CN107335220B - Negative user identification method and device and server - Google Patents
Negative user identification method and device and server Download PDFInfo
- Publication number
- CN107335220B CN107335220B CN201710417460.8A CN201710417460A CN107335220B CN 107335220 B CN107335220 B CN 107335220B CN 201710417460 A CN201710417460 A CN 201710417460A CN 107335220 B CN107335220 B CN 107335220B
- Authority
- CN
- China
- Prior art keywords
- operation index
- index data
- user
- target
- users
- 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
- A63F13/79—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories
-
- 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
Abstract
The application provides a method, a device and a server for identifying a passive user, wherein the method comprises the following steps: acquiring target operation index data of a target user when executing a target interaction task; comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model; and if the target operation index data is not higher than the preset operation index threshold value, judging that the target user is a negative user, and performing processing aiming at the negative user. Passive users may be identified using the methods provided herein.
Description
Technical Field
The application relates to the field of computer communication, in particular to a user identification technology.
Background
With the development of the internet, online games are more and more popular with the masses of online friends, and the amateur life of people is enriched.
However, in the network game process, especially in the team game, some players often have operations such as on-hook, etc., and the game experience of teammates, gold coins, etc. are shared without performing the game operation for a long time, which seriously affects the fairness of the game. Therefore, how to identify the passive users in the game becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, and a server for identifying a passive user, so as to identify the passive user.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of the present application, there is provided a method for identifying a passive user, the method being applied to a server, the method including:
acquiring target operation index data of a target user when executing a target interaction task;
comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
and if the target operation index data is not higher than the preset operation index threshold value, judging that the target user is a negative user, and performing processing aiming at the negative user.
Further, the method further comprises:
acquiring operation index data of a plurality of users when executing a target interaction task;
determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users;
constructing an index threshold model based on a plurality of acquired operation index data for normal users;
and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
Further, the acquiring operation index data of a plurality of users when executing the target interaction task includes:
receiving operation index data with a value exceeding a preset value uploaded by a client or operation index data aiming at a plurality of users uploaded by the client based on a user instruction; alternatively, the first and second electrodes may be,
receiving operation index data which are uploaded by a client and aim at a plurality of users;
respectively calculating the target scores of the operation index data of each user based on a preset scoring rule;
and acquiring operation index data with the target score higher than the preset score.
Further, the acquiring operation index data of a plurality of users when executing the target interaction task includes:
receiving partial operation index data uploaded by a client aiming at a plurality of users;
respectively simulating complete operation index data of each user based on part of operation index data uploaded by the client;
and respectively calculating the target scores of the complete operation index data of the users based on a preset scoring rule, and acquiring the complete operation index data of which the target scores are higher than the preset scores.
Further, the operation index threshold is obtained by a preset index threshold model based on statistical analysis of operation index data samples of a plurality of normal users input into the model; the operation index data samples of the normal users are obtained by carrying out statistical analysis on the operation index data of the users or by calibration;
the comparing the target operation index data with a preset operation index threshold value includes:
and comparing the target operation index data with an operation index threshold value obtained based on statistical analysis of operation index data samples of a plurality of normal users.
Further, the operation index threshold is obtained by a preset index threshold model based on statistical analysis of a plurality of historical operation index data samples of the user input into the model;
the comparing the target operation index data with a preset operation index threshold value includes:
searching an operation index threshold value obtained by carrying out statistical analysis on a plurality of historical operation index data samples of the user;
and comparing the target operation index data with the searched operation index threshold value.
According to a second aspect of the present application, there is provided an apparatus for identifying a passive user, the apparatus being applied to a server, the apparatus comprising:
the acquisition unit is used for acquiring target operation index data of a target user when a target interaction task is executed;
a comparison unit, configured to compare the target operation index data with a preset operation index threshold; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
and the identification unit is used for judging that the target user is a passive user if the target operation index data is not higher than the preset operation index threshold value, and processing aiming at the passive user.
Further, the device also comprises a construction unit, a processing unit and a processing unit, wherein the construction unit is used for acquiring operation index data of a plurality of users when the users execute the target interaction tasks; determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users; constructing an index threshold model based on a plurality of acquired operation index data for normal users; and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
Further, the construction unit is further specifically configured to receive operation index data uploaded by a client and having a score exceeding a preset score, or upload operation index data for a plurality of users by the client based on a user instruction, when acquiring operation index data of the plurality of users when executing a target interaction task; or receiving operation index data which is uploaded by a client and aims at a plurality of users; respectively calculating the target scores of the operation index data of each user based on a preset scoring rule; and acquiring operation index data with the target score higher than the preset score.
Further, the construction unit is specifically configured to receive, when acquiring operation index data of a plurality of users when executing a target interaction task, part of the operation index data uploaded by a client for the plurality of users; respectively simulating complete operation index data of each user based on part of operation index data uploaded by the client; and respectively calculating the target scores of the complete operation index data of the users based on a preset scoring rule, and acquiring the complete operation index data of which the target scores are higher than the preset scores.
Further, the operation index threshold is obtained by a preset index threshold model based on statistical analysis of operation index data samples of a plurality of normal users input into the model; the operation index data samples of the normal users are obtained by carrying out statistical analysis on the operation index data of the users or by calibration;
the comparison unit is specifically configured to compare the target operation index data with an operation index threshold obtained based on statistical analysis of operation index data samples of a plurality of normal users.
Further, the operation index threshold is obtained by a preset index threshold model based on statistical analysis of a plurality of historical operation index data samples of the user input into the model;
the comparison unit is specifically configured to search an operation index threshold obtained by performing statistical analysis on a plurality of historical operation index data samples for the user; and comparing the target operation index data with the searched operation index threshold value.
According to a third aspect of the application, there is provided a server comprising a processor and a machine-readable storage medium, the processor being caused to:
acquiring target operation index data of a target user when executing a target interaction task;
comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
and if the target operation index data is not higher than the preset operation index threshold value, judging that the target user is a negative user, and performing processing aiming at the negative user.
When the passive user is identified, the server side can acquire target operation index data of a target user when the target user executes a target interaction task, and can compare the target operation index data with a preset operation index threshold value. The operation index threshold value can be obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model. If the operation index data is not higher than the preset operation index threshold value, the server side can judge that the user is a passive user and perform processing aiming at the passive user.
On one hand, the server side can compare the target operation index data of the target user with the operation index threshold value, and when the target operation index data is not higher than the operation index threshold value, the target user is judged to be a passive user, and therefore identification of the passive user is achieved.
On the other hand, the operation index threshold value can be dynamically obtained by carrying out statistical analysis on a plurality of user operation index data samples through the index threshold value model, and is more accurate along with the continuous increase of the user operation index data samples, so that the accuracy of the passive user identification is greatly improved.
Drawings
Fig. 1 is a network architecture diagram illustrating a method of identifying passive users according to an exemplary embodiment of the present application;
fig. 2 is a flow chart illustrating a method for identifying passive users according to an exemplary embodiment of the present application;
fig. 3 is a block diagram of a passive user identification device according to an exemplary embodiment of the present application;
fig. 4 is a hardware configuration diagram of a server according to the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
With the development of the internet, online games are more and more popular with the masses of online friends, and the amateur life of people is enriched. In the network game, the player can interact with other players through the Internet, for example, the player can cooperate with the real friend to fight against or play against the strange player, and the entertainment of the network game is greatly enriched.
However, in the network game process, especially in the network game based on team cooperation, some players often do not perform the game operation for a long time, but share the external hanging operations of team friends' game experience, gold coins and the like, and even more, the players in the team lose the game due to the on-hook operation of individual players, thereby seriously affecting the fairness of the game.
In view of this, the present application provides a method for identifying a passive user, where in the identification of the passive user, a server may obtain target operation index data of a target user when the target user performs a target interaction task, and may compare the target operation index data with a preset operation index threshold. The operation index threshold value can be obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model. If the operation index data is not higher than the preset operation index threshold value, the server side can judge that the user is a passive user and perform processing aiming at the passive user.
On one hand, the server side can compare the target operation index data of the target user with the operation index threshold value, and when the target operation index data is not higher than the operation index threshold value, the target user is judged to be a passive user, and therefore identification of the passive user is achieved.
On the other hand, the operation index threshold value can be dynamically obtained by carrying out statistical analysis on a plurality of user operation index data samples through the index threshold value model, and is more accurate along with the continuous increase of the user operation index data samples, so that the accuracy of the passive user identification is greatly improved.
Referring to fig. 1, fig. 1 is a network architecture diagram illustrating a method for identifying a passive user according to an exemplary embodiment of the present application. The network architecture may include a terminal device and a server.
The terminal device may be a mobile terminal device, such as a smart phone, an IPAD, a notebook, or a computer. Usually, the terminal device can be loaded with a client. The user can execute corresponding operation at the client. The client may be a game client or other clients, and here, the type of the client is only exemplified and not specifically limited.
For example, when the client is a competitive game client, a user can control hero in the game to perform operations such as clearing a soldier line, pushing a tower and the like through a visual interface provided by the client for the user.
The server may also be referred to as a background server, and may be a distributed server built by a plurality of servers, and corresponds to the client. The server is mainly used for storing user operation index data uploaded by the client, performing statistical analysis on the user operation index data, maintaining the operation stability of the client and the like. Here, the type and use of the server are merely exemplary described, and are not particularly limited.
In the embodiment of the application, under the network architecture, the client can upload the operation index data of the user to the server, the server can judge whether the user is a passive user by comparing the acquired user operation index data with a preset operation index threshold value, and when the user is the passive user, the server performs processing for the passive user.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for identifying a passive user according to an exemplary embodiment of the present application. The method may include steps 201 through 203.
Step 201: the server side obtains target operation index data of a target user when the target user executes a target interaction task;
step 202: the server compares the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
step 203: and if the target operation index data is not higher than the preset operation index threshold value, the server judges that the target user is a passive user and carries out processing aiming at the passive user.
The target interaction task can be understood as a task operation performed by a user on a client. For example, when the scene to which the method is applied is a game scene, the target interaction task may be a game process performed on a game client by a user. For competitive games, the target interaction task may be a process of a game match performed by a user on a game client. Of course, when the method is applied to other scenes, the target interaction task may also be other target interaction tasks. The target interaction task is only exemplarily illustrated here, and is not particularly limited.
The operation index data may be user operation data defined based on a content type indicated by the data, and the operation index data may include one type of operation index data or may include a plurality of types of operation index data.
Taking the application of the passive user identification method to a scene of a competitive game, the operation index data may be a plurality of operation data defined by the user based on the content type represented by the data during the game. For example, the user operation data may include data related to user operations representing various content types, such as the number of user operations, the instruction feedback time length, and the like, and these data are defined based on different content types, and become operation data indicators.
For example, the operation index data may include a game operation rate of the user, and for the user terminal being a smart phone, the game operation rate of the user may be a rate at which the user clicks a screen of the smart phone within a certain time; in the case that the user terminal is a computer or a notebook, the operation rate of the user game may be a rate at which the user clicks a mouse or a keyboard within a certain time.
The operation index data may further include an instruction feedback time. When the user terminal is taken as the smart phone, in the game process, a user triggers the client to send a user trigger instruction to the server by clicking a screen, and the elapsed time until the client receives a response instruction of the user trigger instruction returned by the server can be instruction feedback time.
Of course, the operation index data may also include other types of operation index data, and the operation index data is only exemplarily illustrated and is not specifically limited.
The preset operation index threshold may be a threshold corresponding to the operation index data. The operation index threshold value can be obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model. The index threshold may be a value or an interval.
Still taking the scene of the competitive game as an example, when the operation index data is the game operation rate of the user, the operation index threshold may be a game operation rate threshold; when the operation index data is feedback time, the operation index threshold may be a feedback time threshold. In terms of the game operation rate threshold, the game operation rate threshold may be a value of 50 times/min, or may be an interval of 40 times/min to 60 times/min.
The above-mentioned passive users can be understood as users who perform the target interactive task at a level lower than that of normal users. For example, even in the case of a competitive game, the passive user may be a user who is not performing a game operation for a long period of time during a game match and hangs up.
When the passive user is quantitatively measured, a user with operation index data lower than an operation index threshold value can be defined as a passive user by comparing a plurality of types of operation index data aiming at the user with the operation index threshold value corresponding to the operation index data.
For example, the operation index data is taken as the game operation rate of the user, and the scene of the competitive game is taken as an example. When the game operation speed of the user acquired by the server is 20 times/min and the game operation speed threshold value is 40 times/min-60 times/min, the user can be defined as a passive user.
The method for identifying a passive user will be described in detail below, in terms of both the creation of the index threshold model and the operation index threshold and the identification of a passive user.
1) Establishing an index threshold model and generating an operation index threshold
In the embodiment of the application, the operation index threshold value can be dynamically obtained by statistical analysis of a plurality of input user operation index data samples through the index threshold value model, and the operation index threshold value is more accurate along with the continuous increase of the user operation index data samples, so that the comparison result of the obtained user operation index data and the operation index threshold value is more accurate, and the accuracy of passive user identification can be greatly improved.
a) Constructing an index threshold model
When the target interaction task is implemented, the server side can obtain operation index data of a plurality of users when the target interaction task is executed.
In an optional implementation manner, when obtaining operation index data of a plurality of users executing a target interaction task, a client may collect the operation index data of the plurality of users, then respectively calculate a target score of the operation index data of each user based on a scoring rule issued by a server, and upload the operation index data of which the target score is higher than a preset score to the server, and the server may obtain the operation index data uploaded by the client.
The scoring rule may be a scoring rule designed by a developer based on an actual situation, for example, the scoring rule may include a binding relationship between a preset score and an operation index data value, and the client may search for the preset score corresponding to the operation index data value through the binding relationship. Of course, the above-mentioned scoring rule may also include a discrete degree between the value of the operation index data and a preset primary index threshold, and the discrete degree is digitized to form a score. Here, the above-mentioned score rules are merely exemplary and are not specifically limited.
In another alternative implementation, the client may upload operation index data for several users based on user instructions. The server side obtains the operation index data.
For example, after the target interaction task is finished, the client outputs prompt information of whether to upload the operation index data, and after the user clicks "confirm", the operation index data can be uploaded to the server based on the user instruction.
In another alternative implementation manner, the client may upload operation index data for several users to the server. Then, the server may calculate a target score of the operation index data of each user based on the scoring rule, and may obtain the operation index data with the target score higher than a preset score.
In another optional implementation manner, when the client cannot upload the complete user operation index data to the server due to the limitation of network conditions, the client may upload part of the operation index data for several users to the server. After receiving part of the operation index data of each user, the server can respectively simulate complete operation index data aiming at each user based on a preset prediction algorithm. Then, the server side can calculate a target score of the complete operation index data for each user according to the scoring rule, and obtains the operation index data of which the target score is higher than a preset score.
The prediction algorithm may be a regression algorithm, a deep learning algorithm, or a prediction algorithm designed by a developer according to practical applications, and the prediction algorithm is only described as an example and is not specifically limited.
After the operation index data is obtained, the server side can determine the operation index data of a normal user, and an index threshold model is constructed based on the operation index data of the normal user.
In an optional implementation manner, when determining the operation index data of the normal user, the server may perform statistical analysis, such as cluster analysis, on the operation index data of the users to obtain the operation index data of the normal user. Of course, during the statistical analysis, the server may also use other algorithms, and the algorithm of the statistical analysis is only exemplarily illustrated and is not specifically limited.
For cluster analysis, the server may classify the operation index data into a class with similar data, and then define the class with the most operation index data as the operation index data of the normal user.
Of course, the operation index data of the normal user can be obtained by manual calibration of a developer.
The scene in which the method is applied is taken as a game scene as an example. Usually, before a game is released, the game is subjected to internal measurement and public measurement, the server can obtain operation index data of a plurality of users through the internal measurement and the public measurement, and the data quality of the user operation index data acquired by the internal measurement and the public measurement is high because the game level, the game familiarity degree and the like of the users aimed at by the internal measurement and the public measurement are high.
The server side can perform cluster analysis on the user operation index data collected by the internal test and the public test, the operation index data are classified into one class in a similar way, and then the class containing the most operation index data is defined as the operation index data of the normal user.
Of course, the developer can also calibrate the data collected by the internal test or the public test into the operation index data of the normal user.
In this embodiment, the server may construct an index threshold model from the index data of the normal user.
It should be noted that, when constructing the index threshold model, a supervised or unsupervised deep learning method may be adopted to continuously train the index threshold model, that is, parameters of each layer of the index threshold model are adjusted, so that the index threshold model outputs a more accurate operation index threshold.
Of course, the developer may also use other algorithms to construct the index threshold model, and the construction of the index threshold model is only described by way of example and is not specifically limited.
In the embodiment of the application, in order to make the generated operation index threshold more accurate, the server may continuously and dynamically optimize the index threshold model based on the operation index data of the continuously added users.
b) Generation of operation index threshold
In an optional implementation manner, after the index threshold model is constructed and trained, the server may input the operation index data of the normal user as a user operation index data sample into the index threshold model, and the index threshold model may perform statistical analysis on the operation index data of the normal user to obtain one or more operation index thresholds.
In another optional implementation manner, the user operation index data sample may be historical operation data of the user.
During implementation, the server side can store the collected user operation index data in a classified manner based on the user identification. When the user operation index data sample is obtained, the historical operation data of the user can be searched based on the user identification to be used as the user operation index data sample.
The server side can input the user operation index data samples into the index threshold model, the index threshold model can perform statistical analysis on index data in the user operation index data samples, and then one or more operation index thresholds for each type of operation index data are obtained.
For the statistical analysis performed by the index threshold model, in implementation, the index threshold model may calculate an average value of all users for a certain type of operation index data based on the index type, and then perform statistical analysis for each type of operation index data based on the average value, and calculate one or more operation index thresholds.
Still taking the scene in which the method is applied as a game scene as an example, assume that the operation index data is a game operation rate. Assume that the user operation index data samples are operation index data of user 1 to user N.
In the statistical analysis, the index threshold model may perform average calculation on the operation index data of the users 1 to N. For example, assuming that the number of game operations in the first minute by the user 1 is 19 times and … times, the number of game operations in the first minute by the user N is 21 times, and the like, the index threshold model may be used to calculate an average value of the number of game operations in the first minute by the users 1 to N.
It is assumed that the index threshold model performs the average calculation of the game operation rates, and obtains a data value in which the average number of game operations of the user is 20 in the first minute, 40 in the second minute, 50 in the third minute, 40 in the fourth minute, and 50 in the fifth minute.
The index threshold model may count the number of user operations per minute, every three consecutive minutes, every five consecutive minutes, and then calculate the game operation rate per minute, every three consecutive minutes, every five consecutive minutes, and use the game operation rate as the operation index threshold.
Assuming that statistics are performed every three consecutive minutes, the index threshold model can be obtained within 1min-3min, the game operation rate of the user is about 36 times/min, within 2min-4min, the game operation rate of the user is about 43 times/min, and within 3min-5min, the game operation rate of the user is about 46 times/min. The index threshold model can be output within 1min-3min, and the game operation speed threshold is 36 times/min; within 2min-4min, the game operation speed threshold is 43 times/min, and within 3min-5min, the game operation speed threshold is 46 times/min.
Of course, the index threshold model may also use other algorithms to calculate the operation index threshold for each operation index data, and is not specifically limited herein.
2) Negative user identification
In the embodiment of the application, the server may compare the target operation index data of the target user with the operation index threshold, and determine that the target user is a passive user when the target operation index data is not higher than the operation index threshold, thereby implementing identification of the passive user.
When the target interaction task is implemented, the client can collect target operation index data of a target user when the target user executes the target interaction task, and then the target operation index data is uploaded to the server. The server can compare the target operation index data with the operation index threshold value output by the index threshold value model.
When the method is realized, the server side can firstly carry out statistical analysis on the target operation index data of the target user to obtain a plurality of parameter values representing the target operation index data.
When the target operation index data is compared with the preset operation index threshold, the server side can compare a plurality of parameter values representing the target operation index data obtained after statistical analysis with the preset operation index threshold.
In an optional implementation manner, when performing statistical analysis on the target operation index data and determining a parameter value representing the target operation index data, the server may count the operation index data in a continuous time period by taking time as a unit, and then obtain an average value of the operation index data in the continuous time period to perform statistical analysis on the target operation index data, to obtain a parameter value representing the target index, and then compare the parameter value with a preset operation index threshold. The calculated parameter value may be plural.
And if the preset number of parameter values are not higher than the preset operation index threshold value, determining that the target operation index data of the target user is not higher than the preset operation index threshold value, and judging that the target user is a negative user.
For example, assuming that the number of parameter values is five, when there are three parameter values not higher than the preset operation index threshold value, it may be determined that the target user is a negative user.
Of course, the statistical analysis of the target operation index data is not limited to the above statistical analysis algorithm, and a developer may design the statistical analysis algorithm based on actual situations, and the statistical analysis algorithm is only exemplified and not particularly limited.
Still, the scene in which the method is applied is a game scene, and the operation index data is a game operation rate as an example. Assuming that the preset operation index threshold is within 1-3 min, and the game operation speed threshold is 36 times/min; within 2min-4min, the game operation speed threshold is 43 times/min, and within 3min-5min, the game operation speed threshold is 46 times/min.
The game operation rate of the target user acquired by the server is assumed to be 5 times in the first minute, 15 times in the second minute, 10 times in the third minute, 0 time in the fourth minute, and 0 time in the fifth minute.
It is assumed that the server counts the number of operations of the target user in a continuous time period, for example, the number of operations per minute, per continuous three minutes, per continuous five minutes, and then calculates the game operation rate per minute, per continuous three minutes, per continuous five minutes for the target user.
For statistics once every three consecutive minutes, the server can calculate the game operation rate of the target user in the three consecutive minutes. The game operation rate of the target user is 10 times/min within 1min-3min, the game operation rate of the target user is about 6 times/min within 2min-4min, and the game operation frequency of the target user is about 3 times/min within 3min-5 min. Then, the server can take the game operation rate of 10 times/min within 1min to 3min, the game operation rate of about 6 times/min within 2min to 4min and the game operation frequency of about 3 times/min within 3min to 5min as the parameter values for the operation index data.
The server may compare the three parameter values with the operation index threshold, and the server finds that the three parameter values are all smaller than the operation index threshold. The server can determine that the target user is a passive user. After determining the passive user, the server may perform corresponding processing on the passive user.
For example, the server may return a prompt message to the client of the negative user, such as "prohibit hang up," or prohibit the user from playing a game for a preset time, or deduct the reputation in the user account of the negative user, etc.
When the passive user is identified, the server side can acquire target operation index data of a target user when the target user executes a target interaction task, and can compare the target operation index data with a preset operation index threshold value. The operation index threshold value can be obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model. If the operation index data is not higher than the preset operation index threshold value, the server side can judge that the user is a passive user and perform processing aiming at the passive user.
On one hand, the server side can compare the target operation index data of the target user with the operation index threshold value, and when the target operation index data is not higher than the operation index threshold value, the target user is judged to be a passive user, and therefore identification of the passive user is achieved.
On the other hand, the operation index threshold value can be dynamically obtained by carrying out statistical analysis on a plurality of user operation index data samples through the index threshold value model, and is more accurate along with the continuous increase of the user operation index data samples, so that the accuracy of the passive user identification is greatly improved.
Corresponding to the embodiment of the passive user identification method, the application also provides an embodiment of the passive user identification device.
Referring to fig. 3, fig. 3 is a block diagram illustrating an apparatus for identifying a passive user according to an exemplary embodiment of the present application; the apparatus may include: an acquisition unit 310, a comparison unit 320 and a recognition unit 330.
The obtaining unit 310 is configured to obtain target operation index data of a target user when the target user executes a target interaction task;
a comparing unit 320, configured to compare the target operation index data with a preset operation index threshold; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
an identifying unit 330, configured to determine that the target user is a passive user if the target operation index data is not higher than the preset operation index threshold, and perform processing for the passive user.
According to an example, the apparatus further includes a construction unit 340, configured to obtain operation index data of a number of users when performing the target interaction task; determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users; constructing an index threshold model based on a plurality of acquired operation index data for normal users; and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
According to an example, when obtaining operation index data of a plurality of users when performing a target interaction task, the constructing unit 340 is further specifically configured to receive operation index data uploaded by a client and having a score exceeding a preset score, or upload operation index data for the plurality of users by the client based on a user instruction; or receiving operation index data which is uploaded by a client and aims at a plurality of users; respectively calculating the target scores of the operation index data of each user based on a preset scoring rule; and acquiring operation index data with the target score higher than the preset score.
According to an example, when obtaining operation index data of a plurality of users during execution of a target interaction task, the constructing unit 340 is further specifically configured to receive a part of operation index data uploaded by a client for the plurality of users; respectively simulating complete operation index data of each user based on part of operation index data uploaded by the client; and respectively calculating the target scores of the complete operation index data of the users based on a preset scoring rule, and acquiring the complete operation index data of which the target scores are higher than the preset scores.
According to one example, the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of operation index data samples of a plurality of normal users input into the model; the operation index data samples of the normal users are obtained by carrying out statistical analysis on the operation index data of the users or by calibration;
the comparing unit 320 is specifically configured to compare the target operation index data with an operation index threshold obtained based on statistical analysis of operation index data samples of a plurality of normal users.
According to one example, the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of historical operation index data samples of the user input into the model;
the comparing unit 320 is specifically configured to search an operation index threshold obtained by performing statistical analysis on a plurality of historical operation index data samples for the user; and comparing the target operation index data with the searched operation index threshold value.
The embodiment of the identification device of the passive user can be applied to the server. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the server where the device is located. From a hardware aspect, as shown in fig. 4, a hardware structure diagram of a server where the apparatus for identifying a negative user is located in the present application is shown, except for the processor 401, the machine-readable storage medium 402, and the network output interface 403 shown in fig. 4, the server where the apparatus is located in the embodiment may also include other hardware according to an actual function of the server, which is not described again.
In various embodiments, the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain stored information, such as executable instructions, data, and so forth. For example, the machine-readable storage medium may be: a RAM (random Access Memory), a volatile Memory, a non-volatile Memory, a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., a compact disk, a DVD, etc.), or similar storage medium, or a combination thereof.
Further, machine-readable storage medium 402 may have stored thereon machine-executable instructions corresponding to control logic for processor 401 executing negative user identification. For example, the machine-readable storage medium 402 may store machine-executable instructions corresponding to the obtaining unit 310, the comparing unit 320, the identifying unit 330, and the constructing unit 340 (not shown in fig. 4).
A processor of the server is caused to:
acquiring target operation index data of a target user when executing a target interaction task;
comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
and if the target operation index data is not higher than the preset operation index threshold value, judging that the target user is a negative user, and performing processing aiming at the negative user.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (7)
1. A method for identifying a passive user, wherein the method is applied to a server side, and the method comprises the following steps:
acquiring target operation index data of a target user when executing a target interaction task;
comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
if the target operation index data is not higher than the preset operation index threshold value, the target user is judged to be a passive user, and processing aiming at the passive user is carried out;
the method further comprises the following steps:
acquiring operation index data with the value higher than a preset value, which is uploaded by a client, as operation index data of a plurality of users when executing a target interaction task; and/or simulating each user to completely supplement part of the index data uploaded by the client, and using the supplemented complete operation index data with the score higher than a preset threshold value as operation index data of a plurality of users when the users execute the target interaction task;
determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users;
constructing an index threshold model based on a plurality of acquired operation index data for the normal user;
and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
2. The method according to claim 1, wherein the operation index threshold is obtained by a preset index threshold model based on statistical analysis of operation index data samples of a plurality of normal users input into the model; the operation index data samples of the normal users are obtained by carrying out statistical analysis on the operation index data of the users or by calibration;
the comparing the target operation index data with a preset operation index threshold value includes:
and comparing the target operation index data with an operation index threshold value obtained based on statistical analysis of operation index data samples of a plurality of normal users.
3. The method of claim 1, wherein the operation index threshold is obtained by a preset index threshold model based on statistical analysis of a number of historical operation index data samples of the user input into the model;
the comparing the target operation index data with a preset operation index threshold value includes:
searching an operation index threshold value obtained by carrying out statistical analysis on a plurality of historical operation index data samples of the user;
and comparing the target operation index data with the searched operation index threshold value.
4. An apparatus for identifying a passive user, the apparatus being applied to a server, the apparatus comprising:
the acquisition unit is used for acquiring target operation index data of a target user when a target interaction task is executed;
a comparison unit, configured to compare the target operation index data with a preset operation index threshold; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
the identification unit is used for judging that the target user is a passive user if the target operation index data is not higher than the preset operation index threshold value and carrying out processing aiming at the passive user;
the device also comprises a construction unit, a processing unit and a display unit, wherein the construction unit is used for acquiring operation index data with the value higher than a preset value, which is uploaded by the client and used as the operation index data of a plurality of users when the users execute the target interaction tasks; and/or simulating each user to completely supplement part of the index data uploaded by the client, and using the supplemented complete operation index data with the score higher than a preset threshold value as operation index data of a plurality of users when the users execute the target interaction task; determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users; constructing an index threshold model based on a plurality of acquired operation index data for the normal user; and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
5. The device of claim 4, wherein the operation index threshold is obtained by a preset index threshold model based on statistical analysis of operation index data samples of a plurality of normal users input into the model; the operation index data samples of the normal users are obtained by carrying out statistical analysis on the operation index data of the users or by calibration;
the comparison unit is specifically configured to compare the target operation index data with an operation index threshold obtained based on statistical analysis of operation index data samples of a plurality of normal users.
6. The apparatus of claim 4, wherein the operation index threshold is obtained by a preset index threshold model based on statistical analysis of a number of historical operation index data samples of the user input into the model;
the comparison unit is specifically configured to search an operation index threshold obtained by performing statistical analysis on a plurality of historical operation index data samples for the user; and comparing the target operation index data with the searched operation index threshold value.
7. A server comprising a processor and a machine-readable storage medium, the processor caused to:
acquiring target operation index data of a target user when executing a target interaction task;
comparing the target operation index data with a preset operation index threshold value; the operation index threshold value is obtained by a preset index threshold value model based on statistical analysis of a plurality of user operation index data samples input into the model;
if the target operation index data is not higher than the preset operation index threshold value, the target user is judged to be a passive user, and processing aiming at the passive user is carried out;
the processor is further caused to:
acquiring operation index data with the value higher than a preset value, which is uploaded by a client, as operation index data of a plurality of users when executing a target interaction task; and/or simulating each user to completely supplement part of the index data uploaded by the client, and using the supplemented complete operation index data with the score higher than a preset threshold value as operation index data of a plurality of users when the users execute the target interaction task;
determining operation index data of a normal user in the operation index data of the users; the operation index data of the normal users are obtained by carrying out statistical analysis or calibration on the operation index data of the users;
constructing an index threshold model based on a plurality of acquired operation index data for the normal user;
and dynamically optimizing the index threshold model based on the operation index data of the newly added user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710417460.8A CN107335220B (en) | 2017-06-06 | 2017-06-06 | Negative user identification method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710417460.8A CN107335220B (en) | 2017-06-06 | 2017-06-06 | Negative user identification method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107335220A CN107335220A (en) | 2017-11-10 |
| CN107335220B true CN107335220B (en) | 2021-01-26 |
Family
ID=60219885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710417460.8A Active CN107335220B (en) | 2017-06-06 | 2017-06-06 | Negative user identification method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107335220B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108854076A (en) * | 2018-06-12 | 2018-11-23 | 北京智明星通科技股份有限公司 | A kind of method, apparatus and server of identification mobile phone games cheating player |
| CN109304034A (en) * | 2018-10-25 | 2019-02-05 | 珠海市君天电子科技有限公司 | A kind of game cheat detection method and relevant device |
| CN111589147B (en) * | 2020-04-28 | 2022-04-08 | 腾讯科技（深圳）有限公司 | User interface display method, device, equipment and storage medium |
| CN111589102B (en) * | 2020-05-09 | 2023-01-10 | 腾讯科技（深圳）有限公司 | Auxiliary tool detection method, device, equipment and storage medium |
| CN112295231A (en) * | 2020-11-05 | 2021-02-02 | 中国联合网络通信集团有限公司 | Operation training method and server |
| CN112973128A (en) * | 2021-03-09 | 2021-06-18 | 杭州电魂网络科技股份有限公司 | Method, device, equipment and medium for automatically analyzing and processing passive game behaviors |
| CN114470788B (en) * | 2021-12-23 | 2023-03-24 | 北京达佳互联信息技术有限公司 | Abnormal user account identification method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402517A (en) * | 2010-09-09 | 2012-04-04 | 北京启明星辰信息技术股份有限公司 | Method and system for establishing normal database login model and method and system for detecting abnormal login behavior |
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| JP2014094170A (en) * | 2012-11-09 | 2014-05-22 | Gloops Inc | Game server, game control method, program, and game system |
| CN104980402A (en) * | 2014-04-09 | 2015-10-14 | 腾讯科技（北京）有限公司 | Method and device for recognizing malicious operation |
| CN106156026A (en) * | 2015-03-24 | 2016-11-23 | 中国人民解放军国防科学技术大学 | A kind of method based on the data online anomaly of stream fictitious assets |
| CN106789885A (en) * | 2016-11-17 | 2017-05-31 | 国家电网公司 | User's unusual checking analysis method under a kind of big data environment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561878B (en) * | 2009-05-31 | 2012-11-21 | 河海大学 | Unsupervised anomaly detection method and system based on improved CURE clustering algorithm |
| CN103390278B (en) * | 2013-07-23 | 2016-03-09 | 中国科学技术大学 | A kind of video unusual checking system |
| CN103699822B (en) * | 2013-12-31 | 2016-11-02 | 同济大学 | User's anomaly detection method in ecommerce based on mouse behavior |
-
2017
- 2017-06-06 CN CN201710417460.8A patent/CN107335220B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402517A (en) * | 2010-09-09 | 2012-04-04 | 北京启明星辰信息技术股份有限公司 | Method and system for establishing normal database login model and method and system for detecting abnormal login behavior |
| JP2014094170A (en) * | 2012-11-09 | 2014-05-22 | Gloops Inc | Game server, game control method, program, and game system |
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| CN104980402A (en) * | 2014-04-09 | 2015-10-14 | 腾讯科技（北京）有限公司 | Method and device for recognizing malicious operation |
| CN106156026A (en) * | 2015-03-24 | 2016-11-23 | 中国人民解放军国防科学技术大学 | A kind of method based on the data online anomaly of stream fictitious assets |
| CN106789885A (en) * | 2016-11-17 | 2017-05-31 | 国家电网公司 | User's unusual checking analysis method under a kind of big data environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107335220A (en) | 2017-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107335220B (en) | Negative user identification method and device and server | |
| CN107998661B (en) | Auxiliary decision-making method, device and storage medium for online battle game | |
| US11458399B2 (en) | Systems and methods for automatically measuring a video game difficulty | |
| CN108499108B (en) | Real-time dynamic modification and optimization of game play parameters within a video game application | |
| CN111773732B (en) | Target game user detection method, device and equipment | |
| CN109814955B (en) | Method and device for determining formation capacity and electronic equipment | |
| CN108920221B (en) | Game difficulty adjusting method and device, electronic equipment and storage medium | |
| US10272341B1 (en) | Procedural level generation for games | |
| US20150065251A1 (en) | Player generated content management | |
| US11253785B1 (en) | Incentivizing fair gameplay through bot detection penalization within online gaming systems | |
| CN116209506A (en) | Classifying gaming activities to identify abusive behavior | |
| JP7383151B2 (en) | Server-based individual play time estimation for game activity | |
| US11351464B2 (en) | Automated coaching for online gaming | |
| CN108905095B (en) | Athlete competition state evaluation method and equipment | |
| CN111035934A (en) | Game teaching method, device, electronic equipment and storage medium | |
| CN112245934B (en) | Data analysis method, device and equipment for virtual resources in virtual scene application | |
| CN110585722A (en) | Block chain-based game time information processing method and device and game control method and device | |
| Kummer et al. | Applying commitment to churn and remaining players lifetime prediction | |
| CN114342411A (en) | Method for providing one or more sets of graphics parameters, computer executing program for implementing the method for providing one or more sets of graphics parameters | |
| CN110368696B (en) | Method, device, equipment and medium for acquiring capability of asymmetric game player | |
| Kummer et al. | A key risk indicator for the game usage lifecycle | |
| JP2017023447A (en) | Server and program | |
| CN117695669A (en) | Method, device, equipment and storage medium for processing player data | |
| KR101640922B1 (en) | Ranking computation method, computer-readable medium and system | |
| CN113941157A (en) | Game matching method and device, electronic equipment and storage medium |
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 |