A game blind box drawing method, system, device and medium based on player data

Abstract

The application is suitable for the field of game blind box drawing, and discloses a game blind box drawing method based on player data. By comprehensively analyzing the historical game data of players, different time window lengths are set for different players to capture their long-term game preferences and short-term interest changes, and the blind box drawing probability is adjusted accordingly. The game behavior data of players in different time periods is identified to eliminate false interests and avoid affecting the drawing probability. For multiple accounts of the same player, the method combines their game data for unified processing to ensure the accuracy of the drawing probability adjustment. The application also constructs a player satisfaction and game balance evaluation model to further fine-tune the blind box drawing probability. The method also has a monitoring function that can identify and prevent abnormal behavior of players manipulating the drawing probability by exploiting system vulnerabilities, monitor the blind box drawing situation, evaluate the impact of the adjusted probability distribution on the game economy, and ensure the fairness and stability of game operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of game blind box extraction, in particular to a game blind box extraction method, system, device and medium based on player data. BACKGROUND

[0002] Game blind box is a popular commodity sales mode, especially favored by young consumers. Consumers cannot predict the specific goods inside the box when purchasing, which brings a sense of mystery and anticipation, increasing the fun of consumer experience. Game blind box usually contains small toys, character models or other goods with collection value. Consumers are full of curiosity about the internal goods before opening the game blind box.

[0003] However, the traditional blind box extraction method often uses a fixed probability distribution, ignoring the personalized needs and interest changes of players, resulting in poor player experience and decreased game participation.

[0004] In addition, some players may exploit system vulnerabilities to manipulate blind box extraction probability distribution, which not only undermines the fairness of the game, but also affects the stability of the game economy. Therefore, how to effectively identify and prevent such abnormal behavior has become a problem to be solved in the current game blind box extraction method. SUMMARY

[0005] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application proposes a game blind box extraction method, system, device and medium based on player data.

[0006] In a first aspect, the present application proposes a game blind box extraction method based on player data, comprising: obtaining historical game data of a player, and setting different time window lengths for different players to obtain long-term game preferences and short-term game interest changes of the player, and adjusting the extraction probability of the blind box based on the long-term game preferences and short-term game interest changes of the player.

[0007] Obtain the game behavior data of the player in different time periods, and identify the false interest of the player. If the player has false interest, do not adjust the blind box extraction probability of the player.

[0008] In the process of adjusting the extraction probability of the blind box, multiple accounts of the same player are identified. For the game data of the associated accounts, the game data is merged and processed, and the extraction probability of the blind box is adjusted according to the merged game data. Or build a player satisfaction evaluation model and a game balance evaluation index, and adjust the blind box extraction probability based on the player satisfaction evaluation model and the game balance evaluation index.

[0009] Monitor the blind box drawing behavior of the player, and identify abnormal behavior of manipulating blind box drawing probability distribution by exploiting system vulnerabilities.

[0010] After adjusting the drawing probability of the blind box, monitor the drawing of the blind box, and determine whether the adjusted probability distribution will affect the game economy.

[0011] Further specifically, in the above technical solution, the historical game data of the player is obtained, and different time window lengths are set for different players to obtain the long-term game preference and short-term game interest change of the player, and the drawing probability of the blind box is adjusted based on the long-term game preference and short-term game interest change of the player, including:

[0012] Obtain the historical game data of the player, and the historical game data includes the game behavior, game duration, game frequency and consumption record of the player;

[0013] According to the historical game data, the player is divided into different player groups, and each player group has similar game preference and behavior mode;

[0014] According to the historical game data of each player group, the length of the time window is determined, and the long-term game preference and short-term interest change of the player for different blind boxes are predicted according to the game behavior and preference in the time window;

[0015] According to the long-term game preference and short-term interest change, the drawing probability distribution of each blind box is adjusted.

[0016] Further specifically, in the above technical solution, the game behavior data of the player in different time periods is obtained, and the false interest of the player is identified, and if the player has false interest, the blind box drawing probability of the player is not adjusted, including:

[0017] Statistical analysis of the frequency of the player drawing each type of blind box in a predetermined time period, and obtaining the preference distribution of the player for different types of blind boxes according to the frequency;

[0018] Compare the preference distribution of the player for the blind box with the long-term game preference, and if there is a significant deviation, it is determined that the interest of the player in the blind box is abnormal;

[0019] Anomaly detection algorithm such as Isolation Forest is used to detect the blind box drawing behavior of the player with abnormal interest, and the player showing false interest is identified;

[0020] Quantify the false interest of the player, obtain the false interest value of the player, and set a corresponding false interest threshold value, when the false interest value exceeds the false interest threshold value, the player is marked as a false player, and the blind box drawing probability of the false player is not adjusted when adjusting the blind box probability.

[0021] Further specifically, in the above technical solution, the player satisfaction evaluation model and the game balance evaluation index are constructed, and the blind box extraction probability is adjusted based on the player satisfaction evaluation model and the game balance evaluation index, which comprises:

[0022] According to the historical game data, a player satisfaction evaluation model is constructed, and the satisfaction evaluation model is used to quantify the player satisfaction under different extraction probabilities;

[0023] Based on the game balance, a game balance evaluation index is constructed, and the game balance evaluation index includes the player's sense of gain and the balance of game resource allocation;

[0024] The player satisfaction and the game balance are taken as the optimization objectives of a multi-objective optimization algorithm, and the two optimization objectives are integrated into a single optimization function through weighted summation;

[0025] A heuristic search method is used to obtain an extraction probability combination that balances the player satisfaction and the game balance;

[0026] The extraction probability combination is optimized, a new extraction probability combination is generated through crossover and mutation operations, and its advantages and disadvantages are evaluated according to an adaptive function;

[0027] According to the optimized extraction probability combination, the blind box extraction probability is adjusted.

[0028] Further specifically, in the above technical solution, the player's blind box extraction behavior is monitored, and abnormal behavior of manipulating blind box extraction probability distribution by exploiting system vulnerabilities is identified, which comprises:

[0029] Behavior data of the player in the blind box extraction process is obtained, and the behavior data includes extraction time, extraction times and obtained item information;

[0030] Based on the behavior data, the features of extraction frequency, continuous extraction times and rare item acquisition probability are extracted, and a player behavior pattern feature vector is constructed;

[0031] According to the player behavior pattern feature vector, the player is divided into different behavior pattern groups;

[0032] Based on each behavior pattern group, the blind box extraction probability distribution of each group is counted to obtain the extraction probability distribution characteristics of each group;

[0033] The extraction probability distribution characteristics of each group are compared with the preset normal probability distribution, and the deviation degree is calculated;

[0034] If the deviation degree exceeds the preset threshold, it is judged that the group has abnormal behavior.

[0035] For the player group judged to have abnormal behavior, analyze the behavior sequence, and identify the blind box extraction algorithm vulnerability exploited;

[0036] According to the identified blind box extraction algorithm vulnerability, take patch repair measures, including perfecting the server verification logic and increasing the random number seed update frequency;

[0037] Players exploiting the blind box extraction algorithm vulnerability are warned or banned.

[0038] Further specifically, in the above technical solution, during the adjustment of the extraction probability of the blind box, multiple accounts of the same player are identified, the game data of the associated accounts are merged, and the extraction probability of the blind box is adjusted according to the merged game data, including:

[0039] Through account association analysis technology, multiple account information related to the player is extracted from the game database;

[0040] Using data merging method, the game data of multiple accounts is summarized under a main account;

[0041] Through data analysis, the real game preference of the player is extracted based on the merged game data;

[0042] According to the real game preference, the extraction probability is adjusted.

[0043] Further specifically, in the above technical solution, after adjusting the extraction probability of the blind box, the extraction of the blind box is monitored, and it is judged whether the adjusted probability distribution will affect the game economy, including:

[0044] Obtain real-time data of blind box extraction, including extraction times and extraction results;

[0045] According to the real-time data, obtain the actual extraction frequency of each type of item;

[0046] Obtain a preset probability distribution model, and calculate the theoretical extraction probability of each type of item;

[0047] Based on each type of item, divide the actual extraction frequency by the total extraction times to obtain the actual extraction probability of the item;

[0048] Calculate the deviation between the actual extraction probability and the theoretical extraction probability;

[0049] If the deviation exceeds a preset threshold, trigger the probability adjustment mechanism, adjust the theoretical extraction probability by increasing or decreasing the weight according to the deviation, and obtain the adjusted probability distribution;

[0050] According to the adjusted probability distribution, a preset number of virtual extraction processes are randomly generated, and simulation extraction frequencies and simulation extraction probabilities of various types of items are counted;

[0051] The simulation extraction probability is compared with the actual extraction probability before adjustment, and the influence of the adjusted probability distribution on item rarity, player experience, and game economy is evaluated;

[0052] A preset game index is obtained, and the game index includes total consumption amount, number of paying players, per capita consumption amount, and daily active user number;

[0053] An association model between the adjusted probability distribution and the game index is established, the influence degree of probability adjustment on each index is predicted, and a prediction result is obtained;

[0054] If there is an index with negative influence exceeding a preset acceptable threshold in the prediction result, the current probability adjustment is cancelled;

[0055] If there is no index with negative influence exceeding a preset acceptable threshold in the prediction result, the adjusted probability distribution parameter is saved to a database.

[0056] In a second aspect, the application also provides a game blind box extraction system based on player data, comprising:

[0057] A first processing module: obtaining historical game data of a player, setting different time window lengths for different players, obtaining long-term game preferences and short-term game interest changes of the player, and adjusting the extraction probability of a blind box based on the long-term game preferences and short-term game interest changes of the player;

[0058] A second processing module: obtaining game behavior data of a player in different time periods, and identifying false interests of the player, if the player has false interests, not adjusting the blind box extraction probability of the player;

[0059] A third processing module: identifying multiple accounts of the same player in the process of adjusting the extraction probability of the blind box, merging game data of associated accounts, adjusting the extraction probability of the blind box according to the merged game data, or constructing a player satisfaction evaluation model and a game balance evaluation index, and adjusting the blind box extraction probability based on the player satisfaction evaluation model and the game balance evaluation index;

[0060] A fourth processing module: monitoring the blind box extraction behavior of the player, and identifying abnormal behavior of manipulating the blind box extraction probability distribution by exploiting system vulnerabilities;

[0061] The fifth processing module: after adjusting the extraction probability of the blind box, monitoring the extraction of the blind box, judging whether the adjusted probability distribution will affect the game economy.

[0062] In a third aspect, the present application also provides a terminal 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 according to any one of the preceding aspects when executing the computer program.

[0063] In a fourth aspect, the present application also provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the method according to any one of the preceding aspects.

[0064] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0065] 1. The present application can set different time window lengths for different players based on their historical game data, thereby accurately capturing the long-term game preferences and short-term interest changes of each player, making the blind box extraction probability no longer fixed and unchangeable, but can be dynamically adjusted with the changes in the player's interest, thereby greatly improving the player's game experience. Through personalized extraction probability, the present application can meet the personalized needs of different players, so that each player can feel the surprise matching their own interest when extracting the blind box, thereby increasing the player's game participation and loyalty.

[0066] 2. The present application has the ability to identify false interest of players, by counting the frequency of players extracting each type of blind box within a preset time period, and comparing with the player's long-term game preference, whether the player has false interest can be identified. If the player's interest in the blind box is abnormal, the extraction probability will not be adjusted, thereby avoiding resource mismatch caused by false interest. Preventing false interest not only protects the game's economic system from the interference of improper operation, but also ensures the fairness and justice of blind box extraction, and maintains the overall order of the game and the trust between players.

[0067] 3. The present application constructs a player satisfaction evaluation model and a game balance evaluation index, which are used to quantify the player satisfaction and the balance of game resources under different extraction probabilities. These two evaluation models provide a scientific basis for adjusting the blind box extraction probability, ensuring that the blind box extraction can meet the needs of players without destroying the balance of the game. Through the satisfaction and balance evaluation, the present application can continuously optimize the blind box extraction strategy, so that the game not only maintains the interest, but also has better sustainability and fairness.

[0068] 4、The application adopts a multi-objective optimization algorithm, takes the player satisfaction and game balance as optimization objectives, and integrates the two optimization objectives into a single optimization function through weighted summation, so that the player's demand and the balance of the game can be considered when adjusting the blind box extraction probability, thereby realizing the global optimal solution. The application of the multi-objective optimization algorithm enables the application to more accurately control the probability distribution of blind box extraction, thereby achieving better balance and stability in the game economic system. BRIEF DESCRIPTION OF DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0070] Figure 1 is a flowchart of a game blind box extraction method based on player data provided by an embodiment of the present application;

[0071] Figure 2 is a structural schematic diagram of a game blind box extraction system based on player data provided by an embodiment of the present application;

[0072] Figure 3 is a structural schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0073] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0074] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or sets thereof.

[0075] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0076] As used in the specification and the appended claims, the term “if’ can be interpreted as meaning “when,” or “upon,” or “in response to a determination,” or “in response to a detection” depending on the context. Similarly, the phrase “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “upon a determination” or “in response to a determination” or “upon a detection of [the described condition or event]” or “in response to a detection of [the described condition or event],” depending on the context.

[0077] In addition, in the description of the present application and the appended claims, the terms “first,” “second,” “third,” etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0078] Reference in the specification to “one embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in additional embodiments,” and so on, in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically stated. The terms “comprise,” “comprises,” “comprising,” “include,” “includes,” “including,” and their variants are meant to be non-limiting, unless otherwise specifically stated.

[0079] See Figure 1 The application provides a game blind box drawing method based on player data, including: S101 obtaining historical game data of a player, and setting different time window lengths for different players to obtain long-term game preferences and short-term game interest changes of the player, and adjusting a drawing probability of a blind box based on the long-term game preferences and short-term game interest changes of the player, S102 obtaining game behavior data of the player in different time periods, and identifying false interests of the player, if the player has false interests, not adjusting the drawing probability of the blind box, S103 in the process of adjusting the drawing probability of the blind box, identifying multiple accounts of the same player, for game data of associated accounts, performing merging processing, and adjusting the drawing probability of the blind box according to the merged game data; or constructing a player satisfaction evaluation model and a game balance evaluation index, adjusting the drawing probability of the blind box based on the player satisfaction evaluation model and the game balance evaluation index, S104 monitoring blind box drawing behaviors of the player, and identifying abnormal behaviors of manipulating blind box drawing probability distribution by using system loopholes, S105 after adjusting the drawing probability of the blind box, monitoring the drawing of the blind box, and judging whether the adjusted probability distribution will affect game economy.

[0080] The historical game data of the player is acquired, different time window lengths are set for different players, long-term game preferences and short-term game interest changes of the players are acquired, and the extraction probability of the blind box is adjusted based on the long-term game preferences and short-term game interest changes of the players; game behavior data of the player in different time periods is acquired, and false interests of the player are identified. If the player has false interests, the extraction probability of the blind box is not adjusted. In the process of adjusting the extraction probability of the blind box, multiple accounts of the same player are identified. For the game data of the associated accounts, the game data is combined and processed, and the extraction probability of the blind box is adjusted according to the combined game data. Or a player satisfaction evaluation model and a game balance evaluation index are constructed, the extraction probability of the blind box is adjusted based on the player satisfaction evaluation model and the game balance evaluation index. The blind box extraction behavior of the player is monitored, and abnormal behavior of manipulating the blind box extraction probability distribution by using system loopholes is identified. After adjusting the extraction probability of the blind box, the extraction of the blind box is monitored, and it is judged whether the adjusted probability distribution will affect the game economy.

[0081] Specifically, by obtaining the historical game data of the players, the game behavior and preferences of the players can be deeply understood. For this purpose, different time window lengths need to be set, for example, a short-term window can be set to 7 days or 30 days to capture the recent interest changes of the players; a long-term window can be set to 90 days or 180 days, or even longer, to reveal the stable preferences of the players. For example, the short-term data of player A shows that he has recently frequently played racing games, while the long-term data indicates that he has always preferred role-playing games. This shows that player A may have a short-term interest in racing games, but role-playing games are still his main preference. Based on these data, the extraction probability of the blind box can be adjusted, for example, the probability of racing game related props is increased, while a certain proportion of role-playing game props is retained to meet the long-term and short-term needs of player A. In order to more accurately capture the real interests of the players, the false interests of the players need to be identified. For example, player B has to play a strategy game that he does not like in order to complete a certain time-limited task. In this case, if the probability of strategy game props is increased based only on short-term data, it may cause player B to be dissatisfied. Therefore, the real interests of the players need to be judged by combining multi-dimensional data such as game length, payment, social interaction, etc. If the system identifies that player B's strategy game behavior belongs to false interest, the blind box extraction probability of player B will not be adjusted, and his original preference probability distribution will be maintained. In the process of adjusting the extraction probability of the blind box, the multiple accounts of the same player also need to be considered. Some players may have multiple game accounts, for example, player C has both iOS and Android accounts. If the data of these two accounts are processed separately, it may cause deviation in understanding the preferences of player C. Therefore, the game data of the associated accounts needs to be identified and merged. For example, through IP address, device ID, game behavior, etc., it can be judged that the two accounts of player C belong to the same person. After merging the data, the overall game preferences of player C can be more accurately understood, and the blind box extraction probability can be adjusted accordingly. In addition to adjusting the extraction probability of the blind box based on the game data of the players, a player satisfaction evaluation model and a game balance evaluation index can also be built. The player satisfaction evaluation model can evaluate the satisfaction of the players with the current blind box probability distribution by collecting the feedback, evaluation, game length, etc. of the players. The game balance evaluation index can measure the value and scarcity of different props, and their impact on the game economic system. For example, if a prop is too rare or powerful, it may disrupt the balance of the game and cause players to leave. Therefore, the extraction probability of the blind box needs to be dynamically adjusted based on the player satisfaction and game balance. For example, if the players are generally dissatisfied with the acquisition probability of a certain type of prop, or the frequency of a certain prop is too high, affecting the balance of the game, the corresponding probability needs to be adjusted. In addition, the blind box extraction behavior of the players needs to be monitored to identify abnormal behavior. For example, some players may use system vulnerabilities to manipulate the probability distribution of the blind box, or use external programs to cheat. These behaviors will disrupt the fairness and stability of the game.Therefore, it is necessary to establish an abnormal behavior detection mechanism, for example, by analyzing the player's draw frequency, amount, time, etc. Data, identify abnormal behavior, and take appropriate measures, such as banning the account, rolling back data, etc. Finally, after adjusting the blind box draw probability, it is also necessary to monitor the draw of the blind box to determine whether the adjusted probability distribution will affect the game economy. For example, if the draw probability of some props is too high, it may lead to a decline in the price of these props, affecting the stability of the in-game economic system. Therefore, it is necessary to continuously monitor various indicators of the in-game economic system, such as prop prices, transaction volumes, player payment situations, etc., and based on the monitoring results, fine-tune the blind box draw probability to ensure the healthy development of the game economic system.

[0082] In some embodiments, historical game data of the player is obtained, and different time window lengths are set for different players to obtain the long-term game preferences and short-term game interest changes of the players, and the draw probability of the blind box is adjusted based on the long-term game preferences and short-term game interest changes of the players. Including:

[0083] Obtain the historical game data of the player, the historical game data including the game behavior, game duration, game frequency and consumption record of the player; according to the historical game data, the player is divided into different player groups, each player group having similar game preferences and behavior patterns; according to the historical game data of each player group, the length of the time window is determined, and the long-term game preferences and short-term interest changes of the player for different blind boxes are predicted according to the game behavior and preferences within the time window; according to the long-term game preferences and short-term interest changes, the draw probability distribution of each blind box is adjusted.

[0084] Specifically, historical game data is collected, including player behavior, game duration, game frequency, and spending history. For example, player A's historical game data shows that their gaming behavior is primarily focused on PvE dungeons, with an average game duration of 2 hours per day and a frequency of 5 times per week. They have never made any in-game purchases. Player B's historical game data shows that they primarily engage in PvP competitive games, spending an average of 5 hours online per day and playing once a day. They also top up a small amount of money monthly to purchase in-game decorative items. Player C's gaming behavior is more balanced, dabbling in both PvE and PvP, playing for approximately 3 hours per day and 4 times per week, and frequently purchasing blind box games. Collecting this data can provide a basis for subsequent player segmentation and probability adjustments. Based on historical game data, players can be divided into different groups, each with similar gaming preferences and behavior patterns. For example, based on the gaming behaviors of the three players mentioned above, player A can be categorized as a casual PvE player, player B as a competitive PvP player, and player C as a mixed PvE / PvP player. Segmenting player groups allows for more refined blind box probability adjustments tailored to the needs of different player groups. For example, casual PVE players may prioritize items for collecting and developing, while competitive PVP players may prefer items that boost combat power. The length of the time window is determined based on each player group's historical gameplay data. The time window length is set to capture short-term changes in players' interests. For casual PVE players, a longer time window, such as one month, can be used, as their gaming preferences are generally more stable. For competitive PVP players and mixed-player types, a shorter time window, such as one or two weeks, can be used to more quickly capture changes in their interest in different blind boxes. For example, for mixed-player types like Player C, who has focused more on PVP gameplay in the past two weeks, the probability of rare items in PVP-related blind boxes can be appropriately increased. Within a defined time window, analyze players' gaming behavior and preferences to predict their long-term gaming preferences and short-term changes in interest in different blind boxes. For example, if the casual PVE player group has long favored collectible items, but recently showed strong interest in a newly released PVE dungeon-related blind box, it can be predicted that this group will experience increased demand for this new blind box in the short term. For competitive PVP players, they have long favored items that enhance combat effectiveness, and in the past two weeks, they have shown interest in a blind box featuring a particularly impressive PVP mount. We predict that this group's demand for this mount will increase in the short term. Based on these long-term gaming preferences and short-term changes in interest, we can adjust the probability distribution of each blind box. For casual PVE players, given their long-standing preference for collection items, we can appropriately increase the probability of blind boxes containing rare collection items when adjusting blind box probabilities. Furthermore, given their recent interest in blind boxes related to new PVE dungeons, we can further increase the probability of rare items in these blind boxes.For PVP competitive players, the probability of receiving a blind box containing a rare power-up item can be appropriately increased. Furthermore, given their recent interest in cool PVP mount blind boxes, the probability of receiving a rare mount in these blind boxes can also be increased. This approach can better meet the needs of different player groups, improving player satisfaction and gaming experience. For example, if Player C has been more focused on PVP gameplay in the past two weeks, the probability of receiving a rare item in a PVP-related blind box can be increased. If Player C tops up the game frequently, the probability of receiving a rare item can be further increased based on their spending history to increase their willingness to pay. This ensures that different types of players receive a gaming experience that meets their expectations, thereby increasing overall game activity and revenue.

[0085] In some embodiments, the game behavior data of players in different time periods is obtained and the players' false interests are identified. If the players have false interests, their blind box drawing probability is not adjusted. This includes:

[0086] Count the frequency of the player's extraction of each type of blind box within a preset time period, and obtain the player's preference distribution for different types of blind boxes based on the frequency; compare the player's preference distribution for blind boxes with his long-term game preference. If there is a significant deviation, it is determined that the player's interest in blind boxes is abnormal; use anomaly detection algorithms such as isolation forest to perform anomaly detection on the blind box extraction behavior of players with abnormal interests, and identify players who show false interest; quantify the player's false interest, obtain the player's false interest value, and set a corresponding false interest threshold. When the false interest value exceeds the false interest threshold, the player is marked as a false player, and when adjusting the blind box probability, the blind box extraction probability of the false player is not adjusted.

[0087] Specifically, players draw blind boxes in the game to obtain the desired virtual items. Understanding the real interests of players can better operate the game and improve the player experience. However, some players may have false interests, such as disguising their interest in certain blind boxes for some improper benefits. In order to distinguish these players, it is necessary to analyze the blind box drawing behavior of players. First, the frequency of players drawing various blind boxes within a certain period of time (such as a month) needs to be counted. Suppose there are three types of blind boxes in the game: A (weapons), B (clothing), and C (props). Player A draws A-type blind boxes 50 times, B-type blind boxes 10 times, and C-type blind boxes 5 times in this month. This indicates that player A's preference for A-type blind boxes (weapons) is much higher than the other two types. This is the player's preference distribution for blind boxes. Then, the player's preference distribution for blind boxes needs to be compared with his long-term game preference. Long-term game preference can be obtained from the player's historical game data, including game behavior, game duration, game frequency, and consumption records. Suppose player A's historical game data shows that he is a player who prefers combat, often participates in PVP activities, and has high consumption on weapons. This is consistent with his preference for A-type blind boxes (weapons). However, if another player B's historical game data shows that he is a player who prefers socializing, mainly participates in leisure activities, and rarely participates in combat, and has high consumption on clothing. However, player B frequently draws A-type blind boxes (weapons) in this month, far exceeding his drawing frequency of B-type blind boxes (clothing), which is a clear deviation. This indicates that player B's interest in blind boxes may be abnormal. In order to further confirm, an anomaly detection algorithm such as Isolation Forest needs to be used to detect the anomaly of the blind box drawing behavior of the player whose interest is abnormal. The core idea of the Isolation Forest algorithm is that abnormal data is more likely to be isolated. If a player's blind box drawing behavior is significantly different from the behavior patterns of most players, he is more likely to be isolated and is more likely to be an abnormal behavior. Suppose through the calculation of the Isolation Forest algorithm, player B's anomaly score is very high, exceeding the preset threshold. Next, the player's false interest needs to be quantified. According to factors such as anomaly score and deviation degree, a false interest value can be calculated. Suppose player B's false interest value is 0.8, and the set false interest threshold is 0.7. Since player B's false interest value exceeds the threshold, he is marked as a false player. Finally, when adjusting the blind box probability, the data of these players marked as false players will be ignored. That is, the drawing probability of the blind box will not be adjusted according to player B's drawing behavior. This can prevent false player data from interfering with normal probability adjustment, ensuring the fairness and healthy development of the game. This can also avoid the game operation being misled by false player data, making wrong decisions.

[0088] In some embodiments, in the process of adjusting the draw probability of the blind box, multiple accounts of the same player are identified, the game data of the associated accounts are combined, and the draw probability of the blind box is adjusted according to the combined game data. It includes:

[0089] Through the account association analysis technology, multiple account information related to the player is extracted from the game database; using a data merging method, the game data of multiple accounts is summarized under a main account; through data analysis, the real game preference of the player is extracted based on the combined game data; and the draw probability is adjusted according to the real game preference.

[0090] Specifically, the account association analysis technique can help identify a player's alt accounts, thus more accurately understanding the player's true game preferences. For example, based on IP address, device ID, registered email, etc., it can be determined whether multiple accounts belong to the same player. For example, player A uses three accounts: account 1 is mainly used for PVE gameplay, account 2 is mainly used for PVP gameplay, and account 3 is mainly used for collecting and nurturing gameplay. Through account association analysis, these three accounts can be associated with player A, so that it is known that player A's true game preference is not single PVE, PVP or collection and nurturing, but interest in all three types of gameplay. This association analysis can avoid drawing one-sided conclusions based on data from a single account, and more comprehensively understand the player's game behavior. The data merging method can aggregate the game data of the associated accounts under the main account, facilitating unified analysis. In the above example, the data of account 1, account 2 and account 3 can be merged into the main account of player A. The aggregated data includes game duration of PVE gameplay, win rate of PVP gameplay, and completion degree of collection and nurturing, etc. These data together constitute the complete behavior portrait of player A, which can more accurately reflect player A's true game preference. Data merging can avoid data fragmentation and provide a more complete data basis for subsequent analysis. Data analysis is a key step to extract the player's true game preference based on the merged game data. For example, by analyzing the merged game data of player A, it is found that player A spends the most time in PVE gameplay and completes high-difficulty instance challenges; in PVP gameplay, the win rate is high and the ranking is high; in the collection and nurturing gameplay, a large number of rare props are collected. These data indicate that player A has a high level of engagement and game level in all three types of gameplay, and the true game preference is relatively balanced. Through data analysis, the player's various data can be converted into valuable information, revealing the player's true game preference. After extracting the player's true game preference, the blind box draw probability can be adjusted according to the preference. For example, assume there are three types of blind boxes in the game: PVE prop blind box, PVP prop blind box and collection and nurturing prop blind box. If only based on the data of account 1 of player A, it may be concluded that player A only likes PVE gameplay, and the draw probability of PVE prop blind box is increased. But through account association analysis and data merging, it is known that player A is interested in all three types of gameplay. Therefore, according to the level of engagement and game level of player A in the three types of gameplay, the draw probability of the three types of blind boxes can be adjusted, for example, the draw probability of PVE prop blind box is 40%, the draw probability of PVP prop blind box is 35%, and the draw probability of collection and nurturing prop blind box is 25%. This adjustment can better meet the needs of players, improve the game experience and satisfaction of players, and effectively avoid the mismatch of resources caused by misjudgment of player preferences. More importantly, this adjustment based on true game preference can encourage players to try more types of games, enrich the game experience of players, and improve the overall activity of the game.Taking player B as an example, assume that player B's account 4 is identified as a fake account, which mainly performs a large number of blind box draws and focuses on a specific type of blind box. Through account association analysis, it is found that this account is associated with other accounts of player B (account 5 and account 6). However, the game behavior data of account 5 and account 6 shows that player B does not show a special preference for this specific type of game content. In this case, it can be determined that player B's account 4 has a fake interest. When adjusting the blind box probability, no special adjustment will be made for account 4, but adjustment will be made according to the data of account 5 and account 6 to avoid negatively affecting the overall game experience of player B. This can effectively identify and deal with the interference of fake accounts, maintain the fairness and healthy development of the game.

[0091] In some embodiments, the player's blind box draw behavior is monitored to identify abnormal behavior that manipulates blind box draw probability distribution using system vulnerabilities. This includes:

[0092] Obtain the behavior data of the player during the blind box draw process, including draw time, draw frequency and obtained item information; preprocess the behavior data to obtain preprocessed behavior data, the preprocessing including removing abnormal data and filling missing values; based on the preprocessed behavior data, extract draw frequency, consecutive draw times and rare item probability key features, and construct a player behavior pattern feature vector; use the K-means clustering algorithm to cluster the player behavior pattern feature vector to obtain a player behavior pattern clustering result; according to the player behavior pattern clustering result, divide the players into different behavior pattern groups; for each behavior pattern group, statistics its blind box draw probability distribution, and obtain the draw probability distribution characteristics of each group; compare the draw probability distribution characteristics of each group with the preset normal probability distribution, and calculate the deviation; if the deviation exceeds the preset threshold, it is determined that the group has abnormal behavior; for the player group judged to have abnormal behavior, analyze the behavior sequence to identify the blind box draw algorithm vulnerability used; for the identified blind box draw algorithm vulnerability, take patch repair measures, including improving the server verification logic and increasing the random number seed update frequency; warn or ban the player account that uses the vulnerability to cheat.

[0093] Specifically, the behavior data of players during the blind box drawing process is obtained, for example, player A draws once at 10:01 on March 1, 2024 and obtains a common prop "magic wand"; draws again at 10:02 on the same day and obtains a rare prop "elf wing". These data include drawing time, drawing frequency, and specific item information obtained. Recording these data is for subsequent analysis of player behavior patterns. The behavior data is preprocessed. For example, due to network fluctuations, the drawing record of player B at a certain time is missing the obtained item information, so a reasonable value needs to be filled in, such as using the item information obtained in his last draw. If player C draws a large number of times in a short period of time, far exceeding the behavior of normal players, it may be abnormal data and needs to be excluded. Data preprocessing is to ensure the accuracy of subsequent analysis results. Key features are extracted based on the preprocessed behavior data. For example, player A draws an average of 5 times a day, the highest number of consecutive draws is 3 times, and the probability of obtaining a rare item is 10%; player B draws an average of 100 times a day, the highest number of consecutive draws is 50 times, and the probability of obtaining a rare item is 50%. These key features include drawing frequency, consecutive drawing times, and probability of obtaining rare items. These features are combined into a player behavior pattern feature vector, for example, player A's feature vector is (5, 3, 0.1), and player B's feature vector is (100, 50, 0.5). Extracting these features is to quantify the behavior patterns of players for subsequent clustering analysis. The K-means clustering algorithm is used to cluster the player behavior pattern feature vectors. For example, input all player feature vectors into the K-means algorithm, set the number of clusters to 3, and the algorithm will divide the players into 3 different groups according to the similarity of the feature vectors. The purpose of clustering is to group players with similar behavior patterns together for group analysis. According to the clustering results, players are divided into different behavior pattern groups. For example, the first group is "casual players", their characteristics are low drawing frequency, few consecutive drawing times, and low probability of obtaining rare items; the second group is "active players", their characteristics are moderate drawing frequency, moderate consecutive drawing times, and moderate probability of obtaining rare items; the third group is "heavy players", their characteristics are high drawing frequency, many consecutive drawing times, and high probability of obtaining rare items. Grouping is to analyze the behavior characteristics of different player groups more specifically. For each behavior pattern group, the blind box drawing probability distribution is calculated. For example, in the "casual player" group, the probability of obtaining a common prop is 90%, and the probability of obtaining a rare prop is 10%; in the "heavy player" group, the probability of obtaining a common prop is 50%, and the probability of obtaining a rare prop is 50%. Statistical probability distribution is to understand the probability of different groups obtaining different items. The drawing probability distribution characteristics of each group are compared with the pre-set normal probability distribution, and the deviation degree is calculated.Suppose the preset normal probability distribution is that the probability of obtaining a common prop is 70%, and the probability of obtaining a rare prop is 30%. For example, the probability distribution of the "casual player" group has a smaller deviation from the preset normal probability distribution, and the probability distribution of the "heavy player" group has a larger deviation from the preset normal probability distribution. The purpose of calculating the deviation is to determine whether there is abnormal behavior. If the deviation exceeds the preset threshold, it is determined that the group has abnormal behavior. For example, the preset threshold is set to 0.2, and if the deviation of the "heavy player" group is 0.4, which exceeds the preset threshold, it is determined that the group has abnormal behavior. The purpose of determining abnormal behavior is to discover and handle possible cheating behavior in a timely manner. For the player group determined to have abnormal behavior, the behavior sequence is analyzed. For example, it is found that some players in the "heavy player" group can always obtain rare items with a very high probability within a specific time period. The purpose of analyzing the behavior sequence is to identify possible vulnerabilities. For the identified blind box extraction algorithm vulnerabilities, patch repair measures are taken. For example, if it is found that the vulnerability is caused by imperfect server verification logic, the server verification logic needs to be improved; if it is found that the vulnerability is caused by a low random number seed update frequency, the random number seed update frequency needs to be increased. The purpose of repairing the vulnerability is to prevent players from continuing to exploit the vulnerability to cheat. The player accounts that exploit the vulnerability to cheat are warned or banned. For example, the players in the "heavy player" group who are confirmed to exploit the vulnerability to cheat are warned or their accounts are directly banned. The purpose of handling the cheating players is to maintain the fairness of the game.

[0094] In some embodiments, after adjusting the extraction probability of the blind box, the extraction of the blind box is monitored to determine whether the adjusted probability distribution will affect the game economy.

[0095] Comprise:

[0096] Obtain real-time data of blind box extraction, the real-time data including extraction times and extraction results; obtain actual extraction frequencies of various items according to the real-time data; obtain a preset probability distribution model, and calculate theoretical extraction probabilities of the various items; based on each item, divide the actual extraction frequency by a total extraction time to obtain an actual extraction probability of the item; calculate a deviation degree between the actual extraction probability and the theoretical extraction probability; if the deviation degree exceeds a preset threshold, trigger a probability adjustment mechanism, adjust the theoretical extraction probability by increasing or decreasing a weight according to the deviation degree to obtain an adjusted probability distribution; according to the adjusted probability distribution, generate a preset number of virtual extraction processes by random, and count simulation extraction frequencies and simulation extraction probabilities of the various items; compare the simulation extraction probabilities with the actual extraction probabilities before adjustment to evaluate influences of the adjusted probability distribution on item rarity, player experience and game economy; obtain preset game indexes including total consumption amount, number of paying players, average consumption amount per person and daily active user number; establish a correlation model between the adjusted probability distribution and the game indexes, predict an influence degree of probability adjustment on each index to obtain a prediction result; if there is an index with negative influence exceeding a preset acceptable threshold in the prediction result, cancel this time of probability adjustment; if there is no index with negative influence exceeding the preset acceptable threshold in the prediction result, save the adjusted probability distribution parameters to a database.

[0097] Specifically, real-time monitoring of blind box extraction data is to timely discover probability deviation and make dynamic adjustment. For example, the theoretical probability of SSR level items in the game is 1%, and theoretically, 1 SSR should appear every 100 times. The system will record the extraction results of each player in real time, and if the actual number of SSRs in a short period of time (such as 1000 times) is much higher than the theoretical value (such as 10 times), the probability adjustment mechanism will be triggered. The actual extraction frequency is obtained dynamically. Assume that there are three items in the game: SSR, SR, and R, with preset theoretical probabilities of 1%, 10%, and 89% respectively. The system records the extraction behavior of all players in real time, for example, in a certain period of time, the total extraction times are 10000, among which SSR appears 80 times, SR appears 1100 times, and R appears 8820 times. The actual extraction probability is calculated by dividing the actual extraction frequency by the total extraction times. Taking the above example, the actual extraction probability of SSR is 80 / 10000=0.8%, SR is 1100 / 10000=11%, and R is 8820 / 10000=88.2%. There are many ways to calculate the deviation, such as using the absolute value of the difference between the actual probability and the theoretical probability, or using the relative deviation. Taking the above example of SSR, if the absolute value method is used, the deviation is |0.8%-1%|=0.2%. The probability adjustment mechanism is to make the actual probability closer to the theoretical probability. For example, if the actual probability of SSR is lower than the theoretical probability, the probability of SSR needs to be increased. A common adjustment method is weight adjustment, which can increase the weight of SSR and reduce the weight of other items to ensure that the total probability remains 100%. The virtual extraction process is to simulate the effect after probability adjustment. Assume that the probability of SSR is adjusted to 1.2%, SR to 9.8%, and R to 89%. The system can simulate 10000 times of extraction, and according to the adjusted probability, it can randomly extract and count the simulation extraction frequency and simulation extraction probability of each type of item. Evaluating the impact of probability adjustment needs to consider multiple factors. For example, increasing the probability of SSR may increase the willingness of players to pay, thereby increasing total consumption and per capita consumption. However, if the probability of SSR is too high, it may reduce the extraction pleasure of players, resulting in a decrease in the number of paying players and daily active users. Therefore, these factors need to be considered comprehensively, and acceptable thresholds need to be set. The establishment of the correlation model requires a large amount of data and statistical analysis. For example, the impact of past probability adjustment on various indicators of the game can be analyzed, and a mathematical model can be established to predict future impact. Assume that the prediction result shows that increasing the probability of SSR will cause the daily active user number to decrease by 10%, and if this decrease exceeds the preset threshold of 5%, the probability adjustment will be cancelled. The database saves the adjusted probability distribution parameters to persist the adjustment results. When the adjusted probability distribution passes all evaluations, the system will save the new probability parameters to the database and apply them to the actual blind box extraction.In this way, the subsequent player draw behavior will be in accordance with the new probability. This can ensure the sustained effectiveness of the probability adjustment.

[0098] In some embodiments, a player satisfaction evaluation model and a game balance evaluation index are constructed, and the blind box draw probability is adjusted based on the player satisfaction evaluation model and the game balance evaluation index. This includes:

[0099] According to the historical game data, a player satisfaction evaluation model is constructed, which is used to quantify the player satisfaction under different draw probabilities; based on the game balance, a game balance evaluation index is constructed, which includes the player's sense of acquisition and the balance of game resource allocation; the player satisfaction and the game balance are taken as the optimization objectives of a multi-objective optimization algorithm, and the two optimization objectives are integrated into a single optimization function through weighted summation; a heuristic search method is used to obtain a draw probability combination that balances the player satisfaction and the game balance; the draw probability combination is optimized, a new draw probability combination is generated through crossover and mutation operations, and its advantages and disadvantages are evaluated according to the fitness function; and the blind box draw probability is adjusted according to the optimized draw probability combination.

[0100] Specifically, player satisfaction and game balance are two crucial aspects in game design. By building an evaluation model and using optimization algorithms, a combination of blind box extraction probabilities that balances both can be found, thereby improving the overall quality of the game. First, build a player satisfaction evaluation model. Based on historical game data, such as players' extraction records, game duration, and payment amounts, the satisfaction of players under different extraction probabilities can be quantified. For example, the average game duration and payment amount of players under different rare item drop rates can be counted. If the drop rate of high-rarity items is too low under a certain probability, it may lead to player churn, decreased game duration, and payment amount, resulting in lower satisfaction. Conversely, if the drop rate is too high, although it may temporarily improve player satisfaction, it may reduce long-term game enjoyment and willingness to pay, also leading to decreased satisfaction. A 1-10 point scale can be used to represent player satisfaction, and a satisfaction function can be developed based on historical data to map game duration, payment amount, and other factors to satisfaction scores. Second, build a game balance evaluation index. Game balance includes player satisfaction and the balance of game resources allocation. Player satisfaction refers to the feeling of players obtaining rewards in the game through effort. For example, a low drop rate may lead to players investing a lot of time and money without any reward, resulting in extremely low satisfaction. The balance of game resource allocation refers to the gap between different players' game resources being controlled within a reasonable range. For example, a high drop rate may lead to a few players quickly obtaining a large number of rare items, disrupting the game balance and harming the game experience of other players. The Gini coefficient can be used to measure the balance of game resource allocation, with a lower Gini coefficient indicating a more balanced resource allocation. Then, player satisfaction and game balance are used as optimization objectives for multi-objective optimization algorithms. Since player satisfaction and game balance sometimes conflict, a balance point needs to be found. The two optimization objectives can be integrated into a single optimization function through weighted summation. For example, the player satisfaction weight can be set to 0.7 and the game balance weight to 0.3, indicating that more emphasis is placed on player satisfaction. Next, a heuristic search method, such as genetic algorithm, is used to obtain a combination of extraction probabilities that balances player satisfaction and game balance. For example, a set of extraction probability combinations can be randomly generated as the initial population, and then new probability combinations are generated through operations such as crossover and mutation, and their merits are evaluated according to the fitness function (i.e., the weighted sum of the optimization function). The probability combinations with high fitness are selected for the next iteration, and ultimately an optimal probability combination is obtained. Take a blind box containing three rare items as an example. The initial probability combination is: low-rarity item drop rate 80%, medium-rarity item drop rate 15%, and high-rarity item drop rate 5%. After multiple rounds of iterative optimization, a new probability combination is obtained: low-rarity item drop rate 70%, medium-rarity item drop rate 25%, and high-rarity item drop rate 5%. This new probability combination achieves a better balance between player satisfaction and game balance.Finally, according to the optimized combination of extraction probability, the blind box extraction probability is adjusted, and the game data is continuously monitored to evaluate the adjustment effect, and fine-tuning is performed according to the actual situation to ensure the continuous and healthy development of the game.

[0101] Please refer to Figure 2 The application also provides a game blind box extraction system based on player data, comprising:

[0102] The first processing module 201 obtains the historical game data of the player, sets different time window lengths for different players, obtains the long-term game preferences and short-term game interest changes of the player, and adjusts the extraction probability of the blind box based on the long-term game preferences and short-term game interest changes of the player.

[0103] The second processing module 202 obtains the game behavior data of the player in different time periods and identifies the false interest of the player. If the player has false interest, the extraction probability of the blind box is not adjusted.

[0104] The third processing module 203 identifies multiple accounts of the same player during the adjustment of the extraction probability of the blind box, combines the game data of the associated accounts, adjusts the extraction probability of the blind box based on the combined game data, or constructs a player satisfaction evaluation model and a game balance evaluation index, and adjusts the extraction probability of the blind box based on the player satisfaction evaluation model and the game balance evaluation index.

[0105] The fourth processing module 204 monitors the blind box extraction behavior of the player and identifies abnormal behavior of manipulating the extraction probability distribution of the blind box by exploiting system vulnerabilities.

[0106] The fifth processing module 205 monitors the extraction of the blind box after adjusting the extraction probability of the blind box, and judges whether the adjusted probability distribution will affect the game economy.

[0107] It can be understood that the contents in the game blind box extraction method embodiment based on player data as shown in the Figure 1 The game blind box extraction system embodiment based on player data is applicable to the game blind box extraction system embodiment based on player data, and the functions realized by the game blind box extraction system embodiment based on player data are the same as those of the game blind box extraction method embodiment based on player data as shown in the Figure 1 The beneficial effects achieved by the game blind box extraction method embodiment based on player data are also the same. Figure 1

[0108] It should be noted that the information interaction, execution process, etc. between the above systems, since the same concept, its specific function and the technology effect brought, specific can refer to the method embodiment part, here will not be repeated.​

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiment, which will not be described here.

[0110] Please refer to Figure 3 The embodiment of the present application also provides a computer device 3, comprising a memory 302 and a processor 301 and a computer program 303 stored in the memory 302, when the computer program 303 is executed on the processor 301, the game blind box drawing method based on player data is realized as any one of the above methods.

[0111] The computer device 3 can be a desktop computer, a notebook computer, a palm computer and a cloud server and the like. The computer device 3 can include, but is not limited to, a processor 301, a memory 302. Those skilled in the art can understand that, Figure 3 The computer device 3 is only an example and does not constitute a limitation on the computer device 3, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, it can also include input and output devices, network access devices and the like.

[0112] The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0113] The memory 302 may, in some embodiments, be an internal storage unit of the computer device 3, such as a hard disk or a memory of the computer device 3. The memory 302 may, in other embodiments, also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, and the like equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as program codes of the computer program, and the like. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0114] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the game blind box drawing method based on player data is realized.

[0115] In the embodiment, the integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a U disk, a mobile hard disk, a magnetic disk or an optical disk, and the like. In some jurisdictions, according to legislation and patent practice, the computer readable medium may not be an electrical carrier signal and a telecommunication signal.

[0116] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A game blind box drawing method based on player data, characterized in that, The method comprises the following steps: acquiring historical game data of a player, setting different time window lengths for different players, acquiring long-term game preferences and short-term game interest changes of the player, and adjusting the draw probability of a blind box based on the long-term game preferences and short-term game interest changes of the player; acquiring game behavior data of the player in different time periods, and identifying false interests of the player, and if the player has false interests, not adjusting the draw probability of the blind box; in the process of adjusting the draw probability of the blind box, identifying multiple accounts of the same player, merging the game data of the associated accounts, and adjusting the draw probability of the blind box based on the merged game data; or constructing a player satisfaction evaluation model and a game balance evaluation index, and adjusting the draw probability of the blind box based on the player satisfaction evaluation model and the game balance evaluation index; monitoring the blind box draw behavior of the player, and identifying abnormal behavior of manipulating the draw probability distribution of the blind box by exploiting system vulnerabilities; after adjusting the draw probability of the blind box, monitoring the draw of the blind box, and determining whether the adjusted probability distribution will affect the game economy; wherein the player satisfaction evaluation model and the game balance evaluation index are constructed, and the draw probability of the blind box is adjusted based on the player satisfaction evaluation model and the game balance evaluation index, comprising: constructing a player satisfaction evaluation model based on the historical game data, wherein the satisfaction evaluation model is used to quantify the player satisfaction under different draw probabilities; constructing a game balance evaluation index based on game balance, wherein the game balance evaluation index includes the player's sense of gain and the balance of game resource allocation; taking the player satisfaction and the game balance as the optimization objectives of a multi-objective optimization algorithm, and integrating the two optimization objectives into a single optimization function through weighted summation; using a heuristic search method to obtain a draw probability combination that balances the player satisfaction and the game balance; optimizing the draw probability combination, generating a new draw probability combination through crossover and mutation operations, and evaluating the advantages and disadvantages of the new draw probability combination according to an adaptive function; adjusting the draw probability of the blind box according to the optimized draw probability combination.

2. The game blind box drawing method of claim 1, wherein, The method comprises the following steps: acquiring historical game data of a player, setting different time window lengths for different players, acquiring long-term game preferences and short-term game interest changes of the player, and adjusting the draw probability of a blind box based on the long-term game preferences and short-term game interest changes of the player; acquiring historical game data of a player, wherein the historical game data includes the game behavior, game duration, game frequency and consumption record of the player; dividing the player into different player groups according to the historical game data, wherein each player group has similar game preferences and behavior patterns; determining the time window length according to the historical game data of each player group, predicting the long-term game preferences and short-term interest changes of the player for different blind boxes according to the game behavior and preferences within the time window; and adjusting the draw probability distribution of each blind box according to the long-term game preferences and short-term interest changes.

3. The game blind box drawing method of claim 1, wherein, The game behavior data of a player in different time periods is acquired, and false interest of the player is identified. If the player has false interest, the blind box drawing probability of the player is not adjusted, including: The frequency of the player drawing each type of blind box in a preset time period is counted, and the preference distribution of the player for different types of blind box is acquired according to the frequency; The preference distribution of the player for the blind box is compared with the long-term game preference of the player. If there is a significant deviation, it is determined that the interest of the player in the blind box is abnormal; An anomaly detection algorithm such as isolation forest is used to detect the abnormality of the blind box drawing behavior of the player whose interest is abnormal, and the player showing false interest is identified; The false interest of the player is quantified, the false interest value of the player is acquired, and a corresponding false interest threshold is set. When the false interest value exceeds the false interest threshold, the player is marked as a false player, and the blind box drawing probability of the false player is not adjusted during the blind box probability adjustment.

4. The game blind box drawing method of claim 1, wherein, The blind box drawing behavior of the player is monitored, and abnormal behavior of manipulating the blind box drawing probability distribution by exploiting system vulnerabilities is identified, including: Acquire the behavior data of the player during the blind box drawing process, including drawing time, drawing frequency and obtained item information; Based on the behavior data, the features of drawing frequency, continuous drawing frequency and rare item probability are extracted, and a player behavior pattern feature vector is constructed; According to the player behavior pattern feature vector, the player is divided into different behavior pattern groups; Based on each behavior pattern group, the blind box drawing probability distribution of the group is counted to obtain the drawing probability distribution characteristics of each group; The drawing probability distribution characteristics of each group are compared with the preset normal probability distribution, and the deviation degree is calculated; If the deviation degree exceeds the preset threshold, it is determined that the group has abnormal behavior; For the player group judged to have abnormal behavior, analyze the behavior sequence to identify the exploited blind box drawing algorithm vulnerability; According to the identified blind box drawing algorithm vulnerability, patch repair measures are taken, including improving the server verification logic and increasing the random number seed update frequency; Players exploiting the blind box drawing algorithm vulnerability are warned or banned.

5. The game blind box drawing method of claim 1, wherein, During the adjustment of the drawing probability of the blind box, multiple accounts of the same player are identified. For the game data of the associated accounts, the game data is merged, and the drawing probability of the blind box is adjusted according to the merged game data, including: Extract multiple account information related to the player from the game database through account association analysis technology; Use data merging method to aggregate game data of multiple accounts under a main account; Through data analysis, the real game preference of the player is extracted based on the merged game data; Adjust the drawing probability according to the real game preference.

6. The game blind box drawing method of claim 1, wherein, After adjusting the drawing probability of the blind box, monitor the drawing of the blind box to determine whether the adjusted probability distribution will affect the game economy, including: Acquire real-time data of blind box drawing, including drawing frequency and drawing result; According to the real-time data, the actual drawing frequency of each type of item is obtained; Obtain a preset probability distribution model, and calculate theoretical extraction probabilities of various items; Based on each type of item, divide the actual extraction frequency by the total extraction times to obtain the actual extraction probability of the item; Calculate the deviation between the actual extraction probability and the theoretical extraction probability; If the deviation exceeds a preset threshold, trigger a probability adjustment mechanism, and adjust the theoretical extraction probability by increasing or decreasing the weight according to the deviation to obtain an adjusted probability distribution; According to the adjusted probability distribution, generate a preset number of virtual extraction processes by random, and count the simulation extraction frequencies and simulation extraction probabilities of various items; Compare the simulation extraction probability with the actual extraction probability before adjustment to evaluate the impact of the adjusted probability distribution on item rarity, player experience, and game economy; Obtain preset game indicators, including total consumption amount, number of paying players, average consumption amount per person, and daily active user number; Establish a correlation model between the adjusted probability distribution and the game indicators to predict the impact of probability adjustment on each indicator, and obtain a prediction result; If there is an indicator with negative impact exceeding a preset acceptable threshold in the prediction result, cancel this probability adjustment; If there is no indicator with negative impact exceeding a preset acceptable threshold in the prediction result, save the adjusted probability distribution parameters to a database. 7.A game blind box drawing system based on player data, characterized in that, It includes: The first processing module: obtaining the historical game data of the player, and setting different time window lengths for different players to obtain the long-term game preferences and short-term game interest changes of the players, and adjusting the extraction probability of the blind box based on the long-term game preferences and short-term game interest changes of the players; The second processing module: obtaining the game behavior data of the player in different time periods, and identifying the false interest of the player, if the player has false interest, do not adjust the blind box extraction probability; The third processing module: in the process of adjusting the extraction probability of the blind box, identify multiple accounts of the same player, merge the game data of the associated accounts, and adjust the extraction probability of the blind box according to the merged game data; or construct a player satisfaction evaluation model and a game balance evaluation index, and adjust the blind box extraction probability based on the player satisfaction evaluation model and the game balance evaluation index; The fourth processing module: monitoring the blind box extraction behavior of the player, and identifying abnormal behavior of manipulating the blind box extraction probability distribution by exploiting system vulnerabilities; The fifth processing module: after adjusting the extraction probability of the blind box, monitor the extraction of the blind box to determine whether the adjusted probability distribution will affect the game economy; Wherein, constructing a player satisfaction evaluation model and a game balance evaluation index, and adjusting the blind box extraction probability based on the player satisfaction evaluation model and the game balance evaluation index, includes: According to the historical game data, construct a player satisfaction evaluation model, and the satisfaction evaluation model is used to quantify the player satisfaction under different extraction probabilities; Based on game balance, a game balance evaluation index is constructed, which includes the sense of acquisition of the player and the balance of game resource allocation; Player satisfaction and game balance are taken as optimization objectives of a multi-objective optimization algorithm, and the two optimization objectives are integrated into a single optimization function through weighted summation; A heuristic search method is used to obtain an extraction probability combination that balances the player satisfaction and the game balance; The extraction probability combination is optimized, a new extraction probability combination is generated through crossover and mutation operations, and its advantages and disadvantages are evaluated according to a fitness function; The blind box extraction probability is adjusted according to the optimized extraction probability combination.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the method of any one of claims 1 to 6.

Images