Player negative behavior detection method, system, electronic device and storage medium

Abstract

The present application relates to a method, system, electronic device and storage medium for detecting negative behavior of players, wherein the method includes: comprehensively collecting behavioral data such as the number of player operations, chat content, combat data, location information and cooperation request responses in a single game; processing and analyzing data by calculating operation frequency scores, single behavior scores, constructing location heat maps, counting the number of negative words, calculating the number of cooperation request responses, etc., to obtain multi-dimensional detection data such as game behavior, game performance and social behavior, compare the player's comprehensive operation frequency score, single behavior score with the expected score, and compare with the scores of other players in the team to judge negative behavior, and output prompt information. This solution effectively solves the problem that the existing reporting system relies on players' active reporting and has low detection efficiency. It can detect negative behavior more comprehensively and accurately, maintain game fairness and a healthy environment, and enhance players' gaming experience.

Description

Technical Field

[0001] The present application relates to the field of game software development, and in particular to a player message behavior detection method, system, electronic device and computer-readable storage medium. Background Art

[0002] Player-vs-player online games, whose core gameplay focuses on the confrontation between players, are usually called "PVP" online games. In this type of game, the game experience of a player is closely linked to the game behavior of other players, and the mutual influence is significant.

[0003] Negative behavior refers to the behavior of players who do not actively participate in the game process, deliberately delay the game, or use other means to adversely affect their teammates or opponents. Once a player exhibits negative behavior, the gaming experience of other players in the game will take a sharp turn for the worse. In the long run, the game will face the dilemma of a large number of players leaving, the credibility of the game product will be greatly reduced, and it may even affect the reputation of the game developer.

[0004] In the relevant technology, in the current field of online player-vs-player games, there are still obvious deficiencies in the detection system for players' negative behaviors. A reporting system is commonly used, which mainly relies on players to actively initiate reports to identify players with negative behaviors and impose penalties accordingly. However, this method has limitations. Since it completely relies on the self-consciousness and initiative of players, it is difficult to fully, quickly and accurately detect all players who have engaged in negative behaviors, resulting in some negative behaviors not being discovered and handled in a timely manner. Summary of the invention

[0005] The embodiments of the present application provide a method, system, computer device and computer-readable storage medium for detecting negative player behavior, so as to at least solve the problem of poor accuracy in detecting negative player behavior in the related art.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting negative player behavior, which is applied to a PVP online game, and the method includes:

[0007] Get the game data of the player during a single game;

[0008] Analyze and classify the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data;

[0009] Based on the multi-dimensional detection data, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

[0010] In some embodiments, the game behavior data includes: the number of moves, the number of skill uses, the number of item uses, the number of attacks, and the real-time position of the player during a single game;

[0011] The game performance data includes: number of defeats, number of assists, number of deaths and total damage;

[0012] The social behavior data includes: the number of negative remarks and the number of responses to cooperation requests.

[0013] In some embodiments, determining whether the player has negative behavior based on the game behavior data includes:

[0014] According to the number of moves, the number of skill uses, the number of item uses, the number of attacks and the duration of a single game, operation frequencies of multiple different dimensions are obtained, and different weight coefficients are assigned to each operation frequency;

[0015] Performing a weighted operation on the multiple operating frequencies assigned weight coefficients to obtain a comprehensive operating frequency score;

[0016] Obtaining a single behavior score according to the minimum and maximum values ​​of the number of moves, the number of skill uses, the number of item uses, and the number of attacks;

[0017] By comparing the comprehensive operation frequency score and the single behavior score to see whether they meet the expected score, it is determined whether the player has negative behavior. If so, the negative behavior prompt information is output.

[0018] In some embodiments, the method further comprises:

[0019] Generating a player position heat map according to the real-time position of the player during a single game;

[0020] According to the ratio of the player position heat map to the global game map, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

[0021] In some embodiments, determining whether the player has negative behavior based on the game performance data includes:

[0022] Obtaining a plurality of different types of single-game performance averages according to the number of defeats, the number of assists, the number of deaths, the total amount of damage, and the duration of a single-game game, and assigning a different weight coefficient to each single-game performance average;

[0023] Performing a weighted calculation based on the average of multiple single-game performances assigned weight coefficients to obtain a game performance score for each player;

[0024] Obtaining a benchmark score according to the game performance scores of players in the same camp during the single game;

[0025] Based on the difference between any player's game performance score and the benchmark score, as well as the difference between the game performance scores of other players in the same camp, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

[0026] In some embodiments, determining whether the player has negative behavior based on the social behavior data includes:

[0027] Determine whether the player has negative behavior according to the number of negative remarks, and if so, output negative behavior prompt information; and adjust the weight coefficient according to the number of negative remarks, and perform weighted calculation according to multiple frequency parameters or game performance of the adjusted weight coefficient;

[0028] According to the number of responses to the cooperation request, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

[0029] In some embodiments, the game data is analyzed and processed to obtain multi-dimensional detection data including:

[0030] According to the open source database and historical battle data, a preset negative word library is constructed, the chat records sent by the player to the battle environment through the social system during a single game are obtained, and the chat records are matched with the preset negative word library to obtain the number of negative remarks;

[0031] During the target period after other players in the same camp request cooperation, the player's operation behavior is obtained, and by matching the operation behavior with a preset response action library, it is determined whether the operation behavior is an operation behavior in response to the cooperation request. If so, the number of the operation behavior is obtained to obtain the number of responses to the cooperation request.

[0032] In a second aspect, an embodiment of the present application provides a player negative behavior detection system, the system comprising: an acquisition module, an analysis and processing module, and a judgment module, wherein:

[0033] The acquisition module is used to acquire the game data of the player during a single game;

[0034] The analysis and processing module is used to analyze and classify the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data;

[0035] The judgment module is used to judge whether the player has negative behavior based on the multi-dimensional detection data, and if so, output negative behavior prompt information.

[0036] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect above when executing the computer program.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect above.

[0038] Compared with related technologies, the method for detecting negative behavior of players provided in the embodiment of the present application comprehensively collects behavioral data such as the number of player operations, chat content, combat data, location information, and cooperation request responses in a single game; and processes and analyzes data by calculating operation frequency scores, single behavior scores, constructing location heat maps, counting the number of negative words, and calculating the number of cooperation request responses, etc., to obtain multi-dimensional detection data such as game behavior, game performance, and social behavior, and compares the player's comprehensive operation frequency score, single behavior score, and expected score. It is combined with the comparison with the scores of other players in the team to judge negative behavior and output prompt information. This solution effectively solves the problem that the existing reporting system relies on players' active reporting and has low detection efficiency. It can detect negative behavior more comprehensively and accurately, maintain game fairness and a healthy environment, and enhance the player's gaming experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0040] Figure 1 is a flow chart of a method for detecting negative behavior of players according to an embodiment of the present application;

[0041] Figure 2 is a flowchart of obtaining game data according to an embodiment of the present application;

[0042] Figure 3 is another flow chart for detecting negative behavior of players according to an embodiment of the present application;

[0043] Figure 4 is a structural block diagram of a player negative behavior detection system according to an embodiment of the present application;

[0044] Figure 5 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0046] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0047] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0048] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0049] In PVP online games, the gaming experience of players is interrelated. If a player plays passively, he may not participate in the output or resistance of damage in the team battle, resulting in the failure of the team battle, which will make the actively participating players feel frustrated and directly affect their gaming experience. In the long run, some players will gradually lose due to their poor gaming experience caused by negative behavior, and the trust in the game product will also be affected. If players feel that the game operator cannot effectively deal with negative behavior, their trust in the game will decrease, which will in turn affect the credibility of the game developer and cause great harm to the long-term operation of the game.

[0050] Currently, well-known PVP games mainly rely on player reports to detect negative behaviors, which has obvious limitations. First, players may not discover their teammates' negative behaviors in time; second, players may be unwilling to report; some players may not report because they are friends with their teammates or are afraid of retaliation, making negative behaviors undetectable. Therefore, it is difficult for the reporting system to quickly detect all players with negative behaviors. In addition, in fast-paced games, a battle may end quickly, and players report after the battle, which will lead to a lag in handling negative behaviors and fail to stop negative behaviors in time during the game, affecting the fairness of the game and the experience of other players.

[0051] In view of this, the present application embodiment provides a method for detecting negative behavior of players. Figure 1 is a flow chart of a method for detecting negative player behavior according to an embodiment of the present application. Figure 1 As shown, the process includes the following steps:

[0052] S101, obtaining game data of a player during a single game;

[0053] Figure 2 is a flowchart of obtaining game data according to an embodiment of the present application, such as Figure 2 As shown, obtaining game data includes the following steps:

[0054] (1) Direct data collection:

[0055] The number of player operations in game data refers to the number of operations performed by players in the game, such as moving, attacking, using skills, using items, etc. For example, in multiplayer online tactical competitive games (MOBA), every time a player clicks a movement key or releases a skill, the game background will immediately record an operation. This recording method can most intuitively reflect the player's operational activity in the game.

[0056] In addition, when players send messages in the chat box within the game, the game system will record the chat content. These chat records can be used for subsequent analysis of the players' communication and whether there are any negative remarks.

[0057] (2) Record the result data:

[0058] During the game, when the player causes damage to the enemy, the game will go through a series of calculations to determine the final damage value. For example, when the player uses a weapon to attack the enemy, the damage of the weapon will be affected by factors such as distance and the target's defense attributes. After the game engine calculates the actual damage value, the damage value will be recorded. This record can reflect the player's output ability in battle.

[0059] At the same time, the game will constantly track the position of the player's character in the map, and the player's movement trajectory in the game map will be recorded. After the game is over, these location data can be used to build a player's movement heat map to analyze whether the player actively explores the map, participates in combat, etc.

[0060] (3) Record monitoring data

[0061] When a player initiates a cooperation request in the game, such as sending a signal to request support from teammates, the game system will start monitoring the responses of other players. If a teammate makes an action that meets the response rules (such as moving to the location requested for support), the system will record a response. If no teammates respond within a set time (for example, 10 seconds), the system will stop monitoring.

[0062] Through the above step S101, the game data of the players in the game can be collected from different angles. Directly recorded data reflects the real-time operation and communication of the players; recorded result data reflects the actual impact of the players' behavior; and monitoring data focuses on the players' performance in teamwork. By combining various types of data, we can fully understand the performance of the players in a single game and provide a data basis for subsequent negative behavior detection.

[0063] S102, analyzing and classifying the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data;

[0064] Optionally, when the amount of data is large, the game data may be preprocessed first, specifically including:

[0065] Remove invalid or noisy data from the raw data, such as incomplete log entries, duplicate records, etc.; convert data from different sources into a unified format to ensure consistency in subsequent processing, and store the cleaned and formatted data in the database to facilitate subsequent analysis and processing.

[0066] Furthermore, according to different types of data and the detection requirements of message behaviors, the collected data is classified into game behavior data, game performance data and social behavior data. Specifically:

[0067] Game behavior data includes: the number of moves, skill usage, item usage, attack count, and real-time location of the player during a single game;

[0068] Among them, the above data is a direct record of the player's operation of the character in the game. The number of moves reflects the player's activities in the map, the number of skill uses reflects the frequency of the player's use of the character's skills, the number of item uses shows the degree of utilization of in-game item resources, and the number of attacks indicates the player's enthusiasm for participating in combat output. They are used together to analyze the player's operation activity and participation in the game process during the game, and then determine whether the player is passive in the game by calculating the operation frequency score and other methods.

[0069] In addition, the specific location is used to construct a player location heat map. By comparing it with the full map percentage and other player location heat maps, it can be determined whether the player is participating in the game normally, such as whether he is actively exploring the map, participating in team battles, etc. The location information can reflect the player's movement strategy and activity in the game.

[0070] Game performance data includes: kills, assists, deaths, and total damage;

[0071] Among them, the number of defeats and assists is the result of the player defeating the enemy or assisting teammates in defeating in battle, reflecting the player's output and auxiliary ability in team battles. The number of deaths reflects the player's survivability and operational risks in the game from the side. The total amount of damage is a comprehensive measure of the damage output caused by the player to the enemy throughout the game. These data are calculated to obtain the player's game score, which is compared with the benchmark score and the team average level to determine whether the player is negative in the game battle performance.

[0072] Social behavior data included: number of negative comments and number of responses to cooperation requests.

[0073] Among them, a preset negative word library can be constructed based on the open source database and historical game battle data; after obtaining the chat records sent by the players to the battle environment through the social system during a single game, the chat records are matched with the preset negative word library to obtain the number of negative remarks;

[0074] During a single game, a player obtains the operation behavior of a certain player within a target period of time after a cooperation request from other players in the same camp, and determines whether the operation behavior is an operation behavior in response to the cooperation request by matching the response behavior with a preset response action library. If so, the number of the operation behaviors is obtained to obtain the number of responses to the cooperation request.

[0075] Records the player's response to other players' cooperation requests (such as requesting support, marking targets, etc.) in the game. It can reflect the player's enthusiasm in teamwork. Actively responding to cooperation requests helps teamwork and game progress. Fewer responses may mean that the player is not active in teamwork, thus helping to determine whether the player has negative behavior.

[0076] S103, judging whether the player has negative behavior based on the multi-dimensional detection data, and if so, outputting negative behavior prompt information, specifically:

[0077] (1) Judging whether a player has negative behavior based on game behavior data includes the following steps:

[0078] Step 1, according to the number of moves, skill usage, item usage, attack number and single game duration, obtain the operation frequencies of multiple different dimensions, and assign different weight coefficients to each operation frequency;

[0079] Different game types and playing methods attach different importance to various operations. Therefore, in the actual application, weight coefficients can be assigned to various operation frequencies according to the game type.

[0080] Step 2, performing weighted operations based on multiple frequency parameters with assigned weight coefficients to obtain a comprehensive operation frequency score;

[0081] Among them, a formula for calculating the comprehensive operation frequency score is shown as follows:

[0082]

[0083] Among them, α, β, γ, and δ represent the weights of moving operations, using skill operations, using items, and attacking operations in the game respectively. The higher the weight, the more important the operation should be in the game.

[0084] It should be noted that the above calculation formula is only an exemplary formula for calculating the player's operation frequency score. Those skilled in the art can understand that under the technical framework of the present application in which weighted operations are performed based on various types of player operation data to obtain a comprehensive operation frequency score, the specific calculation formula can be defined based on actual conditions.

[0085] Step 3, get a single behavior score based on the minimum and maximum values ​​of the number of moves, number of skill uses, number of item uses, and number of attacks;

[0086] In addition, considering that the number of operations alone is not enough to accurately determine whether a player is playing the game passively, because the player may be constantly performing a single operation, such as constantly walking around, and constantly using items in the same place, these situations are also passive behaviors.

[0087] Therefore, in order to more accurately determine whether the player is truly actively participating in the game, this embodiment also provides a single behavior score calculation mechanism, which can further analyze the diversity and balance of the player's operating behavior.

[0088] In an exemplary embodiment, the calculation formula for a single behavior score is as follows:

[0089]

[0090] Step 4, by comparing the comprehensive operation frequency score and the single behavior score to see whether they meet the expected score, determine whether the player has negative behavior. If so, output negative behavior prompt information.

[0091] Specifically, by calculating the distribution of different types of operations performed by players, such as movement, skill use, item use, and attack, we can not only determine whether the player is performing a single meaningless operation, but also more comprehensively evaluate the player's overall behavior pattern in the game.

[0092] In this embodiment, the single behavior score judgment mechanism is combined with other judgment factors such as operation frequency to provide a more comprehensive and accurate judgment of the player's negative behavior. For example, when judging whether a player is playing the game passively, not only the comprehensive operation frequency score (taking into account the number of operations and weight) is considered, but also the single behavior score is combined. If a player's comprehensive operation frequency score is within the normal range, but the single behavior score is very low, it means that the player may have the problem of deliberately performing a single operation, and is also judged as a passive player.

[0093] Optionally, the expected score is determined based on a large amount of game test data and analysis of normal player behavior patterns, covering the operation frequency and single behavior data distribution, setting a threshold range for distinguishing between positive and negative player behaviors, such as the lower limit of the comprehensive operation frequency score, the single behavior score balance threshold, etc., and also considering the judgment criteria for the combined relationship between the two.

[0094] The comprehensive operation frequency score calculated by the player is compared with the expected score and combined with the single behavior score to determine whether it is negative. If the comprehensive operation frequency score is lower than the lower limit or the single behavior score is lower than the balance threshold, or the combination of the two is abnormal (such as the frequency is acceptable but the behavior is single), it may be judged as negative.

[0095] In addition, during the game, players will move to various locations on the game map. In this embodiment, all locations that players move to during the game are collected, and a player position heat map is constructed after the game ends. By comparing the proportion of each player's heat map relative to the entire map, it is determined whether the player has negative behavior. Usually, if a player's heat map accounts for too low a proportion of the entire map, or if a player's heat map overlaps too little with other players' heat maps, it means that the player has negative game behavior.

[0096] (2) Judging whether a player has negative behavior based on game performance data includes the following steps:

[0097] Step 1, obtain multiple single-game performance averages according to the number of defeats, assists, deaths, total damage, and single-game duration, and assign different weight coefficients to each single-game performance average;

[0098] Different game types and playing methods attach different importance to various games. Therefore, in the actual application, weight coefficients can be assigned to various operation frequencies according to the game type.

[0099] Step 2: Perform a weighted calculation based on the average of multiple single-game performances with assigned weight coefficients to obtain the game performance score of each player;

[0100] Among them, a formula for calculating the comprehensive operation frequency score is shown as follows:

[0101]

[0102] It should be noted that α, β, γ, and δ represent the weights of kills, assists, deaths, and total damage, respectively, indicating the importance of these data in the game; KDA is an indicator in the game to measure the player's score, and its formula is:

[0103]

[0104] In this embodiment, the player game score calculated by the above formula can basically reflect the player's performance in a game. In addition, this calculation formula is only an exemplary formula for calculating the player's operation frequency score; in actual development, the measurement indicator data can be added or deleted according to the game type. For example, if there are healing characters in some games, the healing amount can be included in the score calculation system.

[0105] Step 3: Obtain a benchmark score based on the game performance scores of players in the same camp during a single game;

[0106] Step 4: Based on the difference between any player's game performance score and the benchmark score, as well as the difference between the game performance scores of other players in the same camp, determine whether the player has negative behavior. If so, output negative behavior prompt information.

[0107] Among them, the benchmark score is a reference standard for measuring player performance. This benchmark score can reflect the approximate performance level that players should achieve when they actively participate in the game and reasonably play their roles under ideal conditions. It provides a basic quantitative basis for judging whether a player is playing passively. If a player's score is too low and far below the average level of team players, it is considered that the player may have negative gaming behavior.

[0108] Among them, during the game testing phase, professional testers play the game in an ideal environment according to the optimal strategy, record the performance data and statistically analyze it to determine the initial benchmark score. As the game is updated and balanced, the character's ability, task difficulty, game mode, etc. are changed, and re-evaluated or updated based on the normal game data after a large number of players update. It should be noted that the benchmark score needs to be determined separately according to different game modes and characters, combined with experience and knowledge in this field.

[0109] Furthermore, it is not comprehensive to compare a player's individual score with the benchmark score alone. The situations of different game matches may vary. For example, factors such as game difficulty, teammate cooperation, and opponent strength will affect the player's final score.

[0110] In some cases, although a player's score is lower than the benchmark score (such as a player's score of 2 points is lower than the predetermined 5 points), if the entire team faces a greater challenge and other teammates also score low (such as 2 or 3 points), the player's performance may be consistent with the overall level of the team, and he cannot be simply judged as a negative player. By comparing the scores with other players in the team, the relative performance of players in a specific game environment can be more accurately evaluated, eliminating the situation where the scores are generally low due to external factors, and more accurately identifying players who are truly negative in the game.

[0111] Through the above steps Step 1-Step 4, through reasonable benchmark score assignment and team comparison, these negative behaviors can be discovered and handled in a timely manner to ensure the health of the game environment. At the same time, for those players who may be misjudged, this judgment method gives fairer treatment so that they will not be unfairly punished due to unreasonable judgments, thereby improving the overall game satisfaction of players and their recognition of game fairness.

[0112] (3) Judging whether a player has negative behavior based on social behavior data includes the following steps:

[0113] Step 1, judging whether the player has negative behavior according to the number of negative comments, and if so, outputting negative behavior prompt information; adjusting the weight coefficient according to the number of negative comments, and performing weighted calculation according to multiple frequency parameters or game performance of the adjusted weight coefficient to obtain a comprehensive operation frequency score or game performance score;

[0114] It should be noted that in this solution, a negative word library is established during the game development, which includes a series of negative behavior sensitive words, including negative words such as insulting words. After the game is over, the system will collect the chat records of the players in the game, and judge whether the players have made negative remarks based on the number of negative words that appear in the players. This is also regarded as a negative behavior, but the punishment for negative remarks is relatively small. However, it will increase the coefficients of the results of other negative behavior detection modules. If negative behavior does exist, the final punishment will be increased.

[0115] Step 2, based on the number of responses to the cooperation request, determine whether the player has negative behavior. If so, output negative behavior prompt information.

[0116] There are usually a series of cooperation request operations in the game, including sending signals, requesting support, etc. When a player sends such a cooperation request, the response behavior of other players will be recorded. The game will set a series of behaviors that are considered positive responses. Switching the game perspective to view and go to the player's position are considered positive responses. After the game is over, the player's activeness in the game will be judged based on whether he actively responded to the cooperation request.

[0117] also, Figure 3 This is another flow chart for detecting player negative behavior according to an embodiment of the present application.

[0118] Through the above steps S101 to S103, by comprehensively collecting the player's operation times, chat content, combat data, location information, cooperation request response status and other behavioral data in a single game; by calculating the operation frequency score, single behavior score, constructing a location heat map, counting the number of negative words, calculating the number of cooperation request responses and other processing and analysis data, we can obtain multi-dimensional detection data such as game behavior, game performance and social behavior, compare the player's comprehensive operation frequency score, single behavior score with the expected score, and compare it with the scores of other players in the team to judge negative behavior, and output prompt information. This solution effectively solves the problem that the existing reporting system relies on players' active reporting and has low detection efficiency. It can detect negative behavior more comprehensively and accurately, maintain game fairness and a healthy environment, and enhance players' gaming experience.

[0119] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0120] This embodiment also provides a player negative behavior detection system. Figure 4 is a structural block diagram of a player negative behavior detection system according to an embodiment of the present application, such as Figure 4 As shown, the system includes: an acquisition module 40, an analysis and processing module 41 and a judgment module 42, wherein:

[0121] The acquisition module 40 is used to obtain the game data of the player during a single game;

[0122] The analysis and processing module 41 is used to analyze and classify the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data;

[0123] The judgment module 42 is used to judge whether the player has negative behavior based on the multi-dimensional detection data, and if so, output negative behavior prompt information.

[0124] Through the above system, in a single game, we can comprehensively collect behavioral data such as the number of player operations, chat content, combat data, location information, and cooperation request responses; by calculating the operation frequency score, single behavior score, constructing a location heat map, counting the number of negative words, and calculating the number of cooperation request responses, we can process and analyze the data to obtain multi-dimensional detection data such as game behavior, game performance, and social behavior. We can compare the player's comprehensive operation frequency score, single behavior score, and expected score, and compare it with the scores of other players in the team to judge negative behavior and output prompt information. This solution effectively solves the problem that the existing reporting system relies on players' active reporting and has low detection efficiency. It can detect negative behavior more comprehensively and accurately, maintain game fairness and a healthy environment, and enhance players' gaming experience.

[0125] In one embodiment, Figure 5 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 5 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Figure 5 As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with an external terminal through a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement a method for detecting negative behavior of players, and the database is used to store data.

[0126] Those skilled in the art will understand that Figure 5 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0128] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for detecting negative player behavior, characterized in that: Applied in PVP online games, the method includes: Get the game data of the player during a single game; Analyze and classify the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data; Based on the multi-dimensional detection data, multi-dimensional negative detection information is obtained respectively, and by combining the multi-dimensional negative detection information, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output; The game behavior data includes: the number of moves, skill usage, item usage, attack count, and real-time location of the player during a single game; The game performance data includes: number of defeats, number of assists, number of deaths and total damage; The social behavior data includes: the number of negative remarks and the number of responses to cooperation requests; Judging whether the player has negative behavior based on the game performance data includes: Obtaining a plurality of different types of single-game performance averages according to the number of defeats, the number of assists, the number of deaths, the total amount of damage, and the duration of a single-game game, and assigning a different weight coefficient to each single-game performance average; Perform a weighted calculation based on the average of multiple single-game performances after assigning weight coefficients to obtain the game performance score of each player; According to the game performance scores of the players in the same camp during the single game, a benchmark score for measuring the player's performance is obtained, wherein the benchmark score reflects the performance level that the player should achieve when actively participating in the game and reasonably exerting the role's ability under ideal conditions; Based on the difference between any player's game performance score and the benchmark score, as well as the difference between the game performance scores of other players in the same camp, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

2. The method according to claim 1, characterized in that Judging whether the player has negative behavior based on the game behavior data includes: According to the number of moves, the number of skill uses, the number of item uses, the number of attacks and the duration of a single game, operation frequencies of multiple different dimensions are obtained, and different weight coefficients are assigned to each operation frequency; Perform weighted calculation on multiple operation frequencies after assigning weight coefficients to obtain a comprehensive operation frequency score; Obtaining a single behavior score according to the minimum and maximum values ​​of the number of moves, the number of skill uses, the number of item uses, and the number of attacks; By comparing the comprehensive operation frequency score and the single behavior score to see whether they meet the expected score, it is determined whether the player has negative behavior. If so, the negative behavior prompt information is output.

3. The method according to claim 2, characterized in that The method further comprises: Generating a player position heat map according to the real-time position of the player during a single game; According to the ratio of the player position heat map to the global game map, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

4. The method according to any one of claims 2 to 3, characterized in that: Judging whether the player has negative behavior based on the social behavior data includes: Determine whether the player has negative behavior according to the number of negative remarks, and if so, output negative behavior prompt information; and adjust the weight coefficients assigned to each operation frequency or each single-game performance average according to the number of negative remarks, and perform weighted calculation according to the operation frequency or single-game performance average after adjusting the weight coefficient; According to the number of responses to the cooperation request, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

5. The method according to claim 4, characterized in that The game data is analyzed and processed to obtain multi-dimensional detection data including: According to the open source database and historical battle data, a preset negative word library is constructed, the chat records sent by the player to the battle environment through the social system during a single game are obtained, and the chat records are matched with the preset negative word library to obtain the number of negative remarks; During the target period after other players in the same camp request cooperation, the player's operation behavior is obtained, and by matching the operation behavior with a preset response action library, it is determined whether the operation behavior is an operation behavior in response to the cooperation request. If so, the number of the operation behavior is obtained to obtain the number of responses to the cooperation request.

6. A player negative behavior detection system, characterized in that: The system comprises: an acquisition module, an analysis and processing module and a judgment module, wherein: The acquisition module is used to acquire the game data of the player during a single game; The analysis and processing module is used to analyze and classify the game data to obtain multi-dimensional detection data, wherein the multi-dimensional detection data includes: game behavior data, game performance data and social behavior data; The judgment module is used to obtain multi-dimensional negative detection information based on the multi-dimensional detection data, and to judge whether the player has negative behavior by combining the multi-dimensional negative detection information, and if so, output negative behavior prompt information; The game behavior data includes: the number of moves, skill usage, item usage, attack count, and real-time location of the player during a single game; The game performance data includes: number of defeats, number of assists, number of deaths and total damage; The social behavior data includes: the number of negative remarks and the number of responses to cooperation requests; Judging whether the player has negative behavior based on the game performance data includes: Obtaining a plurality of different types of single-game performance averages according to the number of defeats, the number of assists, the number of deaths, the total amount of damage, and the duration of a single-game game, and assigning a different weight coefficient to each single-game performance average; Perform a weighted calculation based on the average of multiple single-game performances after assigning weight coefficients to obtain the game performance score of each player; According to the game performance scores of the players in the same camp during the single game, a benchmark score for measuring the player's performance is obtained, wherein the benchmark score reflects the performance level that the player should achieve when actively participating in the game and reasonably exerting the role's ability under ideal conditions; Based on the difference between any player's game performance score and the benchmark score, as well as the difference between the game performance scores of other players in the same camp, it is determined whether the player has negative behavior, and if so, negative behavior prompt information is output.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images