CN113975818A

CN113975818A - Abnormal role determination method and device, computer equipment and storage medium

Info

Publication number: CN113975818A
Application number: CN202111182440.XA
Authority: CN
Inventors: 高胜杰; 胡志鹏; 程龙; 刘勇成; 袁思思
Original assignee: Netease Hangzhou Network Co Ltd
Current assignee: Netease Hangzhou Network Co Ltd
Priority date: 2021-10-11
Filing date: 2021-10-11
Publication date: 2022-01-28

Abstract

The embodiment of the application discloses an abnormal role determination method, an abnormal role determination device, computer equipment and a storage medium; acquiring a winning rate set of each virtual role in the role pool, wherein the winning rate set comprises the winning rate of the virtual role in fight with other virtual roles; constructing a directed graph by taking all the virtual roles in the role pool as nodes and the victory ratio set of each virtual role as edges; determining an Euler loop in the directed graph; and determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate. In the embodiment of the application, a directed graph capable of representing the strength relationship between virtual characters can be automatically constructed according to the winning rate set of each virtual character, abnormal characters with abnormal winning rates are further determined according to Euler loops in the directed graph, the fight among players is automatically analyzed, and the automatic detection of the abnormal characters in the game is realized.

Description

Abnormal role determination method and device, computer equipment and storage medium

Technical Field

The application relates to the field of games, in particular to an abnormal role determination method, an abnormal role determination device, computer equipment and a storage medium.

Background

With the rapid development of network technology, network games are also receiving more and more attention from many people, especially Multiplayer Online Battle Arena (MOBA). For network games such as MOBA, unbalanced game characters greatly affect the life of the game, the unbalanced game characters may be too strong game characters or too weak game characters, and the unbalanced game characters may cause the balance of the whole game to be lost, which affects the life of the game.

At present, unbalanced characters in a game are determined according to feedback or self experience of a game player, and automatic detection of the unbalanced characters in the game is difficult to realize.

Disclosure of Invention

The embodiment of the application provides an abnormal role determination method, an abnormal role determination device, computer equipment and a storage medium, and unbalanced roles in a game can be automatically detected.

The embodiment of the application provides an abnormal role determination method, which comprises the following steps: acquiring a winning rate set of each virtual role in a role pool, wherein the winning rate set comprises the winning rate of the virtual role in fight with other virtual roles; constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge; determining an Euler loop in the directed graph; and determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate.

An embodiment of the present application further provides an abnormal role determination device, including: the system comprises an acquisition module, a judgment module and a processing module, wherein the acquisition module is used for acquiring a victory ratio set of each virtual role in a role pool, and the victory ratio set comprises victory ratios of the virtual roles in fight with other virtual roles; the building module is used for building a directed graph by taking all the virtual roles in the role pool as nodes and taking the win ratio set of each virtual role as an edge; a first determining module, configured to determine an euler loop in the directed graph; and the second determining module is used for determining an abnormal role from the role pool according to the Euler circuit, wherein the abnormal role is a virtual role with abnormal winning rate.

In some embodiments, the building module further comprises: a node determination unit, configured to use all virtual roles in the role pool as nodes, where each node represents a virtual role; the directed edge construction unit is used for constructing a directed edge according to the size relation between the winning rate of each virtual role and a preset value; and the directed graph determining unit is used for taking all the nodes and the directed edges as the directed graph.

In some embodiments, the directed edge construction unit comprises: a target role determining subunit, configured to determine a virtual role from the role pool as a target role; the designated role determination subunit is used for determining the winning rate which is greater than or equal to the preset value from the winning rates of the target role and other virtual roles in the battle as a designated winning rate, and the other virtual roles corresponding to the designated winning rate are designated roles; a construction subunit, configured to construct a directed edge pointing from the target role to the designated role; the target role determining subunit is further configured to determine a new target role from the virtual roles in the role pool except the target role, and the designated role determining subunit and the constructing subunit repeatedly perform the above steps in sequence until all virtual roles in the role pool are traversed.

In some embodiments, the first determining module is further configured to determine all connected graphs in the directed graph; for each connected graph, a candidate role determination unit in the second determination module is configured to determine a node in the connected graph, which is not in the euler loop, as a candidate node, and determine a virtual role corresponding to the candidate node as a candidate role; an abnormal role determination unit in the second determination module is used for determining the abnormal role from the candidate roles if the number of the established directed graphs is equal to a preset number; if the number of the established directed graphs is not equal to the preset number, after the preset value is updated, the construction module, the first determination module and the second determination module sequentially repeat the steps until the number of the established directed graphs is equal to the preset number.

In some embodiments, the abnormal role determination unit is further configured to determine a number of times the virtual role is determined to be a candidate role; and determining the virtual role with the frequency greater than the preset frequency as the abnormal role.

In some embodiments, the out-degree of a node in the euler loop is equal to the in-degree, and the abnormal role determination unit is further configured to obtain the out-degree and the in-degree of the candidate node in the connected graph; determining that the abnormal state of the candidate role is too strong under the condition that the out-degree is greater than the in-degree; and determining that the abnormal state of the candidate role is too weak under the condition that the out-degree is smaller than the in-degree.

In some embodiments, the abnormal role determination unit is further configured to increase or decrease the preset value according to a preset change value to obtain a new preset value.

In some embodiments, the obtaining module is further configured to obtain a game log; obtaining the fighting characteristics of each fighting record in the game log, wherein the fighting characteristics comprise the type of fighting, the duration of fighting and the reason for ending; and acquiring the winning rate set from the fighting records with the fighting characteristics meeting preset conditions.

The embodiment of the application also provides computer equipment, which comprises a memory, a storage and a control unit, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to perform any of the steps of the method for determining an abnormal role provided by the embodiments of the present application.

The embodiment of the present application further provides a computer-readable storage medium, where a plurality of instructions are stored in the computer-readable storage medium, and the instructions are suitable for being loaded by a processor to perform any one of the steps in the method for determining an abnormal role provided in the embodiment of the present application.

According to the embodiment of the application, the victory ratio set of each virtual character can be obtained, the directed graph capable of representing the strength relation between the virtual characters is automatically constructed based on the victory ratio set, the abnormal character with abnormal victory ratio is further determined according to the Euler loop in the directed graph, the fight among players can be automatically analyzed, the automatic detection of the abnormal character is realized, the feedback of the players is not required to be waited, and therefore the detection efficiency of the abnormal character is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic system diagram for implementing an abnormal role determination method according to an embodiment of the present application;

fig. 2 is a flowchart illustrating an abnormal role determination method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a directed graph provided by an embodiment of the present application;

FIG. 4 is a flowchart illustrating an abnormal role determination method according to another embodiment of the present application;

FIG. 5 is a flow chart providing some of the steps of an abnormal role determination method based on the embodiment provided in FIG. 4;

FIG. 6 is a flowchart illustrating an abnormal role determination method according to still another embodiment of the present application;

fig. 7 is a schematic structural diagram of an abnormal role determination device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides an abnormal role determination method, an abnormal role determination device, computer equipment and a storage medium.

The abnormal role determination apparatus may be specifically integrated in a computer device, and the computer device may be a terminal, a server, or other devices. The terminal can be a mobile phone, a tablet Computer, an intelligent bluetooth device, a notebook Computer, or a Personal Computer (PC), and the like; the server may be a single server or a server cluster composed of a plurality of servers.

In some embodiments, the abnormal role determination apparatus may also be integrated into multiple computer devices, for example, the abnormal role determination apparatus may be integrated into multiple servers, and the abnormal role determination method of the present application is implemented by the multiple servers.

In some embodiments, the server may also be implemented in the form of a terminal.

For example, referring to fig. 1, fig. 1 is a schematic diagram of a system for implementing abnormal role determination according to an embodiment of the present application, where the system may include at least one terminal 1000, at least one server 2000, at least one database 3000, and a network 4000. The terminal 1000 held by the user can be connected to the server 2000 through the network 4000. Wherein terminal 1000 is any device having computing hardware capable of supporting and executing a software product corresponding to a game; the server 2000 may be a single server, or may be a cluster of servers; the network 4000 may be a wireless network or a wired network, such as a Wireless Local Area Network (WLAN), a Local Area Network (LAN), a cellular network, a 2G network, a 3G network, a 4G network, a 5G network, and so on. In addition, different terminals 1000 may also be connected to other terminals or to the server 2000 using their own bluetooth network or hotspot network. In addition, the system may further include at least one database 3000, the database 3000 storing game data generated when the user uses the terminal 1000.

The following are detailed below. The numbers in the following examples are not intended to limit the order of preference of the examples.

Referring to fig. 2, a flow chart of the abnormal role determination method according to the embodiment of the present application is shown, where the method may be executed by a computer device, and the computer device may be a terminal, a server, or other devices.

S110, acquiring a winning rate set of each virtual character in the character pool, wherein the winning rate set comprises the winning rates of the virtual character in fight with other virtual characters.

The character pool may be a set of all virtual characters in a game, or may be a set of virtual characters counted from a game log. For each virtual character in the character pool, a winning rate set of each virtual character can be obtained, wherein the winning rate set comprises the winning rates of the virtual character in fight with other virtual characters, and the winning rate refers to the ratio of the number of winning times to the number of fighting times. For example, the character pool includes a virtual character a, a virtual character B and a virtual character C, the winning rate set of the virtual character a includes the winning rate of the virtual character a when the virtual character a and the virtual character B fight against each other, and the winning rate of the virtual character a when the virtual character a and the virtual character C fight against each other, where the winning rate of the virtual character a when the virtual character a and the virtual character B fight against each other refers to the ratio of the winning number of the virtual character a to the total number of the virtual character a when the virtual character a and the virtual character B fight against each other. It can be understood that when virtual character a and virtual character B are paired, the sum of the win rate of virtual character a and the win rate of virtual character B is 1.

In some embodiments, the winning rate set of each virtual character may be represented by using a matrix, or the winning rate set of each virtual character is represented by using a matrix corresponding to each virtual character, and may be set according to actual needs, which is not specifically limited herein.

In some embodiments, the winning rate set of each virtual character may be obtained by first obtaining a game log, and obtaining the winning rate set of each virtual character based on the game log. To ensure that an accurate set of odds is obtained for each virtual character, the game log obtained may be filtered in advance. Specifically, obtaining the winning rate set of each virtual role may include:

obtaining a game log; obtaining the fighting characteristics of each fighting record in the game log, wherein the fighting characteristics comprise the type of fighting, the duration of fighting and the reason for ending; and acquiring the winning rate set from the fighting records with the fighting characteristics meeting preset conditions.

When the game log is acquired, the game log in a preset time period can be acquired, and the preset time period can be set according to actual needs. For example, the preset time period may be all time periods before the current time is set, and may also be all time periods from the time a certain game version is on-line to the current time. The game log can be a real game log generated when a player plays a game, and can also be a game log generated in a game testing stage.

The fighting type refers to a game mode of fighting time, and may refer to a ranking game, an entertainment game and the like, the fighting duration refers to the total time from the beginning to the end of a game, and the end reason refers to the reason of the end of the game, for example, any game player actively drops and normally ends when meeting the game end condition, wherein the game end condition may be that any party of the game players obtains a preset score value, or any party of the game players defeats a target, and the like.

The preset conditions can comprise sub-conditions corresponding to each fighting characteristic, when each fighting characteristic meets the corresponding sub-condition, the fighting characteristics are considered to meet the preset conditions, when any one fighting characteristic meets the corresponding sub-condition, the fighting characteristics are considered to meet the preset conditions, the fighting characteristics can be specifically set according to actual needs, and specific limitation is not made herein.

In practical application, the sub-condition corresponding to the battle type may be that the battle type is a ranking game, the sub-condition corresponding to the battle duration may be that the battle duration is greater than or equal to 10 minutes, the sub-condition corresponding to the ending reason may not be actively committed to fall for any game player, and the preset condition may be that each sub-condition is simultaneously met, so as to screen the battle records in the game log, and obtain the winning rate set from the battle records meeting the preset condition.

In some embodiments, the winning rate set of each virtual character can be obtained directly through a plug-in with a winning rate calculation function.

After the win rate set for each virtual character is obtained, a directed graph can be constructed using the win rate sets for further analysis.

And S120, constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge.

When the directed graph is constructed, all the virtual roles in the role pool can be used as nodes, and edges between the nodes are constructed according to the winning rate set of each virtual role, so that the directed graph is obtained. One node in the constructed directed graph represents one virtual role in one role pool, and edges between the nodes represent the capacity strength relation of the two virtual roles. Referring specifically to fig. 3, a schematic diagram of a directed graph is shown, in fig. 3, a node a represents a virtual character a, a node E represents a virtual character E, and the node a points to the node E, indicating that the virtual character a is stronger than the virtual character E.

For example, if the directed edge points from the virtual character B to the virtual character a, the capability of representing the virtual character a is stronger than that of the virtual character B, and if the directed edge points from the virtual character B to the virtual character a, the capability of representing the virtual character B is stronger than that of the virtual character a.

Specifically, the directed edge may be constructed in the following manner: determining a virtual role as a target role from the role pool; determining the victory ratio which is greater than or equal to the preset value from the victory ratios of the target role and other virtual roles as a designated victory ratio, wherein the other virtual roles corresponding to the designated victory ratio are designated roles; constructing a directed edge pointing from the target role to the designated role; determining a new target role from the virtual roles in the role pool except the target role, and returning to execute the following steps: determining the rate of winning greater than a preset value as a designated rate of winning from the rates of winning the target role and other virtual roles, wherein the other virtual roles corresponding to the designated rate of winning are designated roles; and constructing a directed edge pointing to the designated role from the target role until all virtual roles in the role pool are traversed.

For example, a virtual character a, a virtual character B and a virtual character C are in the character pool, the target character is the virtual character a, the victory ratio set of the virtual character a includes M (a, B) and M (a, C), where M (a, B) represents the victory ratio of the virtual character a to the virtual character B in the battle, M (a, C) represents the victory ratio of the virtual character a to the virtual character C in the battle, if it is determined that M (a, C) is greater than a preset value, it is determined that M (a, C) is the designated victory ratio, and virtual character C is the designated character, so that a directed edge pointing from the virtual character a to the virtual character C can be constructed. And sequentially determining the virtual role B and the virtual role C as target roles, and repeating the process to construct directed edges between each virtual role and other virtual roles.

The preset value is an empirical value, the value range of the preset value is 0 to 1, and the preset value can be set according to actual needs and is not specifically limited herein.

And S130, determining an Euler loop in the directed graph.

After the directed graph is constructed, the directed graph can be further processed to determine an euler loop in the directed graph. When determining the euler loop in the directed graph, all the connected graphs in the directed graph may be determined, and then whether the euler loop exists or not may be determined from each connected graph. If any two points in a graph are connected, the connection means that the two points are connected by a path, and the graph is a connection graph. If a path in a graph is traced around each edge of the directed graph, and each edge of the directed graph is traced exactly once, the path is called an euler path, and if a loop is an euler path, the loop is an euler loop.

If an euler loop exists in a directed graph, the precondition is a connected graph, and the out degree and the in degree of each node in the directed graph are equal, wherein the out degree refers to the number of edges with the node as a head, and the in degree refers to the number of edges with the node as a tail, for example, the out degree of the node a in fig. 3 is 2, the in degree is 2, the out degree of the node E is 0, and the in degree is 1. That is, the degree of egress and the degree of ingress are equal for each node in the euler loop. Referring to FIG. 3, the path A-C-D-B in FIG. 3 is an Euler loop.

There are two main methods for solving the euler loop, one is DFS search, and the other is the Fleury algorithm. The idea of solving the Euler loop by DFS search is as follows: after an Euler theorem is used for judging that an Euler loop exists in a graph, a correct initial node is selected, all edges are traversed by a DFS algorithm (each edge is traversed once), and the graph is rolled back when walking is stopped. And recording the traversed edges in sequence in the search advancing direction. The arrangement of the set of edges forms an euler loop. The specific implementation manner of the DFS search and the Fleury algorithm is the same as the existing one, and is not described herein again.

S140, determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate.

After determining the euler loop in the directed graph, an abnormal role may be determined based on the euler loop, where the abnormal role refers to a virtual role with an abnormal winning rate, the winning rate abnormality may refer to that the winning rate is too high or too low, the capability of the virtual role with the too high winning rate is too strong, and the capability of the virtual role with the too low winning rate is too weak.

One directed graph can determine a corresponding abnormal role, and in order to improve the accuracy of determining the abnormal role, S120 can be repeated to construct a plurality of directed graphs, specifically, an euler loop in the directed graph is determined; determining an abnormal role from the role pool according to the euler loop may include: determining all connected graphs in the directed graph; determining nodes which are not in the Euler loop in the connected graph as candidate nodes for each connected graph, and determining virtual roles corresponding to the candidate nodes as candidate roles; if the number of the established directed graphs is equal to the preset number, determining the abnormal roles from the candidate roles; if the number of the established directed graphs is not equal to the preset number, after the preset value is updated, the following steps are returned to be executed: constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge; and determining abnormal roles from the role pool according to the Euler loop until the number of the established directed graphs is equal to the preset number. That is to say, the preset value may be updated, a preset number of directed graphs are constructed, for each directed graph, the connected graph in the directed graph is determined, and for each connected graph, when it is determined that an euler loop exists in the connected graph, a node which is not in the euler loop is taken as a candidate node. If the directed graph shown in fig. 3 is a connected graph, where the paths a-C-D-B are euler loops, then nodes E and F may be determined as candidate nodes.

In some embodiments, if no euler loop exists in the connected graph, all nodes in the connected graph may not be considered to be in the euler loop, and all nodes in the connected graph may be determined as candidate nodes.

The method comprises the steps of establishing a plurality of directed graphs, determining candidate roles corresponding to each directed graph, and determining abnormal roles from the candidate roles when the number of the established directed graphs is equal to a preset number. Specifically, the determining the abnormal role from the candidate roles may include: determining a number of times the virtual character is determined to be a candidate character; and determining the virtual role with the frequency greater than the preset frequency as the abnormal role.

The abnormal role determination scheme provided by the embodiment of the application can be applied to game planning scenes and is suitable for balance detection of roles in any MOBA game. For example, in the case of a certain MOBA game, a player can obtain a match result by using a virtual character in the game to match. The method comprises the steps that a victory ratio set of each virtual character used by a player can be obtained based on the fight of the player, and after the victory ratio set is obtained, a directed graph is constructed by taking all the virtual characters in a character pool as nodes and the victory ratio set of each virtual character as edges; determining an Euler loop in the directed graph; and determining abnormal roles from the role pool according to the Euler loop. The game planner can adjust the value or setting of the abnormal role according to the determined abnormal role so as to ensure the balance of the game and prolong the service life of the game.

The abnormal role determining method provided by the embodiment of the application can obtain the success rate set of each virtual role, automatically construct a directed graph capable of representing the strength relationship between the virtual roles based on the success rate set, further determine the abnormal role with abnormal success rate according to the Euler loop in the directed graph, automatically analyze the fight among players without waiting for the feedback of the players, realize the automatic detection of the abnormal role, and further improve the detection efficiency of the abnormal role.

Referring to fig. 4, a flow chart of an abnormal role determination method according to another embodiment of the present application is illustrated, and a process of constructing a directed graph is described in detail below on the basis of the foregoing embodiment.

S210, acquiring a winning rate set of each virtual role in the role pool, wherein the winning rate set comprises the winning rates of the virtual roles in fight with other virtual roles.

S210 may refer to corresponding parts of the foregoing embodiments, and details are not repeated herein to avoid repetition.

S220, taking all the virtual roles in the role pool as nodes, wherein each node represents one virtual role.

And S230, constructing a directed edge according to the size relation between the winning rate of each virtual role and a preset value.

When constructing a directed graph, all virtual roles in the role pool can be taken as nodes, and each node represents one virtual role. After the node is determined, a directed edge may be constructed according to a magnitude relationship between the winning rate of each virtual character and the preset value, specifically, referring to fig. 5, constructing a directed edge according to a magnitude relationship between the winning rate of each virtual character and the preset value may further include the following steps.

S231, determining a virtual role as a target role from the role pool.

The target role refers to a currently determined virtual role, and is any virtual role in the role pool.

S232, determining the victory ratio which is larger than or equal to the preset value from the victory ratios of the target role and other virtual roles as a designated victory ratio, wherein the other virtual roles corresponding to the designated victory ratio are designated roles.

Determining one virtual character as a target character from the character pool, and determining the winning rate which is greater than or equal to a preset value as an appointed winning rate from the winning rate of the target character in fight with other virtual characters, namely from the winning rate set of the target character, wherein other virtual characters corresponding to the appointed winning rate are the appointed characters. For example, the target character is a virtual character a, the winning rate set includes M (a, B) and M (a, C), M (a, B) represents that the virtual character a and the virtual character B match each other, the winning rate of the virtual character a is obtained, and M (a, C) represents that the virtual character a and the virtual character C match each other, and the winning rate of the virtual character a is obtained. If M (A, B) is determined to be the designated rate, the designated role is the virtual role B, and if M (A, C) is determined to be the designated rate, the designated role is the virtual role C.

S233, constructing a directed edge pointing to the designated role from the target role.

And after the designated role is determined, constructing a directed edge pointing to the designated role from the target role.

S234, judging whether all virtual roles in the role pool are traversed or not; if not, executing S235; if so, ending the process.

After the target role and the directed edge of the designated role are constructed, whether all virtual roles in the role pool are traversed or not can be judged. Whether all virtual roles in the role pool are traversed or not refers to whether each virtual role in the role pool is determined to be a target role or not.

In some embodiments, a role set may be set, where the role set includes all virtual roles in the role pool, and each time a target role is determined, the target role is deleted from the role set. When judging whether all the virtual roles in the role pool are traversed, judging whether the role set is empty; if the role set is empty, judging that all virtual roles in the role pool have been traversed; and if the role set is not empty, judging that all virtual roles in the role pool are not traversed.

In some embodiments, a role set may be set, a number is set for each virtual role in the role set, the number is a continuous number, and the virtual roles are determined as target roles according to the numbers in sequence. When determining whether to traverse all the virtual roles in the role pool, the number of the currently determined target role is obtained, the number of the first determined target role is obtained as an initial number, and if the difference value between the current number and the initial number plus 1 is equal to the number of the virtual roles in the role pool, all the virtual roles in the role pool are judged to have been traversed; and if the number is smaller than the number of the virtual roles in the role pool, judging that all the virtual roles in the role pool are not traversed. As in the foregoing example, if the virtual character a is numbered 1, the virtual character B is numbered 2, and the virtual character C is numbered 3, the virtual character a, the virtual character B, and the virtual character C are sequentially determined as target characters, when the virtual character C is determined as a target character, the corresponding number of the virtual character 3 is 3, the first virtual character a determined as a target character is the first virtual character a, the starting number is 1, and at this time, 3-1+1 is equal to 3, which is equal to the number of virtual characters in the character pool, it can be considered that all virtual characters in the character pool have been traversed.

If all the virtual roles in the role pool are judged to be traversed, the completion of the construction of the directed graph is represented; if it is determined that all the virtual roles in the role pool have not been traversed, execution continues with S235.

S235, determining a new target role from the virtual roles except the target role in the role pool.

And if determining that all the virtual roles in the role pool are not traversed, determining a new target role from the virtual roles except the target role in the role pool, namely determining the new target role from other virtual roles.

In some embodiments, a role set may be set, where the role set includes all virtual roles in the role pool, and each time a target role is determined, the target role is deleted from the role set, and when a new target role is determined, a virtual role may be directly determined as the target role from the role set.

In some embodiments, a role set may be set, and each virtual role in the role set is numbered as a consecutive number, and when a new target role is determined, the number corresponding to the current target role is incremented by 1 to obtain a new number, and the virtual role corresponding to the new number is determined as a new target role.

After determining a new target role, the process returns to performing S232, S233 and S234 until all virtual roles in the role pool are traversed.

And S240, taking all the nodes and the directed edges as the directed graph.

After all the nodes and the directed edges are constructed, all the nodes and the directed edges can be used as the established directed graph.

And S250, determining an Euler loop in the directed graph.

S260, determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate.

S250 to S260 refer to corresponding parts in the foregoing embodiments, and are not described herein again.

According to the abnormal role determining method provided by the embodiment of the application, when the directed edges between the nodes are constructed, one virtual role is determined to be a target role from the role pool, the success rate which is greater than or equal to the preset value is determined to be an appointed success rate from the success rate of the target role and other virtual roles in fight, and the other virtual roles corresponding to the appointed success rate are appointed roles; and constructing a directed edge pointing to the designated role from the target role, considering that the directed graph is constructed completely when all the virtual roles in the role pool are traversed, re-determining a new target role when all the virtual roles in the role pool are not traversed, and continuously constructing the directed edge so as to ensure that the constructed directed graph is complete and accurate.

Referring to fig. 6, a flow chart of an abnormal role determination method according to still another embodiment of the present application is shown, and based on the foregoing embodiment, processes of determining an euler loop in the directed graph and determining an abnormal role from a role pool according to the euler loop are mainly described, which will be described in further detail below.

S310, acquiring a winning rate set of each virtual character in the character pool, wherein the winning rate set comprises the winning rates of the virtual character in fight with other virtual characters.

S320, constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge.

S310 to S320 refer to corresponding parts in the foregoing embodiments, and are not described herein again.

S330, determining all connected graphs in the directed graph.

S340, for each connected graph, determining nodes which are not in the Euler loop in the connected graph as candidate nodes, and determining virtual roles corresponding to the candidate nodes as candidate roles.

If an Euler loop exists in a directed graph, the directed graph is a connected graph, and the out-degree of all nodes is equal to the in-degree. Based on the determination principle, all the connected graphs in the directed graph can be determined, and then whether the euler loop exists in the connected graphs or not can be determined. If the Euler loop exists in the connected graph, determining the nodes which are not in the Euler loop in the connected graph as candidate nodes, and determining the virtual roles corresponding to the candidate nodes as candidate roles. The out-degree and the in-degree of the nodes in the euler loop are equal, it can be considered that virtual roles represented by the nodes can be mutually balanced, and the virtual roles not represented by the nodes in the euler loop are possibly abnormal.

In some embodiments, if there is no connected graph in the directed graph, S350 may be directly performed.

In one embodiment, if it is determined that no euler loop exists in the connected graph, all nodes in the connected graph may not be considered to be in the euler loop, and all nodes in the connected graph may be determined as candidate nodes.

The candidate role refers to a virtual role which is possibly abnormal, and after the candidate role is determined, the possible abnormal state of the candidate role can be determined according to the graph characteristics of the candidate nodes. Since the out-degree and the in-degree of the nodes in the euler loop in the connected graph are equal, and then the out-degree and the in-degree of the nodes not in the euler loop are unequal, when the abnormal state of the candidate role is determined, the out-degree and the in-degree of the candidate nodes in the connected graph can be obtained; when the out-degree is greater than the in-degree, the abnormal state of the candidate role can be considered to be too strong; when the out-degree of the candidate node is smaller than the in-degree, the abnormal state of the candidate role can be considered to be too weak.

S350, judging whether the number of the established directed graphs is equal to a preset number or not; if not, executing S360; if yes, go to step S370.

If the abnormal role is determined only according to one established directed graph, the determined abnormal role may be inaccurate enough, in order to further improve the accuracy of the determined abnormal role, a plurality of directed graphs may be established to improve the accuracy of the determination of the abnormal role, and specifically, it may be determined whether the number of the established directed graphs is equal to a preset number, where the preset number is any positive integer set according to actual needs. If it is determined that the number of the created directed graphs is not equal to the preset number, S360 may be performed, and if it is determined that the number of the created directed graphs is equal to the preset number, S370 may be performed.

And S360, updating the preset value.

When the directed graph is constructed, all the virtual roles in the role pool are used as nodes, directed edges are constructed according to the magnitude relation between the winning rate of each virtual role and the preset value, and the change of the preset value can cause the change of the directed edges of the directed graph, so that when the number of the constructed directed graphs is not equal to the preset number, the step of constructing the directed graph can be executed after the preset value is updated, that is, after S360 is executed, S320 to S350 can be executed again, and until the number of the constructed directed graphs is judged to be equal to the preset number, S370 is executed.

In some embodiments, when the preset value is updated, the preset value may be increased or decreased according to a preset change value to obtain a new preset value. Specifically, the current preset value and the preset change value may be subjected to operations, including but not limited to operations such as addition, subtraction, multiplication, division, and the like, and it should be noted that, after the preset value is increased or decreased according to the preset change value, the value range of the obtained new preset value is still 0 to 1.

In some embodiments, a preset value set may be set in advance, where the preset value set includes a plurality of different preset values set by a planner in advance, and when updating the preset values, one preset value different from a current preset value may be selected from the preset value set as a new preset value.

And S370, identifying abnormal roles from the candidate roles.

The candidate roles are virtual roles corresponding to the candidate nodes in the directed graph, and the determined candidate roles may include a plurality of virtual roles. Specifically, a candidate role set may be created, and virtual roles determined as candidate roles each time are stored in the candidate role set, where the candidate roles may include a plurality of identical virtual roles. For example, the candidate character set may include virtual character a, virtual character C, virtual character a, and virtual character a.

In some embodiments, when the abnormal role is determined from the candidate roles, the number of times that the virtual role is determined as the candidate role may be determined; and determining the virtual role with the frequency greater than the preset frequency as the abnormal role. The preset times can be any value set according to needs. For example, the preset number of times is set to 2, the candidate character set includes a virtual character a, a virtual character C, a virtual character a, and a virtual character a, where the number of times that the virtual character a is determined as a candidate character is 3, and the number of times that the virtual character C is determined as a candidate character is 1, so that the virtual character a can be determined as an abnormal character.

After the candidate character is determined, the abnormal state of the candidate character can be further determined. As an embodiment, the determined abnormal state correspondence of each candidate character may be stored in the candidate character set. For example, the abnormal state determined by the virtual character a in a certain directed graph is too weak, and the abnormal state determined by the virtual character a in another directed graph is possibly too strong. After the abnormal role is determined, the abnormal states of the abnormal role can be all taken as the abnormal states of the abnormal role, and the number of times of occurrence of each abnormal state can be counted and associated with the determined abnormal role, for example, the abnormal role is the virtual role a-too strong 3 times-too weak 2 times, which means that the abnormal state of the virtual role a is determined to be too strong 3 times and determined to be too weak 2 times.

According to the abnormal role determining method provided by the embodiment of the application, after the directed graph is established, the candidate nodes and the candidate roles are determined according to Euler loops in the directed graph, when the number of the established directed graphs is equal to the preset number, the abnormal roles are determined from the candidate roles, when the number of the established directed graphs is not equal to the preset number, the preset value is updated, the directed graph is reconstructed according to the updated preset value, the number of the established directed graphs is enough, the condition that the abnormal roles determined according to a single directed graph are not accurate enough is avoided, a certain number of the candidate roles can be determined based on a certain number of the directed graphs, the abnormal roles are further determined according to the number of times that the virtual roles are determined as the candidate roles, and the accuracy of determining the abnormal roles can be further improved.

In order to better implement the method, an abnormal role determination device is further provided in the embodiments of the present application, where the abnormal role determination device may be specifically integrated in a computer device, and the computer device may be a terminal, a server, or other devices. The terminal can be a mobile phone, a tablet computer, an intelligent Bluetooth device, a notebook computer, a personal computer and other devices; the server may be a single server or a server cluster composed of a plurality of servers.

For example, in this embodiment, the method of the embodiment of the present application will be described in detail by taking an example in which the abnormal role determination device is specifically integrated in a computer device.

For example, as shown in fig. 7, the abnormal role determination apparatus may include an acquisition module 410, a construction module 420, a first determination module 430, and a second determination module 440. The obtaining module 410 is configured to obtain a winning rate set of each virtual character in the character pool, where the winning rate set includes the winning rate of the virtual character competing with other virtual characters; a building module 420, configured to build a directed graph with all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge; a first determining module 430, configured to determine an euler loop in the directed graph; a second determining module 440, configured to determine an abnormal role from the role pool according to the euler loop, where the abnormal role is a virtual role with an abnormal winning rate.

In some embodiments, the building module 420 further comprises: a node determination unit, configured to use all virtual roles in the role pool as nodes, where each node represents a virtual role; the directed edge construction unit is used for constructing a directed edge according to the size relation between the winning rate of each virtual role and a preset value; and the directed graph determining unit is used for taking all the nodes and the directed edges as the directed graph.

In some embodiments, the first determination module 430 is further configured to determine all connected graphs in the directed graph; for each of the connected graphs, the candidate role determination unit in the second determination module 440 is configured to determine a node in the connected graph that is not in the euler loop as a candidate node, and determine a virtual role corresponding to the candidate node as a candidate role; an abnormal role determination unit in the second determination module 440 is configured to determine the abnormal role from the candidate roles if the number of the created directed graphs is equal to a preset number; if the number of the created directed graphs is not equal to the preset number, after the preset value is updated, the constructing module 420, the first determining module 430 and the second determining module 440 sequentially repeat the above steps until the number of the created directed graphs is equal to the preset number.

In some embodiments, the obtaining module 410 is further configured to obtain a game log; obtaining the fighting characteristics of each fighting record in the game log, wherein the fighting characteristics comprise the type of fighting, the duration of fighting and the reason for ending; and acquiring the winning rate set from the fighting records with the fighting characteristics meeting preset conditions.

In specific implementation, the above modules may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and specific implementation of the above modules may refer to the foregoing method embodiments, which are not described herein again.

As can be seen from the above, the abnormal character determination device of this embodiment can obtain the success rate set of each virtual character, automatically construct a directed graph that can represent the strength relationship between the virtual characters based on the success rate set, further determine the abnormal character with the abnormal success rate according to the euler loop in the directed graph, and can automatically analyze the battle between players without waiting for the feedback of the players, thereby implementing the automatic detection of the abnormal character, and thus improving the detection efficiency of the abnormal character.

Correspondingly, the embodiment of the present application further provides a computer device, where the computer device may be a terminal or a server, and the terminal may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a touch screen, a game machine, a Personal computer, and a Personal Digital Assistant (PDA).

As shown in fig. 8, fig. 8 is a schematic structural diagram of a computer device 500 according to an embodiment of the present application, where the computer device 500 includes a processor 501 having one or more processing cores, a memory 502 having one or more computer-readable storage media, and a computer program stored in the memory 502 and capable of running on the processor. The processor 501 is electrically connected to the memory 502. Those skilled in the art will appreciate that the computer device configurations illustrated in the figures are not meant to be limiting of computer devices and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.

The processor 501 is a control center of the computer device 500, connects various parts of the entire computer device 500 using various interfaces and lines, performs various functions of the computer device 500 and processes data by running or loading software programs and/or modules stored in the memory 502, and calling data stored in the memory 502, thereby monitoring the computer device 500 as a whole.

In this embodiment of the application, the processor 501 in the computer device 500 loads instructions corresponding to processes of one or more applications into the memory 502, and the processor 501 runs the applications stored in the memory 502, so as to implement various functions as follows:

acquiring a winning rate set of each virtual role in a role pool, wherein the winning rate set comprises the winning rate of the virtual role in fight with other virtual roles; constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge; determining an Euler loop in the directed graph; and determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

Optionally, as shown in fig. 8, the computer device 500 further includes: touch-sensitive display screen 503, radio frequency circuit 504, audio circuit 505, input unit 506 and power 507. The processor 501 is electrically connected to the touch display screen 503, the radio frequency circuit 504, the audio circuit 505, the input unit 506, and the power supply 507, respectively. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 8 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.

The touch display screen 503 can be used for displaying a graphical user interface and receiving an operation instruction generated by a user acting on the graphical user interface. The touch display screen 503 may include a display panel and a touch panel. The display panel may be used, among other things, to display information entered by or provided to a user and various graphical user interfaces of the computer device, which may be made up of graphics, text, icons, video, and any combination thereof. Alternatively, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. The touch panel may be used to collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel using any suitable object or accessory such as a finger, a stylus pen, and the like), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Alternatively, the touch panel may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 501, and can receive and execute commands sent by the processor 501. The touch panel may overlay the display panel, and when the touch panel detects a touch operation thereon or nearby, the touch panel transmits the touch operation to the processor 501 to determine the type of the touch event, and then the processor 501 provides a corresponding visual output on the display panel according to the type of the touch event. In the embodiment of the present application, the touch panel and the display panel may be integrated into the touch display screen 503 to implement input and output functions. However, in some embodiments, the touch panel and the touch panel can be implemented as two separate components to perform the input and output functions. That is, the touch display 503 can also be used as a part of the input unit 506 to implement an input function.

The rf circuit 504 may be used for transceiving rf signals to establish wireless communication with a network device or other computer device via wireless communication, and for transceiving signals with the network device or other computer device.

Audio circuitry 505 may be used to provide an audio interface between a user and a computer device through speakers, microphones. The audio circuit 505 may transmit the electrical signal converted from the received audio data to a speaker, and convert the electrical signal into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 505 and converted into audio data, which is then processed by the audio data output processor 501, and then transmitted to, for example, another computer device via the rf circuit 504, or output to the memory 502 for further processing. The audio circuitry 505 may also include an earbud jack to provide communication of a peripheral headset with the computer device.

The input unit 506 may be used to receive input numbers, character information, or user characteristic information (e.g., fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

The power supply 507 is used to power the various components of the computer device 500. Optionally, the power supply 507 may be logically connected to the processor 501 through a power management system, so as to implement functions of managing charging, discharging, power consumption management, and the like through the power management system. The power supply 507 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

Although not shown in fig. 8, the computer device 500 may further include a camera, a sensor, a wireless fidelity module, a bluetooth module, etc., which are not described in detail herein.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

As can be seen from the above, the computer device provided in this embodiment may obtain the odds and ends set of each virtual character, automatically construct a directed graph that may represent the strength relationship between the virtual characters based on the odds and ends set, further determine an abnormal character with an abnormal odds and ends set according to an euler loop in the directed graph, may automatically analyze the battle between players, implement the automatic detection of the abnormal character, and need not wait for the feedback of the player, thereby improving the detection efficiency of the abnormal character.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer programs can be loaded by a processor to execute the steps in any one of the abnormal role determination methods provided by the present application. For example, the computer program may perform the steps of:

Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the computer program stored in the storage medium can execute the steps in any abnormal role determination method provided in the embodiments of the present application, beneficial effects that can be achieved by any abnormal role determination method provided in the embodiments of the present application can be achieved, and detailed descriptions are omitted herein for the details see the foregoing embodiments.

The method, the apparatus, the storage medium, and the computer device for determining an abnormal role provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An abnormal role determination method, comprising:

acquiring a winning rate set of each virtual role in a role pool, wherein the winning rate set comprises the winning rate of the virtual role in fight with other virtual roles;

constructing a directed graph by taking all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as an edge;

determining an Euler loop in the directed graph;

and determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate.

2. The method of claim 1, wherein the constructing a directed graph with all the virtual roles in the role pool as nodes and the winning rate set of each virtual role as edges comprises:

taking all virtual roles in the role pool as nodes, wherein each node represents a virtual role;

constructing a directed edge according to the magnitude relation between the winning rate of each virtual role and a preset value;

and taking all nodes and directed edges as the directed graph.

3. The method of claim 2, wherein the constructing the directed edge according to the magnitude relationship between the winning rate of each virtual character and the preset value comprises:

determining a virtual role as a target role from the role pool;

determining the victory ratio which is greater than or equal to the preset value from the victory ratios of the target role and other virtual roles as a designated victory ratio, wherein the other virtual roles corresponding to the designated victory ratio are designated roles;

constructing a directed edge pointing from the target role to the designated role;

determining a new target role from the virtual roles except the target role in the role pool, returning to execute the winning rate of the target role and other virtual roles, determining the winning rate larger than a preset value as a designated winning rate, and taking other virtual roles corresponding to the designated winning rate as designated roles; and constructing a directed edge pointing to the designated role from the target role until all virtual roles in the role pool are traversed.

4. The method of claim 2, wherein the determining the euler loop in the directed graph; determining an abnormal role from the role pool according to the Euler loop, wherein the abnormal role is a virtual role with abnormal winning rate, and the method comprises the following steps:

determining all connected graphs in the directed graph;

for each connected graph, determining nodes which are not in the Euler loop in the connected graph as candidate nodes, and determining virtual roles corresponding to the candidate nodes as candidate roles;

if the number of the established directed graphs is equal to the preset number, determining the abnormal roles from the candidate roles;

if the number of the established directed graphs is not equal to the preset number, after the preset value is updated, returning to execute the steps that all the virtual roles in the role pool are taken as nodes, and the success rate set of each virtual role is taken as an edge to establish the directed graphs; and determining abnormal roles from the role pool according to the Euler loop until the number of the established directed graphs is equal to the preset number.

5. The method of claim 4, wherein said determining the abnormal role from the candidate roles comprises:

determining a number of times the virtual character is determined to be a candidate character;

and determining the virtual role with the frequency greater than the preset frequency as the abnormal role.

6. The method of claim 4, wherein the out-degree of the nodes in the Euler loop is equal to the in-degree, and wherein for each of the connected graphs, determining the nodes in the connected graphs that are not in the Euler loop as candidate nodes, and after determining the virtual roles corresponding to the candidate nodes as candidate roles, further comprises:

obtaining the out-degree and the in-degree of the candidate nodes in the connected graph;

determining that the abnormal state of the candidate role is too strong under the condition that the out-degree is greater than the in-degree;

and determining that the abnormal state of the candidate role is too weak under the condition that the out-degree is smaller than the in-degree.

7. The method of claim 4, wherein the updating the preset value comprises:

and increasing or decreasing the preset value according to the preset change value to obtain a new preset value.

8. The method of claim 1, wherein obtaining the set of wins for each virtual character in the character pool comprises:

obtaining a game log;

obtaining the fighting characteristics of each fighting record in the game log, wherein the fighting characteristics comprise the type of fighting, the duration of fighting and the reason for ending;

and acquiring the winning rate set from the fighting records with the fighting characteristics meeting preset conditions.

9. An abnormal role determination apparatus, comprising:

the system comprises an acquisition module, a judgment module and a processing module, wherein the acquisition module is used for acquiring a victory ratio set of each virtual role in a role pool, and the victory ratio set comprises victory ratios of the virtual roles in fight with other virtual roles;

the building module is used for building a directed graph by taking all the virtual roles in the role pool as nodes and taking the win ratio set of each virtual role as an edge;

a first determining module, configured to determine an euler loop in the directed graph;

and the second determining module is used for determining an abnormal role from the role pool according to the Euler circuit, wherein the abnormal role is a virtual role with abnormal winning rate.

10. A computer device comprising a processor and a memory, the memory storing a plurality of instructions; the processor loads instructions from the memory to perform the steps of the method of determining an abnormal role according to any one of claims 1 to 8.

11. A computer readable storage medium storing instructions adapted to be loaded by a processor to perform the steps of the method for determining abnormal role according to any one of claims 1 to 8.