CN108854075B - Method and device for detecting abnormal behaviors of game role - Google Patents
Method and device for detecting abnormal behaviors of game role Download PDFInfo
- Publication number
- CN108854075B CN108854075B CN201810538937.2A CN201810538937A CN108854075B CN 108854075 B CN108854075 B CN 108854075B CN 201810538937 A CN201810538937 A CN 201810538937A CN 108854075 B CN108854075 B CN 108854075B
- Authority
- CN
- China
- Prior art keywords
- consumption
- output
- correlation
- game
- output quantity
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/70—Game security or game management aspects
- A63F13/75—Enforcing rules, e.g. detecting foul play or generating lists of cheating players
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
- A63F2300/55—Details of game data or player data management
- A63F2300/5586—Details of game data or player data management for enforcing rights or rules, e.g. to prevent foul play
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for detecting abnormal behaviors of game roles. The game role abnormal behavior detection method comprises the steps of analyzing the correlation between the consumption of consumables of the full-service game role and the output quantity of actual output products, calculating the output quantity of theoretical output products corresponding to the consumption of the consumables of the current game role according to the correlation, and judging whether the output quantity of the actual output products accords with logic or not according to the output quantity of the actual output products and the output quantity of the theoretical output products, which are obtained by the current game role through the consumables. The method and the device for detecting the abnormal behavior of the game role check whether the current behavior of the game role is abnormal or not through the correlation between the consumption of consumables and the output of actual output products, can monitor whether a current game service has bypass loopholes or not, avoid lawbreakers from acquiring more benefits by utilizing the bypass loopholes, and save the strategy cost of manually maintaining a threshold value.
Description
Technical Field
The invention relates to the technical field of game data processing, in particular to a game role abnormal behavior detection method and a game role abnormal behavior detection device.
Background
Some "bypass type holes" may exist during game development, that is, players may illegally obtain items or tokens after bypassing server logic verification through special means (modifying memory, copying protocol, etc.), for example, tampering the number of items or tokens, etc., a threshold value is usually set for the output number of a type of item or token of each player for monitoring, and an alarm is triggered when the output number of the item or token of a player exceeds the threshold value.
However, game service versions are updated very frequently, each version threshold value generally needs to be updated correspondingly and iteratively, but the types of game props or tokens are generally very numerous, the workload of maintaining the threshold values is huge, the threshold values cannot be updated timely, and finally, the false alarm rate is very high.
Disclosure of Invention
The embodiment of the invention provides a game role abnormal behavior detection method and a game role abnormal behavior detection device.
The game role abnormal behavior detection method is used for detecting whether the output quantity of an actual output product obtained by consuming consumables of the game role accords with logic. The game role abnormal behavior detection method comprises the following steps:
analyzing the correlation between the consumption of the consumables of the full-service game role and the output quantity of the actual output;
calculating the theoretical output quantity corresponding to the consumption quantity of the consumables of the current game role according to the correlation; and
and judging whether the actual output quantity accords with logic or not according to the actual output quantity obtained by the current game role through the consumables and the theoretical output quantity.
The game role abnormal behavior detection device provided by the embodiment of the invention is used for detecting whether the output quantity of an actual output product obtained by consuming consumables of a game role accords with logic. The game role abnormal behavior detection device comprises an analysis module, a calculation module and a judgment module. The analysis module is used for analyzing the correlation between the consumption of the expendables of the full-length game role and the output quantity of the actual output. And the calculation module is used for calculating the theoretical output quantity corresponding to the consumption of the consumables of the current game role according to the correlation. The judging module is used for judging whether the actual output quantity accords with logic or not according to the actual output quantity obtained by the current game role through consumables and the theoretical output quantity.
The game role abnormal behavior detection method and the game role abnormal behavior detection device provided by the embodiment of the invention verify whether the current game role behavior is abnormal or not through the correlation between the consumption of consumables and the output quantity of actual output products, save the strategy cost of manually maintaining the threshold value, can be used for monitoring whether bypass loopholes exist in the current game business or not, and avoid lawbreakers from obtaining more benefits by utilizing the bypass loopholes.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the present invention.
Fig. 2 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the present invention.
Fig. 3 is a block diagram of an abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
Fig. 4 is a block diagram of an abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
Fig. 5 is a scene schematic diagram of a game character abnormal behavior detection method according to some embodiments of the present invention.
FIG. 6 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the present invention.
Fig. 7 is a block diagram of an analysis module of the abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
FIG. 8 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the present invention.
Fig. 9 is a block diagram of a first obtaining sub-module of the game character abnormal behavior detection apparatus according to some embodiments of the present invention.
FIG. 10 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 11 is a block diagram of a first obtaining submodule of the game character abnormal behavior detection apparatus according to some embodiments of the present invention.
Fig. 12 is a schematic view of a game log of a game character abnormal behavior detection method according to some embodiments of the present invention.
FIG. 13 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 14 is a block diagram of an analysis module of the abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
Fig. 15 is a schematic diagram of a fitting curve and a standard fitting curve of a game character abnormal behavior detection method according to some embodiments of the present invention.
FIG. 16 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 17 is a block diagram of an analysis module of the abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
FIG. 18 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 19 is a block diagram of a computing module of an abnormal behavior detection apparatus for a game character according to some embodiments of the present invention.
FIG. 20 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 21 is a block diagram of a computing module of an apparatus for detecting abnormal behavior of a game character according to some embodiments of the present invention.
Fig. 22 is a schematic view of a game log of a game character abnormal behavior detection method according to some embodiments of the present invention.
FIG. 23 is a flow chart illustrating a method for detecting abnormal behavior of a game character according to some embodiments of the invention.
Fig. 24 is a block diagram of an apparatus for detecting abnormal behavior of a game character according to some embodiments of the present invention.
FIG. 25 is a block diagram of a server in accordance with certain embodiments of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Referring to fig. 1, the method for detecting abnormal behavior of a game character according to the embodiment of the present invention is used to detect whether the output quantity of an actual output obtained by consuming consumables of the game character is logical. Wherein, the consumables and the products can be games and/or props. That is, the consumable may be only a prop, or the consumable may be only a token, or the consumable includes both a prop and a token; likewise, the output may be a prop alone, or the output may be a token alone, or the output includes both props and tokens. The game role abnormal behavior detection method comprises the following steps:
s1: analyzing the correlation between the consumption of the consumables of the full-service game role and the output quantity of the actual output;
s2: calculating the theoretical output quantity corresponding to the consumption of the consumables of the current game role according to the correlation;
s3: and judging whether the output quantity of the actual output product accords with the logic or not according to the output quantity of the actual output product and the output quantity of the theoretical output product, which are obtained by consuming consumables by the current game role.
Referring to fig. 2, step S3 includes:
s31: judging whether the actual output quantity obtained by consuming consumables by the current game role is less than or equal to the theoretical output quantity or not; and
s32: and determining that the actual output quantity obtained by consuming the consumables of the current game role accords with the logic when the actual output quantity is less than or equal to the theoretical output quantity.
Referring to fig. 3 and 4 together, the game character abnormal behavior detection method according to the embodiment of the present invention can be implemented by the game character abnormal behavior detection apparatus 10 according to the embodiment of the present invention. The game character abnormal behavior detection device 10 of the embodiment of the invention comprises an analysis module 11, a calculation module 12 and a judgment module 13. Step S1 may be implemented by the analysis module 11. Step S2 may be implemented by the calculation module 12. Step S3 may be implemented by the determination module 13. The determining module 13 further includes a determining submodule 131 and a determining submodule 132. Step S31 may be implemented by the determination sub-module 131. Step S32 may be implemented by the determination submodule 132.
That is, the analysis module 11 can be used to analyze the correlation between the consumption of consumables and the output of actual products of the game characters of the whole suit. The calculation module 12 can be used to calculate the theoretical output quantity corresponding to the consumption of the expendable supplies of the current game role according to the correlation. The judging module 13 can be used for judging whether the output quantity of the actual output product meets the logic according to the output quantity of the actual output product and the output quantity of the theoretical output product obtained by consuming the consumables by the current game role. The judgment sub-module 131 may be configured to judge whether the actual output yield amount obtained by consuming the consumable supplies by the current game character is less than or equal to the theoretical output yield amount, and the determination sub-module 132 may be configured to determine that the actual output yield amount obtained by consuming the consumable supplies by the current game character conforms to the logic when the actual output yield amount is less than or equal to the theoretical output yield amount.
Referring to FIG. 5, in particular, there are multiple types of items in a game, and a token in a game may consume multiple types of tokens or consume multiple other types of items. In the game character abnormal behavior detection method provided by the present invention, the correlation between the consumption of expendables and the output amount of actual outputs includes the correlation between the output amount of actual outputs of each kind of outputs (props and tokens) owned by all game characters in all servers 20 (shown in fig. 25) and the consumption of expendables of all kinds of expendables (props and tokens). For example, assuming that a property novice gift bag (i.e., an output) can be obtained by consuming three consumables of a point ticket, a gold coin, and a diamond in a mall, N game characters in all the servers 20 own the novice gift bag, and each game character has a new gift bagThe number of the hand gift bags is Y respectively 1 、Y 2 、Y 3 …Y n The number of consumables (including three types of coupons, coins and diamonds) consumed by each game role for obtaining the corresponding gift bag of the novice is X 1 、X 2 、X 3 …X n Then the analysis module 11 may be based on the data Y 1 、Y 2 、Y 3 …Y n And X 1 、X 2 、X 3 …X n To analyze the correlation between the output of the novice gift bag and the consumption of the consumables. That is, the analysis module 11 analyzes the average level of the correlation between the consumable consumption amount of the all-uniform game character and the actual output amount, rather than analyzing the correlation between the consumable consumption amount of a certain game character and the actual output amount. Furthermore, the correlation between the actual output quantity and the consumption of consumables for different kinds of outputs is different.
After determining the correlation between the actual output quantities of the various outputs and the corresponding consumption of the consumables, it is checked according to the correlation whether the actual output quantities of the game characters in all the servers 20 meet the logic. For example, when it is checked whether the actual output quantity of the current game character is logical, it is assumed that the current game character has P 1 、P 2 、P 3 …P m The actual output quantity of each output is Y t1 、Y t2 、Y t3 …Y tm Each output corresponding to a consumable consumption of X 1 、X 2 、X 3 …X m The correlation between the actual output quantity per output and the corresponding consumption of consumables is C 1 、C 2 、C 3 …C m Then the calculation module 12 may be based on C 1 、C 2 、C 3 …C m And X 1 、X 2 、X 3 …X m Calculating the product P in turn 1 、P 2 、P 3 …P m Theoretical output quantity Y c1 、Y c2 、Y c3 …Y cm 。
Subsequently, the determining module 13 can determine the position of the target according to Y t1 、Y t2 、Y t3 …Y tm Calculating the actual output quantity Y of all the outputs obtained by consuming consumables of the current game role t According to Y c1 、Y c2 、Y c3 …Y cm Calculating theoretical output quantity Y of all output obtained by consuming consumables by current game role c And further determining Y t And Y c Of (c) is used.
Finally, if the judgment result of the judgment sub-module 131 is Y t ≤Y c The determination sub-module 132 considers that the actual output amount of the current game character by consuming expendables corresponds to the logic, and further considers that there is no abnormality in the behavior of the current game character. If the judgment result of the judgment sub-module 131 is Y t >Y c The determination sub-module 132 considers that the actual output amount obtained by consuming expendables of the current game character does not conform to the logic, and further considers that there is an abnormality in the behavior of the current game character, and generates an alarm signal when there is an abnormality.
It will be appreciated that there may be a "bypass type vulnerability" in game services, i.e., some players may illegally obtain items and tokens after logic verification by bypassing the server 20 by special means such as modifying memory, copying protocols, etc. For example, in a "bypass type bug" generated in a game design link, a game character purchases a prop P to consume N tokens, but the game character can obtain N +1 tokens when selling the prop P, so that the game character can illegally obtain a large number of tokens by continuously purchasing and selling the prop P; as another example, a game character tampers with the amount of props or tokens by special means, and so forth. To address this problem, current solutions monitor the number of outcomes of a type of item and token for each player by setting a threshold value that triggers an alarm when the number of outcomes of the player's item and token exceeds the threshold value. However, since the game service versions are updated very frequently, the threshold value of each version usually needs to be updated iteratively correspondingly, but the game props and tokens are of various types, the workload of maintaining the threshold value is huge, the threshold value may not be updated in time, and finally the false alarm rate is very high.
The game role abnormal behavior detection method provided by the embodiment of the invention verifies whether the current game role behavior is abnormal or not through the correlation between the consumption of consumables and the output quantity of actual products, saves the strategy cost of manually maintaining the threshold value, can be used for monitoring whether the current game business has bypass type loopholes or not, and avoids lawbreakers from acquiring more benefits by utilizing the bypass type loopholes.
Referring to fig. 6, in some embodiments, the step S1 of analyzing the correlation between the consumption of consumables and the actual output of the game character comprises:
s11: acquiring a consumption-output data set of each output of the full-service game role;
s12: calculating a fitted curve for each consumption-production dataset from the consumption-production datasets; and
s13: correlation coefficients for the corresponding consumption-yield data sets are calculated from each consumption-yield data set, one correlation coefficient for each fitted curve.
Referring to fig. 7, in some embodiments, the analysis module 11 includes a first obtaining sub-module 111, a first calculating sub-module 112, and a second calculating sub-module 113. Step S11 may be implemented by the first obtaining sub-module 111, step S12 may be implemented by the first calculating sub-module 112, and step S13 may be implemented by the second calculating sub-module 113. That is, the first obtaining sub-module 111 may be configured to obtain the consumption-outcome data set for each outcome of the full-scale game character. The first calculation sub-module 112 may be operable to calculate, from each consumption-production data set, a fitted curve for the corresponding consumption-production data set. The second calculation sub-module 113 may be configured to calculate, from each consumption-production data set, a correlation coefficient for the corresponding consumption-production data set, one correlation coefficient for each fitted curve.
Referring to fig. 8, the step S11 of obtaining the consumption-output data set of each output of the game character includes:
s111: obtaining a game log of each game role;
s112: obtaining a consumption-output log pair of each output of each game role according to the game log; and
s113: and merging the multiple pairs of consumption-output log pairs corresponding to each output in the full-service game role into the consumption-output data set corresponding to the output.
Referring to fig. 9, the first obtaining submodule 111 includes a first obtaining unit 1111, a second obtaining unit 1112, and a merging unit 1113. Step S111 may be implemented by the first obtaining unit 1111. Step S112 may be implemented by the second acquisition unit 1112. Step S113 may be implemented by the merging unit 1113. That is, the first obtaining unit 1111 may be configured to obtain a game log of each game character. The second obtaining unit 1112 may be configured to obtain a consumption-yield log pair for each of the yields of each of the game characters from the game log. The merge unit 1113 may be configured to merge pairs of consumption-yield log pairs corresponding to each outcome in the full-featured game character into consumption-yield data sets corresponding to the outcomes.
Further, referring to fig. 10, the step S112 of obtaining consumption-yield log pairs for each of the yields of each of the game characters based on the game log includes:
s1121: forming consumption-output log pairs according to game logs of the same game role at the same time; and/or
S1122: consumption-production log pairs are formed from game logs at adjacent times for the same game character.
Referring to fig. 11, the second obtaining unit 1112 further includes a first obtaining sub-unit 1001 and a second obtaining sub-unit 1002. Step S1121 may be implemented by the first acquisition subunit 1001. Step S1122 may be realized by the second acquisition subunit 1002. That is, the first acquisition subunit 1001 may be configured to form a consumption-yield log pair from game logs at the same time of the same game character. The second acquiring subunit 1002 may be configured to form consumption-yield log pairs from game logs at adjacent times for the same game character.
Specifically, each game character generates a game log corresponding to each game character during the game. The game log may record the behavior of the game character, for example, a certain game character has consumed a certain number of tokens (i.e., expendables) through a certain channel at a certain point in time, has produced a certain number of items (i.e., products) at a certain point in time, and the like. Taking fig. 12 as an example, assuming that only two game characters of a user a and B user purchase items of a newsfeed gift bag in a certain day, a part of game log sets of the a user and the B user are shown in fig. 12. Wherein, a user a purchases and consumes 10 point tickets (consumption of consumables of the newsfeed gift package) through the mall at 23. B user consumed 20 point tickets (consumable consumption of novice gift bags) through the mall purchase at 09. Then the consumption-output data set for the prop "novice gift bag" includes: consume 10 point tickets-produce 1 newsletter gift package, and consume 20 point tickets-produce 2 newsletter gift packages. Of course, if there are a plurality of remaining game roles such as C user, D user, E user, etc. that also purchase a novice gift package through a consumption coupon or other consumable, the consumption-production log pairs generated by the plurality of C user, D user, E user, etc. also need to be merged into a consumption-production data set.
As can be seen from fig. 12, in the game logs of the a user and the B user, the consumption-yield log pairs are formed by matching the game logs of the same game character at the same time. However, in the actual game log, there may be a case where the time of consumption of the consumable due to the network delay does not coincide with the time of production corresponding to the production, for example, the game log records that the a user consumes the token at 10. Based on the above situation, the yield-consumption log pair is formed by matching the game logs of the same game character at adjacent time points. In this way, the accuracy of the consumption-production log pair can be guaranteed.
Additionally, in some cases, it may occur that game log records that user A consumes consumables at 10 1 Time of 10 2 At the moment of the consumption of the consumable and the production P at the adjacent moments 2 Is not a consumption-yield log pair. Based on such a situation, the second acquisition subunit 1002 needs to check the consumption-production log pairs at adjacent times. In particular, A user's can be targeted to the output P 2 For outcome P of consumption-outcome log pairs with the remaining game characters 2 The pairs of consumption-production logs are compared for testing. It will be appreciated that it is assumed that a portion of output P is produced 1 5 consumables are consumed, and one output P is produced 2 8 consumables are consumed, then user A consumes 5 consumables at one point in time and produces one output P at the next adjacent point in time 2 A further output P is produced at the next point in time 1 Comparing the game logs of the other majority of game characters, the other majority of game characters all produce one output P after consuming 5 consumables 1 Then, it indicates that the output P is produced 2 The game log is a noise log, and the output product P can be obtained 2 The next game log is searched to find a matching consumption-production log pair. Therefore, the consumption-output log pairs are checked, the accuracy of the consumption-output log pairs is ensured, and the accuracy of the correlation analysis is further improved.
After the consumption-output data set of each output of the full-service game role is obtained, the fitting curve of the consumption-output data set can be calculated according to the consumption-output data set of each output. Specifically, referring to fig. 13, in some embodiments, the step S12 of calculating a fitted curve of the corresponding consumption-production data set according to each consumption-production data set includes:
s121: based on each consumption-yield dataset, a first order linear fitting algorithm is used to calculate a fitted curve for the corresponding consumption-yield dataset.
The mathematical relation of the first-order linear fitting algorithm is as follows: y = a · x + b, where y is the actual output quantity, x is the consumption of the consumable needed to produce the output, a is the slope of the first order linear fit curve, and b is the intercept of the first order linear fit curve.
Referring to fig. 14, in some embodiments, the first computing submodule 112 includes a first computing unit 1121. Step S121 may be implemented by the first calculation unit 1121. That is, the first calculating unit 1121 may be configured to calculate a fitting curve corresponding to the consumption-production data set by using a first-order linear fitting algorithm based on each consumption-production data set. The mathematical relation of the first-order linear fitting algorithm is as follows: y = a · x + b, where y is the actual output quantity, x is the consumption of the consumable needed to produce the output, a is the slope of the first order linear fit curve, and b is the intercept of the first order linear fit curve.
Specifically, referring again to FIG. 12, the consumption-yield data set for a novice gift bag includes: consuming 10 point coupons-producing 1 newsletter gift package, and consuming 20 point coupons-producing 2 newsletter gift packages, when the value of x is 10, the value of y is 1,x is 20, and the value of y is 2. Thus, the first calculation unit 1121 may calculate a fitted curve of the consumption-yield data set of the new-hand gift bag according to (10,1) and (20,2), and the calculated first-order linear fitted curve has a slope a of 0.1 and b of 0, that is, the fitted curve of the consumption-yield data set of the new-hand gift bag is y =0.1x.
Of course, in practical applications, the consumption-production data set corresponding to each production usually includes a plurality of consumption-production log pairs, and in this case, as shown in fig. 15, the first-order linear fit curve calculated by the first calculation unit 1121 may not be a standard fit curve (all data points of all consumption-production log pairs are located on the standard fit curve), i.e., the first-order linear fit curve is only an approximate fit. For such cases, referring to fig. 16, the step S121 of calculating a fitted curve corresponding to the consumption-production data set by using a first-order linear fitting algorithm based on each consumption-production data set further comprises:
s1211: the slope and intercept in the fitted curve are calculated using the least squares method.
Referring to fig. 17, the first calculating unit 1121 includes a first calculating subunit 1003. Step S1211 may be implemented by the first calculation subunit 1003. That is, the first calculation subunit 1003 may be configured to calculate the slope and intercept in the fitted curve by using a least square method.
It will be appreciated that the least squares method may be used to find the best functional match of the data by minimizing the sum of the squares of the errors, so that the use of the least squares method may minimize the deviation of the first order linear fit curve from the standard fit curve, making the first order linear fit curve more accurate and reliable.
Referring back to fig. 13, in some embodiments, the step S13 of calculating the correlation coefficient of the corresponding consumption-production data set according to each consumption-production data set includes:
s131: calculating a pearson coefficient for each consumption-yield data set from the consumption-yield data set;
the mathematical relationship for calculating the pearson coefficient is:
where pr is the pearson coefficient, y is the actual output throughput, and x is the consumption of consumables required to produce the output.
Referring back to fig. 14, in some embodiments, the second computing submodule 113 includes a second computing unit 1131, and the step S131 can be implemented by the second computing unit 1131. That is, the second calculation unit 1131 may be configured to calculate a pearson coefficient for each consumption-yield data set according to the consumption-yield data set. The mathematical relation for calculating the Pearson coefficient is as follows:
wherein pr is the Pearson coefficient and y is the actual product yieldOutput quantity, x is the consumption of consumables required to produce the output.
It will be appreciated that a pearson coefficient may be used to measure the degree of correlation between variable x and variable y, with the pearson coefficient having a value between [ -1, +1 ]. When the pearson coefficient is closer to 0, it means that the correlation between the variable x and the variable y is weaker. As the pearson coefficient is closer to +1, the variable x and the variable y are strongly positively correlated. As the pearson coefficient approaches-1, the variable x and the variable y are strongly negatively correlated. In the embodiment of the invention, the pearson coefficient can measure the degree of correlation between the consumption of the consumables and the output quantity of the actual output, and the degree of correlation can be used for the subsequent calculation of the output quantity of the theoretical output, so that the accuracy of the calculation of the output quantity of the theoretical output is ensured.
Specifically, each consumption-output data set includes data relating an actual output quantity of an output to a consumption of a consumable substance, and accordingly, a degree of correlation between the actual output quantity of the corresponding output and the consumption of the consumable substance can be calculated from each consumption-output data set. Taking fig. 12 as an example, the consumption-yield data set of the newsfeed gift bag includes: consuming 10 point coupons-producing 1 newsletter gift package, and consuming 20 point coupons-producing 2 newsletter gift packages, when the value of x is 10, the value of y is 1,x is 20, and the value of y is 2. Thus, the second calculation unit can calculate the pearson coefficient of the first-order linear fitting curve y =0.1x from (10,1) and (20,2).
Cov (X, Y) in (1) is the covariance of the variables X and Y, σ x Is the variance, σ, of the variable x y The variance of the variable y is 1, which indicates that the actual output quantity of the property novice gift bag is strongly correlated with the consumption of the consumable.
Thus, each consumption-output data set can be used to calculate a fitting curve and a Pearson coefficient corresponding to the fitting curve, and the fitting curve and the Pearson coefficient can be used for subsequent calculation of the output quantity of the theoretical output.
Referring to fig. 18, in some embodiments, the step S2 of calculating the theoretical output quantity corresponding to the consumption quantity of the consumables of the current game character according to the correlation includes:
s21: obtaining a consumption-output data subset for each output of the current game character, the consumption-output data set comprising the consumption-output data subset; and
s22: theoretical output yield quantities for the plurality of outputs are calculated based on the plurality of consumption-yield data subsets and the plurality of Pearson coefficients.
Referring to fig. 19, in some embodiments, the calculation module 12 includes a second acquisition submodule 121 and a third calculation submodule 122. Step S21 may be implemented by the second acquisition submodule 121. Step S22 may be implemented by the third calculation sub-module 122. That is, the second obtaining sub-module 121 may be configured to obtain a consumption-yield data subset for each of the outcomes of the current game character, the consumption-yield data set including the consumption-yield data subset. The third calculation submodule 122 can be configured to calculate theoretical output yield quantities for the plurality of outputs based on the plurality of consumption-yield data subsets and the plurality of Pearson coefficients.
Referring to FIG. 20, step S22 of calculating theoretical output quantities for a plurality of outputs based on a plurality of consumption-output data subsets and a plurality of Pearson coefficients comprises:
s221: and calculating a tolerance coefficient of a fitting curve corresponding to the Pearson coefficient according to the Pearson coefficient, wherein the tolerance coefficient is used for performing correlation compensation according to the Pearson coefficient.
The mathematical relation formula for calculating the theoretical output quantity of various outputs of the current game role is as follows: y is c ＝∑(ai·xi+bi)·f(pri)，i∈N * Wherein i represents the ith output, Y c Pri is the Pearson coefficient corresponding to the ith fitting curve ai, xi + bi, f (pri) is the tolerance coefficient corresponding to the ith fitting curve ai, xi + bi, and f (pri) is the theoretical output of the ith output.
Referring to FIG. 21, the third calculation submodule 122 includes a third calculationAnd (3) a unit 1221. Step S221 may be implemented by the third calculation unit 1221. That is, the third calculating unit 1221 may be configured to calculate a tolerance coefficient of a fitting curve corresponding to the pearson coefficient according to the pearson coefficient, where the tolerance coefficient is used for performing correlation compensation according to the pearson coefficient. The mathematical relation formula for calculating the theoretical output quantity of the various outputs of the current game role is as follows: y is c ＝∑(ai·xi+bi)·f(pri)，i∈N * Wherein i represents the i-th output, Y c For the theoretical output quantity of a plurality of outputs, pri is a Pearson coefficient corresponding to the ith fitting curve ai.xi + bi, f (pri) is a tolerance coefficient corresponding to the ith fitting curve ai.xi + bi, and (ai.xi + bi). F (pri) is the theoretical output quantity of the ith output.
Specifically, it is checked whether there is an abnormal behavior in the full-scale game character, and it is necessary to go through all the game characters, and it is checked whether the output quantity of the actual output obtained by consuming the consumables by each game character meets the logic.
Wherein the consumption-outcome data subset includes data relating an actual outcome yield quantity of an outcome of the current game character to a corresponding consumption quantity of the consumable substance. The plurality of consumption-yield data subsets constitute a consumption-yield data set. Specifically, taking fig. 22 as an example, a user a consumed 30 point tickets (i.e., consumables) through a mall purchase at 07: consume 30 point tickets-produce 3 novice gift bags, and consume 10 point tickets-produce 1 novice gift bag. B user consumed 20 point tickets through the mall purchase at 09: consume 20 point tickets-produce 2 novice gift bags, and consume 40 point tickets-produce 4 novice gift bags. The consumption-yield data set for the novice gift bag at this time includes: consume 30 point tickets-produce 3 novice packages, consume 10 point tickets-produce 1 novice package, consume 20 point tickets-produce 2 novice packages, and consume 40 point tickets-produce 4 novice packages. Correspondingly, the consumption-yield data set at this time includes two consumption-yield data subsets, i.e., the consumption-yield data subset of the a user and the consumption-yield data subset of the B user. Wherein, the consumption-output data subset of the A user comprises consumption of 30 point tickets and output of 3 novice gift bags, and consumption of 10 point tickets and output of 1 novice gift bag, and the consumption-output data subset of the B user comprises consumption of 20 point tickets and output of 2 novice gift bags, and consumption of 40 point tickets and output of 4 novice gift bags. That is, the consumption-output data subset includes data relating to actual output quantities and consumable consumption quantities for the same type of output for the same game character, and the consumption-output data set includes data relating to actual output quantities and consumable consumption quantities for the same type of output for the full-scale game character. In verifying the presence of abnormal behavior for each game character, it is reasonable to calculate the theoretical output yield amount based only on the consumption-yield data subset for that game character.
Taking the current game role as an example, suppose that the current game role has M products, P respectively 1 、P 2 、P 3 …P m Each output having a corresponding consumption-output data subset, then P for the ith output i The fitted curve is y i = ai · xi + bi, fitting curve y i The pearson coefficient for = ai · xi + bi is pri, and the corresponding tolerance coefficient is f (pri). Wherein, the relation between the tolerance coefficient f (pri) and the Pearson coefficient pri is as follows: the closer the pearson coefficient pri is to 0, the larger the tolerance coefficient f (pri), the closer the pearson coefficient pri is to 1, and the closer the tolerance coefficient f (pri) is to 1. It will be appreciated that the closer the pearson coefficient pri is to 0, the less linear correlation between the quantity characterizing the actual output and the consumption of the consumable, in particular, for example, games with different levelsThe number of outcomes produced by the characters after consuming the same amount of consumables may be unequal, with higher game characters producing a greater number of outcomes and lower game characters producing a lesser number of outcomes, thus resulting in a lesser degree of linear correlation between actual outcome outcomes and consumable consumption. In view of the condition that the linear correlation degree between the output quantity of the actual output and the consumption of the consumable is small, a tolerance coefficient is set to compensate the condition of small correlation, so that the accuracy of detecting the abnormal behaviors of the game role can be improved, and the error report rate is reduced.
After M fitting curves corresponding to the M products one by one and tolerance coefficients corresponding to the M fitting curves one by one are determined, the value of the consumption of the consumables in the consumption-output data subset corresponding to each product is substituted into Y as the value of xi c = (ai · xi + bi) · f (pri), thereby calculating theoretical output amounts of a plurality of outputs of the current game character, and calculating the actual output quantity Y of the various outputs of the current game role according to the actual output quantity in the M consumption-output data subsets corresponding to the M outputs t 。
Finally, the judgment module judges 13Y t And Y c The size of (2). If Y is t ≤Y c If the actual output quantity of the output obtained by consuming the consumables by the current game role is consistent with the logic, the behavior of the current game role is not abnormal. If Y is t >Y c Then, the actual output quantity of all the outputs obtained by consuming the consumables by the current game role is considered to be not in accordance with the logic, and the behavior of the current game role is abnormal.
Therefore, the correlation between the output of various products and the consumption of corresponding consumables is analyzed according to the game logs of all game roles in the full-service game roles, manual monitoring and threshold setting are not needed, and the abnormity in the game can be effectively monitored.
Referring to fig. 23, in some embodiments, the step S1 of analyzing the correlation between the consumption of the consumables and the output of the actual output of the game character further comprises:
s14: the correlation between the consumption of the consumables and the actual output quantity is updated every predetermined time.
Referring to fig. 24, in some embodiments, the analysis module 11 further includes an analysis sub-module 114. Step S14 may be implemented by the analysis submodule 114. That is, the analysis submodule 114 may be operable to update the correlation between the amount of consumable consumption and the amount of actual output produced at predetermined time intervals.
It will be appreciated that the versions of the game business are updated more frequently, and correspondingly, the correlation between the consumption of the consumables and the actual output will change. At this time, if the correlation between the consumption amount of consumables and the output amount of actual products is not updated, but the correlation of the current game service version is still verified by the correlation of the previous game service version, a high false alarm rate may occur. Therefore, the correlation between the consumption of consumables and the output of actual products should be updated in time, and the updated correlation is used to check whether the behavior of all the game characters is abnormal, so that the bypass type loophole in the game can be effectively monitored, and a high error report rate cannot be generated. Preferably, in an embodiment of the present invention, the predetermined time may take 24 hours. For example, on the 5 th and 15 th days in 2018, a game log on the 5 th and 14 th days in 2018 is used for analyzing the correlation between the consumption of the consumables and the output of the actual products, and the correlation obtained by analysis is used for detecting whether abnormal behaviors exist in all game characters. After 0 minute in the early morning of 16 days in 2018, 5 and 16, the correlation is updated by using the game log of 15 days in 2018, 5 and 8, and whether abnormal behaviors exist in all game characters is detected by using the updated correlation. Of course, the predetermined time may take other values, such as 12 hours, 36 hours, 48 hours, etc., without limitation.
The detection of the abnormal behavior of the game role can also be performed once every preset time length. The preset time period may be 1 hour, 3 hours, 4.5 hours, 8 hours, 12 hours, 24 hours, and the like, which is not limited herein.
Referring to fig. 25, the present invention further provides a server 20. The server 20 includes one or more processors 21, memory 22, and one or more programs 221. Where the one or more programs 221 are stored in the memory 22 and configured to be executed by the one or more processors 21. The program 221 includes instructions for executing the game character abnormal behavior detection method according to any one of the above embodiments.
For example, the program 221 includes instructions for performing the steps of:
s1: analyzing the correlation between the consumption of the consumables of the full-service game role and the output quantity of the actual output;
s2: calculating the theoretical output quantity corresponding to the consumption of the consumables of the current game role according to the correlation;
s3: and judging whether the output quantity of the actual output product accords with the logic or not according to the output quantity of the actual output product and the output quantity of the theoretical output product, which are obtained by consuming consumables by the current game role.
For another example, the program 221 further includes instructions for performing the steps of:
s11: acquiring a consumption-output data set of each output of the full-service game role;
s12: calculating a fitted curve for each consumption-yield data set from the consumption-yield data sets; and
s13: correlation coefficients for the corresponding consumption-yield data sets are calculated from each consumption-yield data set, one correlation coefficient for each fitted curve.
The invention also provides a computer readable storage medium. The computer readable storage medium includes a computer program for use in conjunction with the server 20. The computer program can be executed by the processor 21 to implement the game character abnormal behavior detection method according to any one of the above embodiments.
For example, the computer program may be executed by the processor 21 to perform the steps of:
s1: analyzing the correlation between the consumption of the consumables and the output quantity of the actual output of the full-scale game role;
s2: calculating the theoretical output quantity corresponding to the consumption of the consumables of the current game role according to the correlation;
s3: and judging whether the output quantity of the actual output product accords with the logic or not according to the output quantity of the actual output product and the output quantity of the theoretical output product, which are obtained by consuming consumables by the current game role.
As another example, the computer program may also be executable by the processor 21 to perform the steps of:
s11: acquiring a consumption-output data set of each output of the full-service game role;
s12: calculating a fitted curve for each consumption-yield data set from the consumption-yield data sets; and
s13: correlation coefficients for the corresponding consumption-yield data sets are calculated from each consumption-yield data set, one correlation coefficient for each fitted curve.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (14)
1. A game character abnormal behavior detection method for detecting whether or not an actual output amount obtained by consuming expendables of a game character conforms to a logic, the game character abnormal behavior detection method comprising:
analyzing a correlation between the consumable consumption amount of the all-suit game character and the actual output yield amount, the correlation between the consumable consumption amount of the all-suit game character and the actual output yield amount comprising a correlation between the actual output yield amount of each output owned by the all-suit game character and the consumable consumption amount of all kinds of consumables;
calculating the theoretical output quantity corresponding to the consumption quantity of the consumables of the current game role according to the correlation; and
judging whether the actual output quantity accords with logic according to the actual output quantity obtained by the current game role through consuming consumables and the theoretical output quantity, wherein if the actual output quantity is less than or equal to the theoretical output quantity, the actual output quantity obtained by the current game role through consuming the consumables accords with the logic;
wherein the step of calculating the theoretical output quantity corresponding to the consumable consumption quantity of the current game role according to the correlation comprises the following steps:
obtaining a consumption-outcome data set for each outcome of the current game character, the consumption-outcome data set comprising a subset of consumption-outcome data; and
theoretical output yield quantities for the plurality of outputs are calculated based on the plurality of subsets of consumption-output data and a plurality of Pearson coefficients, which measure a degree of correlation between the consumption of the consumable and the actual output yield quantities.
2. The method of claim 1, wherein the step of analyzing the correlation between the consumption of consumables and the output of actual products of the game character comprises:
acquiring a consumption-output data set of each output of the full-service game role;
calculating a fitted curve corresponding to each of said consumption-yield data sets from each of said consumption-yield data sets; and
and calculating correlation coefficients corresponding to the consumption-yield data sets according to each consumption-yield data set, wherein each fitting curve corresponds to one correlation coefficient.
3. The method of detecting abnormal game character behavior according to claim 2, wherein the step of acquiring the consumption-output data set for each output of the game character as a whole includes:
obtaining a game log of each game role;
obtaining a consumption-output log pair of each output of each game role according to the game log; and
and merging a plurality of pairs of consumption-output log pairs corresponding to each output in the full-service game role into a consumption-output data set corresponding to the output.
4. The method of claim 2, wherein the step of calculating a fitted curve corresponding to each consumption-yield data set from each consumption-yield data set comprises:
based on each of the consumption-production datasets, a first order linear fitting algorithm is employed to calculate a fitted curve corresponding to the consumption-production dataset.
5. The method of claim 2, wherein the step of calculating a correlation coefficient corresponding to each of the consumption-yield data sets according to the consumption-yield data sets comprises:
calculating a Pearson coefficient corresponding to each of the consumption-yield data sets from each of the consumption-yield data sets.
6. The method of claim 1, wherein the step of calculating theoretical output yield quantities for a plurality of outputs based on the plurality of consumption-yield data subsets and the plurality of Pearson coefficients comprises:
and calculating a tolerance coefficient of a fitting curve corresponding to the Pearson coefficient according to the Pearson coefficient, wherein the tolerance coefficient is used for performing correlation compensation according to the Pearson coefficient.
7. The method of claim 1, wherein the step of determining whether the actual output quantity is logical according to the actual output quantity obtained by consuming consumables of the current game character and the theoretical output quantity comprises:
judging whether the actual output quantity obtained by the current game role through consuming consumables is less than or equal to the theoretical output quantity or not; and
and when the actual output quantity is less than or equal to the theoretical output quantity, determining that the actual output quantity obtained by consuming consumables of the current game role accords with logic.
8. A game character abnormal behavior detection apparatus for detecting whether or not an actual output amount obtained by consuming expendables of the game character conforms to a logic, comprising:
an analysis module for analyzing a correlation between the consumable consumption amount and the actual output quantity of the all-suit game character, the correlation between the consumable consumption amount and the actual output quantity of the all-suit game character including a correlation between the actual output quantity of each output owned by the all-suit game character and the consumable consumption amounts of all kinds of consumables;
the calculation module is used for calculating the theoretical output quantity corresponding to the consumption of the consumables of the current game role according to the correlation;
the judging module is used for judging whether the actual output quantity accords with the logic according to the actual output quantity obtained by the current game role through consuming consumables and the theoretical output quantity, wherein if the actual output quantity is less than or equal to the theoretical output quantity, the actual output quantity obtained by the current game role through consuming the consumables accords with the logic;
wherein the calculation module comprises:
a second obtaining submodule for obtaining a consumption-outcome data set for each outcome of the current game character, the consumption-outcome data set including a consumption-outcome data subset; and
a third calculation submodule for calculating theoretical output quantities for a plurality of outputs based on a plurality of said consumption-output data subsets and a plurality of Pearson coefficients, said Pearson coefficients being used to measure a degree of correlation between the consumption of the consumable and the actual output quantities.
9. The apparatus of claim 8, wherein the analysis module comprises:
a first obtaining submodule for obtaining a consumption-output data set of each output of a full-scale game role;
a first computation submodule for computing, from each of the consumption-production datasets, a fitted curve corresponding to the consumption-production dataset; and
a second calculation submodule configured to calculate, from each of the consumption-production data sets, a correlation coefficient corresponding to the consumption-production data set, each of the fitting curves corresponding to one of the correlation coefficients.
10. The apparatus for detecting abnormal behavior of a game character according to claim 9, wherein the first obtaining sub-module includes:
a first acquisition unit configured to acquire a game log of each of the game characters;
a second acquisition unit configured to acquire a consumption-output log pair of each output of each of the game characters from the game log; and
a merging unit for merging pairs of consumption-output log pairs corresponding to each output in the full-serve game role into a consumption-output data set corresponding to the output.
11. The game character abnormal behavior detection apparatus according to claim 9, wherein the first calculation sub-module includes:
a first computing unit configured to compute a fitted curve corresponding to the consumption-production data set using a first order linear fitting algorithm based on each of the consumption-production data sets.
12. The apparatus of claim 9, wherein the second computation submodule includes:
a second calculation unit for calculating, from each of the consumption-yield data sets, a Pearson coefficient corresponding to the consumption-yield data set.
13. The apparatus of claim 8, wherein the third computing submodule comprises a third computing unit, and the third computing unit is configured to compute a tolerance coefficient of a fitting curve corresponding to the pearson coefficient according to the pearson coefficient, and the tolerance coefficient is configured to compensate correlation according to the pearson coefficient.
14. The apparatus of claim 8, wherein the determining module comprises:
the judgment submodule is used for judging whether the actual output quantity obtained by the current game role through consuming consumables is less than or equal to the theoretical output quantity or not; and
a sub-module is determined which is, the determining submodule is used for determining that the actual output quantity obtained by consuming expendables of the current game role accords with logic when the actual output quantity is smaller than or equal to the theoretical output quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538937.2A CN108854075B (en) | 2018-05-30 | 2018-05-30 | Method and device for detecting abnormal behaviors of game role |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538937.2A CN108854075B (en) | 2018-05-30 | 2018-05-30 | Method and device for detecting abnormal behaviors of game role |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108854075A CN108854075A (en) | 2018-11-23 |
| CN108854075B true CN108854075B (en) | 2023-04-18 |
Family
ID=64335856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810538937.2A Active CN108854075B (en) | 2018-05-30 | 2018-05-30 | Method and device for detecting abnormal behaviors of game role |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108854075B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885417B (en) * | 2018-12-28 | 2022-08-02 | 广州卓动信息科技有限公司 | Anomaly analysis method, electronic device and readable storage medium |
| CN110008415A (en) * | 2019-03-21 | 2019-07-12 | 北京仝睿科技有限公司 | A kind of data object variation tendency determines method, apparatus and server |
| CN114422225B (en) * | 2022-01-13 | 2023-07-07 | 深圳市爱的番茄科技有限公司 | Cloud game big data analysis method and system based on network information security |
| CN115317918A (en) * | 2022-07-20 | 2022-11-11 | 杭州电魂网络科技股份有限公司 | Method, system, device and medium for detecting abnormity of game props |
| CN118121940A (en) * | 2024-05-10 | 2024-06-04 | 深圳市奇迅新游科技股份有限公司 | Data detection method, device and computer readable storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512762A (en) * | 2015-12-04 | 2016-04-20 | 网易（杭州）网络有限公司 | Game numerical value launching estimation method and device based on correlation analysis |
| CN107644347A (en) * | 2016-07-21 | 2018-01-30 | 盛趣信息技术（上海）有限公司 | The acquisition method of MMO game operation datas |
-
2018
- 2018-05-30 CN CN201810538937.2A patent/CN108854075B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108854075A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108854075B (en) | Method and device for detecting abnormal behaviors of game role | |
| US6856972B1 (en) | Automated method for analyzing and comparing financial data | |
| US8336085B2 (en) | Tuning product policy using observed evidence of customer behavior | |
| US10565185B2 (en) | MSET-based process for certifying provenance of time-series data in a time-series database | |
| CN109308035A (en) | System, method and the control unit of operation for control technology system | |
| CN111538642B (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
| US20100262858A1 (en) | Invariants-Based Learning Method and System for Failure Diagnosis in Large Scale Computing Systems | |
| CN110781605B (en) | Advertisement putting model testing method and device, computer equipment and storage medium | |
| AU2006214307A2 (en) | Embedded warranty management | |
| CN104813353A (en) | System and method for generating subscriber churn predictions | |
| MX2008016351A (en) | Independent computation environment and provisioning of computing device functionality. | |
| US20100293020A1 (en) | Embedded warranty management | |
| CN110222504B (en) | User operation monitoring method, device, terminal equipment and medium | |
| CN110490516A (en) | A kind of unmanned store shelf article detection method and device | |
| WO2008088121A1 (en) | Apparatus and method for detecting program plagiarism through memory access log analysis | |
| CN112581291A (en) | Risk assessment transaction detection method, device, equipment and storage medium | |
| CN109766958B (en) | A kind of data preprocessing method and device for data fusion | |
| JP7096398B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN114780358A (en) | Detection method and detection device for abnormal operation behaviors | |
| CN101490690A (en) | Determining validity of subscription to use digital content | |
| CN110458713B (en) | Model monitoring method, device, computer equipment and storage medium | |
| US20220222580A1 (en) | Deterioration detection method, non-transitory computer-readable storage medium, and information processing device | |
| Arora et al. | Competitive and Strategic Effects in the Timing of Patch Release. | |
| MacNeill et al. | Multiple change‐point models for time series | |
| KR20200023160A (en) | Server detecting abnormal game activity and operating method of thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |