CN112870725A - Method for detecting electronic competitive false competition or cheating behavior and storage medium - Google Patents
Method for detecting electronic competitive false competition or cheating behavior and storage medium Download PDFInfo
- Publication number
- CN112870725A CN112870725A CN202110166458.4A CN202110166458A CN112870725A CN 112870725 A CN112870725 A CN 112870725A CN 202110166458 A CN202110166458 A CN 202110166458A CN 112870725 A CN112870725 A CN 112870725A
- Authority
- CN
- China
- Prior art keywords
- data
- competition
- game
- cheating
- baseline
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000002860 competitive effect Effects 0.000 title claims description 35
- 230000006399 behavior Effects 0.000 claims abstract description 46
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000014509 gene expression Effects 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/70—Game security or game management aspects
- A63F13/75—Enforcing rules, e.g. detecting foul play or generating lists of cheating players
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Abstract
The invention relates to the technical field of data processing, and discloses a method for detecting electronic competition fake games or cheating behaviors, which comprises the following steps: s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2; s2, setting different baseline indexes aiming at different game types, and entering the step S3; s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process; and S4, judging whether the data fluctuation occurs in two or more baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior. The electronic competition device aims to solve the problem that the false competition or cheating behavior of the existing electronic competition cannot be detected and judged.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for detecting electronic competition fake games or cheating behaviors and a storage medium.
Background
In the electric competition game, the essence of cheating or fake competition is that the absolute advantage in the game is achieved by means of technical means, or the personal strength is hidden, so that the opponent wins. For game development and agents, the environment of fair games can be greatly damaged, players can be lost, and economic losses are brought to developers and operators. The electronic contestants usually reveal sensitive information in advance and carry out on-site linkage by means of a technical mode and hiding personal strength so as to obtain benefits in the electronic contestants; the cheating means are various and numerous, and are often prohibited; the misoperation of the competitive players is sometimes difficult to observe and difficult to obtain evidence, and the competitive players can easily escape from the competition due to the failure of the competitive players.
Disclosure of Invention
The invention mainly aims to provide a method for detecting electronic competitive false matches or cheating behaviors and a storage medium, so as to solve the problem that the false matches or the cheating behaviors of the current electronic competitive matches cannot be detected and distinguished.
In order to achieve the above object, the present invention provides the following techniques:
a method for detecting electronic competitive false competition or cheating behavior comprises the following steps:
s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2;
s2, setting different baseline indexes aiming at different game types, and entering the step S3;
s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process;
and S4, judging whether the data fluctuation occurs in two or more baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior.
Further, the competitive game types include: shooting games, instant strategy games, and card games.
Further, in step S2 or S3, besides using the baseline indicator to see the fluctuation of the competition data of the players, the TrueSkill algorithm can be used to obtain the fighting force value of each team by combining the historical fighting performances of the electric competition players and the teams; predicting the match by using the fighting force value to obtain the probability of winning two teams; the winning rate is higher than fifty percent, but the competition is lost, the abnormal record is recorded, and the deep analysis competition is triggered.
Further, in step S1, in addition to the game play internal data index, the identification of off-board data abnormality characteristics is included.
Further, in step S1, in addition to the data index inside the game match, the method also includes acquiring the data characteristic of the game by means of image processing technology; image processing techniques include framing services and recognition processes.
Further, the offsite data includes physical characteristics, expressions, and behavior data of the competitive player.
Further, the selection of each time period in step S3 includes: before, during and after the competitive match.
Further, the off-site data also comprises the data of the disk mouth of the game which is opened out, and public sentiment data of microblogs and related communities.
Further, step S5 is included, if the index of the game match data deviates from the baseline, a warning is issued to notify the monitoring personnel.
A storage medium for detecting electronic competitive false matches or cheating behaviors stores executable instructions for causing a processor to execute the executable instructions to realize the method for detecting the electronic competitive false matches or the cheating behaviors.
Compared with the prior art, the invention can bring the following technical effects:
1. identifying abnormal behaviors of players or participants in the game to finish the discrimination of the fake match or the cheating behavior;
2. the method comprises the steps that players or participants change around a base line within a certain time range, and cheating in the game is detected by using the characteristic;
3. different baseline models are set for detection, and in order to improve the success rate of identification, auxiliary detection can be performed by means of historical data, public opinion data and off-site data.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention and to enable other features, objects and advantages of the invention to be more fully apparent. The drawings and their description illustrate the invention by way of example and are not intended to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method of electronic competition fraud or cheating action detection of the present invention;
FIG. 2 is a schematic diagram of an embodiment of detecting different baseline indicators of a method for detecting a fraud or cheating behavior in an electronic competition according to the present invention;
FIG. 3 is a schematic diagram of a technical framework of a method for detecting a fraud or cheating behavior in an electronic competition according to the present invention;
fig. 4 is a schematic diagram of an image processing technical framework of a method for detecting a cheating behavior or a competition in an electronic competition according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present invention, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "center", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Example 1
As shown in fig. 1, 2, 3 and 4, a method for detecting a fraud or cheating in an electronic competition, comprises the steps of:
s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2;
the electronic contest game types include: shooting games, instant strategy games, and card games.
One large characteristic of STG, RTS and CAG games is that the basic unit of play may be a single game play. This feature makes it a subject of many machine learning, neural network enthusiasts to extract large data, such as predicting the outcome of a game through huge historical combat data. In single-game battles, the gravity center of the games is biased to strategies and tactics, the requirement on simple mouse operation is obviously inferior to the grasp of the general view, and different baseline indexes need to be quantized aiming at different games. The various baseline performance metrics for the bidding program are selected from the following table.
In step S1, in addition to the baseline index of the data within the game match, the method further includes acquiring the baseline index of the game by means of image processing technology, wherein the image processing technology includes a frame drawing service and a recognition process. Frame extraction service: (1) externally sending out > RabbitMQ (1: game type-which game, 2: game url, 3: frame drawing frequency, 4: personalized transparent data)
(2) RabbitMQ guardian- > consumption MQ- > video frame extraction start, and temporarily stores the frame in local disk
(3) Sending an identification start message to the identification module
The identification process comprises the following steps: (1) RabbitMQ daemon- > consume identify begin MQ- > identify begin- > run the different game models described above- > result write Kafka.
(2) And the abnormal result and the data interface perform related information pushing for exposing and knowing abnormal information.
In step S1, in addition to the game play internal data baseline indicator, identification of off-board data anomaly characteristics is included.
Off-site data includes physical characteristics, expression and behavior data of the competitive player.
S2, setting different baseline indexes aiming at different game types, and entering the step S3;
s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process;
the athletes in the competitive race project are generally relatively stable in the corresponding index data, the base line of data training inspection in the field can be selected, the base line is used as reference to check the data in the race time in real time, huge fluctuation is found, and the race state of the athletes is judged to be abnormal if two indexes and more than 3 times of fluctuation occur. For example, in the hero alliance, the C-position may select the number of the previous 6 minutes of the complement of knifes, the skill hit rate, the first key equipment time, the equipment forming time, etc. as the examination baseline of the C-position player, find two indexes and the number of fluctuations more than 3 times, and then identify the state abnormality of the C-position player.
In step S2 or S3, besides using the baseline indicator to see the fluctuation of the competition data of the players, the TrueSkill algorithm can be used to obtain the fighting force value of each team by combining the historical fighting performances of the electric contestants and the teams; predicting the match by using the fighting force value to obtain the probability of winning two teams; the winning rate is higher than fifty percent, but the competition is lost, the abnormal record is recorded, and the deep analysis competition is triggered.
The selection of each time period in step S3 includes: before, during and after the competitive match.
And S4, judging whether the data fluctuation occurs in two or more baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior.
The off-site data also comprises local match score data issued by global mainstream lottery companies and public opinion data of microblogs and related communities.
Step S5 is further included, wherein if the index of the game play data deviates from the baseline, a warning is issued to notify the monitoring personnel.
A storage medium for detecting electronic competitive false matches or cheating behaviors stores executable instructions for causing a processor to execute the executable instructions to realize the method for detecting the electronic competitive false matches or the cheating behaviors.
Example 2
As shown in fig. 1, 2, 3 and 4, a method for detecting a fraud or cheating in an electronic competition, comprises the steps of:
s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2;
s2, setting different baseline indexes aiming at different game types, and entering the step S3;
s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process;
and S4, judging whether the data fluctuation occurs in two or more baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior.
The electronic contest game types include: shooting games, instant strategy games, and card games.
In step S2 or S3, besides using the baseline indicator to see the fluctuation of the competition data of the players, the TrueSkill algorithm can be used to obtain the fighting force value of each team by combining the historical fighting performances of the electric contestants and the teams; predicting the match by using the fighting force value to obtain the probability of winning two teams; the winning rate is higher than fifty percent, but the competition is lost, the abnormal record is recorded, and the deep analysis competition is triggered.
In step S1, in addition to the baseline index of the data within the game match, the method further includes acquiring the baseline index of the game by means of image processing technology, wherein the image processing technology includes a frame drawing service and a recognition process.
In step S1, in addition to the game play internal data baseline indicator, identification of off-board data anomaly characteristics is included. Off-site data includes physical characteristics, expression and behavior data of the competitive player.
The selection of each time period in step S3 includes: before, during and after the competitive match.
The off-site data also comprises the data of the game board opening of the local game, which is produced by the global lottery company, and the public opinion data of microblogs and related communities.
Monitoring the abnormal conditions of the disc opening plays an important role in identifying cheating. First choose to monitor data from the global mainstream gaming companies. Second, focus on data changes per family, (1) pre-race: whether the odds have large amplitude of change or not; (2) in the competition: deviation of actual odds from odds that should be present. Then the occurrence of either (1) or (2) marks the anomaly, triggering a warning.
Through the analysis of the historical cheating cases, some cheating cases are discussed in microblogs and related communities in the early stage and the later stage of the competition, and even some people provide chat record screenshots of the WeChat. Public sentiment monitoring is carried out on the microblogs and related communities, and the defects of match field data and dish data can be overcome. Key events such as community reporting, discussion of vacation, advance knowledge of competition results, and the like are focused on, and high-priority display or risk fusing weight increase is adopted on the system.
The specific judgment standard of public opinion monitoring is as follows: firstly: and carrying out secondary classification on the public opinion data, dividing the public opinion data into a match item and a non-match item, then scoring the keywords of the match item (1, 2 and 3 represent different sensitive grades), and when the density of the sensitive words with the scoring grade larger than 1 continuously occurs for 3 times, automatically identifying the system as risk early warning. In addition, different communities have different scoring weights, and depending on the quality and popularity of the communities, the higher the quality of the communities is, the higher the scoring weight is.
Besides the data in the field, the data outside the field can also well assist in identifying abnormal conditions of the match, and has good feedback abnormal characteristics. The off-site data mainly includes physical characteristics, expressions and behavior data of the competitive athletes. According to the psychology and ethology principle, when a person carries out something wrong with the back and the daily necessities, the body can show index characteristics, and when the person lies, the person can show some characteristics such as being like eyes lost, dare not to look directly at the opposite side, and the speaking is not fluent. The off-site data related to the player can better assist in verifying the identification result. Similar logic is also true for a sports player. The attention, facial expression tension and body index data (heart rate, respiration, respiratory frequency, temperature and pulse) of the athlete are respectively collected by means of an eye tracker, expression recognition and wearing equipment, and stable base lines of the athlete can be obtained after data are collected and accumulated for a period of time.
The core idea of a particular application is also baseline detection. During the game, the attention, facial expression tension and body index data of the players are collected in real time and are compared with the baseline data of the players, and if baseline deviation and average deviation occur, the abnormal index of the off-site data is defined, namely the index deviates from the baseline.
Step S5 is further included, wherein if the index of the game play data deviates from the baseline, a warning is issued to notify the monitoring personnel.
Active monitoring: real-time monitoring is carried out in the whole process, (1) if abnormal conditions such as abnormal pan entrance data and the like are found, for example, abnormal pan entrance fluctuation can not be explained by recent sports related factors and events, reports are carried out as soon as possible, and lottery reports are synchronously generated; (2) if the competition field performance of the electric competition athletes fluctuates, the competition data can be deeply analyzed, and a competition field performance report can be synchronously generated.
Passive monitoring: if a certain game is suspected of having a false play, a subsequent series of monitoring and analysis will be performed for that game and involving the club. The overall evidence collection can be carried out by combining with the public sentiment system.
Detection procedures and standards
01. Real-time monitoring of the performance of the electric competition athletes at the competition field:
tracking data in the field in real time, finding that indexes deviate from a base line, warning by a system, and then notifying an official;
tracking off-site data in real time, finding that indexes deviate from a baseline, warning by a system, and then notifying an official;
02. odds/disc mouth anomaly:
before the competition: whether the odds have large amplitude of change or not, 20%, the system will warn and then notify the authorities;
in the competition: deviation of actual odds from the odds to be held, if the deviation is too large, warning, and then notifying the authorities;
03. indirect evidence: the electronic contestants/practitioners and the lottery criminal organization have some associations and connections;
04. direct evidence: the method finds that the electronic contestants/practitioners and criminal institutions have practical cooperation, or receive evidence of a large amount of money and the like, or are directly reported by people and the like.
And (3) judging standard: if the two items are met, the cheating behavior can be judged to exist, and the system can synchronously output related reports so as to facilitate the related officials to carry out evidence obtaining treatment.
A storage medium for detecting electronic competitive false matches or cheating behaviors stores executable instructions for causing a processor to execute the executable instructions to realize the method for detecting the electronic competitive false matches or the cheating behaviors.
Example 3
Firstly, for different electronic competition games, the cheating modes of players are different, and the same electronic competition game also has a plurality of different cheating phenomena, so that it is difficult to use a machine learning model to analyze all electronic competition games in a general way, even different cheating modes and phenomena of the same game. Therefore, the machine learning model should be studied for a cheating phenomenon or a cheating manner of an electronic game, i.e. the cheating phenomenon or the cheating manner is combined with the electronic game as shown in fig. 3 to form a core technical framework diagram.
Secondly, for cheating phenomena or manners, the game behavior or game data of the player can show characteristics, which may be simple expressions of a certain data exceeding a threshold value, concussion and the like, or complex characteristics (such as shooting jitter behavior of a chicken game) needing to be analyzed from the game behavior expressions of the player. These somewhat complex features require the game developer to analyze the player's game behavior and extract appropriate data for reference in machine learning training. Therefore, in detail, the method of analyzing the data features and extracting the data is also important.
Finally, as with other machine learning applications, machine learning training validation also requires adjustments, which may be combined with game operating strategies, such as paying attention to precision or recall, and giving some feedback or putting a penalty on game cheating. Finally, a cheating identification process which can be continuously updated and advanced is obtained.
As shown in fig. 1, 2, 3 and 4, a method for detecting a fraud or cheating in an electronic competition, comprises the steps of:
s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2;
s2, setting different baseline indexes aiming at different game types, and entering the step S3;
s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process;
the data (KDA and the like) of different indexes corresponding to the game player are relatively stable, a base line exists, the base line is used as a reference, and if the indexes fluctuate greatly in the competition time, it can be determined that the game player has problems. By means of the characteristic, different baseline models can be set for detection, and in order to improve the success rate of recognition, auxiliary detection can be performed by means of historical data, public opinion data and off-site data.
And S4, judging whether the data fluctuation occurs in two or more baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior.
The electronic contest game types include: shooting games, instant strategy games, and card games.
In step S2 or S3, besides using the baseline indicator to see the fluctuation of the competition data of the players, the TrueSkill algorithm can be used to obtain the fighting force value of each team by combining the historical fighting performances of the electric contestants and the teams; predicting the competition by using the warfare value to obtain the probability of winning two teams; the winning rate is higher than fifty percent, but the competition is lost, the abnormal record is recorded, and the deep analysis competition is triggered.
In step S1, in addition to the baseline index of the data within the game match, the method further includes acquiring the baseline index of the game by means of image processing technology, wherein the image processing technology includes a frame drawing service and a recognition process.
In step S1, in addition to the game play internal data baseline indicator, identification of off-board data anomaly characteristics is included.
Off-site data includes physical characteristics, expression and behavior data of the competitive player.
The selection of each time period in step S3 includes: before, during and after the competitive match.
Baseline detection protection feature selection timeline:
prior (prevention, prediction): (1) historical competition prediction performance (2) updates a historical baseline (3) and pays attention to pre-competition lottery public sentiment;
in service (monitoring, blocking): in the process of a player match, detecting whether the data stream of the player is abnormal or not, marking field abnormality, and informing a service of fusing if the abnormal threshold is excessive;
after the fact (correction, recovery, tracing): and (4) offline scanning and checking, wherein offline model scans players in a full scale, and abnormal players in the running water are identified.
The off-site data also comprises local match score data issued by global mainstream lottery companies and public opinion data of microblogs and related communities.
Step S5 is further included, wherein if the index of the game play data deviates from the baseline, a warning is issued to notify the monitoring personnel.
A storage medium for detecting electronic competitive false matches or cheating behaviors stores executable instructions for causing a processor to execute the executable instructions to realize the method for detecting the electronic competitive false matches or the cheating behaviors.
Compared with the prior art, the invention can bring the following technical effects:
1. identifying abnormal behaviors of players or participants in the game to finish the discrimination of the fake match or the cheating behavior;
2. the method comprises the steps that players or participants change around a base line within a certain time range, and cheating in the game is detected by using the characteristic;
3. different baseline models are set for detection, and in order to improve the success rate of identification, auxiliary detection can be performed by means of historical data, public opinion data and off-site data.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for detecting electronic competitive false matches or cheating behaviors is characterized by comprising the following steps:
s1, analyzing the behaviors and data characteristics of the game role through historical competition game data, identifying the competition game type, and entering the step S2;
s2, setting different baseline indexes aiming at different game types, and entering the step S3;
s3, judging whether the competition state of the player is abnormal or not according to the fluctuation condition of the data of the baseline index in each time period of the electronic competition, if so, entering the step S4, and if so, ending the whole detection process;
and S4, judging whether the data fluctuation occurs in more than two baseline indexes, and judging whether the data fluctuation occurs in a fake match or in a cheating behavior.
2. A method for electronic competitive tournament or detection of cheating action according to claim 1, wherein the type of electronic tournament game comprises: shooting games, instant strategy games, and card games.
3. A method of electronic competitive tournament or cheating behavior detection according to claim 1 or 2, wherein in step S2 or S3, in addition to the fluctuation of competition data of players using the baseline index, the warfare value of each team is obtained using TrueSkill algorithm in combination with the historical performance of electric competitors and teams; predicting the competition by using the warfare value to obtain the probability of winning by two teams; the winning rate is higher than fifty percent, but the competition is lost, the abnormal record is recorded, and the deep analysis competition is triggered.
4. A method for detecting electronic competitive competitions or cheating actions according to claim 3, characterized in that, in step S1, it includes identification of abnormal characteristics of off-site data in addition to the baseline indicators of data inside the game match.
5. A method as claimed in claim 3, wherein the method further comprises obtaining the baseline indicator of the game by means of image processing technique, in addition to the baseline indicator of the data in the game match, the image processing technique including frame extraction service and identification process.
6. A method of electronic competitive competition or cheating behavior detection as claimed in claim 4, wherein the off-site data includes physical characteristics, expression and behavior data of the electronic contestant.
7. The method of claim 1, wherein the selection of the time periods in step S3 comprises: before, during and after the competitive match.
8. The method as claimed in claim 4 or 6, wherein the off-site data further comprises data of the opening of the local game, and public opinion data of microblogs and related communities.
9. The method of claim 8, further comprising step S5 of issuing a warning to notify a monitoring person if the index of the game play data deviates from the baseline.
10. A storage medium for electronic competitive competition or detection of cheating activities, wherein executable instructions are stored for causing a processor to execute the method for detecting electronic competitive competition or cheating activities of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166458.4A CN112870725A (en) | 2021-02-05 | 2021-02-05 | Method for detecting electronic competitive false competition or cheating behavior and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166458.4A CN112870725A (en) | 2021-02-05 | 2021-02-05 | Method for detecting electronic competitive false competition or cheating behavior and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112870725A true CN112870725A (en) | 2021-06-01 |
Family
ID=76057439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110166458.4A Pending CN112870725A (en) | 2021-02-05 | 2021-02-05 | Method for detecting electronic competitive false competition or cheating behavior and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112870725A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071456A (en) * | 2007-04-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Network game cheat monitoring method and system |
| CN103678841A (en) * | 2012-09-03 | 2014-03-26 | 人人游戏网络科技发展（上海）有限公司 | Monitoring alarm method and device for game |
| US20170287269A1 (en) * | 2011-11-10 | 2017-10-05 | Gamblit Gaming, Llc | Anti-cheating system |
| CN109886111A (en) * | 2019-01-17 | 2019-06-14 | 深圳壹账通智能科技有限公司 | Match monitoring method, device, computer equipment and storage medium based on micro- expression |
| CN110750636A (en) * | 2018-07-04 | 2020-02-04 | 百度在线网络技术（北京）有限公司 | Network public opinion information processing method and device |
| CN111558226A (en) * | 2020-04-28 | 2020-08-21 | 腾讯科技(成都)有限公司 | Method, device, equipment and storage medium for detecting abnormal operation behaviors |
| CN111773732A (en) * | 2020-09-04 | 2020-10-16 | 完美世界(北京)软件科技发展有限公司 | Target game user detection method, device and equipment |
| CN112107866A (en) * | 2020-09-28 | 2020-12-22 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, equipment and storage medium |
-
2021
- 2021-02-05 CN CN202110166458.4A patent/CN112870725A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071456A (en) * | 2007-04-29 | 2007-11-14 | 腾讯科技（深圳）有限公司 | Network game cheat monitoring method and system |
| US20170287269A1 (en) * | 2011-11-10 | 2017-10-05 | Gamblit Gaming, Llc | Anti-cheating system |
| CN103678841A (en) * | 2012-09-03 | 2014-03-26 | 人人游戏网络科技发展（上海）有限公司 | Monitoring alarm method and device for game |
| CN110750636A (en) * | 2018-07-04 | 2020-02-04 | 百度在线网络技术（北京）有限公司 | Network public opinion information processing method and device |
| CN109886111A (en) * | 2019-01-17 | 2019-06-14 | 深圳壹账通智能科技有限公司 | Match monitoring method, device, computer equipment and storage medium based on micro- expression |
| CN111558226A (en) * | 2020-04-28 | 2020-08-21 | 腾讯科技(成都)有限公司 | Method, device, equipment and storage medium for detecting abnormal operation behaviors |
| CN111773732A (en) * | 2020-09-04 | 2020-10-16 | 完美世界(北京)软件科技发展有限公司 | Target game user detection method, device and equipment |
| CN112107866A (en) * | 2020-09-28 | 2020-12-22 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Winter et al. | Tactical metrics that discriminate winning, drawing and losing teams in UEFA Euro 2012® | |
| Gòmez et al. | Game related statistics discriminating between starters and nonstarters players in Women’s National Basketball Association League (WNBA) | |
| Plessner et al. | Sports performance judgments from a social cognitive perspective | |
| AU2020201599A1 (en) | Collusion detection | |
| Thomson et al. | The development of a reliable amateur boxing performance analysis template | |
| CN107530585B (en) | Method, apparatus and server for determining cheating in dart game | |
| Pantzalis et al. | Sports analytics for football league table and player performance prediction | |
| Forrest et al. | Using statistics to detect match fixing in sport | |
| Andreff | An economic roadmap to the dark side of sport | |
| Almulla et al. | Machine learning models reveal key performance metrics of football players to win matches in qatar stars league | |
| Cotta et al. | Using fifa soccer video game data for soccer analytics | |
| Schumaker et al. | Sports knowledge management and data mining. | |
| CN107548318A (en) | System for managing indivedual performance challenges in simulated race | |
| Chazan-Pantzalis et al. | Sports Analytics for Football League Table and Player Performance Prediction | |
| CN112870725A (en) | Method for detecting electronic competitive false competition or cheating behavior and storage medium | |
| US20220222999A1 (en) | Real time action of interest notification system | |
| Chazan-Pantzalis | Sports Analytics Algorithms for Performance Prediction | |
| Russell | Sport as a legal system | |
| do Vale | Analysis of Video Assistant Referee (VAR) in football | |
| CN117271904B (en) | Game recommendation method and system based on big data | |
| Parmar et al. | Performance analysis in rugby | |
| Supola et al. | Modeling the extra pass in basketball–an assessment of one of the most crucial skills for creating great ball movement | |
| US20220405511A1 (en) | Method and apparatus for detecting tokens on game table, device, and storage medium | |
| Kihl et al. | Sport, Corruption, and Fraud | |
| Merolla et al. | Lotto, Blotto or Frontrunner: US presidential elections and the nature of ‘Mistakes’ |
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 |