018-05-14 | 2018-10-16 | 网易(杭州)网络有限公司 | Method, medium, device and computing device for verification of practising fraud in game |
CN108875817A (en) * | 2018-06-06 | 2018-11-23 | 网易(杭州)网络有限公司 | Identify plug-in method and device, storage medium, electronic device |
CN109858549A (en) * | 2019-01-30 | 2019-06-07 | 腾讯科技(深圳)有限公司 | Training method, device and the medium of application identification and its identification model |
CN111265883A (en) * | 2019-12-24 | 2020-06-12 | 武汉勾勾互娱科技有限公司 | Anti-plug-in system and method for PC game |
CN111382329A (en) * | 2020-02-17 | 2020-07-07 | 山东外事职业大学 | Data mining method and system for big data analysis |
CN111744204A (en) * | 2020-06-18 | 2020-10-09 | 网易(杭州)网络有限公司 | Game plug-in detection method and device, computer storage medium and electronic equipment |
CN111744204B (en) * | 2020-06-18 | 2024-02-02 | 网易(杭州)网络有限公司 | Game plug-in detection method and device, computer storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106815451A (en) | A kind of solution of the anti-external hanging of online game of Behavior-based control characteristic model | |
CN103678613B (en) | Method and device for calculating influence data | |
CN106934042B (en) | Knowledge graph representation system and implementation method thereof | |
CN105306475B (en) | A kind of network inbreak detection method based on Classification of Association Rules | |
Yoshizaki et al. | Modeling misidentification errors in capture–recapture studies using photographic identification of evolving marks | |
CN102495919B (en) | Extraction method for influence factors of carbon exchange of ecosystem and system | |
CN104967587B (en) | A kind of recognition methods of malice account and device | |
CN106296195A (en) | A kind of Risk Identification Method and device | |
CN108874927A (en) | Intrusion detection method based on hypergraph and random forest | |
CN105095238A (en) | Decision tree generation method used for detecting fraudulent trade | |
CN103607391B (en) | SQL injection attack detection method based on K-means | |
CN110084149A (en) | A kind of face verification method based on difficult sample four-tuple dynamic boundary loss function | |
CN104253863B (en) | A kind of TCP flow recombination method based on Hadoop platform and distributed treatment programming model | |
CN116957049B (en) | Unsupervised internal threat detection method based on countermeasure self-encoder | |
CN104933365B (en) | A kind of malicious code based on calling custom automates homologous decision method and system | |
CN111428151B (en) | False message identification method and device based on network acceleration | |
CN102123062B (en) | Network data anomaly detection method based on dendritic cell algorithm | |
CN117556369B (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
Gilmore | A comparison of antemortem tooth loss in human hunter‐gatherers and non‐human catarrhines: Implications for the identification of behavioral evolution in the human fossil record | |
CN103902894B (en) | Virus defense method and system based on user behavior differentiation | |
CN107766737A (en) | A kind of database audit method | |
CN110071884A (en) | A kind of Modulation Recognition of Communication Signal method based on improvement entropy cloud feature | |
CN109588781A (en) | A kind of device for helping smoker giving-up smoking and method based on machine learning | |
CN113127696A (en) | Method for improving accuracy of influence measurement based on behaviors | |
CN103020079B (en) | A kind of industrial data supplementation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170609 |
|
WD01 | Invention patent application deemed withdrawn after publication |