Game resource location determination method and system based on multi-role historical data

Abstract

The present invention discloses a method and system for determining the location of game resources based on multi-role historical data. The method includes: obtaining historical play data of multiple game players in a target game area; determining predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm; determining a plurality of candidate resource location distributions according to the area parameters of the target game area; and determining the optimal resource distribution of the target game area according to the predicted player distribution parameters and the plurality of candidate resource location distributions. It can be seen that the present invention can achieve reasonable allocation and precise placement of game resources, enhance the gaming experience of game players, and at the same time improve the balance and competitiveness of the game area.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for determining the location of game resources based on multi-character historical data. Background Art

[0002] In the development and operation of multiplayer games, the placement and strategy of game resources are extremely important. Existing game systems usually adopt a fixed distribution or random distribution method for resource placement. Although it can ensure a certain degree of fairness, it fails to fully consider the actual activity patterns of players, resulting in a low match between resource distribution and player needs, which in turn affects the game experience. Although there are some improvement schemes that attempt to optimize resource distribution based on the static characteristics of the game map, due to the failure to dynamically adapt to changes in player behavior, resources may be concentrated in low-activity areas or fail to be reasonably distributed in high-demand areas. In addition, the existing technology lacks accurate prediction of player behavior and cannot optimize resource placement based on player activity patterns, resulting in low resource utilization, making it difficult for some players to obtain key resources, affecting the competitiveness and balance of the game. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for determining the location of game resources based on multi-character historical data, which can achieve reasonable allocation and delivery accuracy of game resources, enhance the gaming experience of game players, and improve the balance and competitiveness of the game area.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for determining the location of game resources based on multi-character historical data, the method comprising:

[0005] Obtain historical game data of multiple game players in the target game area;

[0006] Determine predicted player distribution parameters of the target game area based on the historical game data and a prediction algorithm;

[0007] Determining the location distribution of multiple candidate resources according to the area parameters of the target game area;

[0008] The optimal resource distribution of the target game area is determined based on the predicted player distribution parameters and the multiple candidate resource location distributions.

[0009] As an optional embodiment, in the first aspect of the present invention, the historical play data includes at least one of the game player's game operations, game routes, game positions, game triggered plots, game execution tasks and game character information in a historical time period.

[0010] As an optional implementation manner, in the first aspect of the present invention, determining the predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm includes:

[0011] Grouping the historical play data according to the obtained historical time periods to obtain play data sets corresponding to multiple different historical time periods;

[0012] Inputting each of the play data sets into the player distribution recognition algorithm model to obtain the player distribution parameters corresponding to each of the play data sets; the player distribution recognition algorithm model is trained by a training data set including a plurality of training play data and corresponding player distribution parameter annotations; the player distribution parameters include at least the group position, group quantity, moving direction, moving speed, frequent activity area, and internal player density of at least one player group;

[0013] Analyzing the variation law with time corresponding to the player distribution parameters corresponding to all the play data sets to obtain the predicted player distribution parameters of the target game area in a future time period.

[0014] As an optional implementation manner, in the first aspect of the present invention, analyzing the variation law with time corresponding to the player distribution parameters corresponding to all the play data sets to obtain the predicted player distribution parameters of the target game area in a future time period includes:

[0015] Sorting the player distribution parameters of the player groups in all the player distribution parameters from early to late according to the corresponding historical time periods to obtain a player distribution parameter sequence;

[0016] Inputting the player distribution parameter sequence into a trained LSTM neural network to obtain the predicted player distribution parameters of the target game area in a future time period; the predicted player distribution parameters include player group position parameters, player group quantity parameters, and player group activity areas; the LSTM neural network is trained by a training data set including a plurality of training player distribution parameters sorted with time.

[0017] As an optional implementation manner, in the first aspect of the present invention, the area parameters include at least one of area shape, area area, area position, tasks in the area, trigger plots in the area, and NPC characters in the area.

[0018] As an optional implementation manner, in the first aspect of the present invention, determining a plurality of candidate resource position distributions according to the area parameters of the target game area includes:

[0019] Match multiple matching resource distribution schemes with all or some of the parameters identical in the historical resource distribution database according to the area parameters of the target game area;

[0020] For each of the matching resource distribution schemes, obtain the historical player complaint records and player play data corresponding to the historical application period of the matching resource distribution scheme;

[0021] Calculate the first similarity between the player play data and all the historical play data;

[0022] Input the historical player complaint records into the resource-related complaint recognition algorithm model to obtain the resource-related complaint ratio corresponding to the historical player complaint records; the resource-related complaint recognition algorithm model is trained by a training data set including multiple training player complaint records and corresponding resource-related complaint annotations;

[0023] Calculate the product of the first similarity and the resource-related complaint ratio to obtain the priority of the matching resource distribution scheme;

[0024] Filter out all the matching resource distribution schemes with the priority greater than the priority threshold to obtain multiple candidate resource location distributions.

[0025] As an optional implementation manner, in the first aspect of the present invention, the determining the optimal resource distribution of the target game area according to the predicted player distribution parameters and the multiple candidate resource location distributions includes:

[0026] Based on the predicted player distribution parameters and the multiple candidate resource location distributions, determine the objective function and the constraint conditions;

[0027] Through the dynamic programming algorithm, perform iterative calculations on the resource distribution scheme based on the objective function and the constraint conditions until it is optimal to obtain the optimal resource distribution of the target game area.

[0028] As an optional implementation manner, in the first aspect of the present invention, the objective function includes:

[0029] The average value of the second similarities between the resource distribution scheme and each of the candidate resource location distributions reaches the maximum;

[0030] The distribution uniformity corresponding to the resource distribution scheme reaches the minimum; the distribution uniformity is calculated by the spatial distribution uniformity algorithm for the resource locations and resource quantities of multiple arranged resources in the resource distribution scheme;

[0031] The constraint conditions include:

[0032] The positional distance between the resource position of each deployed resource in the resource distribution plan and the position of the nearest player group in the predicted player distribution parameters is less than the distance threshold;

[0033] The resource quantity of each deployed resource in the resource distribution plan is less than the average resource quantity corresponding to the predicted player distribution parameters; the average resource quantity is the product of the average value of the player group quantities of all player groups in the predicted player distribution parameters and a preset ratio parameter;

[0034] The resource quantity of the deployed resources in the area corresponding to the player group activity area in the resource distribution plan is greater than a preset quantity threshold.

[0035] A second aspect of an embodiment of the present invention discloses a game resource position determination system based on multi-role historical data, the system includes:

[0036] An acquisition module, configured to acquire historical play data of multiple game players in a target game area;

[0037] A first determination module, configured to determine the predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm;

[0038] A second determination module, configured to determine a plurality of candidate resource position distributions according to the area parameters of the target game area;

[0039] A third determination module, configured to determine the optimal resource distribution of the target game area according to the predicted player distribution parameters and the plurality of candidate resource position distributions.

[0040] As an optional implementation manner, in the second aspect of the present invention, the historical play data includes at least one of game operations, game routes, game positions, game-triggered storylines, game-executed tasks, and game character information of the game players in a historical time period.

[0041] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the first determination module determines the predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm includes:

[0042] Group the historical play data according to the acquired historical time period to obtain play data sets corresponding to multiple different historical time periods;

[0043] Input each of the gameplay data sets into the player distribution recognition algorithm model to obtain the player distribution parameters corresponding to each gameplay data set; the player distribution recognition algorithm model is trained through a training data set including a plurality of training gameplay data and corresponding player distribution parameter annotations; the player distribution parameters include the group positions, group quantities, moving directions, moving speeds, frequently active areas, and internal player densities of at least one player group.

[0044] Analyze the variation law over time corresponding to the player distribution parameters corresponding to all the gameplay data sets to obtain the predicted player distribution parameters of the target game area in a future time period.

[0045] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the first determination module analyzes the variation law over time corresponding to the player distribution parameters corresponding to all the gameplay data sets to obtain the predicted player distribution parameters of the target game area in a future time period includes:

[0046] Sort the player distribution parameters of the player groups in all the player distribution parameters in ascending order according to the corresponding historical time periods to obtain a player distribution parameter sequence;

[0047] Input the player distribution parameter sequence into a trained LSTM neural network to obtain the predicted player distribution parameters of the target game area in a future time period; the predicted player distribution parameters include player group position parameters, player group quantity parameters, and player group activity areas; the LSTM neural network is trained through a training data set including a plurality of training player distribution parameters sorted over time.

[0048] As an optional implementation manner, in the second aspect of the present invention, the area parameters include at least one of area shape, area area, area position, tasks within the area, trigger plots within the area, and NPC characters within the area.

[0049] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the second determination module determines a plurality of candidate resource location distributions according to the area parameters of the target game area includes:

[0050] According to the area parameters of the target game area, match a plurality of matching resource distribution schemes with all or some of the parameters identical in a historical resource distribution database;

[0051] For each of the matching resource distribution schemes, obtain the corresponding historical player complaint records and player gameplay data during the historical application period of the matching resource distribution scheme;

[0052] Calculate a first similarity between the player's gameplay data and all the historical gameplay data;

[0053] Input the historical player complaint records into a resource-related complaint recognition algorithm model to obtain a resource-related complaint ratio corresponding to the historical player complaint records; the resource-related complaint recognition algorithm model is trained by a training data set including a plurality of training player complaint records and corresponding resource-related complaint annotations;

[0054] Calculate the product of the first similarity and the resource-related complaint ratio to obtain the priority of this matching resource distribution plan;

[0055] Filter out all the matching resource distribution plans with the priority greater than the priority threshold to obtain a plurality of candidate resource location distributions.

[0056] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the third determination module determines the optimal resource distribution of the target game area according to the predicted player distribution parameters and the plurality of candidate resource location distributions includes:

[0057] Based on the predicted player distribution parameters and the plurality of candidate resource location distributions, determine an objective function and constraint conditions;

[0058] Through a dynamic programming algorithm, perform iterative calculations on the resource distribution plan based on the objective function and constraint conditions until it is optimal, to obtain the optimal resource distribution of the target game area.

[0059] As an optional implementation manner, in the second aspect of the present invention, the objective function includes:

[0060] The average value of the second similarities between the resource distribution plan and each of the candidate resource location distributions reaches the maximum;

[0061] The distribution uniformity corresponding to the resource distribution plan reaches the minimum; the distribution uniformity is obtained by performing calculations on the resource positions and resource quantities of multiple arranged resources in the resource distribution plan through a spatial distribution uniformity algorithm;

[0062] The constraint conditions include:

[0063] The position distance between the resource position of each arranged resource in the resource distribution plan and the position of the nearest player group in the predicted player distribution parameters is less than the distance threshold;

[0064] The resource quantity of each arranged resource in the resource distribution plan is less than the average resource quantity corresponding to the predicted player distribution parameters; the average resource quantity is the product of the average value of the player group quantities of all player groups in the predicted player distribution parameters and a preset ratio parameter;

[0065] The quantity of resources arranged within the area corresponding to the player group activity area in the prediction player distribution parameter in the resource distribution plan is greater than a preset quantity threshold.

[0066] The third aspect of the present invention discloses another game resource location determination system based on multi-character historical data, and the system includes:

[0067] A memory storing executable program code;

[0068] A processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory and executes some or all of the steps in the game resource location determination method based on multi-character historical data disclosed in the first aspect of the present invention.

[0070] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute some or all of the steps in the game resource location determination method based on multi-character historical data disclosed in the first aspect of the present invention when being called.

[0071] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0072] The present invention can determine the prediction player distribution parameter of the target game area based on historical play data and prediction algorithms, screen candidate resource location distributions in combination with the area parameters of the target game area, and further optimize the resource distribution according to the prediction player distribution parameter, so as to achieve reasonable configuration and accurate placement of game resources, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0074] Figure 1 It is a flowchart of a game resource location determination method based on multi-character historical data disclosed in the embodiments of the present invention.

[0075] Figure 2 It is a structural schematic diagram of a game resource location determination system based on multi-character historical data disclosed in the embodiments of the present invention.

[0076] Figure 3It is a schematic structural diagram of another game resource location determination system based on multi-role historical data disclosed in an embodiment of the present invention. Detailed implementation manners

[0077] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0078] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0079] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0080] The present invention discloses a method and system for determining the location of game resources based on multi-role historical data, which can determine the predicted player distribution parameters of the target game area based on historical play data and prediction algorithms, screen the candidate resource location distributions in combination with the area parameters of the target game area, and further optimize the resource distribution according to the predicted player distribution parameters, so as to realize the reasonable configuration and accurate placement of game resources, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area. The following will be described in detail respectively.

[0081] Embodiment 1

[0082] Please refer to Figure 1 , Figure 1 which is a schematic flow diagram of a method for determining the location of game resources based on multi-role historical data disclosed in an embodiment of the present invention. Among them, Figure 1The described method for determining the location of game resources based on multi-role historical data can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 1 shown, the method for determining the location of game resources based on multi-role historical data may include the following operations:

[0083] 101. Obtain the historical play data of multiple game players in the target game area.

[0084] 102. Determine the predicted player distribution parameters of the target game area according to the historical play data and the prediction algorithm.

[0085] 103. Determine multiple candidate resource location distributions according to the area parameters of the target game area.

[0086] 104. Determine the optimal resource distribution of the target game area according to the predicted player distribution parameters and the multiple candidate resource location distributions.

[0087] Optionally, the resources in the resource location distribution or resource distribution referred to in the present invention can be defined as data objects in the game that are available for players to collect, consume, convert, or use to improve the performance of characters. Its type can be a single resource type or can include a combination of multiple resource types. The number of resource types is not clearly limited in the present invention because the method of the present invention does not involve the determination and identification of resource types. However, even when the method of the present invention is applied to the determination of the distribution of multiple types of resources, such an application is considered to fall within the protection scope of the present invention.

[0088] It can be seen that the above-mentioned embodiments of the invention can determine the predicted player distribution parameters of the target game area based on historical play data and the prediction algorithm, screen the candidate resource location distributions in combination with the area parameters of the target game area, and further optimize the resource distribution according to the predicted player distribution parameters, so as to achieve the reasonable allocation of game resources and the accuracy of placement, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0089] As an optional embodiment, in the above steps, the historical play data includes at least one of the game operations, game routes, game positions, game-triggered plots, game-executed tasks, and game character information of game players in the historical time period.

[0090] Specifically, in actual R & D, the historical play data of players is usually collected and stored in JSON format, and can be saved to a database (such as MongoDB) or a log file for playing back the historical behaviors of players or analyzing game data, and can also be used in multiplayer online games to synchronize the player status to the server. Subsequently, developers can trace back bugs or optimize the game experience through these data.

[0091] It can be seen that through the above optional embodiments, the content of the historical play data is defined to comprehensively characterize the play-related characteristics of players, so as to facilitate subsequent accurate prediction of player distribution and resource distribution, assist in realizing the reasonable allocation and accurate placement of game resources, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0092] As an optional embodiment, in the above steps, according to the historical play data and the prediction algorithm, the predicted player distribution parameters of the target game area are determined, including:

[0093] Group the historical play data according to the obtained historical time periods to obtain play data sets corresponding to multiple different historical time periods;

[0094] Input each play data set into the player distribution recognition algorithm model to obtain the player distribution parameters corresponding to each play data set; optionally, the player distribution recognition algorithm model is trained through a training data set including multiple training play data and corresponding player distribution parameter annotations; the player distribution parameters include the group position, group quantity, moving direction, moving speed, frequently active area and internal player density of at least one player group.

[0095] Analyze the variation law with time corresponding to the player distribution parameters corresponding to all play data sets to obtain the predicted player distribution parameters of the target game area in the future time period.

[0096] In a specific implementation scheme, the player distribution recognition algorithm model includes a data extraction model and a distribution information prediction model. The data extraction model is used to screen out the data related to player distribution in the historical play data, and the distribution information prediction model is used to predict the player distribution parameters according to the relevant data. Specifically, the data extraction model is a multi-classifier model, and the distribution information prediction model is a CNN neural network model. Both models are trained and optimized through the same training data set.

[0097] It can be seen that through the above optional embodiments, it is possible to group based on historical play data according to time periods, use the player distribution recognition algorithm model to extract the player distribution parameters corresponding to each time period, further analyze the variation law of the player distribution parameters over time, so as to predict the player distribution in future time periods, thereby accurately identifying the dynamic characteristics of player groups in the game environment, improving the understanding of player activity patterns, making the distribution of resources more in line with the actual needs of players, assisting in achieving the reasonable allocation of game resources and the accuracy of resource placement, enhancing the gaming experience of game players, and at the same time improving the balance and competitiveness of the game area.

[0098] As an optional embodiment, in the above steps, analyzing the variation law over time of the player distribution parameters corresponding to all play data sets to obtain the predicted player distribution parameters of the target game area in the future time period includes:

[0099] Sort the player distribution parameters of the player groups in all player distribution parameters from early to late according to the corresponding historical time periods to obtain a player distribution parameter sequence;

[0100] Input the player distribution parameter sequence into the trained LSTM neural network to obtain the predicted player distribution parameters of the target game area in the future time period; optionally, the predicted player distribution parameters include player group position parameters, player group quantity parameters, and player group activity areas; the LSTM neural network is trained through a training data set including multiple training player distribution parameters sorted over time.

[0101] Specifically, in the training data set of the LSTM neural network, the multiple training player distribution parameters sorted over time are obtained by statistically analyzing the player distribution parameters at multiple historical time points of the same game area, which are used to show the variation law of the player distribution in the game area. Training the LSTM neural network based on this can enable the LSTM neural network to accurately predict the player distribution parameters of the target game area in the future time period.

[0102] It can be seen that through the above optional embodiments, it is possible to sort the player distribution parameter sequence based on historical time periods and use the trained LSTM neural network to predict the player distribution parameters of the target game area in the future time period, including the position, quantity, and activity area of the player group, thereby accurately predicting the aggregation trend and activity pattern of players, improving the pertinence and timeliness of resource placement, assisting in achieving the reasonable allocation of game resources and the accuracy of resource placement, enhancing the gaming experience of game players, and at the same time improving the balance and competitiveness of the game area.

[0103] As an alternative embodiment, in the above steps, the area parameters include at least one of area shape, area area, area location, tasks within the area, trigger plots within the area, and NPC characters within the area.

[0104] It can be seen that through the above alternative embodiments, the content of the area parameters is defined to effectively characterize the relevant features of the game area, facilitating subsequent accurate resource distribution prediction, assisting in achieving reasonable resource allocation and precise placement accuracy in the game, enhancing the gaming experience of game players, and at the same time improving the balance and competitiveness of the game area.

[0105] As an alternative embodiment, in the above steps, determining multiple candidate resource location distributions according to the area parameters of the target game area includes:

[0106] According to the area parameters of the target game area, match multiple matching resource distribution schemes with all or partially identical parameters in the historical resource distribution database;

[0107] For each matching resource distribution scheme, obtain the corresponding historical player complaint records and player play data during the historical application period of the matching resource distribution scheme;

[0108] Calculate the first similarity between the player play data and all historical play data;

[0109] Input the historical player complaint records into the resource-related complaint recognition algorithm model to obtain the resource-related complaint ratio corresponding to the historical player complaint records; optionally, the resource-related complaint recognition algorithm model is trained through a training data set including multiple training player complaint records and corresponding resource-related complaint annotations;

[0110] Calculate the product of the first similarity and the resource-related complaint ratio to obtain the priority of the matching resource distribution scheme;

[0111] Screen out all matching resource distribution schemes with priorities greater than the priority threshold to obtain multiple candidate resource location distributions.

[0112] Optionally, the resource distribution schemes in the historical resource distribution database can be resource allocation schemes pre-generated by the operator according to instructions or algorithm models, or schemes actually cited after the operator or algorithm model adjusts the resource schemes in the game according to actual player needs or game plot needs.

[0113] Optionally, the calculation of the similarity in the present invention can be implemented through a data same ratio algorithm or a vector distance algorithm, and those skilled in the art can select the existing algorithms according to the actual situation.

[0114] Specifically, the resource-related complaint recognition algorithm model is implemented as a text classification model in an actual scenario, which is used to identify and classify the text in the complaint record to determine whether it is a complaint text related to dissatisfaction with resource distribution.

[0115] It can be seen that through the above optional embodiments, multiple similar resource distribution schemes can be matched from the historical resource distribution database based on the regional parameters of the target game area, and the priority of the matching scheme can be calculated by combining the historical player complaint records and play data, so as to screen out the candidate resource location distributions with high priority. Therefore, the historical data and player feedback can be comprehensively considered, the rationality and adaptability of the resource distribution scheme can be improved, the reasonable configuration and accurate placement of game resources can be assisted, the game experience of game players can be enhanced, and at the same time, the balance and competitiveness of the game area can be improved.

[0116] As an optional embodiment, in the above steps, determining the optimal resource distribution of the target game area according to the predicted player distribution parameters and multiple candidate resource location distributions includes:

[0117] Based on the predicted player distribution parameters and multiple candidate resource location distributions, determine the objective function and constraints;

[0118] Through the dynamic programming algorithm, perform iterative calculations on the resource distribution scheme based on the objective function and constraints until the optimal solution is obtained, and obtain the optimal resource distribution of the target game area.

[0119] It can be seen that through the above optional embodiments, the objective function and constraints can be constructed based on the predicted player distribution parameters and multiple candidate resource location distributions, and iterative optimization can be performed through the dynamic programming algorithm to calculate the optimal resource distribution of the target game area. Therefore, the resource placement can be dynamically adjusted according to the player distribution trend, the resource utilization rate can be improved, the player interaction experience can be optimized, and the fairness and strategy of the game environment can be enhanced.

[0120] As an optional embodiment, in the above steps, the objective function includes:

[0121] The average value of the second similarity between the resource distribution scheme and each candidate resource location distribution reaches the maximum;

[0122] The distribution uniformity corresponding to the resource distribution scheme reaches the minimum; optionally, the distribution uniformity is obtained by calculating the resource locations and resource quantities of multiple deployed resources in the resource distribution scheme through the spatial distribution uniformity algorithm;

[0123] The constraints include:

[0124] The position distance between the resource location of each deployed resource in the resource distribution scheme and the position of the nearest player group in the predicted player distribution parameters is less than the distance threshold;

[0125] The resource quantity of each arranged resource in the resource distribution plan is less than the average resource quantity corresponding to the predicted player distribution parameter; optionally, the average resource quantity is the product of the average value of the player group quantities of all player groups in the predicted player distribution parameter and a preset ratio parameter.

[0126] The resource quantity of the arranged resources in the area corresponding to the player group activity area in the resource distribution plan is greater than a preset quantity threshold.

[0127] It can be seen that through the above optional embodiments, the constructed objective function takes into account the similarity and distribution uniformity between the resource distribution plan and the candidate resource distribution plan, and the constraint conditions ensure that the resource distribution plan conforms to the spatial distribution characteristics and resource requirements of the player group, thereby improving the accuracy and rationality of resource placement, optimizing the fairness and strategy of the game environment, and enhancing the game experience of players.

[0128] Embodiment 2

[0129] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a game resource location determination system based on multi-role historical data disclosed in an embodiment of the present invention. Among them, Figure 2 The described game resource location determination system based on multi-role historical data can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the game resource location determination system based on multi-role historical data can include:

[0130] An acquisition module 201, configured to acquire historical play data of multiple game players in a target game area.

[0131] A first determination module 202, configured to determine a predicted player distribution parameter of the target game area according to the historical play data and a prediction algorithm.

[0132] A second determination module 203, configured to determine a plurality of candidate resource location distributions according to the area parameters of the target game area.

[0133] A third determination module 204, configured to determine an optimal resource distribution of the target game area according to the predicted player distribution parameter and the plurality of candidate resource location distributions.

[0134] It can be seen that the above-mentioned invention embodiments can determine the predicted player distribution parameters of the target game area based on historical gameplay data and prediction algorithms, screen the candidate resource location distributions in combination with the area parameters of the target game area, and further optimize the resource distribution according to the predicted player distribution parameters, so as to achieve the reasonable allocation and accurate placement of game resources, enhance the gaming experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0135] As an optional embodiment, the historical gameplay data includes at least one of the game operations, game routes, game positions, game-triggered storylines, game-executed tasks, and game character information of game players in a historical time period.

[0136] It can be seen that through the above optional embodiment, the content of the historical gameplay data is defined to comprehensively represent the gameplay-related characteristics of players, so as to facilitate subsequent accurate prediction of player distribution and resource distribution, assist in achieving the reasonable allocation and accurate placement of game resources, enhance the gaming experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0137] As an optional embodiment, the specific manner in which the first determination module determines the predicted player distribution parameters of the target game area according to the historical gameplay data and the prediction algorithm includes:

[0138] Group the historical gameplay data according to the obtained historical time period to obtain multiple gameplay data sets corresponding to different historical time periods;

[0139] Input each gameplay data set into the player distribution recognition algorithm model to obtain the player distribution parameters corresponding to each gameplay data set; optionally, the player distribution recognition algorithm model is trained through a training data set including multiple training gameplay data and corresponding player distribution parameter annotations; the player distribution parameters include the group positions, group quantities, moving directions, moving speeds, frequently active areas, and internal player densities of at least one player group;

[0140] Analyze the time-varying law corresponding to the player distribution parameters of all gameplay data sets to obtain the predicted player distribution parameters of the target game area in the future time period.

[0141] It can be seen that through the above optional embodiments, it is possible to group based on historical play data according to time periods, use the player distribution recognition algorithm model to extract the player distribution parameters corresponding to each time period, further analyze the variation law of the player distribution parameters over time, so as to predict the player distribution in future time periods, thereby accurately identifying the dynamic characteristics of player groups in the game environment, improving the understanding of player activity patterns, making the distribution of resources more in line with the actual needs of players, assisting in realizing the reasonable allocation and accurate placement of game resources, enhancing the game experience of game players, and at the same time improving the balance and competitiveness of the game area.

[0142] As an optional embodiment, the specific manner in which the first determination module analyzes the variation law over time of the player distribution parameters corresponding to all play data sets to obtain the predicted player distribution parameters of the target game area in a future time period includes:

[0143] Sort the player distribution parameters of the player groups in all player distribution parameters in ascending order according to the corresponding historical time periods to obtain a player distribution parameter sequence;

[0144] Input the player distribution parameter sequence into a trained LSTM neural network to obtain the predicted player distribution parameters of the target game area in a future time period; optionally, the predicted player distribution parameters include player group position parameters, player group quantity parameters, and player group activity areas; the LSTM neural network is trained through a training data set including multiple training player distribution parameters sorted over time.

[0145] It can be seen that through the above optional embodiments, it is possible to sort the player distribution parameter sequence based on historical time periods and use the trained LSTM neural network to predict the player distribution parameters of the target game area in a future time period, including the position, quantity, and activity area of the player group, thereby accurately predicting the aggregation trend and activity pattern of players, improving the pertinence and timeliness of resource placement, assisting in realizing the reasonable allocation and accurate placement of game resources, enhancing the game experience of game players, and at the same time improving the balance and competitiveness of the game area.

[0146] As an optional embodiment, the area parameters include at least one of area shape, area area, area position, tasks within the area, triggered plot within the area, and NPC characters within the area.

[0147] It can be seen that through the above optional embodiments, the content of the area parameters is defined to effectively represent the relevant characteristics of the game area, so as to facilitate subsequent accurate resource distribution prediction, assist in realizing the reasonable allocation and accurate placement of game resources, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0148] As an optional embodiment, the specific manner in which the second determination module determines a plurality of candidate resource location distributions according to the regional parameters of the target game area includes:

[0149] According to the regional parameters of the target game area, match multiple matching resource distribution schemes with all or some of the parameters the same in the historical resource distribution database;

[0150] For each matching resource distribution scheme, obtain the historical player complaint records and player play data corresponding to the historical application period of the matching resource distribution scheme;

[0151] Calculate the first similarity between the player play data and all historical play data;

[0152] Input the historical player complaint records into the resource-related complaint recognition algorithm model to obtain the resource-related complaint ratio corresponding to the historical player complaint records; Optionally, the resource-related complaint recognition algorithm model is trained through a training data set including a plurality of training player complaint records and corresponding resource-related complaint annotations;

[0153] Calculate the product of the first similarity and the resource-related complaint ratio to obtain the priority of the matching resource distribution scheme;

[0154] Filter out all matching resource distribution schemes with a priority greater than the priority threshold to obtain a plurality of candidate resource location distributions.

[0155] Optionally, the calculation of the similarity in the present invention can be implemented by calculating the vector distance of the vector data after vectorizing the data, or by other optional data similarity algorithms.

[0156] Optionally, the resource-related complaint recognition algorithm model can be a pre-trained BERT model or other text processing algorithm models, such as the LLM model.

[0157] It can be seen that through the above optional embodiments, it is possible to match multiple similar resource distribution schemes from the historical resource distribution database based on the regional parameters of the target game area, and calculate the priority of the matching schemes in combination with the historical player complaint records and play data, so as to screen out candidate resource location distributions with high priority, thereby being able to comprehensively consider historical data and player feedback, improve the rationality and adaptability of the resource distribution scheme, assist in realizing the reasonable configuration and accurate placement of game resources, enhance the game experience of game players, and at the same time improve the balance and competitiveness of the game area.

[0158] As an optional embodiment, the specific manner in which the third determination module determines the optimal resource distribution of the target game area according to the predicted player distribution parameters and a plurality of candidate resource location distributions includes:

[0159] Determine the objective function and constraints based on the predicted player distribution parameters and the distributions of multiple candidate resource locations;

[0160] Through the dynamic programming algorithm, perform iterative calculations on the resource distribution plan based on the objective function and constraints until the optimal solution is obtained, and obtain the optimal resource distribution in the target game area.

[0161] It can be seen that through the above optional embodiments, it is possible to construct the objective function and constraints based on the predicted player distribution parameters and the distributions of multiple candidate resource locations, and perform iterative optimization through the dynamic programming algorithm to calculate the optimal resource distribution in the target game area, so as to dynamically adjust the resource placement according to the player distribution trend, improve the resource utilization rate, optimize the player interaction experience, and enhance the fairness and strategic nature of the game environment.

[0162] As an optional embodiment, the objective function includes:

[0163] The average value of the second similarity between the resource distribution plan and each candidate resource location distribution reaches the maximum;

[0164] The distribution uniformity corresponding to the resource distribution plan reaches the minimum; optionally, the distribution uniformity is obtained by performing calculations on the resource locations and resource quantities of multiple deployed resources in the resource distribution plan through a spatial distribution uniformity algorithm;

[0165] The constraints include:

[0166] The position distance between the resource location of each deployed resource in the resource distribution plan and the position of the nearest player group in the predicted player distribution parameters is less than the distance threshold;

[0167] The resource quantity of each deployed resource in the resource distribution plan is less than the average resource quantity corresponding to the predicted player distribution parameters; optionally, the average resource quantity is the product of the average value of the player group quantities of all player groups in the predicted player distribution parameters and a preset ratio parameter;

[0168] The resource quantity of the deployed resources in the area corresponding to the player group activity area in the resource distribution plan is greater than a preset quantity threshold.

[0169] Optionally, the spatial distribution uniformity algorithm can be obtained by calculating the similarity between multiple deployed resources in the resource distribution plan and a preset uniform distribution plan. For example, a uniform distribution plan stipulates the positions and quantities of different deployed resources. Calculate the position distance and quantity difference between each deployed resource in the resource distribution plan and the nearest deployed resource in the uniform distribution plan, and perform weighted summation to obtain a discrimination parameter. Then, calculate the reciprocal of this discrimination parameter to obtain the distribution uniformity. Optionally, a trained uniformity recognition algorithm model can be used to directly recognize the uniformity of the resource distribution plan.

[0170] It can be seen that through the above optional embodiments, the constructed objective function takes into account the similarity and distribution uniformity between the resource distribution plan and the candidate resource distribution plan, while the constraint conditions ensure that the resource distribution plan conforms to the spatial distribution characteristics and resource requirements of the player group, thereby improving the accuracy and rationality of resource placement, optimizing the fairness and strategy of the game environment, and enhancing the player's gaming experience.

[0171] Embodiment III

[0172] Please refer to Figure 3 , Figure 3 which is another game resource position determination system based on multi-role historical data disclosed in the embodiments of the present invention. Figure 3 The described game resource position determination system based on multi-role historical data is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the game resource position determination system based on multi-role historical data may include:

[0173] A memory 301 storing executable program code;

[0174] A processor 302 coupled to the memory 301;

[0175] Among them, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the game resource position determination method described in Embodiment I.

[0176] Embodiment IV

[0177] The embodiments of the present invention disclose a computer-readable storage medium that stores a computer program for electronic data exchange. Among them, the computer program causes a computer to execute the steps of the game resource position determination method described in Embodiment I.

[0178] Embodiment V

[0179] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the method for determining the location of game resources based on multi-role historical data described in the first embodiment.

[0180] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be in the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0181] The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0182] For convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit may be implemented in one or more software and / or hardware.

[0183] Those skilled in the art should understand that the embodiments of this specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0184] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 means for the functions specified in one or more processes and / or blocks Figure 1 or multiple blocks.

[0185] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions in the process Figure 1 one or more processes and / or blocks Figure 1 or the functions specified in multiple blocks.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide means for implementing the functions in the process Figure 1 one or more processes and / or blocks Figure 1 or the steps of the functions specified in multiple blocks.

[0187] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0188] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0189] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0190] It should also be noted that the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0191] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0192] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar among the embodiments, reference may be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, they are described relatively simply, and reference may be made to the relevant parts of the method embodiments for the related content.

[0193] Finally, it should be noted that: what is disclosed in a method and system for determining the location of game resources based on multi-role historical data disclosed in the embodiments of the present invention is only the preferred embodiments of the present invention, and is only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some 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 invention.

Claims

1. A method for determining the location of game resources based on multi-role historical data, characterized in that, The method includes: Obtaining historical play data of multiple game players in a target game area; Determining predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm, including: Grouping the historical play data according to the obtained historical time periods to obtain play data sets corresponding to multiple different historical time periods; Inputting each of the play data sets into the player distribution recognition algorithm model to obtain player distribution parameters corresponding to each of the play data sets; the player distribution recognition algorithm model is trained by a training data set including multiple training play data and corresponding player distribution parameter annotations; the player distribution parameters include the group position, group quantity, moving direction, moving speed, frequently active area, and internal player density of at least one player group; Analyzing the time-varying law corresponding to the player distribution parameters corresponding to all the play data sets to obtain predicted player distribution parameters of the target game area in a future time period; Determining multiple candidate resource location distributions according to the area parameters of the target game area, including: Matching multiple matching resource distribution schemes with all or partially identical parameters in a historical resource distribution database according to the area parameters of the target game area; For each of the matching resource distribution schemes, obtaining the historical player complaint records and player play data corresponding to the historical application period of the matching resource distribution scheme; Calculating a first similarity between the player play data and all the historical play data; Inputting the historical player complaint records into a resource-related complaint recognition algorithm model to obtain a resource-related complaint ratio corresponding to the historical player complaint records; the resource-related complaint recognition algorithm model is trained by a training data set including multiple training player complaint records and corresponding resource-related complaint annotations; Calculating the product of the first similarity and the resource-related complaint ratio to obtain the priority of the matching resource distribution scheme; Filtering out the matching resource distribution schemes with all the priorities greater than a priority threshold to obtain multiple candidate resource location distributions; Determining the optimal resource distribution of the target game area according to the predicted player distribution parameters and the multiple candidate resource location distributions.

2. The method for determining the location of game resources based on multi-role historical data according to claim 1, wherein The historical play data includes at least one of the game operations, game routes, game positions, game-triggered storylines, game-executed tasks, and game character information of the game players in the historical time period.

3. The method for determining the location of game resources based on multi-role historical data according to claim 1, wherein The analyzing the time-varying law corresponding to the player distribution parameters corresponding to all the play data sets to obtain the predicted player distribution parameters of the target game area in a future time period includes: Sorting the player distribution parameters of the player groups in all the player distribution parameters from early to late according to the corresponding historical time periods to obtain a player distribution parameter sequence; Input the sequence of the player distribution parameters into the trained LSTM neural network to obtain the predicted player distribution parameters of the target game area in a future time period; the predicted player distribution parameters include player group position parameters, player group quantity parameters, and player group activity areas; the LSTM neural network is trained by a training data set including a plurality of training player distribution parameters sorted over time.

4. The method for determining the location of game resources based on multi-role historical data according to claim 1, wherein The area parameters include at least one of area shape, area area, area position, tasks within the area, trigger plots within the area, and NPC characters within the area.

5. The method for determining the location of game resources based on multi-role historical data according to claim 1, wherein Determining the optimal resource distribution of the target game area according to the predicted player distribution parameters and the plurality of candidate resource location distributions includes: Based on the predicted player distribution parameters and the plurality of candidate resource location distributions, determine an objective function and constraints; Through a dynamic programming algorithm, perform iterative calculations on the resource distribution plan based on the objective function and constraints until it is optimal, to obtain the optimal resource distribution of the target game area.

6. The method for determining the location of game resources based on multi-role historical data according to claim 5, wherein The objective function includes: The average of the second similarities between the resource distribution plan and each of the candidate resource location distributions reaches the maximum; The distribution uniformity corresponding to the resource distribution plan reaches the minimum; the distribution uniformity is obtained by performing calculations on the resource positions and resource quantities of multiple arranged resources in the resource distribution plan through a spatial distribution uniformity algorithm; The constraints include: The position distance between the resource position of each arranged resource in the resource distribution plan and the position of the nearest player group in the predicted player distribution parameters is less than a distance threshold; The resource quantity of each arranged resource in the resource distribution plan is less than the average resource quantity corresponding to the predicted player distribution parameters; the average resource quantity is the product of the average of the player group quantities of all player groups in the predicted player distribution parameters and a preset ratio parameter; The resource quantity of the arranged resources within the area corresponding to the player group activity area in the predicted player distribution parameters is greater than a preset quantity threshold.

7. A game resource location determination system based on multi-role historical data, characterized in that, The system includes: An acquisition module, configured to acquire historical play data of a plurality of game players in a target game area; A first determination module, configured to determine the predicted player distribution parameters of the target game area according to the historical play data and a prediction algorithm, including: Group the historical play data according to the acquired historical time periods to obtain play data sets corresponding to a plurality of different historical time periods; Input each of the play data sets into the player distribution recognition algorithm model to obtain the player distribution parameters corresponding to each of the play data sets; the player distribution recognition algorithm model is trained by a training data set including a plurality of training play data and corresponding player distribution parameter annotations; the player distribution parameters include the group position, group quantity, moving direction, moving speed, frequent activity area, and internal player density of at least one player group; Analyze the variation law over time corresponding to the player distribution parameters corresponding to all the play data sets to obtain the predicted player distribution parameters of the target game area in a future time period. A second determination module, configured to determine a plurality of candidate resource location distributions according to the regional parameters of the target game area, including: Matching, in a historical resource distribution database, a plurality of matching resource distribution schemes with all or some of the parameters being the same according to the regional parameters of the target game area; For each of the matching resource distribution schemes, obtaining the corresponding historical player complaint records and player play data during the historical application period of the matching resource distribution scheme; Calculating a first similarity between the player play data and all the historical play data; Inputting the historical player complaint records into a resource-related complaint recognition algorithm model to obtain a resource-related complaint ratio corresponding to the historical player complaint records; the resource-related complaint recognition algorithm model is trained by a training data set including a plurality of training player complaint records and corresponding resource-related complaint annotations; Calculating the product of the first similarity and the resource-related complaint ratio to obtain the priority of the matching resource distribution scheme; Filtering out the matching resource distribution schemes with all the priorities greater than a priority threshold to obtain a plurality of candidate resource location distributions; A third determination module, configured to determine an optimal resource distribution of the target game area according to the predicted player distribution parameters and the plurality of candidate resource location distributions.

8. A game resource location determination system based on multi-role historical data, characterized in that, The system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the game resource location determination method based on multi-role historical data according to any one of claims 1-6.

Images