Method, apparatus, medium and device for determining game parameters

Abstract

The present disclosure relates to a method, apparatus, medium and device for determining game parameters. The method includes: determining a target performance rule corresponding to a target interest metric in a target game; determining a target parameter vector corresponding to the target performance rule and candidate values of the target parameter vector according to the target performance rule; determining the value of a target game parameter in the target game according to the candidate values of the target parameter vector, and performing an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule; determining whether the candidate values meet the target performance rule according to the simulation data; if not, adjusting the candidate values according to the simulation data and using the adjusted values as new candidate values to re-execute the steps of obtaining the simulation data corresponding to the target performance rule and determining whether the candidate values meet the target performance rule; if so, determining the latest candidate values as the target values of the target parameter vector.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, and in particular, to a method, apparatus, medium, and device for determining game parameters. Background Art

[0002] Currently, the audience range of game applications is gradually increasing. Reasonable game parameter settings can provide users with a better interaction experience, such as corresponding rewards in each level, skill output damage corresponding to different user operations, etc.

[0003] In related technologies, artificial numerical planning is usually carried out by game designers and operators, etc., or prediction settings are made through mathematical models. However, the game system is a complex interaction system. The numerical feelings in different stages of the game may be different, there are many gameplay systems in the game, and the numerical coupling between systems is very strong, making it difficult to accurately model with a mathematical model. This results in low efficiency when setting parameters through the above processes, difficult modification, and it is also difficult to verify the accuracy of the parameters. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a brief form, which will be described in detail in the subsequent Detailed Description section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a method for determining game parameters, the method comprising:

[0006] Determine a target performance rule corresponding to a target interest metric in a target game, wherein the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to the execution of the target operation;

[0007] According to the target performance rule, determine a target parameter vector corresponding to the target performance rule and candidate values of the target parameter vector, wherein each dimension in the target parameter vector corresponds to a target game parameter in the target game;

[0008] Determine the value of the target game parameter in the target game according to the candidate values of the target parameter vector, and perform interactive simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule;

[0009] According to the simulation data, determine whether the candidate values satisfy the target performance rule;

[0010] If the candidate value does not meet the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as the new candidate value to re - execute the steps of determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and performing an interaction simulation based on multiple user models and the target game to obtain the simulation data corresponding to the target performance rule and the step of determining whether the candidate value meets the target performance rule according to the simulation data; if the candidate value meets the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

[0011] In a second aspect, the present disclosure provides a device for determining game parameters, the device includes:

[0012] A first determination module, configured to determine a target performance rule corresponding to a target interest metric in a target game, where the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to performing the target operation;

[0013] A second determination module, configured to determine a target parameter vector corresponding to the target performance rule and a candidate value of the target parameter vector according to the target performance rule, where each dimension in the target parameter vector corresponds to a target game parameter in the target game;

[0014] A simulation module, configured to determine the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and perform an interaction simulation based on multiple user models and the target game to obtain simulation data corresponding to the target performance rule;

[0015] A third determination module, configured to determine whether the candidate value meets the target performance rule according to the simulation data;

[0016] An update module, configured to, if the candidate value does not meet the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as the new candidate value to trigger the simulation module to re - execute the steps of determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and performing an interaction simulation based on multiple user models and the target game to obtain the simulation data corresponding to the target performance rule and the third determination module determining whether the candidate value meets the target performance rule according to the simulation data; if the candidate value meets the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

[0017] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processing device, the steps of the method described in the first aspect are implemented.

[0018] In a fourth aspect, the present disclosure provides an electronic device, including:

[0019] a storage device having a computer program stored thereon;

[0020] a processing device configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect.

[0021] In the above technical solution, by determining the target performance rule corresponding to the target interest metric in the target game, as well as the target parameter vector corresponding to the target performance rule and the candidate values of the target parameter vector, and then assigning the candidate values as the parameters in the target game, it is possible to perform interaction simulation based on multiple user models and the target game, obtain the simulation data corresponding to the target performance rule, and based on the simulation data, determine whether the candidate value satisfies the target performance rule; by adjusting the candidate value, the target value that finally satisfies the target performance rule is determined. Thus, through the above technical solution, there is no need for game personnel to model a mathematical model or analyze the highly coupled parameter logic, which can simplify the parameter setting process while saving manual workload, avoid the problem of missing updates of game parameters, and can automatically verify the rationality and accuracy of parameter settings during the determination process of the parameter values of the target game, further improving the accuracy of the determined target value, making the parameter settings in the target game accurate and reasonable, providing accurate data support for maintaining the safe operation of the game ecosystem, ensuring the stability of the target game when it is launched and run, and at the same time improving the matching degree between the operation of the target game and the experience of game players to a certain extent.

[0022] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In combination with the accompanying drawings and with reference to the following specific implementation, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the original elements and elements are not necessarily drawn to scale. In the drawings:

[0024] Figure 1 is a flowchart of a method for determining game parameters provided according to an embodiment of the present disclosure;

[0025] Figure 2 is a block diagram of a device for determining game parameters provided according to an embodiment of the present disclosure;

[0026] Figure 3 The structural schematic diagram of an electronic device suitable for implementing the embodiments of the present disclosure is shown. Detailed implementation manners

[0027] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0028] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be executed in different orders and / or executed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0029] The term "including" and its variants used herein are open-ended, that is, "including but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0031] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0034] For example, when receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application, a server, or a storage medium that performs the operations of the present disclosure's technical solution based on the prompt message.

[0035] As an optional but non-limiting implementation manner, when receiving an active request from a user, the manner of sending a prompt message to the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It can be understood that the above process of notifying and obtaining user authorization is only illustrative and does not limit the implementation manner of the present disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0037] At the same time, it can be understood that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of corresponding laws, regulations and related provisions.

[0038] In an actual application scenario, the game system is a complex dynamic system. There are too many gameplay systems in the game, and the numerical coupling between systems is very strong. When adding a new system or adjusting a certain parameter value in the game, if the adaptive adjustment of a certain related parameter value is ignored, it is easy to cause numerical loopholes and affect the ecological stability of the game system. And it is difficult to have a relatively clear indication of the optimization direction of the numerical values. Their adjustable range is large, and it is even possible that the parameter values after adjustment are more deviated from the initial game setting expectations. And if the game parameter settings in the internal circulation and production and sales in the game's economic system are unreasonable, it may lead to the collapse of the game ecosystem or serious inflation.

[0039] Based on this, the present disclosure provides a method for determining game parameters. Figure 1 As shown, it is a flowchart of a method for determining game parameters provided according to an embodiment of the present disclosure. As Figure 1 shown, the method may include:

[0040] In step 11, determine the target performance rule corresponding to the target interest index in the target game, where the target performance rule includes the target operation in the target game and the expectation of the target interest index corresponding to the execution of the target operation.

[0041] The target game in the embodiments of the present disclosure can be a single-player game or a network game.

[0042] First, define the target interest metrics of interest in the target game. For example, the target interest metrics of interest can be the number of gold coins of the player, the combat power of the player, the number of game monsters defeated, the number of remaining monsters, scene switching, etc. The target performance rules include target operations and the target values corresponding to the target interest metrics under the performance of the user performing the target operations in the target game, that is, the expected measurement metrics, specifically the quantitative representation of the target interest metrics of interest, so as to quantify the user's operation experience. In a specific embodiment, the target interest metric can be set to the number of gold coins of the player, and the target performance rule can be that the number of gold coins obtained by the player for hitting the target object N times in a row is M. For example, hitting the target object 5 times in a row obtains 100,000 gold coins, so as to quantify the user's reward experience. Another example is that the target interest metric can be scene switching, and the target performance rule can be that hitting the target object N times in a row switches to the next scene, so as to quantify the user's progress experience. Another example is that the target interest metric can be set to the number of remaining monsters, and the target performance rule can be set to that the number of remaining monsters in the scene within T time of the start battle is U. For example, the number of remaining monsters in the scene within 10 minutes of the start battle is 0.

[0043] Among them, the above is only an exemplary illustration and does not limit the present disclosure. The target performance rules corresponding to the target interest metrics in the target game can be preset by analyzing the application scenarios of the target game. Then, when determining the target performance rules corresponding to the target game and the target interest metrics, corresponding selection instructions can be triggered according to the user's selection operation, so as to determine from multiple preset performance rules according to the indication of the selection instructions. Another example is that configuration information input by the user can be received through a configuration interface. For example, the user can fill in the interest metrics and performance rules in the corresponding menu in the configuration interface. Then, in response to the confirmation operation, the target performance rules corresponding to the target interest metrics are determined according to the configuration information, thereby realizing the quantitative metrics of the game experience of game players.

[0044] In step 12, according to the target performance rules, determine the target parameter vector corresponding to the target performance rules and the candidate values of the target parameter vector. Among them, each dimension in the target parameter vector corresponds to at least one target game parameter in the target game.

[0045] Among them, when the user operates in the target game, in response to the user's operation, the target game will respond according to the algorithm corresponding to the operation to achieve interaction. The vector formed by taking each parameter of the algorithm corresponding to the operation in the target game as a dimension can be determined as the target parameter vector. As another example, the vector formed by taking the parameters related to the target interest metrics among the parameters of the algorithm corresponding to the operation in the target game as dimensions can be determined as the target parameter vector.

[0046] Exemplarily, the target performance rule can be set such that the remaining number of monsters in the opening battle within T time is U. Then, the parameters corresponding to the user's offensive operations in the target game can include the number of rewarded gold coins, offensive power, defensive power, number of monsters, health, etc. In this target performance rule, the corresponding target interest metric is the remaining number of monsters. Thus, a vector formed by parameters in dimensions related to the remaining number of monsters, such as offensive power, defensive power, number of monsters, etc., can be used as the target parameter vector. Among them, the monsters are defeated through offensive power and defensive power, and the number of monsters is used to control the number of monsters appearing in the scene. The target parameter vector corresponding to the target performance rule can be preset by game personnel through the corresponding relationship, so that it can be directly determined based on this corresponding relationship. Alternatively, after determining the target performance rule, each parameter of the algorithm corresponding to the user's operations in the target game can be displayed through a configuration interface. In response to the selection operation of the game personnel in the configuration interface, the vector formed by the parameters selected by the game personnel as dimensions is determined as the target parameter vector.

[0047] After determining the target parameter vector, as an example, the parameters in each dimension of the target parameter vector can be randomly initialized to obtain candidate values. As another example, the values set by the game personnel based on experience can be assigned to each parameter in the target parameter vector to obtain candidate values.

[0048] In step 13, the value of the target game parameter in the target game is determined according to the candidate value of the target parameter vector, and based on multiple user models and the target game for interactive simulation, the simulation data corresponding to the target performance rule is obtained.

[0049] Among them, during the interactive simulation process, the value of the target game parameter in the target game is the candidate value corresponding to the dimension of the target game parameter in the target parameter vector. In this step, each target game parameter in the target game can be assigned the candidate value corresponding to its dimension in the target parameter vector, so that the target game can run according to the parameter model of the candidate value. The user model is used to simulate the operations of player users, thus eliminating the need for game personnel to obtain game data, improving the convenience of obtaining simulation data, and accurately verifying the candidate values.

[0050] On this basis, multiple user models are interacted with the target game to simulate the interactive process between the operations performed by real player users and the target game with candidate values set, so as to obtain simulation data, thereby improving the acquisition efficiency and diversity of the simulation data.

[0051] Taking the target performance rules described above as an example, multiple user models can be adopted to control the interaction between the user model and the target game, record the remaining number of monsters after 10 minutes of each opening battle, so as to quickly obtain a large amount of simulation data, and determine the standard for the candidate value to achieve the target performance rules based on the simulation data.

[0052] In step 14, according to the simulation data, determine whether the candidate value meets the target performance rules.

[0053] Among them, the simulation data is obtained by interacting and simulating the target game obtained by assigning values to the corresponding parameters in the target game through the candidate value of the target parameter vector and the user model corresponding to the anthropomorphic player. It can simulate the operation of the target game after the upper limit of the candidate value is assigned, so as to determine whether the target game can meet the target performance rules under the candidate value and achieve the stable operation of the target game.

[0054] As an example, the difference between the simulation data and the expectation corresponding to the target performance rules can be calculated. If the difference is less than the preset threshold, it is determined that the candidate value meets the target performance rules. If the difference is not less than the preset threshold, it is determined that the candidate value does not meet the target performance rules. Another example is that if the number of simulation times of the simulation data reaches the quantity threshold, it is determined that the candidate value does not meet the target performance rules. If the number of simulation times of the simulation data does not reach the quantity threshold, it is determined that the candidate value does not meet the target performance rules. Among them, the preset threshold and the quantity threshold can be set based on the actual application scenario.

[0055] In step 15, if the candidate value does not meet the target performance rules, adjust the candidate value according to the simulation data, and use the adjusted value as the new candidate value to re-execute the step of determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and perform interactive simulation based on multiple user models and the target game to obtain the simulation data corresponding to the target performance rules in step 13 and the step of determining whether the candidate value meets the target performance rules according to the simulation data in step 14, so as to re-determine the value of the target game parameter in the target game according to the new candidate value, perform interactive simulation based on the updated value of the target game parameter, obtain new simulation data, and further determine whether the new candidate value meets the target performance rules based on the new simulation data.

[0056] In step 16, if the candidate value meets the target performance rules, determine the latest candidate value as the target value of the target parameter vector.

[0057] Thus, in the above technical solution, by determining the target performance rule corresponding to the target interest metric in the target game, as well as the target parameter vector corresponding to the target performance rule and the candidate values of the target parameter vector, the candidate value is used as the parameter in the target game for assignment. Furthermore, it is possible to perform interaction simulation based on multiple user models and the target game, obtain the simulation data corresponding to the target performance rule, and determine whether the candidate value meets the target performance rule based on the simulation data. By adjusting the candidate value, the target value that finally meets the target performance rule is determined. Thus, through the above technical solution, it is not necessary for game personnel to model a mathematical model or analyze the highly coupled parameter logic, which can simplify the parameter setting process while saving manual workload, avoid the problem of missing updates of game parameters, and can automatically verify the rationality and accuracy of parameter setting during the determination process of the parameter values in the target game, further improving the accuracy of the determined target value, making the parameter setting in the target game accurate and reasonable, providing accurate data support for maintaining the safe operation of the game ecosystem, ensuring the stability of the target game during online operation, and at the same time improving the matching degree between the operation of the target game and the experience of game players to a certain extent.

[0058] In a possible embodiment, the method may further include:

[0059] Determine the user type distribution corresponding to the target performance rule, where the user type distribution is used to represent the proportion of users in each user type to the total user volume.

[0060] In the actual application process of the target game, the game levels of its corresponding player users are diverse. Correspondingly, multiple user types can be preset, and the user models under each user type can be trained. For example, the setting of user types can be based on specific application scenarios, and the present disclosure does not limit this. For example, the player ratios of multiple user types can be preset based on the player positioning corresponding to the target game, which can improve the matching degree between multiple user models and the actual player users corresponding to the target game to a certain extent.

[0061] As an example, the user type distribution corresponding to the target game can be directly used as the user type distribution corresponding to the target operation, and the user type distribution corresponding to the target user can be determined based on the quantity prediction of different types of player users.

[0062] As another example, if the operation difficulties corresponding to different performance rules are different, the corresponding user type distributions may also be different. For example, user types can be divided into primary type, intermediate type, and advanced type. For the performance rule of obtaining 100,000 gold coins by hitting the target object 5 times in a row, the user classification distributions of the primary type, intermediate type, and advanced type can be 0.5, 0.3, and 0.2 in sequence. For the performance rule that the remaining number of monsters in the scene is 0 within 10 minutes of the start of the battle, the user classification distributions of the primary type, intermediate type, and advanced type can be 0.1, 0.8, and 0.1 in sequence. Therefore, the corresponding relationship between different performance rules and user type distributions can be obtained in advance based on experience or statistical data. When the target performance rule is determined, its corresponding user type distribution can be directly determined based on the pre-determined corresponding relationship.

[0063] After that, user models for each user type in the user type distribution are generated according to the user type distribution. Thus, the number of users of different user types can be restricted, so that the number of simulated users of each user type during the simulation of the target performance rule is more in line with the actual user distribution, in order to accurately determine whether the candidate value can meet the target performance rule.

[0064] Exemplarily, the exemplary implementation manner of generating user models for each user type in the user type distribution according to the user type distribution may include:

[0065] According to the user type distribution and the preset number of simulations, determine the number of users corresponding to each user type in the user type distribution.

[0066] Among them, the number of simulations can be set based on the actual application scenario. Exemplarily, the number of simulations may be positively correlated with the number of player users corresponding to the target game to ensure the coverage of sample data during the simulation. In this step, the product of the number of simulations and the proportion of each user type in the user type distribution can be determined as the number of users corresponding to that user type. For example, if the determined user type distribution is that the primary type, intermediate type, and advanced type account for 0.1, 0.8, and 0.1 respectively, and the number of simulations is n times, then the number of users corresponding to the primary type, intermediate type, and advanced type are 0.1n, 0.8n, and 0.1n respectively.

[0067] After that, for each user type, based on the pre-trained model corresponding to the user type, a preset number of user models corresponding to the user type are generated, where the decision-making strategies for determining decision actions of the pre-trained models corresponding to different user types are different.

[0068] Exemplarily, user types can be divided into primary type, intermediate type, and advanced type. The primary type is used to simulate novice players who make random decisions when determining decision-making actions, that is, randomly select from the actions available in the current game state. The intermediate type is used to simulate ordinary players who can choose based on the currently determined optimal action to make a profit without conducting in-depth decision-making searches, that is, mostly select actions beneficial to themselves from the currently available actions, and at the same time do not rule out the small probability of selecting random actions. The advanced type is used to simulate high-end players who will conduct in-depth decision-making searches when determining decision-making actions to seek decision-making actions under the strategy with the optimal long-term return, that is, select the action that can bring the greatest long-term return from the current actions, so as to obtain user models corresponding to different decision-making strategies to simulate real player users with different operation levels.

[0069] As an example, different user models can be pre-trained based on different models. For example, the user models corresponding to the primary type and intermediate type can be trained based on decision trees, and the user model corresponding to the advanced type can be trained based on search technology or reinforcement learning technology, so as to obtain user models under each user type. Among them, sample data can be generated by game players of different types for training. The training methods of decision trees and reinforcement learning models can be carried out in the common ways in this field and will not be elaborated here.

[0070] As another example, the deep reinforcement model can be directly trained based on the sample data. The trained model is determined as the user model under the advanced type, and the models updated in the initial stage and intermediate stage during the training process are respectively used as the user models under the primary type and intermediate type. Exemplarily, the initial stage and intermediate stage can be determined according to the total number of training times. For example, if the number of training times is M, the model after 0.4M training times can be used as the user model under the primary type, and the model after 0.7M training times can be used as the user model under the intermediate type. Among them, the selection of the above initial stage and intermediate stage is an exemplary way and does not limit the present disclosure, and the corresponding number of training times can also be set based on the actual application scenario.

[0071] Thus, through the above technical solutions, the corresponding number of simulation times under different user types in the simulation process can be determined to generate the corresponding number of user models, so that the simulation process conforms to the normal distribution of the operation levels of real player users, improving the accuracy of the simulation process, so as to improve the accuracy of the simulation data, and further ensuring the accuracy and rationality of verifying the candidate values based on the simulation data.

[0072] Further, an exemplary manner of performing interaction simulation based on multiple user models and the target game to obtain simulation data corresponding to the target performance rule may include:

[0073] For each of the user models, perform Monte Carlo simulation on the operations in the target performance rule based on the user model and the target game to obtain an interaction sequence corresponding to the user model.

[0074] Among them, the decision actions for executing the operations in the target performance rule output based on the decision-making strategies in different user models can be used to interact with the target game, and the interaction sequence during the interaction process is recorded. The interaction sequence may include a sequence formed by state-action in the target game, that is, the state S is collected from the environment in the target game, and the decision action A executed in this state is recorded until the decision action is completed, obtaining the interaction sequence. Exemplarily, the interaction sequence is represented as follows:

[0075] <S0,A0; S1,A1;...; S T ,A T >

[0076] S T is used to represent the state at time T, and A T is used to represent the decision action at time T.

[0077] Among them, performing multiple Monte Carlo simulations based on the user model in the target game is equivalent to simulating multiple virtual player users playing the game together. In each Monte Carlo simulation operation, according to the game state corresponding to each action decision moment in the game state sequence, the virtual player user makes an action decision starting from the first action decision moment and executes the decision action until the action decision at the last action decision moment is completed and then ends.

[0078] For each of the interaction sequences, statistically analyze the data in the interaction sequence corresponding to the target performance rule to obtain the simulation data.

[0079] Among them, the interaction sequence may include rewards or punishments obtained after executing decision-making actions. Then, statistics can be performed based on the change of the target performance rule of the state representation in the interaction sequence to obtain simulation data. Taking the performance rule of obtaining 100,000 gold coins by hitting the target object 5 times as described above as an example, in the interaction sequence, the number of gold coins corresponding to state S0 is N0. At this time, decision-making action A0 is executed to obtain state S1, and the number of gold coins corresponding to state S1 is N1. At this time, decision-making action A1 is executed to obtain state S2, and so on until the interaction ends. Then, the number of gold coins corresponding to the execution of A0 can be determined by the change between N1 and N0, and the change between the number of gold coins in the final state and N0 can determine the number of gold coins corresponding to the interaction simulation, that is, the simulation data. The determination method of the simulation data corresponding to other performance rules is similar and can be obtained by statistics from the fields corresponding to the game metrics in the interaction sequence, which will not be elaborated here.

[0080] Thus, through the above technical solution, a large amount of simulation data can be obtained based on the Monte Carlo simulation method, so that the performance rules of the target game with the candidate value during operation can be simulated, providing accurate and a large amount of data support for verifying the rationality of the candidate value.

[0081] In a possible embodiment, the target performance rule further includes the target distribution condition corresponding to the target interest metric. Exemplarily, taking the performance rule that the remaining number of monsters in the scene within 10 minutes of the start of the battle as described above as an example, the target performance rule may further include its corresponding target distribution condition, for example, the proportion of the simulation data corresponding to the remaining number of monsters in the scene within 10 minutes of the start of the battle being 0 is not less than 90%.

[0082] Correspondingly, the exemplary implementation manner of determining whether the candidate value meets the target performance rule according to the simulation data may include:

[0083] For each target interest metric, statistics are performed on the data corresponding to each distribution value of the target interest metric in the simulation data to obtain the simulation distribution corresponding to the target interest metric.

[0084] Continuing with the above example, if the target interest metric is the remaining number of monsters, then the number of remaining monsters in the simulation data can be used as a distribution value. Then, statistics can be performed on the remaining number of monsters in each simulation data, and the simulation distribution can be obtained based on the statistical data. For example, the proportion of the simulation data corresponding to the remaining number of monsters being 0 is 91%, the proportion of the simulation data corresponding to the remaining number of monsters being 1 is 8%, the proportion of the simulation data corresponding to the remaining number of monsters being 2 is 0.5%, and the proportion of the simulation data corresponding to the remaining number of monsters being 3 is 0.5%.

[0085] If the target interest metric is the number of gold coins, the corresponding distribution values for the number of gold coins can be set in advance. For example, multiple distribution values can be set according to the range of the number of gold coins. For instance, the number of gold coins from 90,000 to 100,000 corresponds to one distribution value, and the number of gold coins from 100,000 to 110,000 corresponds to one distribution value. It can be set based on the actual application scenario and will not be elaborated here.

[0086] If the simulated distribution of each said target interest metric meets the target distribution condition corresponding to the target interest metric, it is determined that the candidate value meets the target performance rule; if the simulated distribution of any one of the target interest metrics does not meet the target distribution condition corresponding to the target interest metric, it is determined that the candidate value does not meet the target performance rule.

[0087] As an example, if there is one target interest metric, as in the example described above, if it is determined that the proportion of the simulated data corresponding to the remaining monster count of 0 is 91%, which is not less than 90%, it can be considered that the simulated distribution of the remaining monster count in the simulated data meets its corresponding target distribution condition. That is, when the value of the target game parameter in the target game is this candidate value, the operation of the target game can meet the standard of the target performance rule, and it is determined that the candidate value meets the target performance rule. If it is determined that the proportion of the simulated data corresponding to the remaining monster count of 0 is 87%, which is less than 90%, it can be considered that the simulated distribution of the remaining monster count in the simulated data does not meet its corresponding target distribution condition. That is, when the value of the target game parameter in the target game is this candidate value, the operation of the target game cannot meet the standard of the target performance rule, and it is determined that the candidate value does not meet the target performance rule.

[0088] As another example, if there are multiple target interest metrics, such as the target performance rule being that the proportion of the remaining monster count in the scene within 10 minutes of the start of the battle being 0 is not less than 90%, and the proportion of the collected reward gold coins reaching 100,000 is not less than 95%, then the simulated distributions corresponding to the remaining monster count and the reward gold coins can be statistically analyzed respectively for each of the above target interest metrics to determine whether they meet their corresponding target distribution conditions. If, based on the simulated data, it is determined that the proportion of the remaining monster count in the scene within 10 minutes of the start of the battle being 0 is not less than 90%, and the proportion of the collected reward gold coins reaching 100,000 is not less than 95%, it is considered that this candidate value meets the target performance rule; otherwise, it is considered that this candidate value does not meet the target performance rule.

[0089] Thus, through the above technical solution, by statistically analyzing a large amount of simulation data, it is possible to determine whether the interaction process in the target game can meet the criteria of the target performance rule when the target game parameter in the target game takes a candidate value for operation, so as to verify the candidate value, simplify the verification process and improve the accuracy of the candidate value, providing reliable data support for determining the parameters in the target game.

[0090] In a possible embodiment, the method may further include:

[0091] If the candidate value meets the target performance rule, output the target performance rule, the target value, and the simulation distribution corresponding to the target interest metric at the target value. Among them, the simulation distribution corresponding to the target interest metric at the target value is the distribution determined based on the simulation data corresponding to the target game when the target parameter vector takes the target value.

[0092] Among them, that the candidate value meets the target performance rule means that when the value of the target game parameter in the target game is the candidate value, the operation of the target game can meet the criteria of the target performance rule. In this case, output the target performance rule, the target value, and the simulation distribution corresponding to the target interest metric at the target value. Based on this simulation distribution, game personnel can know the credibility of the value setting of the target game parameter in the target game, without the need for game personnel to verify, determine the accurate value of the target game parameter, and provide data reference for whether game personnel accept the target value, improving the accuracy of the determined value of the game parameter.

[0093] In a possible embodiment, an exemplary implementation manner of adjusting the candidate value according to the simulation data is as follows. This step may include:

[0094] For each target interest metric, extract the data corresponding to the target interest metric from the simulation data to obtain sub-simulation data corresponding to the target interest metric.

[0095] Exemplarily, if there is 1 target interest metric, the simulation data can be directly determined as the sub-simulation data corresponding to the target interest metric. If there are multiple target interest metrics, such as the number of rewarded gold coins and the number of remaining monsters, the number of rewarded gold coins in each simulation data can be extracted to obtain sub-simulation data corresponding to the number of rewarded gold coins, and the number of remaining monsters in each simulation data can be extracted to obtain sub-simulation data corresponding to the number of remaining monsters.

[0096] For each sub-simulation data corresponding to the target interest metric, determine the sub-loss corresponding to the target interest metric; perform weighted summation on the sub-losses corresponding to the respective target interest metrics to obtain a target loss, and adjust the candidate value according to the target loss.

[0097] For each sub-simulation data corresponding to a target interest metric, the difference between the sequence formed by the sub-model data and the expectation corresponding to the target performance rule can be used as the sub-loss corresponding to the target interest metric. For example, this difference can be the Euclidean distance. If there is 1 target interest metric, the sub-loss can be directly used as the target loss. If there are multiple target interest metrics, weighted summation is performed on the respective sub-losses according to the weights corresponding to the target interest metrics to obtain the target loss. Among them, the weights corresponding to the target interest metrics can be the same or different to conform to the focus of the numerical settings in the target game.

[0098] Exemplarily, adjusting the candidate value according to the target loss can be to adjust the candidate value in the optimization direction of reducing the target loss based on the gradient descent method to obtain a new candidate value after adjustment and optimization, and assign a value to the target game parameter in the target game based on the new candidate value, and perform an interactive simulation on the target game after parameter update to verify the new candidate value.

[0099] Thus, through the above technical solution, the optimization direction of numerical adjustment can be automatically determined based on the data obtained from the interactive simulation between the user model and the target game, improving the accuracy and efficiency of parameter determination in the target game and ensuring the stability of the operation ecosystem of the target game.

[0100] In a possible implementation, the exemplary implementation manner of performing interactive simulation based on multiple user models and the target game to obtain the simulation data corresponding to the target performance rule may include:

[0101] For each user model, perform interactive simulation based on the user model and the game kernel simulator corresponding to the target game to obtain the simulation data corresponding to the target performance rule, where the game kernel simulator is modeled based on the processing logic of the target game, and the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game.

[0102] In this step, the game kernel simulator is modeled based on the processing logic of the target game. For example, the processing logic may include the processing rules and values of the target game, so that when the user model interacts with the game kernel simulator, the same test data as the interaction between the user model and the target game can be obtained. Moreover, based on the interaction between the game kernel simulator and the user model, no human participation is required, and the game kernel simulator and the user model can be controlled to perform fast simulation at N times the speed, so that it can be applied to application scenarios with a large amount of simulation data, improving the acquisition efficiency of simulation data and the total sample size. Among them, the game kernel simulator can be independent of the target game itself. For example, it does not have to be composed of the code of the game client or server of the target game and can be coded in other programming languages as long as its processing logic is the same as that of the target game. In addition, the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game, so that no rendering of the interactive interface is required during the interaction process, further improving the acquisition efficiency of simulation data, and then improving the determination efficiency of game parameters and reducing the manual workload.

[0103] The present disclosure also provides a device for determining game parameters, as Figure 2 shown. The device 10 includes:

[0104] A first determination module 100, configured to determine a target performance rule corresponding to a target interest metric in the target game, where the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to the execution of the target operation;

[0105] A second determination module 200, configured to determine a target parameter vector corresponding to the target performance rule and candidate values of the target parameter vector according to the target performance rule, where each dimension in the target parameter vector corresponds to a target game parameter in the target game;

[0106] A simulation module 300, configured to determine the values of the target game parameters in the target game according to the candidate values of the target parameter vector, and perform interactive simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule;

[0107] A third determination module 400, configured to determine whether the candidate values meet the target performance rule according to the simulation data;

[0108] An update module 500, configured to, if the candidate value does not meet the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as a new candidate value to trigger the simulation module 300 to re-execute determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and perform an interaction simulation based on multiple user models and the target game to obtain simulation data corresponding to the target performance rule, and the third determination module 400 determines whether the candidate value meets the target performance rule according to the simulation data; if the candidate value meets the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

[0109] Optionally, the apparatus further includes:

[0110] A fourth determination module, configured to determine the user type distribution corresponding to the target performance rule;

[0111] A generation module, configured to generate user models for each user type in the user type distribution according to the user type distribution;

[0112] The simulation module includes:

[0113] A simulation sub-module, configured to perform Monte Carlo simulation on the operations in the target performance rule based on each user model and the target game to obtain an interaction sequence corresponding to the user model;

[0114] A first processing sub-module, configured to, for each interaction sequence, count the data corresponding to the target performance rule in the interaction sequence to obtain the simulation data.

[0115] Optionally, the generation module includes:

[0116] A first determination sub-module, configured to determine the number of users corresponding to each user type in the user type distribution according to the user type distribution and a preset number of simulations;

[0117] A generation sub-module, configured to, for each user type, generate a preset number of user models corresponding to the user type based on a pre-trained model corresponding to the user type, where the decision-making strategies for determining decision actions by the pre-trained models corresponding to different user types are different.

[0118] Optionally, the target performance rule includes a target distribution condition corresponding to the target interest index;

[0119] The third determination module includes:

[0120] A second processing sub-module, configured to, for each of the target interest metrics, perform statistics on the data in the simulation data corresponding to each distribution value of the target interest metric, to obtain a simulation distribution corresponding to the target interest metric;

[0121] A second determination sub-module, configured to determine that the candidate value satisfies the target performance rule if the simulation distribution of each of the target interest metrics satisfies the target distribution condition corresponding to the target interest metric; and determine that the candidate value does not satisfy the target performance rule if the simulation distribution of any one of the target interest metrics does not satisfy the target distribution condition corresponding to the target interest metric.

[0122] Optionally, the apparatus further includes:

[0123] An output module, configured to output the target performance rule, the target value, and the simulation distribution corresponding to the target interest metric under the target value if the candidate value satisfies the target performance rule.

[0124] Optionally, the update module includes:

[0125] An extraction sub-module, configured to, for each of the target interest metrics, extract the data in the simulation data corresponding to the target interest metric respectively, to obtain sub-simulation data corresponding to the target interest metric;

[0126] A third determination sub-module, configured to determine a sub-loss corresponding to the target interest metric for the sub-simulation data corresponding to each of the target interest metrics;

[0127] An adjustment sub-module sums up the sub-losses corresponding to each of the target interest metrics after weighting, to obtain a target loss, and adjusts the candidate value according to the target loss.

[0128] Optionally, the simulation module is used for:

[0129] For each of the user models, perform interactive simulation based on the user model and a game kernel simulator corresponding to the target game, to obtain simulation data corresponding to the target performance rule, where the game kernel simulator is modeled based on the processing logic of the target game, and the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game.

[0130] Next, refer to Figure 3, which shows a schematic structural diagram of an electronic device 600 suitable for implementing the embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The shown electronic device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0131] As Figure 3 shown, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 602 or the programs loaded from the storage device 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0132] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 the shown electronic device 600 has various devices, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be alternatively implemented or had.

[0133] Specifically, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

[0134] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0135] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (for example, a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0136] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; it can also exist separately and not be assembled into the electronic device.

[0137] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: determine a target performance rule corresponding to a target interest metric in a target game, where the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to the execution of the target operation; determine a target parameter vector corresponding to the target performance rule and candidate values of the target parameter vector according to the target performance rule, where each dimension in the target parameter vector corresponds to a target game parameter in the target game; determine the value of the target game parameter in the target game according to the candidate values of the target parameter vector, and perform an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule; determine whether the candidate values satisfy the target performance rule according to the simulation data; if the candidate values do not satisfy the target performance rule, adjust the candidate values according to the simulation data, and use the adjusted values as new candidate values to re-execute the steps of determining the value of the target game parameter in the target game according to the candidate values of the target parameter vector and performing an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule and the step of determining whether the candidate values satisfy the target performance rule according to the simulation data; if the candidate values satisfy the target performance rule, determine the latest candidate values as the target values of the target parameter vector.

[0138] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0140] The modules described in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the module itself in some cases. For example, the first determination module can also be described as "the module for determining the target performance rule corresponding to the target interest index in the target game".

[0141] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuits (ASIC), Application Specific Standard Products (ASSP), System on a Chip (SOC), Complex Programmable Logic Devices (CPLD), and so on.

[0142] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM or Flash Memory), an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0143] According to one or more embodiments of the present disclosure, Example 1 provides a method for determining game parameters, wherein the method includes:

[0144] Determine a target performance rule corresponding to a target interest metric in a target game, wherein the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to the execution of the target operation;

[0145] According to the target performance rule, determine a target parameter vector corresponding to the target performance rule and candidate values of the target parameter vector, wherein each dimension in the target parameter vector corresponds to a target game parameter in the target game;

[0146] Determine the value of the target game parameter in the target game according to the candidate values of the target parameter vector, and perform an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule;

[0147] According to the simulation data, determine whether the candidate values satisfy the target performance rule;

[0148] If the candidate values do not satisfy the target performance rule, adjust the candidate values according to the simulation data, and use the adjusted values as new candidate values to re-execute the steps of determining the value of the target game parameter in the target game according to the candidate values of the target parameter vector and performing an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule, and the step of determining whether the candidate values satisfy the target performance rule according to the simulation data; if the candidate values satisfy the target performance rule, determine the latest candidate values as the target values of the target parameter vector.

[0149] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, wherein the method further includes:

[0150] Determine the user type distribution corresponding to the target performance rule;

[0151] Generate user models for each user type in the user type distribution according to the user type distribution;

[0152] The performing an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule includes:

[0153] For each user model, perform a Monte Carlo simulation on the operation in the target performance rule based on the user model and the target game to obtain an interaction sequence corresponding to the user model;

[0154] For each of the interaction sequences, count the data corresponding to the target performance rule in the interaction sequence to obtain the simulation data.

[0155] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, wherein generating user models for each user type in the user type distribution according to the user type distribution includes:

[0156] Determine the number of users corresponding to each user type in the user type distribution according to the user type distribution and a preset number of simulations;

[0157] For each of the user types, generate a preset number of user models corresponding to the user type based on the pre-trained model corresponding to the user type, wherein the decision-making strategies for determining decision actions by the pre-trained models corresponding to different user types are different.

[0158] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 1, wherein the target performance rule further includes a target distribution condition corresponding to the target interest metric;

[0159] Determining whether the candidate value satisfies the target performance rule according to the simulation data includes:

[0160] For each of the target interest metrics, count the data corresponding to each distribution value of the target interest metric in the simulation data to obtain a simulated distribution corresponding to the target interest metric;

[0161] If the simulated distribution of each of the target interest metrics satisfies the target distribution condition corresponding to the target interest metric, determine that the candidate value satisfies the target performance rule;

[0162] If the simulated distribution of any one of the target interest metrics does not satisfy the target distribution condition corresponding to the target interest metric, determine that the candidate value does not satisfy the target performance rule.

[0163] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, wherein the method further includes:

[0164] If the candidate value satisfies the target performance rule, output the target performance rule, the target value, and the simulated distribution corresponding to the target interest metric under the target value.

[0165] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 1, wherein adjusting the candidate value according to the simulation data includes:

[0166] For each of the target interest metrics, extract the data corresponding to the target interest metrics from the simulation data to obtain sub-simulation data corresponding to the target interest metrics;

[0167] For the sub-simulation data corresponding to each of the target interest metrics, determine the sub-loss corresponding to the target interest metric;

[0168] Perform a weighted sum of the sub-losses corresponding to each of the target interest metrics to obtain a target loss, and adjust the candidate values according to the target loss.

[0169] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 1, wherein the interacting and simulating based on multiple user models and the target game to obtain simulation data corresponding to the target performance rule includes:

[0170] For each of the user models, perform an interactive simulation based on the user model and a game kernel simulator corresponding to the target game to obtain simulation data corresponding to the target performance rule, wherein the game kernel simulator is modeled based on the processing logic of the target game, and the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game.

[0171] According to one or more embodiments of the present disclosure, Example 8 provides a device for determining game parameters, wherein the device includes:

[0172] A first determination module, configured to determine a target performance rule corresponding to a target interest metric in a target game, wherein the target performance rule includes a target operation in the target game and an expectation of the target interest metric corresponding to the execution of the target operation;

[0173] A second determination module, configured to determine a target parameter vector corresponding to the target performance rule and a candidate value of the target parameter vector according to the target performance rule, wherein each dimension in the target parameter vector corresponds to a target game parameter in the target game;

[0174] A simulation module, configured to determine the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and perform an interactive simulation based on multiple user models and the target game to obtain simulation data corresponding to the target performance rule;

[0175] A third determination module, configured to determine whether the candidate value satisfies the target performance rule according to the simulation data;

[0176] An update module, configured to, if the candidate value does not meet the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as a new candidate value to trigger the simulation module to re-execute determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and perform an interaction simulation based on a plurality of user models and the target game to obtain simulation data corresponding to the target performance rule, and the third determination module determines whether the candidate value meets the target performance rule according to the simulation data; if the candidate value meets the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

[0177] According to one or more embodiments of the present disclosure, Example 9 provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processing device, the steps of the method according to any one of Examples 1-7 are implemented.

[0178] According to one or more embodiments of the present disclosure, Example 10 provides an electronic device, including:

[0179] A storage device having a computer program stored thereon;

[0180] A processing device configured to execute the computer program in the storage device to implement the steps of the method according to any one of Examples 1-7.

[0181] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principle. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0182] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0183] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

Claims

1. A method for determining game parameters, characterized in that, The method includes: Determine the target performance rule corresponding to the target interest metric in the target game, where the target performance rule includes the target operation in the target game and the expectation of the target interest metric corresponding to the execution of the target operation; According to the target performance rule, determine the target parameter vector corresponding to the target performance rule and the candidate values of the target parameter vector, where each dimension in the target parameter vector corresponds to a target game parameter in the target game; Determine the value of the target game parameter in the target game according to the candidate values of the target parameter vector, and for each of the multiple user models, perform an interactive simulation based on the game kernel simulator corresponding to the target game of the user model to obtain the simulation data corresponding to the target performance rule, where the game kernel simulator is modeled based on the processing logic of the target game, and the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game; According to the simulation data, determine whether the candidate value satisfies the target performance rule; If the candidate value does not satisfy the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as the new candidate value to re-execute the step of determining the value of the target game parameter in the target game according to the candidate values of the target parameter vector, and for each of the multiple user models, perform an interactive simulation based on the game kernel simulator corresponding to the target game of the user model to obtain the simulation data corresponding to the target performance rule and the step of determining whether the candidate value satisfies the target performance rule according to the simulation data; if the candidate value satisfies the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

2. The method according to claim 1, characterized in that The method further includes: Determine the user type distribution corresponding to the target performance rule; Generate user models for each user type in the user type distribution according to the user type distribution; The obtaining the simulation data corresponding to the target performance rule includes: For each user model, perform a Monte Carlo simulation on the operation in the target performance rule based on the user model and the target game to obtain the interaction sequence corresponding to the user model; For each interaction sequence, statistically analyze the data corresponding to the target performance rule in the interaction sequence to obtain the simulation data.

3. The method according to claim 2, characterized in that, The generating user models for each user type in the user type distribution according to the user type distribution includes: Determine the number of users corresponding to each user type in the user type distribution according to the user type distribution and the preset number of simulations; For each user type, generate a preset number of user models corresponding to the user type based on the pre-trained model corresponding to the user type, where the decision-making strategies for determining decision actions by the pre-trained models corresponding to different user types are different.

4. The method according to claim 1, characterized in that The target performance rule further includes a target distribution condition corresponding to the target interest index; Determining whether the candidate value satisfies the target performance rule according to the simulation data includes: For each target interest index, count the data in the simulation data corresponding to each distribution value of the target interest index to obtain a simulation distribution corresponding to the target interest index; If the simulation distribution of each target interest index satisfies the target distribution condition corresponding to the target interest index, it is determined that the candidate value satisfies the target performance rule; If the simulation distribution of any target interest index does not satisfy the target distribution condition corresponding to the target interest index, it is determined that the candidate value does not satisfy the target performance rule.

5. The method according to claim 4, characterized in that The method further includes: If the candidate value satisfies the target performance rule, output the target performance rule, the target value, and the simulation distribution corresponding to the target interest index under the target value.

6. The method according to claim 1, wherein Adjusting the candidate value according to the simulation data includes: For each target interest index, extract the data in the simulation data corresponding to the target interest index respectively to obtain sub-simulation data corresponding to the target interest index; For the sub-simulation data corresponding to each target interest index, determine the sub-loss corresponding to the target interest index; Perform weighted summation on the sub-losses corresponding to each target interest index to obtain a target loss, and adjust the candidate value according to the target loss.

7. A device for determining game parameters, characterized in that The device includes: A first determination module for determining a target performance rule corresponding to a target interest index in a target game, where the target performance rule includes a target operation in the target game and an expectation of the target interest index corresponding to the execution of the target operation; A second determination module for determining a target parameter vector corresponding to the target performance rule and a candidate value of the target parameter vector according to the target performance rule, where each dimension in the target parameter vector corresponds to a target game parameter in the target game; A simulation module for determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and for each user model among multiple user models, performing interactive simulation based on the game kernel simulator corresponding to the user model and the target game to obtain simulation data corresponding to the target performance rule, where the game kernel simulator is modeled based on the processing logic of the target game, and the game kernel simulator is used to provide a non-interactive interface operating environment corresponding to the target game; A third determination module for determining whether the candidate value satisfies the target performance rule according to the simulation data; An update module, configured to, if the candidate value does not meet the target performance rule, adjust the candidate value according to the simulation data, and use the adjusted value as a new candidate value to trigger the simulation module to re-execute the step of determining the value of the target game parameter in the target game according to the candidate value of the target parameter vector, and for each of the multiple user models, perform an interactive simulation with the game kernel simulator corresponding to the target game based on the user model, obtain the simulation data corresponding to the target performance rule, and the third determination module determines whether the candidate value meets the target performance rule according to the simulation data; if the candidate value meets the target performance rule, determine the latest candidate value as the target value of the target parameter vector.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by a processing device, the program implements the steps of the method according to any one of claims 1-6.

9. An electronic device, characterized in that, Comprising: A storage device storing a computer program thereon; A processing device configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1-6.

Images