Game control method and device, medium, program product and electronic equipment

Abstract

The invention relates to the technical field of computers, and provides a game control method, a game control device, a computer readable storage medium, a computer program product and electronic equipment. The game control method comprises the following steps: generating a to-be-simulated virtual resource acquisition container according to virtual resource acquisition configuration of a game; determining a first target operation feature for performing a selection operation in the to-be-simulated virtual resource acquisition container; inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the to-be-simulated virtual resource acquisition container; performing virtual resource selection simulation on the to-be-simulated virtual resource acquisition container according to the first prediction probability until a game simulation stop condition is met, and obtaining a game simulation result; and based on the game simulation result, adjusting the virtual resource acquisition configuration to determine a target virtual resource acquisition configuration. According to the scheme, the determination efficiency and accuracy of the game configuration can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a game control method, a game control device, a computer-readable storage medium, a computer program product, and an electronic device. Background Art

[0002] At present, in order to attract traffic or increase user activity, companies will carry out promotional activities for users. In promotional activities, companies or brands can design games for obtaining virtual resources to attract users to participate in the promotion. For example, such games allow users to exchange points for opportunities to select virtual resources, and then perform selection operations in the virtual resource acquisition container. According to the virtual resource acquisition configuration, virtual resources, such as game props, are issued for the user's selection operation.

[0003] The virtual resource acquisition configuration will affect the user's virtual resource acquisition. If the virtual resources are too difficult to obtain or the virtual value of the obtained virtual resources is relatively low, it will affect the user's enthusiasm and fail to achieve the purpose of promotion. However, it is also impossible to distribute virtual resources to users without limit. Therefore, how to accurately and efficiently determine the virtual resource acquisition configuration to assist the smooth progress of promotional activities is a technical problem that urgently needs to be solved.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a game control method, a game control device, a computer-readable storage medium, a computer program product and an electronic device, thereby improving the accuracy and efficiency of determining the virtual resource acquisition configuration at least to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to a first aspect of the present disclosure, a game control method is provided, comprising: generating a to-be-simulated virtual resource acquisition container according to an initial virtual resource acquisition configuration of a game, wherein the to-be-simulated virtual resource acquisition container comprises a preset number of selection opportunities, each selection opportunity corresponding to an obtainable virtual resource; determining a first target operation feature for performing a selection operation in the to-be-simulated virtual resource acquisition container according to the virtual resources in the to-be-simulated virtual resource acquisition container; inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the to-be-simulated virtual resource acquisition container; performing a virtual resource selection simulation on the to-be-simulated virtual resource acquisition container according to the first prediction probability until a game simulation stop condition is met to obtain a game simulation result; and adjusting the virtual resource acquisition configuration based on the game simulation result to determine a target virtual resource acquisition configuration.

[0008] In an optional embodiment, the virtual resource selection simulation is performed on the virtual resource acquisition container to be simulated according to the first predicted probability until the game simulation stop condition is met, and the game simulation result is obtained, which includes: in response to the first predicted probability indicating a selection operation, controlling the virtual resource acquisition container to be simulated to perform a selection operation simulation to acquire virtual resources; updating the first target operation feature according to the virtual resources in the virtual resource acquisition container to be simulated and the acquired virtual resources; inputting the updated first target operation feature into a pre-trained selection operation prediction model, and again obtaining the first predicted probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; repeating the above process until the game simulation stop condition is met, and the game simulation result is obtained; wherein, the game simulation stop condition includes: in response to the first predicted probability, determining to indicate to stop the selection operation or the number of simulations of the selection operation reaches the preset number.

[0009] In an optional embodiment, updating the first target operation characteristic according to the virtual resources in the virtual resource acquisition container to be simulated and the virtual resources that have been acquired includes: determining the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated according to all virtual resources in the virtual resource acquisition container to be simulated; determining the characteristics of currently acquired virtual resources according to the currently acquired virtual resources; obtaining the remaining virtual resources in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated and all virtual resources that have been acquired, and determining the resource value distribution characteristics of the remaining virtual resources; updating the first target operation characteristic according to at least one of the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of currently acquired virtual resources, and the resource value distribution characteristics of the remaining virtual resources.

[0010] In an optional embodiment, determining the first target operation characteristics for performing a selection operation in the virtual resource acquisition container to be simulated based on the virtual resources in the virtual resource acquisition container to be simulated includes: determining the first target operation characteristics for performing a selection operation for the first time in the resource acquisition container to be simulated based on the resource value distribution characteristics of all virtual resources in the virtual resource acquisition container to be simulated.

[0011] In an optional embodiment, the game simulation result includes: the total amount of virtual resources acquired when the game simulation stops and the number of simulations of the selection operation; adjusting the virtual resource acquisition configuration based on the game simulation result to determine the target virtual resource acquisition configuration includes: adjusting the virtual resource acquisition configuration based on the total amount of virtual resources acquired, the number of simulations of the selection operation and the preset virtual resource quota to determine the target virtual resource acquisition configuration.

[0012] In an optional embodiment, the preset virtual resource quota includes a preset total amount of virtual resources and a preset number of selection operations, and the adjusting the virtual resource acquisition configuration based on the acquired total amount of virtual resources, the simulation number of the selection operation and the preset virtual resource quota to determine the target virtual resource acquisition configuration includes: adjusting the virtual resource acquisition configuration when the difference between the acquired total amount of virtual resources and the preset virtual total amount is greater than a first preset value, and the simulation number of the selection operation is less than the preset number of selection operations; regenerating the virtual resource acquisition container to be simulated according to the adjusted virtual resource acquisition configuration; re-performing virtual resource selection simulation based on the adjusted virtual resource acquisition configuration, the regenerated virtual resource acquisition container to be simulated, and the pre-trained selection operation prediction model until the difference between the acquired total amount of virtual resources and the preset virtual total amount is less than or equal to the first preset value, and the simulation number of the selection operation is greater than or equal to the preset number of selection operations, and determining the currently adjusted virtual resource acquisition configuration as the target virtual resource acquisition configuration.

[0013] In an optional embodiment, the method for determining the pre-trained selection operation prediction model includes: obtaining training samples and sample labels corresponding to the training samples, the training samples are determined according to a historical virtual resource acquisition container, and the sample labels are determined according to whether a selection operation is performed in the historical virtual resource acquisition container, wherein each historical virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; based on the virtual resource information in the historical virtual resource acquisition container, determining the sample operation characteristics of the selection operation performed in the historical virtual resource acquisition container; inputting the sample operation characteristics into the selection operation prediction model to be trained to obtain a prediction result of whether a selection operation is performed in the historical virtual resource acquisition container; determining the training loss value of the selection operation model to be trained based on the degree of difference between the prediction result and the sample label; iteratively training the selection operation model to be trained based on the training loss value until a training stop condition is met to obtain the pre-trained selection operation prediction model; wherein the training stop condition includes: the training loss value is less than a preset loss value, or the number of iterative training reaches a preset number of iterations.

[0014] According to a second aspect of the present disclosure, a game control device is provided, including: a module for generating a virtual resource acquisition container to be simulated, configured to generate a virtual resource acquisition container to be simulated according to an initial virtual resource acquisition configuration of a game, wherein the virtual resource acquisition container to be simulated includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; a module for determining a first target operation feature, configured to determine a first target operation feature for performing a selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated; a selection operation prediction module, configured to input the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; a selection simulation module, configured to perform a virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first prediction probability until a game simulation stop condition is met to obtain a game simulation result; and a virtual resource acquisition configuration adjustment module, configured to adjust the virtual resource acquisition configuration based on the game simulation result to determine a target virtual resource acquisition configuration.

[0015] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the game control method of the first aspect of the above embodiment is implemented.

[0016] According to a fourth aspect of the present disclosure, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the steps of the game control method as described in the first aspect.

[0017] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the game control method as described in the first aspect of the above embodiment.

[0018] It can be seen from the above technical solutions that the game control method, game control device, and computer program product and electronic device implementing the game control method in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:

[0019] In the technical solutions provided by some embodiments of the present disclosure, a virtual resource acquisition container to be simulated can be generated according to the virtual resource acquisition configuration, and then a virtual resource selection simulation can be automatically performed according to the pre-trained selection operation prediction model and the first target operation characteristics of the selection operation determined in the virtual resource acquisition container to be simulated, so as to adjust the virtual resource acquisition configuration according to the simulation results until the target virtual resource acquisition configuration is obtained. Compared with the related art, on the one hand, the present disclosure can perform game simulation of virtual resource acquisition games through the virtual resource acquisition configuration and the selection operation prediction model, and determine the final virtual resource acquisition configuration according to the simulation results, thereby improving the accuracy of the virtual resource acquisition configuration determination in the game based on the game simulation method; on the other hand, the present disclosure can determine the virtual resource acquisition configuration in the game without human participation, thereby assisting the game design through the determined virtual resource acquisition configuration, and improving the design efficiency of the game.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0022] Figure 1 A schematic diagram showing an exemplary system architecture to which embodiments of the present disclosure may be applied;

[0023] Figure 2A flowchart showing a game control method in an exemplary embodiment of the present disclosure is shown;

[0024] Figure 3 A schematic flow chart showing a method for determining the number of virtual resource acquisition containers to be simulated in an exemplary embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram showing a flow chart of a method for training a selection operation prediction model in an exemplary embodiment of the present disclosure;

[0026] Figure 5 A schematic flow chart showing a method for obtaining a game simulation result in an exemplary embodiment of the present disclosure;

[0027] Figure 6 A schematic flow chart showing a method for updating a first target operating characteristic in an exemplary embodiment of the present disclosure;

[0028] Figure 7 A schematic flow chart showing an interactive process during a virtual resource selection simulation in an exemplary embodiment of the present disclosure;

[0029] Figure 8 A flow chart showing a method for determining target virtual resource acquisition configuration in an exemplary embodiment of the present disclosure;

[0030] Fig. 9 A schematic diagram showing the composition of a game control device in an exemplary embodiment of the present disclosure;

[0031] Fig.10 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0033] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0034] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0035] In the related art, artificial experience is relied upon to determine the virtual resource acquisition configuration of virtual resource acquisition games according to historical game situations and historical game virtual resource acquisition configurations, thereby designing virtual resource acquisition games.

[0036] However, manually determining the configuration of virtual resource acquisition is inefficient and its accuracy is difficult to guarantee.

[0037] In order to solve the above problems, the present invention provides a game control method and device, which can be applied to Figure 1 In the system architecture of the exemplary application environment shown.

[0038] like Figure 1 As shown, the system architecture 100 may include a terminal device 110 and a server 120. The terminal device 110 may be a terminal device such as a smart phone, a tablet computer, a desktop computer, a laptop computer, a smart wearable device, etc. The server 120 generally refers to a background system that provides related services of the game control method in this exemplary embodiment, and may be a server or a cluster formed by multiple servers. The terminal device 110 and the server 120 may be connected via a wired or wireless communication link to perform data exchange.

[0039] In an exemplary embodiment, the game control method described above can be executed by the terminal device 110. Accordingly, the game control device can be set in the terminal device 110 to implement the corresponding module functions. For example, a virtual acquisition container to be simulated can be generated in the terminal device 110 according to the initial virtual resource acquisition configuration of the game, and then the first target operation feature of the selection operation in the virtual resource acquisition container to be simulated is determined according to the virtual resources in the virtual resource acquisition container to be simulated, and the first target operation feature is input into the pre-trained selection operation prediction model to perform virtual resource selection simulation until the game simulation stop condition is met, and the initial virtual resource acquisition configuration is adjusted according to the obtained game simulation result, and the above process is repeated until the target preset condition is met and the target virtual resource configuration is determined.

[0040] In an exemplary embodiment, the game control method described above can be executed by the server 120. Accordingly, the game control device can be set in the server 120 to implement the corresponding module functions. For example, the server 120 can generate a virtual acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game, and then determine the first target operation feature of the selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated, and input the first target operation feature into the pre-trained selection operation prediction model to perform virtual resource selection simulation until the game simulation stop condition is met, and adjust the initial virtual resource acquisition configuration according to the obtained game simulation result, and repeat the above process until the target preset condition is met and the target virtual resource configuration is determined.

[0041] It should be understood that Figure 1 The number of terminal devices and servers in the example is only illustrative. Any number of terminal devices and servers may be provided as required. For example, the server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0042] Figure 2 A flowchart of a game control method in an exemplary embodiment of the present disclosure is shown. Figure 2 , the method comprising:

[0043] Step S210, generating a virtual resource acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game;

[0044] Step S220, determining a first target operation feature for performing a selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated;

[0045] Step S230, inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated;

[0046] Step S240, performing virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first predicted probability until a game simulation stop condition is met, thereby obtaining a game simulation result;

[0047] Step S250: adjusting the virtual resource acquisition configuration based on the game simulation result to determine the target virtual resource acquisition configuration.

[0048] exist Figure 2 In the technical solution provided by the illustrated embodiment, a virtual resource acquisition container to be simulated can be generated according to the virtual resource acquisition configuration, and then a virtual resource selection simulation can be automatically performed according to the pre-trained selection operation prediction model and the determined first target operation characteristics of the selection operation in the virtual resource acquisition container to be simulated, thereby adjusting the virtual resource acquisition configuration according to the simulation results until the target virtual resource acquisition configuration is obtained. Compared with the related art, on the one hand, the present disclosure can perform game simulation of virtual resource acquisition games through the virtual resource acquisition configuration and the selection operation prediction model, and determine the final virtual resource acquisition configuration according to the simulation results, thereby improving the accuracy of the virtual resource acquisition configuration determination in the game based on the game simulation method; on the other hand, the present disclosure can determine the virtual resource acquisition configuration in the game without human participation, thereby assisting the game design through the determined virtual resource acquisition configuration, thereby improving the design efficiency of the game.

[0049] Next, the specific implementation method of step S210, generating a virtual resource acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game, is described in detail.

[0050] In an optional implementation, the to-be-simulated virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource.

[0051] In an exemplary application scenario, a resource acquisition container to be simulated may be generated according to the initial virtual resource acquisition configuration of the game.

[0052] For example, in a scenario where a user consumes points to exchange for a virtual resource selection opportunity, and then performs a selection operation in a virtual resource acquisition container based on the selection opportunity, and then determines the virtual resource corresponding to the user's selection operation based on the game's virtual resource acquisition configuration, such as mobile network traffic, for each user, a selection operation can be performed in a virtual resource acquisition container with the same available access, so as to obtain the virtual resource corresponding to the selection operation based on the virtual resource acquisition configuration. At this time, for different users, the virtual resource acquisition container can be the same, so a virtual resource acquisition container to be simulated can be generated. In subsequent steps, when performing a virtual resource selection simulation, multiple virtual accounts with different points can be set, and virtual resource selection simulation can be performed based on the virtual account and the virtual resource to be simulated.

[0053] In another exemplary application scenario, a plurality of virtual resource acquisition containers to be simulated may be generated according to the initial virtual resource acquisition configuration of the game.

[0054] For example, in a scenario where a game player redeems a virtual resource selection opportunity with game points, and then performs a selection operation in a virtual resource acquisition container based on the selection opportunity, and then determines the virtual resource corresponding to the game player's selection operation based on the game's virtual resource acquisition configuration, such as a game prop, at this time, for different users, the virtual resources in the virtual resource acquisition container may be different. Therefore, in this scenario, multiple different virtual resource acquisition containers to be simulated may be generated based on the virtual resource acquisition configuration. Then, in subsequent steps, virtual resource selection simulation is performed based on the multiple different resource acquisition containers to be simulated.

[0055] That is to say, in the actual game process of the game disclosed in the present invention, the available virtual resources in the virtual resource acquisition container issued to different users can be the same or different. For example, if the corresponding selection opportunities of the virtual resource acquisition container are 9 times, the virtual resource acquisition container issued to different users may include 9 identical available virtual resources, but each selection operation generates corresponding virtual resources for different users from the 9 available virtual resources according to the virtual resource acquisition configuration. Continuing to take the corresponding selection opportunities in the virtual resource acquisition container as 9 times as an example, the virtual resource acquisition container issued to different users may include 9 completely different or not completely the same virtual resources. Based on this, when simulating the game, the corresponding virtual resource acquisition container to be simulated can also be generated according to the virtual resource acquisition configuration according to the actual game situation.

[0056] In an optional implementation, in the actual game process of the present disclosure, the selection opportunities and obtainable virtual resources included in the virtual resource acquisition container are known to the user. For example, if the virtual resource acquisition container includes 9 selection opportunities, the user knows which 9 virtual resources are included in the virtual resource acquisition container, but in each selection operation, the virtual resource obtained by the user's current selection operation is determined from the 9 virtual resources according to the virtual resource acquisition configuration.

[0057] In an optional implementation, when there are multiple virtual resource acquisition containers to be simulated, the selection opportunity of each virtual resource acquisition container to be simulated may be the same or different, and this exemplary implementation does not specifically limit this.

[0058] In an optional implementation, the virtual resource acquisition configuration is generated by the game designer. The virtual resource acquisition configuration may include information such as the selection opportunities included in the virtual resource acquisition container, the available virtual resources, and the probability of the user selecting each virtual resource. It can be customized according to the game requirements, and this exemplary implementation does not specifically limit this.

[0059] When the generated virtual resource acquisition container to be simulated includes multiple ones, Figure 3 The method shown in FIG. 1 determines the number of virtual resource acquisition containers to be generated for simulation. Figure 3 A flow chart showing a method for determining the number of virtual resource acquisition containers to be simulated in an exemplary embodiment of the present disclosure is shown.

[0060] In step S310, a candidate number of first virtual resource acquisition containers are generated according to historical virtual resource acquisition configurations in historical games.

[0061] In an exemplary implementation, the historical virtual resource acquisition configuration in the historical game may be obtained based on the virtual resource acquisition configuration in the virtual resource acquisition game corresponding to the ended promotional activity.

[0062] In an exemplary embodiment, the number of candidates can be customized according to experience or demand, or can be randomly determined, such as randomly determining the number of candidates to be 3000, etc., which is not specifically limited in this exemplary embodiment. For example, 3000 first virtual resource acquisition containers can be generated according to the historical game acquisition configuration.

[0063] Next, in step S320, selection operation simulation is performed on each candidate number of first virtual resource acquisition containers based on the pre-trained selection operation prediction model until each first virtual resource acquisition container meets the game simulation stop condition, thereby obtaining game simulation results for the candidate number of first virtual resource acquisition containers.

[0064] For example, for each first virtual resource acquisition container, the second target operation feature can be determined based on the virtual resources in the first virtual resource acquisition container, and then the second target operation feature can be input into the pre-trained virtual resource acquisition container to obtain a prediction result of whether a selection operation is performed in the first virtual resource acquisition container. If the prediction result is to perform a selection operation in the first virtual resource acquisition container, the virtual resource corresponding to the current selection operation is determined based on the historical virtual resource acquisition configuration. Then, based on information such as the virtual resource corresponding to the current selection operation, the remaining virtual resources in the first virtual resource acquisition container, and all virtual resources included in the first virtual resource acquisition container, the second target operation feature is updated, and the updated second target operation feature is input into the pre-trained selection operation prediction model again to obtain a prediction result of whether a selection operation is performed in the first virtual resource acquisition container.

[0065] If the prediction result is to perform a selection operation in the first virtual resource acquisition container, the virtual resource corresponding to the current selection operation is determined according to the historical virtual resource acquisition configuration, and the above-mentioned prediction process of whether to perform the selection operation is repeated until the prediction result indicates to stop selecting in the first virtual resource acquisition container or the number of selections in the first virtual resource acquisition container reaches a preset number, that is, all opportunities for selection in the first virtual resource acquisition container are used up, then it is determined that the simulation of the first virtual resource acquisition container is stopped.

[0066] It should be noted that the determination method and update method of the second target operation feature can refer to the determination method and update method of the first target operation feature described below. The determination method of the pre-trained selection operation prediction model will also be described in the following embodiments, and you can refer to the following embodiments.

[0067] When each first virtual resource acquisition container stops simulating, it is determined that the game simulation is ended, and the game simulation result can be obtained.

[0068] In an exemplary embodiment, the game simulation result may include the total amount of first virtual resources acquired in a candidate number of first virtual resource acquisition containers when the game simulation ends, and the first total number of selection operations performed in the candidate number of first virtual resource acquisition containers when the game simulation ends.

[0069] In step S330, determine whether the game simulation result meets the preset conditions, if yes, go to step S350, if not, go to step S340.

[0070] In an exemplary embodiment, the preset conditions are determined based on the total amount of first virtual resources acquired in a candidate number of first virtual resource acquisition containers at the end of the game simulation, the first total number of selection operations performed in a candidate number of first pseudo-virtual resource acquisition containers at the end of the game simulation, the total amount of second virtual resources acquired at the end of the historical game, and the second total number of selection operations performed at the end of the historical game.

[0071] For example, the preset condition may include that the difference between the first total amount of virtual resources and the second total amount of virtual resources is less than a certain threshold, and the first total number of times is greater than or equal to the second total number of times.

[0072] In step S340, the number of candidates is adjusted and the process returns to step S310.

[0073] For example, when the game simulation results of the current candidate number of first virtual resource acquisition containers do not meet the preset conditions, the candidate number can be adjusted, and then the above steps S310 to S320 are repeated to regenerate an adjusted candidate number of first virtual resource acquisition containers based on the historical virtual resource acquisition configuration, and then a virtual resource selection simulation is performed on the regenerated first virtual resource acquisition container to obtain the game simulation result again, and it is determined whether the re-obtained game simulation result meets the preset conditions. If not, the candidate number is continued to be adjusted, and the above process is repeated until the game simulation results of the current adjusted candidate number of first virtual resource acquisition containers meet the preset conditions. In step S350, the current adjusted candidate number is determined as the number of virtual resource acquisition containers to be simulated.

[0074] In an optional implementation, the number of candidates can be adjusted based on experience, such as if the total amount of the first virtual resource is much smaller than the total amount of the second virtual resource, the number of candidates can be increased, etc. Of course, how to adjust the number of candidates can also be determined in other ways, such as randomly generating the number of candidates each time, etc., and this exemplary implementation does not specifically limit this.

[0075] In step S350, the adjusted candidate quantity is determined as the quantity of virtual resource acquisition containers to be simulated.

[0076] For example, if the game simulation result does not meet the preset conditions, it means that the simulation effect of the current candidate number of first virtual resource acquisition containers is poor, which may cause the final target virtual resource acquisition configuration to be inaccurate, so the candidate number can be adjusted, and the game simulation can be re-performed according to the adjusted candidate number to obtain the game simulation result again. If the game simulation result meets the preset conditions, it means that the simulation effect of the current candidate number of first virtual resource acquisition containers is good, and the current candidate number can be used as the number of virtual resource acquisition containers to be simulated. For example, if the game simulation result of 5000 first virtual resource acquisition containers meets the preset conditions when the candidate number is 5000, 5000 virtual resource acquisition containers to be simulated can be generated according to the initial game resource acquisition configuration.

[0077] In an optional implementation, a candidate number of first virtual resource acquisition containers may be generated based on multiple historical virtual resource acquisition configurations, and then the average value of the game simulation results of the candidate number of first virtual resource acquisition containers generated based on each historical virtual resource acquisition configuration is determined to see whether the average value meets the preset conditions, thereby determining the candidate number. For example, for a candidate number of 3000, 3000 first virtual resource acquisition containers may be generated based on historical virtual resource acquisition configuration 1 to obtain game simulation result 1, and then 3000 first virtual resource acquisition containers may be generated based on historical virtual resource acquisition configuration 2 to obtain game simulation result 2, and then 3000 first virtual resource acquisition containers may be generated based on historical virtual resource acquisition configuration 3 to obtain game simulation result 3. Then, for the candidate number of 3000, the average value of game simulation result 1, game simulation result 2, and game simulation result 3 may be used as the game simulation result of the candidate number of 3000, and then it is determined whether the game simulation result meets the preset conditions to determine whether 3000 can be determined as the number of virtual resource acquisition containers to be obtained.

[0078] In this way, through multiple evaluations of historical virtual resource acquisition configurations and actual game results, the accuracy of determining the number of candidates can be improved, thereby assisting in improving the accuracy of determining the target virtual resource acquisition configuration.

[0079] In another exemplary embodiment, the number of virtual resource acquisition containers to be simulated may be determined according to the number of historical virtual resource acquisition containers in historical games.

[0080] For example, the number of virtual resource acquisition containers to be simulated may be determined based on the number of game accounts participating in the last three promotional activities or the average number of virtual resource acquisition containers that have undergone selection operations.

[0081] In another exemplary implementation, the number of virtual resource acquisition containers to be simulated may also be determined directly based on experience, and this exemplary implementation does not impose any characteristic limitation on this.

[0082] In an exemplary embodiment, when there is only one virtual resource acquisition container to be simulated, when simulation is performed based on multiple game accounts and the one virtual resource acquisition container, Figure 3 The number of simulated game accounts used for game simulation is determined in this way.

[0083] In an exemplary embodiment, the method of generating the virtual resource acquisition container to be simulated according to the virtual resource acquisition configuration can be consistent with the method of generating the virtual resource acquisition container for the user in the actual game. For example, if the probability of game prop 1 being selected is configured as 0.2 in the virtual resource acquisition configuration, when generating the virtual resource acquisition container to be simulated, the proportion of game prop 1 in the virtual resources in all the generated resource acquisition containers to be simulated can be 20%.

[0084] Next, a specific implementation method of step S220, determining the first target operation feature for performing a selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated, will be described in detail.

[0085] In an exemplary embodiment, the virtual resources in the virtual resource acquisition container to be simulated may include the selection opportunities and obtainable virtual resources included in the virtual resource acquisition container to be simulated. For example, the virtual resources in a virtual resource acquisition container to be simulated include: there are 9 selection opportunities, and the obtainable virtual resources included in these 9 selections are game props 1, game props 2, game props 3, 2x multiple rewards, 5x multiple rewards, 3x multiple rewards, rare game props 4, rare game props 5, and rare game props 6. Among them, the multiple reward can be understood as if the virtual resource generated by the current selection operation is a multiple virtual resource, and the number of game props generated next time will double when the selection operation continues in the virtual resource acquisition container to be simulated. For example, if the virtual resource determined by the current selection operation is a 5x multiple reward, and the virtual resource generated by the next selection operation is game props 2, the number of game props 2 generated by the next selection operation will increase by 5 times, that is, 6 game props 2.

[0086] For example, historical virtual resource acquisition data may be analyzed to determine factors that affect the user's next selection in the virtual resource acquisition container, and then based on the analysis results, determine the operational features that affect whether to perform a selection operation in the virtual resource acquisition container.

[0087] For example, the factors that influence whether a user performs a selection operation in a virtual resource acquisition container mainly include the initial virtual resources in the virtual resource acquisition container (i.e., all virtual resources included in the virtual resource acquisition container before any selection operation is performed), the virtual value information of the remaining virtual resources in the virtual resource acquisition container, and the probability of selecting special virtual resources, such as the probability of selecting multiple virtual resources and high-value virtual resources.

[0088] By analyzing historical virtual resource acquisition data, it is found that the higher the proportion of virtual resources with high virtual value in the virtual resource acquisition container, the higher the probability that the user will perform a re-selection operation in the virtual resource acquisition container. In other words, users have a clear preference for the ratio of virtual resources with high, medium, and low virtual values ​​in the virtual resource acquisition container. If the virtual value of the available virtual resources in the virtual resource acquisition container is obviously low, the virtual resource acquisition container may be directly discarded, that is, the user may not perform a selection operation in the virtual resource acquisition container.

[0089] By analyzing the relationship between the initial virtual resources of the virtual resource acquisition container and the number of selection operations performed by the user, it is found that virtual resource acquisition containers that have performed more than 6 selection operations are mainly concentrated in virtual resource acquisition containers containing virtual resources with high virtual value, while virtual resource acquisition containers with a high proportion of medium-value virtual resources are more likely to reach more than 4 selection operations than virtual resource acquisition containers with a high proportion of low-value virtual resources.

[0090] That is to say, the composition of the obtainable virtual resource value included in the virtual resource acquisition container is highly correlated with whether the user performs a selection operation in the virtual resource acquisition container. Therefore, the virtual value ratio of the obtainable virtual resources included in the virtual resource acquisition container (such as the number of high, medium, and low value rewards, etc.), and the virtual value distribution of the virtual resources included in the virtual resource acquisition container (such as total value, minimum value, maximum value, average value, etc.) can be used as operation features.

[0091] By analyzing the user's selection operation behavior, it is found that when the user receives a multiple reward according to the selection operation, there is a 98% probability that the user will perform the next selection operation. When the user selects a virtual resource with a high virtual value, there is a 97% probability that the user will stop selecting, and most virtual resource acquisition containers stop selecting for the second time. In other words, most virtual resource acquisition containers end the selection after performing two selection operations. Therefore, it can be determined that the virtual value of the currently selected virtual resource, the current number of selections, etc. are highly correlated with whether the user continues to perform the selection operation in the virtual resource acquisition container. Therefore, the operation characteristics can also include the virtual value information of the currently selected virtual resource (such as the virtual value of the virtual resource, the type of virtual resource, etc.) and the virtual value influence of the currently selected virtual resource (such as the total value of the currently accumulated selected virtual resources, etc.).

[0092] By analyzing the historical virtual resource selection operation behaviors of users, it is also found that after the initial virtual resources included in the virtual resource acquisition container are determined, no matter what the initial virtual value ratio of the virtual resources is, the higher the virtual value of the remaining virtual resources in the virtual resource acquisition container, the higher the probability that the user will continue to perform the selection operation in the virtual resource acquisition container. In other words, the virtual value of the remaining virtual resources in the virtual resource acquisition container has a greater impact on whether the user continues to perform the selection operation.

[0093] Based on this, through the aforementioned analysis, in an exemplary embodiment, the operational characteristics that affect whether to perform a selection operation in the virtual resource acquisition container may include one or more of the resource value distribution characteristics of all virtual resources in the virtual resource acquisition container, the currently acquired virtual resource characteristics of the virtual resource acquisition container, and the resource value distribution characteristics of the remaining virtual resources in the virtual resource acquisition container.

[0094] In an exemplary implementation, resource value distribution characteristics of all virtual resources in the to-be-simulated resource acquisition container may be determined based on all virtual resources in the to-be-simulated virtual resource acquisition container.

[0095] In an optional embodiment, the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated may include one or more of the ratio of virtual resources of different virtual values ​​in the virtual resource acquisition container to be simulated, the total virtual value of all virtual resources in the virtual resource acquisition container to be simulated, the highest value of the virtual value of all virtual resources included in the virtual resource acquisition container to be simulated, the lowest value and the average value of the virtual value of all virtual resources included in the virtual resource acquisition container to be simulated, the average value of the virtual value of virtual resources of the target type, the variance of the virtual value of virtual resources of the target type, and the number of virtual resources of the target type.

[0096] For example, the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated may include the number of virtual resources with high virtual value, medium virtual value, and low virtual value, the total virtual value of other virtual resources in the virtual resources contained in the virtual resource acquisition container to be simulated excluding multiple virtual resources, the total virtual value of virtual resources in the virtual resource acquisition container to be simulated (wherein, the virtual value of multiple virtual resources = (multiple of multiple virtual resources - 1) * the largest medium virtual value in the virtual resource library), the lowest virtual value, the highest virtual value, the average virtual value, the average value of high or ultra-high virtual resources, the value of virtual resources with medium virtual value, the virtual value variance of other virtual resources excluding multiple virtual resources, the largest multiple virtual resources, the number of virtual resources with ultra-high or high virtual value, the number of multiple rewards, the total multiples of multiple virtual resources, the number of 2- and 3-fold virtual resources, the number of 5-fold virtual resources, the number of 10- to 20-fold virtual resources, etc.

[0097] In an optional implementation, the current virtual resource characteristics may be determined based on the currently acquired virtual resources.

[0098] In an optional embodiment, the current virtual resource characteristics may include the number of selections currently being made in the virtual resource acquisition container to be simulated, the points required for the current selection operation, the virtual value of the virtual resources obtained by the current selection operation, the total accumulated multiple virtual resources, the virtual value of the virtual resources obtained by the current selection operation plus the multiple virtual resources (if the virtual resources obtained by the previous selection operation are multiple virtual resources, then the value is the virtual value of the virtual resources obtained by the current selection operation multiplied by the multiple virtual resources obtained by the previous selection operation; if the virtual resources obtained by the current selection operation are still multiple virtual resources, then the value is 0), the virtual value level of the virtual resources obtained by the current selection operation, whether the virtual resources obtained by the current selection operation are multiple virtual resources, the multiple value of the virtual resources obtained by the current selection operation (if they are not multiple virtual resources, the value is 1), the virtual value ranking of the virtual resources obtained by the current selection operation among all virtual resources in the virtual resource acquisition container to be simulated, the total points spent up to the current selection operation, the total virtual value of the virtual resources obtained up to the current selection operation, etc.

[0099] The method for determining the total multiple virtual resources currently accumulated includes: the sum of the multiple virtual resources obtained in the last selection operation and the multiple virtual resources obtained continuously before that. If the last selection operation is a non-multiple virtual resource, the value is 1. For example, if the last selection operation obtains a multiple virtual resource, the previous continuous multiple virtual resources are searched until they are no longer multiple virtual resources, and their multiples are accumulated. If the current selection operation is the 4th one, and the virtual resources obtained by the 3rd selection operation are "2 times", the virtual resources obtained by the 2nd selection operation are "4 times", and the virtual resources obtained by the 1st selection operation are non-multiple virtual resources, then the value is 2+4=6; if the virtual resources obtained by the 3rd selection operation are "2 times", the virtual resources obtained by the 2nd selection operation are non-multiple virtual resources, and the virtual resources obtained by the 1st selection operation are "4 times", then the value is 2; if the virtual resources obtained by the 3rd selection operation are non-multiple virtual resources, the virtual resources obtained by the 2nd selection operation are "2 times", and the virtual resources obtained by the 1st selection operation are "4 times", then the value is 1. If the first 3 selection operations all obtain multiple virtual resources, then the value is the sum of the multiples of the multiple virtual resources obtained in the 3 times.

[0100] In an optional implementation, the remaining virtual resources in the virtual resource acquisition container to be simulated can be obtained based on the virtual resources in the virtual resource acquisition container to be simulated and all the acquired virtual resources, and the resource value distribution characteristics of the remaining virtual resources can be determined.

[0101] For example, the remaining virtual resources in the virtual resource acquisition container to be simulated can be obtained based on the initial virtual resources in the virtual resource acquisition container to be simulated before the current selection operation and all the virtual resources that have been acquired, and then the resource value distribution characteristics of the remaining virtual resources can be determined based on the resource value information of the remaining virtual resources.

[0102] In an optional embodiment, the resource value distribution characteristics of the remaining virtual resources include: the number of remaining multiple virtual resources, the sum of the multiples of the remaining multiple virtual resources, the largest remaining multiple virtual resources, the number of remaining 2-fold and 3-fold virtual resources, the number of remaining 5-fold virtual resources, the number of remaining 10-fold to 20-fold virtual resources, the number of remaining high-value or ultra-high-value virtual resources, the average virtual value of the remaining high-value or ultra-high-value virtual resources, the average virtual value of the remaining medium-value virtual resources, the virtual values ​​of the remaining virtual resources, the total virtual value of the remaining virtual resources, the maximum value of the virtual values ​​of the remaining virtual resources, the average virtual value of the remaining virtual resources, the virtual value variance of the remaining virtual resources, and other information.

[0103] Exemplarily, an implementation of step S220 may include: determining the first target operation feature of the first selection operation in the virtual resource acquisition container to be simulated based on the resource value distribution feature of all virtual resources in the virtual resource acquisition container to be simulated. For example, whether the user performs a selection operation in the virtual resource acquisition container for the first time is determined based on all virtual resources included in the virtual resource acquisition container. That is, for the prediction of the first selection operation, the first target operation feature may include the resource value distribution feature of all virtual resources in the resource acquisition container to be simulated.

[0104] As for the Nth (N is greater than 1 and less than or equal to the preset number of times) selection operation, since the user has performed at least one selection operation, the operation characteristics for determining whether the user continues to perform the selection operation in the virtual resource acquisition container may include the above-mentioned: resource value distribution characteristics of all virtual resources in the virtual resource acquisition container, characteristics of currently acquired virtual resources in the virtual resource acquisition container, and resource value distribution characteristics of the remaining virtual resources in the virtual resource acquisition container.

[0105] Next, a specific implementation method of step S230, inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated, is described in detail.

[0106] For example, according to Figure 4 The model is trained in the manner shown to obtain a pre-trained selection operation prediction model. Figure 4 , the training method for selecting the operation prediction model may include steps S410 to S450. Among them:

[0107] In step S410, training samples and sample labels corresponding to the training samples are obtained.

[0108] In an optional embodiment, the training sample is determined based on a historical virtual resource acquisition container, and the sample label is determined based on whether a selection operation is performed in the historical virtual resource acquisition container, wherein each historical virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource.

[0109] For example, the training samples may include the behavioral data of the selection operation performed by the user in the historical virtual resource acquisition container in the historical game, such as the selection operation data of the user in the virtual resource acquisition container in the last three promotional activities can be used as the training samples, and the training sample label is whether the user performs the selection operation in the virtual resource acquisition container. For example, the current status of the virtual resources of the virtual resource acquisition container in the last three promotional activities can be used as the training data, and whether the user performs the selection operation under the current status of the virtual resources of the virtual resource acquisition container can be used as the sample label of the training data.

[0110] For example, in a historical game, if a user performs four selection operations in a virtual resource acquisition container, five training data can be generated. That is, when the user selects for the first time, the virtual resource status in the virtual resource acquisition container is 1, when the user selects for the second time, the virtual resource status in the virtual resource acquisition container is 2, when the user selects for the third time, the virtual resource status in the virtual resource acquisition container is 3, when the user selects for the fourth time, the virtual resource status in the virtual resource acquisition container is 4, and after the fourth selection is completed, the virtual resource status in the virtual resource acquisition container is 5. Among them, the sample labels of virtual resource status 1, virtual resource status 2, virtual resource status 3, and virtual resource status 4 are selection operations, and the sample label of virtual resource status 5 is no selection operation.

[0111] In step S420, based on the virtual resource information in the historical virtual resource acquisition container, sample operation features of the selection operation in the historical virtual resource acquisition container are determined.

[0112] For example, the sample operation characteristics of the selection operation in the historical virtual resource acquisition container can be determined according to the virtual resource information in the historical virtual resource acquisition container and the above-mentioned method of determining the operation characteristics.

[0113] That is to say, for the sample operation feature, the corresponding sample operation feature can also be determined according to whether it is the first time to perform the selection operation. That is, if it is the first selection operation, the virtual resource value distribution feature of all virtual resources in the historical virtual resource acquisition container can be determined according to all virtual resources included in the historical virtual resource acquisition container, thereby obtaining the sample operation feature. If it is a subsequent selection operation, the sample operation feature can be determined according to at least one of the resource value distribution feature of all virtual resources in the historical virtual resource acquisition container indicated by the training data, the current acquisition virtual resource feature, and the resource value distribution feature of the remaining virtual resources.

[0114] In step S430, the sample operation features are input into the selection operation prediction model to be trained to obtain a prediction result of whether a selection operation is performed in the historical virtual resource acquisition container.

[0115] For example, the sample operation feature may be input into a selection operation prediction model to be trained, and a prediction result of whether to perform a selection operation under the sample operation feature may be obtained through the selection operation prediction model to be trained.

[0116] In an optional embodiment, the selection operation prediction model to be trained in the present disclosure may include any machine learning model capable of prediction, such as a deep neural network, a convolutional neural network, a support vector machine, etc., and this exemplary embodiment does not specifically limit this.

[0117] In an exemplary embodiment, the function of the selection operation prediction model is to predict whether to perform a selection operation in the virtual resource acquisition container based on the selection operation characteristics. For example, the selection operation prediction model can be used to predict the probability of performing a selection operation in the virtual resource acquisition container, and the prediction result can be obtained based on the relationship between the probability and the probability threshold. For example, if the predicted probability is greater than the probability threshold, the prediction result is to perform a selection operation in the virtual resource acquisition container, otherwise, the prediction result is not to perform a selection operation in the virtual resource acquisition container.

[0118] In step S440, the training loss value of the selected operation model to be trained is determined according to the degree of difference between the prediction result and the sample label.

[0119] In an optional implementation, the degree of difference between the prediction result and the sample label may be measured by one or more of mean square error, mean absolute error, cross entropy, etc., which is not particularly limited in this exemplary implementation.

[0120] For example, the mean square error between the prediction result and the sample label can be calculated to obtain the training loss value of the selected operation model to be trained.

[0121] In step S450, the selection operation model to be trained is iteratively trained according to the training loss value until the training stop condition is met, thereby obtaining a pre-trained selection operation prediction model.

[0122] In an exemplary embodiment, the training stop condition includes: the training loss value is less than a preset loss value, or the number of iterative training reaches a preset number of iterations.

[0123] For example, after a certain iterative training is completed, the currently trained selection operation model can be evaluated using model evaluation indicators, such as accuracy, recall rate, etc. If the model evaluation indicators meet the requirements, the training is determined to be completed, and a pre-trained selection operation prediction model can be obtained. If the model evaluation indicators do not meet the requirements, the above steps S410 to S450 can be repeated and retrained until the model evaluation indicators of the selection operation model obtained after retraining meet the requirements, and the pre-trained selection operation prediction model can be obtained.

[0124] After obtaining the pre-trained selection operation prediction model, the selection operation simulation can be performed on the virtual resource acquisition container to be simulated based on the pre-trained selection operation model.

[0125] For example, the first target operation feature determined according to the virtual resource acquisition container to be simulated can be input into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated.

[0126] Next, the specific implementation method of step S240, performing virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first predicted probability until the game simulation stop condition is met to obtain the game simulation result, is described in detail.

[0127] Below, reference Figure 5 The specific implementation of step S240 is described. For example, Figure 5 A flowchart of a method for obtaining a game simulation result in an exemplary embodiment of the present disclosure is shown. Figure 5 , the method may include steps S510 to S540.

[0128] In step S510, in response to the first prediction probability indicating a selection operation, the virtual resource acquisition container to be simulated is controlled to perform a selection operation simulation to acquire virtual resources.

[0129] For example, when the first preset probability is greater than the above-mentioned probability threshold, it means that the first preset probability indicates that the virtual resource acquisition container to be simulated is performing a selection operation. At this time, the virtual resources obtained by the selection operation can be automatically generated based on the game mechanism according to the virtual resource acquisition configuration of the game.

[0130] In step S520, the first target operation characteristic is updated according to the virtual resources in the virtual resource acquisition container to be simulated and the acquired virtual resources.

[0131] For example, Figure 6 A flowchart of a method for updating a first target operating characteristic in an exemplary embodiment of the present disclosure is shown. Figure 6 , the method may include steps S610 to S640. Wherein: in step S610, according to all virtual resources in the virtual resource acquisition container to be simulated, the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated are determined; in step S620, according to the currently acquired virtual resources, the characteristics of the currently acquired virtual resources are determined; in step S630, according to the virtual resources in the virtual resource acquisition container to be simulated and all acquired virtual resources, the remaining virtual resources in the virtual resource acquisition container to be simulated are obtained, and the resource value distribution characteristics of the remaining virtual resources are determined; in step S640, according to at least one of the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of the currently acquired virtual resources, and the resource value distribution characteristics of the remaining virtual resources, the first target operation characteristics are updated.

[0132] Among them, the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of the currently acquired virtual resources, and the method for determining the resource value distribution characteristics of the remaining virtual resources have been explained in the aforementioned related content and will not be repeated here.

[0133] In other words, in an optional embodiment, the first target operation characteristic may include at least one of the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of the currently acquired virtual resources, and the resource value distribution characteristics of the remaining virtual resources.

[0134] For example, as mentioned above, when the selection operation simulation is performed for the first time in the virtual resource acquisition container to be simulated, since the selection operation has not yet been performed, there are no currently acquired virtual resources, and all the virtual resources in the virtual resource acquisition container to be simulated are the same as the remaining virtual resources, so the first target operation can be determined based on the resource value distribution characteristics of all the virtual resources in the resource acquisition container to be simulated.

[0135] When the user performs a selection operation in the virtual resource acquisition container, the remaining virtual resources in the virtual resource acquisition container change with the virtual resources obtained by each selection operation of the user, and each selection operation corresponds to the currently obtained virtual resources, and the current virtual resource characteristics can be determined. At this time, the first target operation characteristics can include the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of the currently obtained virtual resources, and the resource value distribution characteristics of the remaining virtual resources. However, all virtual resources in the virtual resource acquisition container to be simulated do not change with the user's selection operation, only the characteristics of the currently obtained virtual resources and the resource value distribution characteristics of the remaining virtual resources change with the user's selection operation. After the first selection is completed, when predicting whether to perform a selection operation in the virtual resource acquisition container to be simulated, the current virtual resource acquisition characteristics and the resource value distribution characteristics of the current remaining virtual resources can be re-determined, so as to update the first target operation characteristics according to the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the current virtual resource acquisition characteristics, and the resource value distribution characteristics of the current remaining virtual resources.

[0136] Next, in step S530, the updated first target operation feature is input into the pre-trained selection operation prediction model to obtain again the first prediction probability of whether the selection operation is performed in the virtual resource acquisition container to be simulated.

[0137] For example, after the first target operation feature is updated, the updated first target operation feature can be input again into the pre-trained selection operation prediction model to obtain the first prediction probability of whether to perform the selection operation in the virtual resource acquisition container to be simulated.

[0138] In step S530, determine whether the game simulation stop condition is met, if so, go to step S540, otherwise go to step S510.

[0139] In an optional embodiment, the game simulation stop condition may include: in response to the first prediction probability determining an instruction to stop the selection operation or the number of simulations of the selection operation reaches a preset number.

[0140] For example, the game simulation stop condition can be understood as the condition for stopping the selection operation simulation for each virtual resource acquisition container to be simulated, and can also be understood as the condition for stopping the selection operation for each simulated game account in the virtual resource acquisition container to be simulated. In other words, for each virtual resource acquisition container to be simulated, determining the condition for stopping the simulation of the virtual resource acquisition container to be simulated may include determining an indication to stop the selection operation in response to the first predicted probability or the number of simulations of the selection operation reaching a preset number. For example, if the selection opportunities of the virtual resource acquisition container to be simulated include 9 times, then when the first predicted probability is less than or equal to the above-mentioned probability threshold, it can be determined that the simulation is stopped in the virtual resource acquisition container to be simulated, or the current selection operation is the 9th selection operation performed in the virtual resource acquisition container to be simulated, then after the current selection operation ends, the selection simulation of the virtual resource acquisition container to be simulated stops.

[0141] After all the virtual resource acquisition containers to be simulated have stopped simulating, it can be determined that the game simulation is over. When the game simulation is over, the game simulation result can be obtained according to the simulation of the selection operation of the resource acquisition container to be simulated.

[0142] In step S540, the game simulation result is obtained.

[0143] In an exemplary embodiment, the game simulation result includes: the total amount of virtual resources acquired when the game simulation stops and the number of simulations of the selection operation.

[0144] As mentioned above, after all the virtual resource acquisition containers to be simulated have stopped simulating, it can be determined that the game simulation is over. At this time, the game simulation result can be determined based on the total amount of virtual resources selected in all the virtual resource acquisition containers to be simulated and the number of selection operations performed in all the virtual resource acquisition containers to be simulated when the game simulation ends. For example, there are a total of 5,000 virtual resource acquisition containers to be simulated, and a total of 14,999 selection operations have been performed in these 5,000 virtual resource acquisition containers to be simulated. Then the game simulation result can include: the total amount of virtual resources obtained by 14,999 selection operations, and the number of simulations of the selection operation is 14,999 times.

[0145] For example, taking a single virtual resource acquisition container to be simulated as an example, Figure 7 A flowchart showing an interactive process during a virtual resource selection simulation in an exemplary embodiment of the present disclosure is shown.

[0146] For example, the server 71 can generate a virtual resource acquisition container to be simulated according to the virtual resource acquisition configuration, determine the first target operation feature of the virtual resource acquisition container to be simulated, and then send the determined first target operation feature to the pre-trained selection operation prediction model 72. The selection operation prediction model 72 can take the first target operation feature as input, output a first prediction probability of whether the selection operation is performed in the virtual resource acquisition container to be simulated, and obtain a prediction result of whether the selection operation is performed in the virtual resource acquisition container to be simulated according to the relationship between the first prediction probability and the probability threshold, and send the prediction result to the server 71. The server 71 performs a selection simulation on the virtual resource acquisition container to be simulated according to the received prediction result. Specifically, if the prediction result is yes, the server 71 determines the virtual resources obtained by the current selection operation according to the game mechanism and the current virtual resource configuration of the game, and updates the first target operation feature according to the information such as the virtual resources obtained by the current operation, and sends the updated first target operation feature to the pre-trained selection operation prediction model 72 again, so as to predict the result of whether the selection operation is performed in the virtual resource acquisition container to be simulated again. After the prediction is completed, the prediction result is sent to the server 71 again. The above prediction process is repeatedly performed until the prediction result is no, or the number of selections in the to-be-simulated virtual resource acquisition container reaches a preset number, and then it is determined that the to-be-simulated virtual resource acquisition container stops selecting and simulating.

[0147] Next, a specific implementation method of step S250, adjusting the virtual resource acquisition configuration based on the game simulation result to determine the target virtual resource acquisition configuration, is described.

[0148] In an exemplary embodiment, as described above, the game simulation result includes: the total amount of virtual resources acquired and the number of simulated selection operations when the game simulation stops. That is, the game simulation result may include the total amount of virtual resources acquired and the number of selection operations performed in all virtual resource acquisition containers to be simulated when each virtual resource acquisition container to be simulated stops simulating.

[0149] For example, at the end of the game simulation, each virtual resource acquisition container to be simulated has been subjected to several selection operations during the selection operation simulation process, and the virtual resources obtained by each selection operation are determined, so the total amount of virtual resources obtained and the number of simulation times of the selection operation can be obtained based on this information.

[0150] Exemplarily, an exemplary implementation of step S250 may include: adjusting the virtual resource acquisition configuration based on the total amount of virtual resources acquired, the number of simulations of the selection operation, and a preset virtual resource quota to determine a target virtual resource acquisition configuration.

[0151] In an optional implementation, the preset virtual resource quota includes a preset total amount of virtual resources and a preset number of selection operations.

[0152] Based on this, the virtual resource acquisition configuration is adjusted based on the total amount of virtual resources acquired, the number of simulations of the selection operation, and the preset virtual resource quota to determine the implementation method of the target virtual resource acquisition configuration. Figure 8 Reference Figure 8 , an exemplary method for determining a target virtual resource acquisition configuration may include steps S810 to S830.

[0153] In step S810, when the difference between the total amount of virtual resources acquired and the preset total amount of virtual resources is greater than a first preset value, and the number of simulations of the selection operation is less than the preset number of selection operations, the virtual resource acquisition configuration is adjusted.

[0154] For example, the preset total amount of virtual resources may include the total amount of virtual resources issued to users in this promotion. When the total amount of virtual resources acquired is greater than the preset total amount of virtual resources and the difference with the preset total amount of virtual resources is greater than the first preset value, it means that the current virtual resource acquisition configuration makes it less likely that the user will extract virtual resources with higher virtual value. If the number of simulations of the selection operation is less than the preset number of selection operations, it means that the current virtual resource configuration makes the user's participation low and does not achieve the expected effect of the promotion. Therefore, the current virtual resource configuration can be adjusted.

[0155] In step S820, the virtual resource acquisition container to be simulated is regenerated according to the adjusted virtual resource acquisition configuration.

[0156] The specific implementation of step S820 may refer to the specific implementation of step S210 described above, and will not be described in detail here.

[0157] In step S830, the virtual resource selection simulation is performed again based on the adjusted virtual resource acquisition configuration, the regenerated virtual resource acquisition container to be simulated, and the pre-trained selection operation prediction model, until the difference between the total amount of virtual resources acquired and the preset virtual total amount is less than or equal to a first preset value, and the number of simulations of the selection operation is greater than or equal to the preset number of selection operations, and the currently adjusted virtual resource acquisition configuration is determined as the target virtual resource acquisition configuration.

[0158] For example, according to the adjusted virtual resource acquisition configuration and the pre-trained selection operation model, according to the implementation of the above-mentioned steps S220 to S240, the virtual resource selection simulation can be re-performed on the regenerated virtual resource acquisition container to be simulated to obtain the game simulation result again. Repeat this process until the difference between the total amount of virtual resources acquired in the re-obtained game simulation result and the preset virtual total amount is less than or equal to the first preset value, and the number of simulations of the selection operation is greater than or equal to the preset number of selection operations, then the currently adjusted virtual resource configuration is determined as the target virtual resource configuration.

[0159] For example, when the difference between the total amount of virtual resources obtained and the preset total amount of virtual resources is less than the first preset value and the number of simulations of the selection operation is greater than or equal to the preset number of selection operations, it means that the current virtual resource configuration makes the difference between the total amount of virtual resources obtained by the user and the preset total amount of virtual resources not much, and the user's participation is high, so the virtual resource configuration can be used in actual promotional activities to realize promotional games.

[0160] Exemplarily, as mentioned above, the present disclosure can be applied to user points redemption selection opportunities, thereby distributing virtual resources, such as mobile phone traffic, game props, etc. In this scenario, the preset virtual resource quota can also include a preset total amount of redemption points. The preset total amount of redemption points can be understood as the total amount of points that can be redeemed by all users in this promotion. Among them, when points are used to redeem selection opportunities, the points required for each selection opportunity can be the same or different. For example, as the number of selection opportunities increases, the points required to be spent also increase. For example, the first selection opportunity requires 1 point to redeem, the second selection opportunity requires 2 points to redeem, and the third selection opportunity requires 4 points to redeem, etc.

[0161] In this scenario, when the difference between the total points spent on all virtual resource selection simulation operations at the end of the game simulation and the preset total redemption points is less than or equal to the second preset value, and the difference between the total amount of virtual resources acquired and the preset virtual total amount is less than or equal to the first preset value, and the number of simulations of the selection operation is greater than or equal to the preset number of selection operations, the current virtual resource acquisition configuration obtained from the game simulation result is determined as the target virtual resource configuration.

[0162] Of course, the preset virtual resource quota may also include other information, which is not particularly limited in this exemplary embodiment.

[0163] The game control method disclosed in the present disclosure can be applied in advertising promotion and other scenarios. In advertising promotion scenarios, virtual resource acquisition games can be designed to reward or attract users. For example, virtual resources can be game props, and users can then exchange game points for selection opportunities, so that selection operations can be performed in the virtual resource acquisition container according to the selection opportunities, and corresponding game props are generated according to the virtual resource acquisition configuration for the user's selection operation. In this process, it is necessary to balance the user experience and the total virtual value of the virtual resources issued, that is, it is necessary to improve the user's experience of participating in promotional activities, but the total virtual value of the virtual resources issued cannot be increased indefinitely in order to improve the user's participation experience.

[0164] Through the game control method disclosed in the present invention, based on the advance simulation of the game in the actual promotional activities, the virtual resource acquisition configuration of the game can be adjusted according to the simulation results, so that the final game results can meet the expected needs and improve the accuracy and efficiency of game design.

[0165] In addition, it should be noted that the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0166] Furthermore, an exemplary embodiment of the present disclosure also provides a game control device. Fig. 9 As shown, the game control device 900 includes the following program modules: a to-be-simulated virtual resource acquisition container generation module 910, configured to generate a to-be-simulated virtual resource acquisition container according to the initial virtual resource acquisition configuration of the game, wherein the to-be-simulated virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; a first target operation feature determination module 920, configured to determine a first target operation feature for performing a selection operation in the to-be-simulated virtual resource acquisition container according to the virtual resources in the to-be-simulated virtual resource acquisition container; a selection operation prediction module 930, configured to input the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the to-be-simulated virtual resource acquisition container; a selection simulation module 940, configured to perform a virtual resource selection simulation on the to-be-simulated virtual resource acquisition container according to the first prediction probability until a game simulation stop condition is met to obtain a game simulation result; a virtual resource acquisition configuration adjustment module 950, configured to adjust the virtual resource acquisition configuration based on the game simulation result to determine a target virtual resource acquisition configuration.

[0167] In an optional embodiment, the selection simulation module 940 can be specifically configured as follows: in response to the first prediction probability indicating a selection operation, control the virtual resource acquisition container to be simulated to perform a selection operation simulation to acquire virtual resources; update the first target operation feature according to the virtual resources in the virtual resource acquisition container to be simulated and the acquired virtual resources; input the updated first target operation feature into a pre-trained selection operation prediction model, and again obtain the first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; repeat the above process until the game simulation stop condition is met to obtain the game simulation result; wherein the game simulation stop condition includes: in response to the first prediction probability determination indicating to stop the selection operation or the number of simulations of the selection operation reaches the preset number of times.

[0168] In an optional embodiment, updating the first target operation characteristic according to the virtual resources in the virtual resource acquisition container to be simulated and the virtual resources that have been acquired includes: determining the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated according to all virtual resources in the virtual resource acquisition container to be simulated; determining the characteristics of currently acquired virtual resources according to the currently acquired virtual resources; obtaining the remaining virtual resources in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated and all virtual resources that have been acquired, and determining the resource value distribution characteristics of the remaining virtual resources; updating the first target operation characteristic according to at least one of the resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated, the characteristics of currently acquired virtual resources, and the resource value distribution characteristics of the remaining virtual resources.

[0169] In an optional embodiment, the first target operation feature determination module 920 can be specifically configured to: determine the first target operation feature of the first selection operation in the resource acquisition container to be simulated based on the resource value distribution characteristics of all virtual resources in the virtual resource acquisition container to be simulated.

[0170] In an optional embodiment, the game simulation result includes: the total amount of virtual resources acquired when the game simulation stops and the number of simulations of the selection operation; based on this, the virtual resource acquisition configuration adjustment module 950 can be specifically configured as: based on the total amount of virtual resources acquired, the number of simulations of the selection operation and the preset virtual resource quota, adjust the virtual resource acquisition configuration to determine the target virtual resource acquisition configuration.

[0171] In an optional embodiment, the preset virtual resource quota includes a preset total amount of virtual resources and a preset number of selection operations, and the adjusting the virtual resource acquisition configuration based on the acquired total amount of virtual resources, the simulation number of the selection operation and the preset virtual resource quota to determine the target virtual resource acquisition configuration includes: adjusting the virtual resource acquisition configuration when the difference between the acquired total amount of virtual resources and the preset virtual total amount is greater than a first preset value, and the simulation number of the selection operation is less than the preset number of selection operations; regenerating the virtual resource acquisition container to be simulated according to the adjusted virtual resource acquisition configuration; re-performing virtual resource selection simulation based on the adjusted virtual resource acquisition configuration, the regenerated virtual resource acquisition container to be simulated, and the pre-trained selection operation prediction model until the difference between the acquired total amount of virtual resources and the preset virtual total amount is less than or equal to the first preset value, and the simulation number of the selection operation is greater than or equal to the preset number of selection operations, and determining the currently adjusted virtual resource acquisition configuration as the target virtual resource acquisition configuration.

[0172] In an optional embodiment, the method for determining the pre-trained selection operation prediction model includes: obtaining training samples and sample labels corresponding to the training samples, the training samples are determined according to a historical virtual resource acquisition container, and the sample labels are determined according to whether a selection operation is performed in the historical virtual resource acquisition container, wherein each historical virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; based on the virtual resource information in the historical virtual resource acquisition container, determining the sample operation characteristics of the selection operation performed in the historical virtual resource acquisition container; inputting the sample operation characteristics into the selection operation prediction model to be trained to obtain a prediction result of whether a selection operation is performed in the historical virtual resource acquisition container; determining the training loss value of the selection operation model to be trained based on the degree of difference between the prediction result and the sample label; iteratively training the selection operation model to be trained based on the training loss value until a training stop condition is met to obtain the pre-trained selection operation prediction model; wherein the training stop condition includes: the training loss value is less than a preset loss value, or the number of iterative training reaches a preset number of iterations.

[0173] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0174] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0175] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0176] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the game control method described above is implemented.

[0177] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0178] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0179] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, Python, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0180] The computer program can be carried or transmitted by electrical, magnetic, optical, electromagnetic, infrared and other signals. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program is running on the electronic device, its code is used to make the electronic device execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned game control method, which includes the following steps: generating a virtual resource acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game, wherein the virtual resource acquisition container to be simulated includes a preset number of selection opportunities, each selection opportunity corresponds to an obtainable virtual resource; according to the virtual resources in the virtual resource acquisition container to be simulated, determining the first target operation feature of the selection operation in the virtual resource acquisition container to be simulated; inputting the first target operation feature into the pre-trained selection operation prediction model to obtain the first prediction probability of whether the selection operation is performed in the virtual resource acquisition container to be simulated; performing virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first prediction probability until the game simulation stop condition is met to obtain the game simulation result; based on the game simulation result, adjusting the virtual resource acquisition configuration to determine the target virtual resource acquisition configuration.

[0181] By executing the above method steps through a computer program, on the one hand, based on the virtual resource acquisition configuration and the selection operation prediction model, a game simulation of a virtual resource acquisition game can be performed, and the final virtual resource acquisition configuration can be determined according to the simulation results, thereby improving the accuracy of the virtual resource acquisition configuration in the game based on the game simulation method; on the other hand, the virtual resource acquisition configuration in the game can be determined without human participation, thereby assisting the game design through the determined virtual resource acquisition configuration, thereby improving the design efficiency of the game.

[0182] The exemplary embodiments of the present disclosure also provide an electronic device, such as the terminal device 110 or the server 120 described above. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions. In addition, the electronic device may also include a display for displaying a graphical user interface.

[0183] Reference below Fig.10 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Fig.10 The electronic device 1000 shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0184] like Fig.10 As shown, the electronic device 1000 may include: a processor 1010 , a memory 1020 , a bus 1030 , an I / O (input / output) interface 1040 , a network adapter 1020 , and a display 1060 .

[0185] The memory 1020 may include a volatile memory, such as a RAM 1021, a cache unit 1022, and may also include a non-volatile memory, such as a ROM 1023. The memory 1020 may also include one or more program modules 1024, such program modules 1024 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 1024 may include each module in the above-mentioned device.

[0186] The processor 1010 may include one or more processing units. For example, the processor 1010 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0187] Processor 1010 can be used to execute executable instructions stored in memory 1020, such as the above-mentioned game control method, which includes the following steps: generating a virtual resource acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game, wherein the virtual resource acquisition container to be simulated includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; determining a first target operation feature for performing a selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated; inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; performing a virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first prediction probability until a game simulation stop condition is met to obtain a game simulation result; and adjusting the virtual resource acquisition configuration based on the game simulation result to determine the target virtual resource acquisition configuration.

[0188] The above method is implemented through a computer program. On the one hand, based on the virtual resource acquisition configuration and the selection operation prediction model, a game simulation of a virtual resource acquisition game can be performed, and the final virtual resource acquisition configuration can be determined according to the simulation results, thereby improving the accuracy of the virtual resource acquisition configuration in the game based on the game simulation method; on the other hand, the virtual resource acquisition configuration in the game can be determined without human participation, thereby assisting the game design through the determined virtual resource acquisition configuration, thereby improving the design efficiency of the game.

[0189] The bus 1030 is used to realize the connection between different components of the electronic device 1000, and may include a data bus, an address bus, and a control bus.

[0190] The electronic device 1000 can communicate with one or more external devices 1100 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 1040 .

[0191] The electronic device 1000 can communicate with one or more networks through the network adapter 1020. For example, the network adapter 1020 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 1020 can communicate with other modules of the electronic device 1000 through the bus 1030.

[0192] The electronic device 1000 may display a graphical user interface through the display 1060 , such as displaying virtual resources in a virtual resource acquisition container to be simulated.

[0193] although Fig.10Not shown, other hardware and / or software modules may also be provided in the electronic device 1000, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0194] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0195] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0196] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A game control method, characterized in that: include: Generate a to-be-simulated virtual resource acquisition container according to the initial virtual resource acquisition configuration of the game, wherein the to-be-simulated virtual resource acquisition container includes a preset number of selection opportunities, each selection opportunity corresponding to an obtainable virtual resource; Determining, according to the virtual resources in the to-be-simulated virtual resource acquisition container, a first target operation feature for performing a selection operation in the to-be-simulated virtual resource acquisition container; Inputting the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; Performing a virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first predicted probability until a game simulation stop condition is met, thereby obtaining a game simulation result; Based on the game simulation result, the virtual resource acquisition configuration is adjusted to determine a target virtual resource acquisition configuration.

2. The game control method according to claim 1, characterized in that: The performing virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first predicted probability until a game simulation stop condition is met to obtain a game simulation result includes: In response to the first prediction probability indicating a selection operation, controlling the to-be-simulated virtual resource acquisition container to perform a selection operation simulation to acquire virtual resources; updating the first target operation characteristic according to the virtual resources in the to-be-simulated virtual resource acquisition container and the acquired virtual resources; Inputting the updated first target operation feature into a pre-trained selection operation prediction model to again obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; Repeat the above process until the game simulation stop condition is met to obtain the game simulation result; The game simulation stopping condition includes: in response to the first prediction probability determining instruction to stop the selection operation or the number of simulations of the selection operation reaches the preset number.

3. The game control method according to claim 2, characterized in that: The acquiring of the virtual resources in the container and the acquired virtual resources according to the virtual resources to be simulated, and updating the first target operation characteristic comprises: Determining resource value distribution characteristics of all virtual resources in the resource acquisition container to be simulated based on all virtual resources in the virtual resource acquisition container to be simulated; Determine the characteristics of the currently acquired virtual resources according to the currently acquired virtual resources; According to the virtual resources in the virtual resource acquisition container to be simulated and all the virtual resources that have been acquired, the remaining virtual resources in the virtual resource acquisition container to be simulated are obtained, and the resource value distribution characteristics of the remaining virtual resources are determined; The first target operation feature is updated according to at least one of the resource value distribution features of all virtual resources in the resource acquisition container to be simulated, the features of the currently acquired virtual resources, and the resource value distribution features of the remaining virtual resources.

4. The game control method according to claim 1, characterized in that: The determining, based on the virtual resources in the to-be-simulated virtual resource acquisition container, of a first target operation feature for performing a selection operation in the to-be-simulated virtual resource acquisition container comprises: According to the resource value distribution characteristics of all virtual resources in the virtual resource acquisition container to be simulated, a first target operation characteristic of the first selection operation in the resource acquisition container to be simulated is determined.

5. The game control method according to claim 1, characterized in that: The game simulation result includes: the total amount of virtual resources acquired when the game simulation stops and the number of simulations of the selection operation; adjusting the virtual resource acquisition configuration based on the game simulation result to determine the target virtual resource acquisition configuration includes: Based on the total amount of virtual resources acquired, the number of simulations of the selection operation, and the preset virtual resource quota, the virtual resource acquisition configuration is adjusted to determine a target virtual resource acquisition configuration.

6. The game control method according to claim 5, characterized in that: The preset virtual resource quota includes a preset total amount of virtual resources and a preset number of selection operations, and the adjusting the virtual resource acquisition configuration based on the acquired total amount of virtual resources, the simulated number of selection operations, and the preset virtual resource quota to determine the target virtual resource acquisition configuration includes: When the difference between the total amount of virtual resources acquired and the preset total amount of virtual resources is greater than a first preset value, and the number of simulations of the selection operation is less than the preset number of selection operations, adjusting the virtual resource acquisition configuration; Regenerate the virtual resource acquisition container to be simulated according to the adjusted virtual resource acquisition configuration; Based on the adjusted virtual resource acquisition configuration, the regenerated virtual resource acquisition container to be simulated, and the pre-trained selection operation prediction model, the virtual resource selection simulation is performed again until the difference between the total amount of virtual resources acquired and the preset virtual total amount is less than or equal to a first preset value, and the number of simulations of the selection operation is greater than or equal to the preset number of selection operations, and the currently adjusted virtual resource acquisition configuration is determined as the target virtual resource acquisition configuration.

7. The game control method according to claim 1, characterized in that: The method for determining the pre-trained selection operation prediction model includes: Acquire training samples and sample labels corresponding to the training samples, wherein the training samples are determined according to a historical virtual resource acquisition container, and the sample labels are determined according to whether a selection operation is performed in the historical virtual resource acquisition container, wherein each historical virtual resource acquisition container includes a preset number of selection opportunities, and each selection opportunity corresponds to an obtainable virtual resource; Determining, based on virtual resource information in a historical virtual resource acquisition container, sample operation features for performing a selection operation in the historical virtual resource acquisition container; Inputting the sample operation feature into a selection operation prediction model to be trained to obtain a prediction result of whether a selection operation is performed in the historical virtual resource acquisition container; Determining a training loss value of the selected operation model to be trained according to the degree of difference between the prediction result and the sample label; Iteratively training the selection operation model to be trained according to the training loss value until a training stop condition is met, thereby obtaining the pre-trained selection operation prediction model; The training stop condition includes: the training loss value is less than a preset loss value, or the number of iterative training reaches a preset number of iterations.

8. A game control device, characterized in that: include: A module for generating a virtual resource acquisition container to be simulated is configured to generate a virtual resource acquisition container to be simulated according to the initial virtual resource acquisition configuration of the game, wherein the virtual resource acquisition container to be simulated includes a preset number of selection opportunities, each selection opportunity corresponding to an obtainable virtual resource; A first target operation feature determination module is configured to determine a first target operation feature of performing a selection operation in the virtual resource acquisition container to be simulated according to the virtual resources in the virtual resource acquisition container to be simulated; A selection operation prediction module is configured to input the first target operation feature into a pre-trained selection operation prediction model to obtain a first prediction probability of whether a selection operation is performed in the virtual resource acquisition container to be simulated; a selection simulation module, configured to perform a virtual resource selection simulation on the virtual resource acquisition container to be simulated according to the first prediction probability, until a game simulation stop condition is met, thereby obtaining a game simulation result; The virtual resource acquisition configuration adjustment module is configured to adjust the virtual resource acquisition configuration based on the game simulation result to determine a target virtual resource acquisition configuration.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 7.

Images