Abnormal Character Determination Method, Device, Computer Equipment and Storage Medium

Abstract

Embodiments of the present application disclose an abnormal character determination method, apparatus, computer device, and storage medium; obtaining a win rate set for each virtual character in a character pool, where the win rate set includes the win rates of the virtual character in battles against other virtual characters; constructing a directed graph with all virtual characters in the character pool as nodes and the win rate set of each virtual character as edges; determining an Euler circuit in the directed graph; and determining an abnormal character from the character pool according to the Euler circuit, where the abnormal character is a virtual character with an abnormal win rate. In the embodiments of the present application, a directed graph representing the strength relationship between virtual characters can be automatically constructed based on the win rate set of each virtual character, and further, an abnormal character with an abnormal win rate can be determined according to the Euler circuit in the directed graph, automatically analyzing player-versus-player battles, and realizing automatic detection of abnormal characters in the game.

Description

Technical Field

[0001] This application relates to the field of games, and particularly to a method, apparatus, computer device, and storage medium for determining abnormal characters. Background Art

[0002] With the rapid development of network technology, online games have attracted more and more attention, especially Multiplayer Online Battle Arena (MOBA) games. For online games such as MOBA, the emergence of unbalanced game characters will greatly affect the lifespan of the game. Unbalanced game characters can refer to game characters that are too powerful or too weak. Unbalanced game characters will cause the entire game to lose balance and affect the game lifespan.

[0003] Currently, it is usually based on the feedback or personal experience of game players to determine the unbalanced characters in the game, and it is difficult to achieve automatic detection of unbalanced characters in the game. Summary of the Invention

[0004] Embodiments of this application provide a method, apparatus, computer device, and storage medium for determining abnormal characters, which can automatically detect unbalanced characters in the game.

[0005] An embodiment of this application provides a method for determining abnormal characters, including: obtaining the win rate set of each virtual character in the character pool, where the win rate set includes the win rates of the virtual character against other virtual characters; constructing a directed graph with all virtual characters in the character pool as nodes and the win rate set of each virtual character as edges; determining the Euler circuit in the directed graph; and determining abnormal characters from the character pool according to the Euler circuit, where the abnormal characters are virtual characters with abnormal win rates.

[0006] An embodiment of this application further provides an apparatus for determining abnormal characters, including: an obtaining module for obtaining the win rate set of each virtual character in the character pool, where the win rate set includes the win rates of the virtual character against other virtual characters; a constructing module for constructing a directed graph with all virtual characters in the character pool as nodes and the win rate set of each virtual character as edges; a first determining module for determining the Euler circuit in the directed graph; and a second determining module for determining abnormal characters from the character pool according to the Euler circuit, where the abnormal characters are virtual characters with abnormal win rates.

[0007] In some embodiments, the construction module further includes: a node determination unit, configured to use all virtual characters in the character pool as nodes, where each of the nodes represents a virtual character; a directed edge construction unit, configured to construct directed edges according to the magnitude relationship between the winning rate of each virtual character and a preset value; and a directed graph determination unit, configured to use all the nodes and directed edges as the directed graph.

[0008] In some embodiments, the directed edge construction unit includes: a target character determination subunit, configured to determine a virtual character in the character pool as a target character; a designated character determination subunit, configured to determine, from the winning rates of the target character against other virtual characters, the winning rates greater than or equal to the preset value as designated winning rates, and the other virtual characters corresponding to the designated winning rates as designated characters; and a construction subunit, configured to construct a directed edge pointing from the target character to the designated character. The target character determination subunit is further configured to determine a new target character from the virtual characters in the character pool other than the target character, and the designated character determination subunit and the construction subunit sequentially repeat the above steps until all virtual characters in the character pool are traversed.

[0009] In some embodiments, the first determination module is further configured to determine all connected graphs in the directed graph; for each of the connected graphs, the candidate character determination unit in the second determination module is configured to determine the nodes not in the Euler circuit in the connected graph as candidate nodes, and determine the virtual characters corresponding to the candidate nodes as candidate characters; the abnormal character determination unit in the second determination module is configured to, if the number of established directed graphs is equal to a preset number, determine the abnormal characters from the candidate characters; if the number of established directed graphs is not equal to the preset number, after updating the preset value, the construction module, the first determination module, and the second determination module sequentially repeat the above steps until the number of established directed graphs is equal to the preset number.

[0010] In some embodiments, the abnormal character determination unit is further configured to determine the number of times the virtual character is determined as a candidate character; and determine the virtual character with the number of times greater than a preset number of times as the abnormal character.

[0011] In some embodiments, the out-degree of a node in the Euler circuit is equal to the in-degree. The abnormal character determination unit is further configured to obtain the out-degree and in-degree of the candidate node in the connected graph; in the case where the out-degree is greater than the in-degree, determine the abnormal state of the candidate character as being too strong; and in the case where the out-degree is less than the in-degree, determine the abnormal state of the candidate character as being too weak.

[0012] In some embodiments, the abnormal character determination unit is further configured to increase or decrease the preset value according to a preset change value to obtain a new preset value.

[0013] In some embodiments, the acquisition module is further configured to acquire game logs; acquire the battle characteristics of each battle record in the game logs, where the battle characteristics include battle type, battle duration, and reason for ending; and acquire the win rate set from the battle records whose battle characteristics meet preset conditions.

[0014] An embodiment of the present application further provides a computer device, including a memory storing multiple instructions; the processor loads the instructions from the memory to execute the steps in any one of the abnormal character determination methods provided by the embodiments of the present application.

[0015] An embodiment of the present application further provides a computer-readable storage medium storing multiple instructions, and the instructions are suitable for being loaded by a processor to execute the steps in any one of the abnormal character determination methods provided by the embodiments of the present application.

[0016] The embodiments of the present application can acquire the win rate set of each virtual character, automatically construct a directed graph representing the strength relationship between virtual characters based on the win rate set, and further determine abnormal characters with abnormal win rates according to the Euler circuit in the directed graph, which can automatically analyze player battles, realize automatic detection of abnormal characters, and do not need to wait for player feedback, thereby improving the detection efficiency of abnormal characters. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 is a schematic diagram of a system for implementing the abnormal character determination method provided by the embodiments of the present application;

[0019] Figure 2 is a flowchart of an abnormal character determination method provided by an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a directed graph provided by the embodiments of the present application;

[0021] Figure 4 is a flowchart of an abnormal character determination method provided by another embodiment of the present application;

[0022] Figure 5 is on Figure 4 a flowchart of partial steps of an abnormal character determination method provided on the basis of the provided embodiment;

[0023] Figure 6 FIG. Figure 6 is a schematic flowchart of an abnormal role determination method provided by another embodiment of the present application;

[0024] Figure 7 FIG. is a schematic structural diagram of an abnormal role determination device provided by an embodiment of the present application;

[0025] Figure 8 FIG. Figure 8 is a schematic structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0027] The embodiments of the present application provide an abnormal role determination method, device, computer device, and storage medium.

[0028] Among them, the abnormal role determination device may be specifically integrated in a computer device, and the computer device may be a device such as a terminal or a server. Among them, the terminal may be a device such as a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, or a personal computer (PC); the server may be a single server or a server cluster composed of multiple servers.

[0029] In some embodiments, the abnormal role determination device may also be integrated in multiple computer devices. For example, the abnormal role determination device may be integrated in multiple servers, and the abnormal role determination method of the present application may be implemented by multiple servers.

[0030] In some embodiments, the server may also be implemented in the form of a terminal.

[0031] For example, referring to Figure 1 , Figure 1Schematic diagram of a system for determining an abnormal character provided by an embodiment of the present application. 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 a user can be connected to the server 2000 through the network 4000. Among them, the terminal 1000 is any device with computing hardware that can support and execute a software product corresponding to a game; the server 2000 can be a single server or a server cluster; the network 4000 can be a wireless network or a wired network, such as a wireless network being 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, etc. In addition, different terminals 1000 can also use their own Bluetooth network or hotspot network to connect to other terminals or to the server 2000. In addition, the system may further include at least one database 3000, and the database 3000 is used to store game data generated when the user uses the terminal 1000.

[0032] The following will be described in detail respectively. It should be noted that the serial numbers of the following embodiments do not limit the preferred order of the embodiments.

[0033] Please refer to Figure 2 , which is a flowchart schematic diagram of an abnormal character determination method provided by an embodiment of the present application. This method can be executed by a computer device, and the computer device can be a terminal, a server, or other devices. Specifically, this method may include the following steps.

[0034] S110. Obtain the win rate set of each virtual character in the character pool, where the win rate set includes the win rate of the virtual character in battles against other virtual characters.

[0035] The character pool refers to the set of all virtual characters in a certain game, or it can also refer to the set of virtual characters statistically obtained from game logs. For each virtual character in the character pool, the win rate set of each virtual character can be obtained. Among them, the win rate set includes the win rate of the virtual character in battles against other virtual characters, and the win rate is the ratio of the number of wins to the number of battles. For example, in the character pool, there are virtual character A, virtual character B, and virtual character C. The win rate set of virtual character A includes the win rate of virtual character A when virtual character A battles against virtual character B, and the win rate of virtual character A when virtual character A battles against virtual character C. Among them, the win rate of virtual character A when virtual character A battles against virtual character B refers to the ratio of the number of wins of virtual character A to the total number of battles between the two when virtual character A battles against virtual character B. It can be understood that when virtual character A battles against virtual character B, the sum of the win rate of virtual character A and the win rate of virtual character B is 1.

[0036] In some embodiments, the winning rate set of each virtual character can be represented by a matrix, or for each virtual character, a matrix can be used to represent the winning rate set of that virtual character, which can be set according to actual needs and will not be specifically limited here.

[0037] In some embodiments, the way to obtain the winning rate set of each virtual character can be to first obtain game logs and then obtain the winning rate set of each virtual character based on the game logs. To ensure obtaining the accurate winning rate set of each virtual character, the obtained game logs can be filtered in advance. Specifically, obtaining the winning rate set of each virtual character can include:

[0038] Obtain game logs; obtain the battle characteristics of each battle record in the game logs, where the battle characteristics include the battle type, battle duration, and end reason; obtain the winning rate set from the battle records whose battle characteristics meet the preset conditions.

[0039] When obtaining game logs, it can be to obtain game logs within a preset time period, and the preset time period can be set according to actual needs. For example, the preset time period can be set to all time periods before the current time, or it can also be set to all time periods from the launch of a certain game version to the current time. Game logs can refer to the real game logs generated when players play the game, or can also be the game logs generated during the game testing phase.

[0040] The battle type refers to the game mode during the battle, which can be a ranked match, an entertainment match, etc. The battle duration refers to the total time from the start to the end of a game. The end reason refers to the reason for the termination of the game. For example, any game player surrenders actively, or the game ends normally when the game end condition is met. Among them, the game end condition can be that any one of the game players obtains a preset score value, or any one of the game players defeats the target, etc.

[0041] Among them, the preset conditions can include sub-conditions corresponding to each battle characteristic. When each battle characteristic meets the corresponding sub-conditions, it is considered that the battle characteristic meets the preset conditions. It can also be that when any one battle characteristic meets the corresponding sub-condition, it is considered that the battle characteristic meets the preset conditions, which can be specifically set according to actual needs and will not be specifically limited here.

[0042] In practical applications, the sub-condition corresponding to the battle type can be that the battle type is a ranked match, the sub-condition corresponding to the battle duration can be that the battle duration is greater than or equal to 10 minutes, and the sub-condition corresponding to the end reason can be that it is not that any game player surrenders actively. The preset condition can be to meet each sub-condition simultaneously, so as to screen the battle records in the game logs and obtain the winning rate set from the battle records that meet the preset conditions.

[0043] In some embodiments, the winning rate sets of each virtual character can be directly obtained through a plug-in with the function of calculating the winning rate.

[0044] After obtaining the winning rate sets of each virtual character, a directed graph can be constructed using the winning rate sets for further analysis.

[0045] S120: Construct a directed graph with all virtual characters in the character pool as nodes and the winning rate sets of each virtual character as edges.

[0046] When constructing the directed graph, all virtual characters in the character pool can be used as nodes, and the edges between nodes can be constructed according to the winning rate sets of each virtual character, thereby obtaining the directed graph. Among them, a node in the constructed directed graph represents a virtual character in a character pool, and the edge between nodes represents the strength relationship between two virtual characters. For details, please refer to Figure 3 , which shows a schematic diagram of the directed graph. In Figure 3 , node A represents virtual character A, node E represents virtual character E, and the arrow from node A to node E indicates that virtual character A is stronger than virtual character E.

[0047] The edges in the directed graph are directional, and different directions of the edges have different meanings. For example, if the directed edge points from virtual character A to virtual character B, it means that the ability of virtual character A is stronger than that of virtual character B. If the directed edge points from virtual character B to virtual character A, it means that the ability of virtual character B is stronger than that of virtual character A. Therefore, when constructing the directed graph, the direction of the directed edge also needs to be determined.

[0048] Specifically, the directed edge can be constructed in the following way: Determine a virtual character in the character pool as the target character; From the winning rates of the target character's battles with other virtual characters, determine the winning rates greater than or equal to the preset value as the specified winning rates, and the other virtual characters corresponding to the specified winning rates are the specified characters; Construct a directed edge from the target character to the specified character; Determine a new target character from the virtual characters in the character pool other than the target character, and return to execute the following steps: From the winning rates of the target character's battles with other virtual characters, determine the winning rates greater than the preset value as the specified winning rates, and the other virtual characters corresponding to the specified winning rates are the specified characters; Construct a directed edge from the target character to the specified character until all virtual characters in the character pool are traversed.

[0049] For example, in a character pool, there are virtual characters A, B, and C. The target character is virtual character A. The win rate set of virtual character A includes M(A, B) and M(A, C), where M(A, B) represents the win rate of virtual character A when playing against virtual character B, and M(A, C) represents the win rate of virtual character A when playing against virtual character C. If it is determined that M(A, C) is greater than the preset value, M(A, C) can be determined as the specified win rate, and virtual character C can be determined as the specified character. Thus, a directed edge can be constructed from virtual character A to virtual character C. By sequentially determining virtual characters B and C as the target characters and repeating the above process, directed edges can be constructed between each virtual character and other virtual characters.

[0050] Among them, the preset value is an empirical value, and the value range of the preset value is from 0 to 1, which can be set according to actual needs and will not be specifically limited here.

[0051] S130. Determine the Euler circuit in the directed graph.

[0052] After constructing the directed graph, the directed graph can be further processed to determine the Euler circuit in the directed graph. When determining the Euler circuit in the directed graph, it can be to first determine all the connected graphs in the directed graph, and then determine whether there is an Euler circuit in each connected graph. Among them, if any two points in a graph are connected, where connection means there is a path between the two points, the graph is a connected graph. If a path in a graph passes through each edge of the directed graph and each edge of the directed graph is exactly passed through once, the path is called an Euler path. If a circuit is an Euler path, the circuit is an Euler circuit.

[0053] For a directed graph to have an Euler circuit, the prerequisite is that it is a connected graph, and the out-degree and in-degree of each node in the directed graph are equal. The out-degree refers to the number of edges with the node as the head, and the in-degree refers to the number of edges with the node as the tail. For example Figure 3 in the out-degree of node A is 2, and the in-degree is 2. The out-degree of node E is 0, and the in-degree is 1. That is to say, the out-degree and in-degree of each node in the Euler circuit are equal. For reference Figure 3 , Figure 3 the path A - C - D - B in is an Euler circuit.

[0054] There are mainly two methods for solving the Euler circuit. One is DFS search, and the other is the Fleury algorithm. The idea of using DFS search to solve the Euler circuit is as follows: After determining that a graph has an Euler circuit using Euler's theorem, select a correct starting node, and use the DFS algorithm to traverse all the edges (each edge is traversed only once). If you can't go any further, backtrack. Record the traversed edges in order in the search forward direction. The arrangement of this set of edges forms an Euler circuit. The specific implementation methods of DFS search and the Fleury algorithm are the same as the existing methods and will not be elaborated here.

[0055] S140. Determine an abnormal role from the role pool according to the Euler circuit, where the abnormal role is a virtual role with an abnormal win rate.

[0056] After determining the Euler circuit in the directed graph, an abnormal role can be determined based on the Euler circuit. Among them, the abnormal role refers to a virtual role with an abnormal win rate. The abnormal win rate can mean too high or too low. The ability of a virtual role with too high a win rate is too strong, and the ability of a virtual role with too low a win rate is too weak.

[0057] A directed graph can determine the corresponding abnormal role. To improve the accuracy of determining the abnormal role, multiple directed graphs can be constructed by repeating S120. Specifically, determine the Euler circuit in the directed graph; determining the abnormal role from the role pool according to the Euler circuit can include: determining all the connected graphs in the directed graph; for each connected graph, determine the nodes in the connected graph that are not in the Euler circuit as candidate nodes, and determine the virtual role corresponding to the candidate node as a candidate role; if the number of constructed directed graphs is equal to the preset number, determine the abnormal role from the candidate roles; if the number of constructed directed graphs is not equal to the preset number, after updating the preset value, return and execute the following steps: use all the virtual roles in the role pool as nodes and the win rate set of each virtual role as edges to construct a directed graph; until the abnormal role is determined from the role pool according to the Euler circuit until the number of constructed directed graphs is equal to the preset number. That is to say, the preset value can be updated, and a preset number of directed graphs can be constructed. For each directed graph, determine the connected graphs in the directed graph. For each connected graph, when it is determined that there is an Euler circuit in the connected graph, the nodes not in the Euler circuit are used as candidate nodes. As Figure 3 The directed graph shown in is a connected graph. Among them, the path A - C - D - B is an Euler circuit, then nodes E and node F can be determined as candidate nodes.

[0058] In some embodiments, if there is no Euler circuit in the connected graph, it can be considered that all the nodes in the connected graph are not in the Euler circuit, and all the nodes in the connected graph can be determined as candidate nodes.

[0059] Among them, multiple directed graphs are established. For each directed graph, candidate roles can be determined. When the number of constructed directed graphs is equal to a preset number, abnormal roles are determined from the candidate roles. Specifically, determining abnormal roles from candidate roles may include: determining the number of times the virtual role is determined as a candidate role; determining the virtual role with the number of times greater than the preset number as the abnormal role.

[0060] The abnormal role determination solution provided by the embodiments of the present application can be applied in the game planning scenario and is applicable to the balance detection of roles in any MOBA game. For example, taking a certain MOBA game as an example, players use virtual roles in the game for battles, and the battle results can be obtained. Based on the players' battles, the win rate set of each virtual role used by the players can be obtained. After obtaining the win rate set, a directed graph is constructed with all virtual roles in the role pool as nodes and the win rate set of each virtual role as edges; the Euler circuit in the directed graph is determined; and abnormal roles are determined from the role pool according to the Euler circuit. The game planner can adjust the values or settings of the abnormal roles according to the determined abnormal roles to ensure the balance of the game and increase the game lifespan.

[0061] Through the abnormal role determination method provided by the embodiments of the present application, the win rate set of each virtual role can be obtained, a directed graph representing the strength relationship between virtual roles can be automatically constructed based on the win rate set, and abnormal roles with abnormal win rates can be further determined according to the Euler circuit in the directed graph. Without waiting for players' feedback, the battles between players can be automatically analyzed to achieve the automated detection of abnormal roles, thereby improving the detection efficiency of abnormal roles.

[0062] Please refer to Figure 4 , which is a schematic flowchart of the abnormal role determination method provided by another embodiment of the present application. On the basis of the foregoing embodiment, the process of constructing a directed graph is mainly described and will be further described in detail below.

[0063] S210. Obtain the win rate set of each virtual role in the role pool, where the win rate set includes the win rates of the virtual role in battles with other virtual roles.

[0064] S210 can refer to the corresponding part of the foregoing embodiment. To avoid repetition, it will not be elaborated here.

[0065] S220. Use all virtual roles in the role pool as nodes, where each node represents a virtual role.

[0066] S230. Construct directed edges according to the magnitude relationship between the win rate of each virtual role and a preset value.

[0067] When constructing a directed graph, all virtual characters in the character pool can be used as nodes, and each node represents a virtual character. After determining the nodes, directed edges can be constructed according to the magnitude relationship between the win rate of each virtual character and a preset value. Specifically, reference can be made to Figure 5 Constructing directed edges according to the magnitude relationship between the win rate of each virtual character and the preset value may further include the following steps.

[0068] S231. Determine a virtual character from the character pool as the target character.

[0069] Among them, the target character refers to the currently determined virtual character, and the target character is any virtual character in the character pool.

[0070] S232. From the win rates of the target character's battles with other virtual characters, determine the win rates greater than or equal to the preset value as the specified win rates, and the other virtual characters corresponding to the specified win rates are the specified characters.

[0071] Determine a virtual character from the character pool as the target character. From the win rates of the target character's battles with other virtual characters, that is, from the win rate set of the target character, determine the win rates greater than or equal to the preset value as the specified win rates. Among them, the other virtual characters corresponding to the specified win rates are the specified characters. For example, if the target character is virtual character A, and the win rate set includes M(A,B) and M(A,C), where M(A,B) represents the win rate of virtual character A in the battle with virtual character B, and M(A,C) represents the win rate of virtual character A in the battle with virtual character C. If M(A,B) is determined as the specified win rate, the specified character is virtual character B; if M(A,C) is determined as the specified win rate, the specified character is virtual character C.

[0072] S233. Construct a directed edge from the target character to the specified character.

[0073] After determining the specified character, construct a directed edge from the target character to the specified character.

[0074] S234. Determine whether all virtual characters in the character pool have been traversed; if not, execute S235; if so, the process ends.

[0075] After constructing the directed edges of the target character and the specified character, it can be determined whether all virtual characters in the character pool have been traversed. Among them, whether all virtual characters in the character pool have been traversed means whether each virtual character in the character pool has been determined as the target character.

[0076] In some embodiments, a set of roles can be set up, which includes all the virtual roles in the role pool. Each time a target role is determined, the target role is removed from the set of roles. When determining whether all the virtual roles in the role pool have been traversed, it can be determined by checking whether the set of roles is empty. If the set of roles is empty, it is determined that all the virtual roles in the role pool have been traversed. If the set of roles is not empty, it is determined that not all the virtual roles in the role pool have been traversed.

[0077] In some embodiments, a set of roles can be set up, and each virtual role in the set of roles is assigned a number, which are consecutive numbers. The virtual roles are sequentially determined as target roles according to the numbers. When determining whether all the virtual roles in the role pool have been traversed, it can be done by obtaining the number of the currently determined target role and taking the number of the first determined target role as the starting number. If the difference between the current number and the starting number plus 1 is equal to the number of virtual roles in the role pool, it is determined that all the virtual roles in the role pool have been traversed. If the number is less than the number of virtual roles in the role pool, it is determined that not all the virtual roles in the role pool have been traversed. In the previous example, if virtual role A is numbered 1, virtual role B is numbered 2, and virtual role C is numbered 3, and virtual roles A, B, and C are sequentially determined as target roles. When virtual role C is determined as the target role, the number corresponding to virtual role 3 is 3, and the first determined target role is virtual role A with a starting number of 1. At this time, 3 - 1 + 1 = 3, which is equal to the number of virtual roles in the role pool, so it can be considered that all the virtual roles in the role pool have been traversed.

[0078] If it is determined that all the virtual roles in the role pool have been traversed, it means that the construction of the directed graph is completed. If it is determined that not all the virtual roles in the role pool have been traversed, continue to execute S235.

[0079] S235: Determine a new target role from the virtual roles in the role pool other than the target role.

[0080] If it is determined that not all the virtual roles in the role pool have been traversed, determine a new target role from the virtual roles in the role pool other than the target role, that is, determine a new target role from other virtual roles.

[0081] In some embodiments, a set of roles can be set up, which includes all the virtual roles in the role pool. Each time a target role is determined, the target role is removed from the set of roles. When determining a new target role, a virtual role can be directly determined as the target role from the set of roles.

[0082] In some embodiments, a set of roles can be set, and each virtual role in the set of roles is numbered with consecutive numbers. When determining a new target role, 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 the new target role.

[0083] After determining the new target role, return to execute S232, S233, and S234 until all virtual roles in the role pool are traversed.

[0084] S240. Take all the nodes and directed edges as the directed graph.

[0085] After constructing all the nodes and directed edges, all the nodes and directed edges can be taken as the established directed graph.

[0086] S250. Determine the Euler circuit in the directed graph.

[0087] S260. Determine the abnormal role from the role pool according to the Euler circuit, where the abnormal role is a virtual role with an abnormal win rate.

[0088] S250 to S260 can refer to the corresponding parts in the foregoing embodiments and will not be elaborated herein.

[0089] In the abnormal role determination method provided by the embodiments of the present application, when constructing the directed edge between nodes, a virtual role is determined from the role pool as the target role, and from the win rates of the target role against other virtual roles, the win rates greater than or equal to the preset value are determined as the specified win rates, and the other virtual roles corresponding to the specified win rates are the specified roles; a directed edge pointing from the target role to the specified role is constructed. When all virtual roles in the role pool are traversed, it is considered that the directed graph is constructed. When not all virtual roles in the role pool are traversed, a new target role is re-determined and the directed edge is continued to be constructed to ensure the integrity and accuracy of the established directed graph. Based on the complete and accurate directed graph, the accuracy of abnormal role determination can be further improved.

[0090] Please refer to Figure 6 , which is a flowchart schematic diagram of the abnormal role determination method provided by another embodiment of the present application. On the basis of the foregoing embodiments, the process of determining the Euler circuit in the directed graph and determining the abnormal role from the role pool according to the Euler circuit is mainly described, and the following will be further described in detail.

[0091] S310. Obtain the win rate set of each virtual role in the role pool, where the win rate set includes the win rates of the virtual role against other virtual roles.

[0092] S320. Construct a directed graph with all virtual roles in the role pool as nodes and the win rate set of each virtual role as edges.

[0093] S310 to S320 may refer to the corresponding parts in the aforementioned embodiment, which will not be described in detail here.

[0094] S330: Determine all connected graphs in the directed graph.

[0095] S340: For each of the connected graphs, determine a node in the connected graph that is not in the Euler circuit as a candidate node, and determine a virtual character corresponding to the candidate node as a candidate character.

[0096] If there is an Euler circuit in a directed graph, then the directed graph is a connected graph, and the out-degree of all nodes is equal to the in-degree. Based on this judgment principle, all connected graphs in the directed graph can be determined first, and then it can be determined whether there is an Euler circuit in the connected graph. If there is an Euler circuit in the connected graph, the nodes in the connected graph that are not in the Euler circuit are determined as candidate nodes, and the virtual characters corresponding to the candidate nodes are determined as candidate characters. Among them, the out-degree and in-degree of the nodes in the Euler circuit are equal, and it can be considered that the virtual characters represented by these nodes can check and balance each other, and the virtual characters represented by the nodes that are not in the Euler circuit may be abnormal.

[0097] In some implementations, if there is no connected graph in the directed graph, S350 may be directly executed.

[0098] In one implementation, if it is determined that there is no Euler circuit in the connected graph, it can be considered that all nodes in the connected graph are not in the Euler circuit, and all nodes in the connected graph can be determined as candidate nodes.

[0099] A candidate role refers to a virtual role that may be abnormal. After determining the candidate role, the possible abnormal state of the candidate role can also be determined based on the graph features of the candidate node. Since the out-degree and in-degree of the nodes in the Euler circuit in the connected graph are equal, the out-degree and in-degree of the nodes not in the Euler circuit are not equal. Therefore, when determining the abnormal state of the candidate role, the out-degree and in-degree of the candidate node 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 less than the in-degree, the abnormal state of the candidate role can be considered to be too weak.

[0100] S350, determine whether the number of established directed graphs is equal to a preset number; if not, execute S360; if so, execute S370.

[0101] If only one directed graph is established to determine the abnormal role, the determined abnormal role may not be accurate enough. To further improve the accuracy of the determined abnormal role, multiple directed graphs can be established to enhance the accuracy of abnormal role determination. Specifically, it can be determined whether the number of 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 established directed graphs is not equal to the preset number, S360 can be executed. If it is determined that the number of established directed graphs is equal to the preset number, S370 is executed.

[0102] S360. Update the preset value.

[0103] When constructing a directed graph, all virtual roles in the role pool are used as nodes, and directed edges are constructed according to the size relationship between the winning rate of each virtual role and the preset value. The change of the preset value will cause the change of the directed edges of the directed graph. Therefore, when the number of established directed graphs is not equal to the preset number, the preset value can be updated and then the step of constructing the directed graph can be executed. That is, after executing S360, it can return to execute S320 to S350 until it is determined that the number of established directed graphs is equal to the preset number, and then S370 is executed.

[0104] In some embodiments, when updating the preset value, the preset value can 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 can be operated, including but not limited to addition, subtraction, multiplication, division, etc. It should be noted that after increasing or decreasing the preset value according to the preset change value, the value range of the obtained new preset value is still from 0 to 1.

[0105] In some embodiments, a preset value set can be set in advance, and the preset value set includes multiple different preset values set in advance by planners. When updating the preset value, a preset value different from the current preset value can be selected from the preset value set as the new preset value.

[0106] S370. Determine the abnormal role from the candidate roles.

[0107] The candidate roles are the virtual roles corresponding to the candidate nodes in the directed graph, and the determined candidate roles may include multiple virtual roles. Specifically, a candidate role set can be created, and the virtual roles determined as candidate roles each time are stored in the candidate role set, where the candidate roles can include multiple identical virtual roles. For example, the candidate role set can include virtual role A, virtual role C, virtual role A, virtual role A.

[0108] In some embodiments, when determining an abnormal role from candidate roles, the number of times the virtual role is determined as a candidate role can be determined; the virtual role with the number of times greater than a preset number is determined as an abnormal role. The preset number can be any value set as needed. For example, the preset number is set to 2, and the candidate role set includes virtual role A, virtual role C, virtual role A, virtual role A. Among them, the number of times virtual role A is determined as a candidate role is 3, and the number of times virtual role C is determined as a candidate role is 1. Thus, virtual role A can be determined as an abnormal role.

[0109] After determining the candidate roles, the abnormal state of the candidate roles can be further determined. As an implementation, the abnormal state of each determined candidate role can be correspondingly stored in the candidate role set. For the same virtual role, the determined abnormal states may be different. For example, the abnormal state determined for virtual role A in a certain directed graph is too weak, and the abnormal state determined for virtual role A in another directed graph may be too strong. After determining the abnormal role, all the abnormal states that the abnormal role has appeared can be used as the abnormal states of the abnormal role, and the number of times each abnormal state appears can also be counted and associated with the determined abnormal role. For example, the abnormal role is virtual role A - too strong 3 times - too weak 2 times, indicating that the abnormal state of virtual role A is determined as too strong 3 times and too weak 2 times.

[0110] The abnormal role determination method provided by the embodiments of the present application, after establishing a directed graph, determines candidate nodes and candidate roles according to the Euler circuit in the directed graph. When the number of established directed graphs is equal to the preset number, abnormal roles are determined from the candidate roles. When the number of established directed graphs is not equal to the preset number, after updating the preset value, a directed graph is reconstructed with the updated preset value to ensure that the number of established directed graphs is large enough to avoid inaccurate determination of abnormal roles based on a single directed graph. Based on a certain number of directed graphs, a certain number of candidate roles can be determined, and then abnormal roles are further determined according to the number of times the virtual role is determined as a candidate role, which can further improve the accuracy of abnormal role determination.

[0111] To better implement the above method, the embodiments of the present application also provide an abnormal role determination device. The abnormal role determination device can be specifically integrated in a computer device, and the computer device can be a device such as a terminal or a server. Among them, the terminal can be a device such as a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, or a personal computer; the server can be a single server or a server cluster composed of multiple servers.

[0112] For example, in this embodiment, taking the abnormal role determination device being specifically integrated in a computer device as an example, the method of the embodiments of the present application will be described in detail.

[0113] For example, as Figure 7 shown, the abnormal character determination device may include an acquisition module 410, a construction module 420, a first determination module 430, and a second determination module 440. Among them, the acquisition module 410 is used to acquire the winning rate set of each virtual character in the character pool, and the winning rate set includes the winning rate of the virtual character in the battle with other virtual characters; the construction module 420 is used to construct a directed graph with all the virtual characters in the character pool as nodes and the winning rate set of each virtual character as edges; the first determination module 430 is used to determine the Euler circuit in the directed graph; the second determination module 440 is used to determine the abnormal character from the character pool according to the Euler circuit, and the abnormal character is a virtual character with an abnormal winning rate.

[0114] In some embodiments, the construction module 420 further includes: a node determination unit for using all the virtual characters in the character pool as nodes, and each of the nodes represents a virtual character; a directed edge construction unit for constructing directed edges according to the magnitude relationship between the winning rate of each virtual character and a preset value; a directed graph determination unit for using all the nodes and directed edges as the directed graph.

[0115] In some embodiments, the directed edge construction unit includes: a target character determination subunit for determining a virtual character in the character pool as the target character; a designated character determination subunit for determining, from the winning rates of the target character in the battles with other virtual characters, the winning rates greater than or equal to the preset value as the designated winning rates, and the other virtual characters corresponding to the designated winning rates as the designated characters; a construction subunit for constructing a directed edge from the target character to the designated character; the target character determination subunit is further used to determine a new target character from the virtual characters in the character pool other than the target character, and the designated character determination subunit and the construction subunit sequentially repeat the above steps until all the virtual characters in the character pool are traversed.

[0116] In some embodiments, the first determination module 430 is further used to determine all the connected graphs in the directed graph; for each of the connected graphs, the candidate character determination unit in the second determination module 440 is used to determine the nodes not in the Euler circuit in the connected graph as candidate nodes, and determine the virtual characters corresponding to the candidate nodes as candidate characters; the abnormal character determination unit in the second determination module 440 is used to determine the abnormal character from the candidate characters if the number of established directed graphs is equal to the preset number; if the number of established directed graphs is not equal to the preset number, after updating the preset value, the construction module 420, the first determination module 430, and the second determination module 440 sequentially repeat the above steps until the number of established directed graphs is equal to the preset number.

[0117] In some embodiments, the abnormal role determination unit is further configured to determine the number of times the virtual role is determined as a candidate role; and determine the virtual role with the number greater than a preset number as the abnormal role.

[0118] In some embodiments, in an Euler circuit, the out-degree of a node is equal to the in-degree. The abnormal role determination unit is further configured to obtain the out-degree and in-degree of the candidate node in the connected graph; when the out-degree is greater than the in-degree, determine that the abnormal state of the candidate role is too strong; when the out-degree is less than the in-degree, determine that the abnormal state of the candidate role is too weak.

[0119] 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.

[0120] In some embodiments, the obtaining module 410 is further configured to obtain game logs; obtain the battle characteristics of each battle record in the game logs, where the battle characteristics include battle type, battle duration, and end reason; and obtain the win rate set from the battle records whose battle characteristics meet preset conditions.

[0121] In specific implementation, each of the above modules can be implemented as an independent entity, or can be arbitrarily combined and implemented as the same or several entities. For the specific implementation of each of the above modules, reference can be made to the foregoing method embodiments, which will not be elaborated herein.

[0122] As can be seen from the above, the abnormal role determination device of this embodiment can obtain the win rate set of each virtual role, automatically construct a directed graph that can represent the strength relationship between virtual roles based on the win rate set, and further determine the abnormal role with abnormal win rate according to the Euler circuit in the directed graph, without waiting for the feedback of players, can automatically analyze the battles between players, and realize the automatic detection of abnormal roles, thereby improving the detection efficiency of abnormal roles.

[0123] Correspondingly, an embodiment of the present application further provides a computer device, which can be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet computer, a notebook computer, a touch screen, a game console, a personal computer, a personal digital assistant (Personal Digital Assistant, PDA), etc.

[0124] As Figure 8 shown, Figure 8It is a schematic structural diagram of a computer device provided by an embodiment of the present application. 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 on the memory 502 and executable on the processor. Among them, the processor 501 is electrically connected to the memory 502. Those skilled in the art can understand that the computer device structure shown in the figure does not constitute a limitation on the computer device, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0125] The processor 501 is the control center of the computer device 500, connecting various parts of the entire computer device 500 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 502, and calling data stored in the memory 502, it executes various functions of the computer device 500 and processes data, thereby monitoring the computer device 500 as a whole.

[0126] In the embodiment of the present application, the processor 501 in the computer device 500 will load the instructions corresponding to the processes of one or more application programs into the memory 502 according to the following steps, and the processor 501 will run the application programs stored in the memory 502 to achieve various functions:

[0127] Obtain the win rate set of each virtual role in the role pool, where the win rate set includes the win rate of the virtual role in battles with other virtual roles; construct a directed graph with all virtual roles in the role pool as nodes and the win rate set of each virtual role as edges; determine the Euler circuit in the directed graph; determine an abnormal role from the role pool according to the Euler circuit, and the abnormal role is a virtual role with an abnormal win rate.

[0128] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, and details will not be repeated here.

[0129] Optionally, as Figure 8 shown, the computer device 500 further includes: a touch display screen 503, a radio frequency circuit 504, an audio circuit 505, an input unit 506, and a power supply 507. Among them, 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 can understand that Figure 8 the computer device structure shown in

[0130] The touch display screen 503 can be used to display a graphical user interface and receive operation instructions generated by a user acting on the graphical user interface. The touch display screen 503 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the computer device. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. The touch panel can be used to collect touch operations of the user on or near it (such as operations of the user using any suitable object or accessory such as a finger or a stylus on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel can include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the touch orientation of the user, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 501, and can receive and execute the commands sent by the processor 501. The touch panel can cover the display panel. After the touch panel detects a touch operation on or near it, it is transmitted to the processor 501 to determine the type of touch event. Subsequently, the processor 501 provides a corresponding visual output on the display panel according to the type of touch event. In the embodiments of the present application, the touch panel and the display panel can 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 independent components to implement input and output functions. That is, the touch display screen 503 can also be used as part of the input unit 506 to implement the input function.

[0131] The radio frequency circuit 504 can be used to receive and transmit radio frequency signals to establish wireless communication with a network device or other computer devices through wireless communication, and receive and transmit signals with the network device or other computer devices.

[0132] The audio circuit 505 can be used to provide an audio interface between the user and the computer device through a speaker and a microphone. The audio circuit 505 can transmit the electrical signal converted from the received audio data to the speaker, and the speaker converts it 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 then converted into audio data. After the audio data is output to the processor 501 for processing, it is transmitted through the radio frequency circuit 504 to, for example, another computer device, or the audio data is output to the memory 502 for further processing. The audio circuit 505 may also include an earphone jack to provide communication between the peripheral earphone and the computer device.

[0133] The input unit 506 can be used to receive input digital, character information or user characteristic information (such as fingerprint, iris, face information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0134] The power supply 507 is used to supply power to each component of the computer device 500. Optionally, the power supply 507 can be logically connected to the processor 501 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 507 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0135] Although Figure 8 not shown in the figure, the computer device 500 may further include a camera, a sensor, a Wi-Fi module, a Bluetooth module, etc., which will not be elaborated here.

[0136] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] As can be seen from the above, the computer device provided in this embodiment can obtain the win rate set of each virtual character, automatically construct a directed graph representing the strength relationship between virtual characters based on the win rate set, further determine the abnormal characters with abnormal win rates according to the Euler circuit in the directed graph, can automatically analyze the battles between players, realize the automatic detection of abnormal characters, and without waiting for the feedback of players, thereby improving the detection efficiency of abnormal characters.

[0138] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0139] For this reason, the embodiments of the present application provide a computer-readable storage medium, in which multiple computer programs are stored. The computer programs can be loaded by a processor to execute the steps in any of the abnormal character determination methods provided by the embodiments of the present application. For example, the computer program can execute the following steps:

[0140] Obtain the win rate set of each virtual character in the character pool, where the win rate set includes the win rate of the virtual character in battles against other virtual characters; construct a directed graph with all virtual characters in the character pool as nodes and the win rate set of each virtual character as edges; determine the Euler circuit in the directed graph; determine the abnormal characters from the character pool according to the Euler circuit, where the abnormal characters are virtual characters with abnormal win rates.

[0141] For the specific implementation of each of the above operations, reference can be made to the previous embodiments and will not be elaborated here.

[0142] Among them, the storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0143] Since the computer program stored in the storage medium can execute the steps in any of the abnormal character determination methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the abnormal character determination methods provided in the embodiments of the present application can be realized. For details, reference can be made to the previous embodiments and will not be elaborated here.

[0144] The above has introduced in detail an abnormal character determination method, device, storage medium, and computer device provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An abnormal role determination method, characterized in that, Including: Obtain the win rate set of each virtual character in the character pool, where the win rate set includes the win rate of the virtual character in battles against other virtual characters; Use all virtual characters in the character pool as nodes, where each of the nodes represents a virtual character; Construct directed edges according to the magnitude relationship between the win rate of each virtual character and a preset value; Use all the nodes and directed edges as a directed graph; Determine all connected graphs in the directed graph; For each of the connected graphs, determine the nodes that are not in the Euler circuit in the connected graph as candidate nodes, and determine the virtual characters corresponding to the candidate nodes as candidate characters; If the number of established directed graphs is equal to the preset number, determine the number of times the virtual character is determined as a candidate character; Determine the virtual characters with the number of times greater than the preset number as abnormal characters.

2. The method according to claim 1, characterized in that, The constructing of directed edges according to the magnitude relationship between the win rate of each virtual character and a preset value includes: Determine a virtual character in the character pool as the target character; From the win rates of the target character in battles against other virtual characters, determine the win rates greater than or equal to the preset value as designated win rates, and the other virtual characters corresponding to the designated win rates as designated characters; Construct a directed edge from the target character to the designated character; Determine a new target character from the virtual characters in the character pool other than the target character, and return to execute the steps of determining, from the win rates of the target character in battles against other virtual characters, the win rates greater than the preset value as designated win rates, and the other virtual characters corresponding to the designated win rates as designated characters; to constructing a directed edge from the target character to the designated character, until all virtual characters in the character pool are traversed.

3. The method according to claim 1, characterized in that, The method further includes: If the number of established directed graphs is not equal to the preset number, after updating the preset value, return to execute the steps of using all virtual characters in the character pool as nodes; to for each of the connected graphs, determining the nodes that are not in the Euler circuit in the connected graph as candidate nodes, and determining the virtual characters corresponding to the candidate nodes as candidate characters, until the number of established directed graphs is equal to the preset number.

4. The method according to claim 3, characterized in that, In the Euler circuit, the out-degree of a node is equal to the in-degree. After determining, for each of the connected graphs, the nodes that are not in the Euler circuit in the connected graph as candidate nodes and determining the virtual characters corresponding to the candidate nodes as candidate characters, it further includes: Obtain the out-degree and in-degree of the candidate nodes in the connected graph; In the case where the out-degree is greater than the in-degree, determine the abnormal state of the candidate character as too strong; In the case where the out-degree is less than the in-degree, determine the abnormal state of the candidate character as too weak.

5. The method according to claim 3, characterized in that, The updating of the preset value includes: Increase or decrease the preset value according to a preset change value to obtain a new preset value.

6. The method according to claim 1, characterized in that, The obtaining of the win rate set of each virtual character in the character pool includes: Obtain game logs; Obtain the battle characteristics of each battle record in the game logs, where the battle characteristics include battle type, battle duration, and end reason; Obtain the win rate set from the battle records whose battle characteristics meet the preset conditions.

7. An abnormal role determination device, characterized in that, Including: An acquisition module, configured to acquire a win rate set of each virtual character in a character pool, where the win rate set includes the win rate of the virtual character in battles against other virtual characters; A construction module, configured to use all virtual characters in the character pool as nodes, where each node represents a virtual character, construct directed edges according to the magnitude relationship between the win rate of each virtual character and a preset value, and use all the nodes and directed edges as a directed graph; A first determination module and a second determination module, configured to determine all connected graphs in the directed graph. For each connected graph, determine the nodes that are not in the Euler circuit in the connected graph as candidate nodes, and determine the virtual characters corresponding to the candidate nodes as candidate characters. If the number of established directed graphs is equal to a preset number, determine the number of times the virtual character is determined as a candidate character, and determine the virtual characters with the number of times greater than the preset number as abnormal characters.

8. A computer device, characterized in that, It includes a processor and a memory, and the memory stores multiple instructions; the processor loads the instructions from the memory to execute the steps in the abnormal character determination method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the abnormal character determination method according to any one of claims 1 to 6.

Images