Data processing method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a data processing method and device, electronic equipment and storage medium, and relate to the fields of artificial intelligence and multimedia. The data processing method comprises: obtaining an initial formation set; each initial game formation comprises at least two formation units, and each formation unit comprises at least two formation elements; performing at least one formation optimization operation until a preset termination condition is met, determining at least one target ladder formation based on the initial formation set after formation optimization; the formation optimization operation comprises: determining the formation strength of the initial game formation by using a trained strength prediction model; selecting a plurality of first game formations from the initial formation set based on the determined formation strength; obtaining a plurality of second game formations by performing a formation unit-based exchange operation on at least part of the plurality of first game formations; and determining a new initial formation set based on the plurality of second game formations.

Description

Technical Field

[0001] This application relates to the fields of computer, big data and cloud technology. Specifically, this application relates to a data processing method, apparatus, electronic device, computer-readable storage medium and computer program product. Background Technology

[0002] A game lineup is a collection of virtual characters with certain skills in a simulation game (SLG) application. A collection of multiple lineups (e.g., 100) is called a ladder lineup. These lineups need to have a high win-draw rate, that is, when the virtual characters of these lineups fight against the virtual characters of other lineups, the probability of these lineups winning or drawing is relatively high, and the duplication of virtual characters between different lineups in the ladder lineup is low.

[0003] Typically, when an SLG (Strategy / Simulation) game application is launched, the game publisher provides players with a ranked lineup to guide them in building their own teams and improving their combat power. However, in current technology, before the SLG game application launches, the game publisher often releases ranked lineups based on their own understanding. This approach fails to guarantee a high win-loss ratio for the ranked lineups, leading to player churn. Summary of the Invention

[0004] The purpose of this application is to provide a data processing method, apparatus, electronic device, and storage medium that can improve query efficiency. To achieve the above objective, the technical solutions provided by this application are as follows: On one hand, embodiments of this application provide a data processing method, the method comprising: Obtain the initial lineup set; the initial lineup set includes multiple initial game lineups; each initial game lineup includes at least two lineup units, and each lineup unit includes at least two lineup elements; Perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and determine at least one target ladder lineup based on the optimized initial lineup set. The lineup optimization operations include: For each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined by a trained strength prediction model based on the initial game lineup. Based on the determined strength of each lineup, multiple first-game lineups are selected from the initial lineup set; Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least a portion of the multiple first game lineups; A new initial lineup set is determined based on multiple second game lineups.

[0005] In some possible implementations, for each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined based on the initial game lineup using a trained strength prediction model, including: For each initial game lineup, obtain the lineup characteristics of the initial game lineup; where the lineup characteristics include the element characteristics of each lineup element contained in the game lineup; The lineup features are input into the trained strength prediction model to obtain the lineup strength of the initial game lineup; the strength prediction model is trained based on multiple sample game lineups and the sample lineup strength corresponding to each sample game lineup.

[0006] In some possible implementations, the intensity prediction model is trained based on the following method: Obtain multiple sample game lineups; For each sample game lineup, the sample game lineup is compared with multiple preset reference lineups, and the sample lineup strength is determined based on the results of the comparison. Obtain the sample lineup features for each sample game lineup; Based on the sample lineup features and corresponding sample lineup strength of each sample game lineup, the initial prediction model is trained to obtain the strength prediction model.

[0007] In some possible implementations, a new initial lineup set is determined based on multiple second game lineups, including: Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups; The update operation includes at least one of the element swapping operation or element replacement operation, and the lineup elements targeted by one update operation are the same lineup elements.

[0008] In some possible implementations, lineup elements include virtual characters; update operations include element replacement operations; A new initial lineup set is obtained by performing at least one update operation on at least some of the lineups in multiple second game lineups, including: For virtual characters in at least a portion of multiple second game lineups, obtain replaceable characters corresponding to the virtual characters; A new initial lineup set is obtained by replacing at least one virtual character in at least a portion of multiple second game lineups with a replaceable character.

[0009] In some possible implementations, lineup elements include at least one virtual attribute possessed by the virtual character; update operations include element swapping operations; The update process includes the following steps: Determine the strength of each game lineup before the current update operation; the game lineup before the first update operation is the second game lineup; the game lineup before each update operation other than the first one is the game lineup obtained from the previous update operation. Based on the determined lineup strength, several first-update lineups were identified from the game lineups before multiple update operations. By performing an element swap operation on a virtual attribute of at least some of the multiple first update lineups, multiple second update lineups obtained in the current update operation are obtained. The multiple second-update lineups obtained from the current update operation are used as the game lineups before the next update operation. An initial lineup set is obtained based on the multiple second-update lineups obtained from the last update operation.

[0010] In some possible implementations, the update operation also includes an element replacement operation; By performing an element swap operation on at least some of the virtual attributes in multiple first-update lineups, multiple second-update lineups are obtained from the current update operation, including: Perform an element swap operation on a virtual attribute of at least some of the multiple first-update lineups to obtain multiple third-update lineups; Perform element replacement operations on virtual attributes in at least some of the multiple third-update lineups to obtain multiple second-update lineups.

[0011] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by the virtual characters, wherein the virtual characters possess at least one virtual attribute. Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups, including: Multiple third game lineups are obtained by performing an update operation on at least one virtual character in at least some of the multiple second game lineups; Determine the strength of multiple third game lineups, and then determine multiple fourth game lineups from the multiple third game lineups based on the determined lineup strengths. A new initial lineup set is obtained by updating at least one virtual attribute in at least some of the multiple fourth game lineups; at least one virtual attribute belongs to the same virtual attribute.

[0012] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters; The method also includes: Based on at least one target ladder lineup, calculate the evaluation value of each virtual character in the lineup element database; the evaluation value includes at least one of the virtual character's appearance count or frequency in at least one target ladder lineup; Adjust the virtual attributes of virtual characters whose evaluation values ​​exceed the reference range; Based on the adjusted lineup element database, generate multiple new initial game lineups; Perform at least one lineup optimization operation on multiple new initial game lineups to obtain the corresponding new target ladder lineups.

[0013] On the other hand, embodiments of this application provide a data processing apparatus, which includes: The acquisition module is used to acquire an initial lineup set; the initial lineup set includes multiple initial game lineups; each initial game lineup includes at least two lineup units, and each lineup unit includes at least two lineup elements; The optimization module is used to perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and to determine at least one target ladder lineup based on the initial lineup set after lineup optimization. Specifically, the optimization module, when performing lineup optimization operations, is used for: For each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined by a trained strength prediction model based on the initial game lineup. Based on the determined strength of each lineup, multiple first-game lineups are selected from the initial lineup set; Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least a portion of the multiple first game lineups; A new initial lineup set is determined based on multiple second game lineups.

[0014] In some possible implementations, when the optimization module determines the strength of each initial game lineup in the initial lineup set using a trained strength prediction model, it specifically performs the following: For each initial game lineup, obtain the lineup characteristics of the initial game lineup; where the lineup characteristics include the element characteristics of each lineup element contained in the game lineup; The lineup features are input into the trained strength prediction model to obtain the lineup strength of the initial game lineup; the strength prediction model is trained based on multiple sample game lineups and the sample lineup strength corresponding to each sample game lineup.

[0015] In some possible implementations, the intensity prediction model is trained based on the following method: Obtain multiple sample game lineups; For each sample game lineup, the sample game lineup is compared with multiple preset reference lineups, and the sample lineup strength is determined based on the results of the comparison. Obtain the sample lineup features for each sample game lineup; Based on the sample lineup features and corresponding sample lineup strength of each sample game lineup, the initial prediction model is trained to obtain the strength prediction model.

[0016] In some possible implementations, the optimization module, when determining a new initial lineup set based on multiple second game lineups, is specifically used for: Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups; The update operation includes at least one of the element swapping operation or element replacement operation, and the lineup elements targeted by one update operation are the same lineup elements.

[0017] In some possible implementations, lineup elements include virtual characters; update operations include element replacement operations; When the optimization module obtains a new initial lineup set by performing at least one update operation on at least some lineup elements in multiple second game lineups, it is specifically used for: For virtual characters in at least a portion of multiple second game lineups, obtain replaceable characters corresponding to the virtual characters; A new initial lineup set is obtained by replacing at least one virtual character in at least a portion of multiple second game lineups with a replaceable character.

[0018] In some possible implementations, lineup elements include at least one virtual attribute possessed by the virtual character; update operations include element swapping operations; The update process includes the following steps: Determine the strength of each game lineup before the current update operation; the game lineup before the first update operation is the second game lineup; the game lineup before each update operation other than the first one is the game lineup obtained from the previous update operation. Based on the determined lineup strength, several first-update lineups were identified from the game lineups before multiple update operations. By performing an element swap operation on a virtual attribute of at least some of the multiple first update lineups, multiple second update lineups obtained in the current update operation are obtained. The multiple second-update lineups obtained from the current update operation are used as the game lineups before the next update operation. An initial lineup set is obtained based on the multiple second-update lineups obtained from the last update operation.

[0019] In some possible implementations, the update operation also includes an element replacement operation; When the optimization module obtains multiple second-update lineups from the current update operation by performing element swap operations on at least some of the virtual attributes of multiple first-update lineups, it is specifically used for: Perform an element swap operation on a virtual attribute of at least some of the multiple first-update lineups to obtain multiple third-update lineups; Perform element replacement operations on virtual attributes in at least some of the multiple third-update lineups to obtain multiple second-update lineups.

[0020] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by the virtual characters, wherein the virtual characters possess at least one virtual attribute. The optimization module, when dealing with lineup elements as units and performing at least one update operation on at least one lineup element in at least some of the second game lineups to obtain a new initial lineup set, is specifically used for: Multiple third game lineups are obtained by performing an update operation on at least one virtual character in at least some of the multiple second game lineups; Determine the strength of multiple third game lineups, and then determine multiple fourth game lineups from the multiple third game lineups based on the determined lineup strengths. A new initial lineup set is obtained by updating at least one virtual attribute in at least some of the multiple fourth game lineups; at least one virtual attribute belongs to the same virtual attribute.

[0021] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters; The device also includes an adjustment module for: Based on at least one target ladder lineup, calculate the evaluation value of each virtual character in the lineup element database; the evaluation value includes at least one of the virtual character's appearance count or frequency in at least one target ladder lineup; Adjust the virtual attributes of virtual characters whose evaluation values ​​exceed the reference range; Based on the adjusted lineup element database, generate multiple new initial game lineups; Perform at least one lineup optimization operation on multiple new initial game lineups to obtain the corresponding new target ladder lineups.

[0022] On the other hand, embodiments of this application also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method provided in any optional embodiment of this application.

[0023] On the other hand, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in any optional embodiment of this application.

[0024] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the methods provided in any optional embodiment of this application.

[0025] The beneficial effects of the technical solution provided in this application are as follows: When optimizing a portion of the lineups in multiple first-tier game lineups, the exchange operation is performed on a lineup unit basis. That is, at least two lineup elements in a lineup unit are bound together for the exchange operation. The first-tier game lineups are already strong game lineups selected through lineup strength screening. This exchange operation method can further optimize the first-tier game lineups while controlling the range of changes, avoiding the possibility that the lineups will not be optimized due to too large changes during the optimization process. It can also more efficiently discover target ladder lineups.

[0026] Furthermore, by using a trained strength prediction model to determine the strength of the initial game lineup, it is not necessary to play against multiple reference lineups in real time to determine the lineup strength. This can effectively improve the prediction efficiency of lineup strength, especially when the number of initial game lineups is large. It can effectively reduce the time spent calculating lineup strength, thereby more efficiently identifying target ladder lineups.

[0027] Furthermore, through different levels of lineup optimization and update operations, firstly, at least one lineup optimization operation is performed on the initial lineup set as a unit to obtain multiple second game lineups, which can control the change range during the lineup optimization operation within a reasonable range; then, at least one update operation is performed on at least some of the multiple second game lineups as a unit, which can be adjusted on the basis of the second game lineups to further optimize the second game lineups, thereby more accurately identifying the target ladder lineups.

[0028] Furthermore, this solution can more accurately and efficiently identify target team compositions in the game, allowing for timely adjustments to the numerical values ​​of virtual characters or skills that are used too frequently or too infrequently, thereby improving game balance and ultimately enhancing the player's in-game experience. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0030] Figure 1 This is a schematic diagram illustrating the application environment of the data processing method provided in the embodiments of this application; Figure 2 A flowchart illustrating a data processing method provided in an embodiment of this application; Figure 3 This is a schematic diagram of a scheme for predicting lineup strength in one example of this application; Figure 4 This is a schematic diagram illustrating a scheme for determining the target ladder lineup in one example of this application; Figure 5 This is a schematic diagram illustrating a scheme for determining the target ladder lineup in one example of this application; Figure 6 This is a schematic diagram illustrating a scheme for determining the target ladder lineup in one example of this application; Figure 7 This is a schematic diagram illustrating a scheme for determining the target ladder lineup in one example of this application; Figure 8 A diagram illustrating the evaluation values ​​of each virtual character before identifying the target ladder lineup; Figure 9 This is a schematic diagram illustrating the evaluation values ​​of each virtual character after the target ladder lineup has been mined using the data processing method described in this application; Figure 10 This is a comparison chart showing the execution effects of the data processing method in this application and existing solutions; Figure 11 This is a comparison chart showing the frequency of occurrence of each virtual character and virtual skill before and after the target ladder lineup was mined using the data processing method of this application; Figure 12 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application; Figure 13 This is a schematic diagram of the structure of an electronic device to which this application applies. Detailed Implementation

[0031] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0032] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.” When describing multiple (two or more) items, if the relationship between the multiple items is not explicitly defined, the multiple items can refer to one, several or all of the multiple items. For example, the description of "parameter A includes A1, A2, A3" can be implemented as parameter A includes A1 or A2 or A3, or it can be implemented as parameter A includes at least two of the three items A1, A2 and A3.

[0033] This application addresses the technical problems of low formation generation efficiency and unreliable combat power in existing formation generation methods by proposing a data processing method. Based on this method, formations with high combat power can be automatically generated, which can better meet the needs of practical applications.

[0034] Optionally, the data processing involved in the embodiments of this application can be implemented based on cloud technology. For example, steps such as lineup optimization can be implemented using cloud technology. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or local area network to realize data computing, storage, processing, and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, and application technology applied based on the cloud computing business model. It can form a resource pool, be used on demand, and is flexible and convenient. Cloud computing technology will become an important support. Cloud computing refers to the delivery and use model of IT infrastructure, which means obtaining the required resources through the network in an on-demand and easily scalable manner; in a broader sense, cloud computing refers to the delivery and use model of services, which means obtaining the required services through the network in an on-demand and easily scalable manner. Such services can be IT and software, Internet-related, or other services. With the development of the Internet, real-time data streams, and the diversification of connected devices, as well as the driving force of demands such as search services, social networks, mobile commerce, and open collaboration, cloud computing has developed rapidly. Unlike previous parallel distributed computing, the emergence of cloud computing will, conceptually, drive a revolutionary change in the entire Internet model and enterprise management model.

[0035] Optionally, the data processing method provided in this application embodiment can also be implemented based on artificial intelligence (AI) technology. For example, the strength of a lineup can be predicted by a trained neural network model (i.e., a strength prediction model). Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain optimal results. In other words, artificial intelligence is a comprehensive technology of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. Artificial intelligence is also the study of the design principles and implementation methods of various intelligent machines, enabling machines to have the functions of perception, reasoning, and decision-making.

[0036] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instructional learning.

[0037] With the research and advancement of artificial intelligence (AI) technology, AI is being studied and applied in various fields, such as smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, robots, smart healthcare, and smart customer service. It is believed that with the development of technology, AI will be applied in more fields and play an increasingly important role.

[0038] To better illustrate and understand the solutions provided in the embodiments of this application, some related technical terms used in the embodiments of this application will be introduced first: SLG: Simulation game, refers to a strategy simulation game in which heroes (virtual characters in the game) and skills (virtual character skills that heroes have in the game) are combined to form a lineup.

[0039] Team composition: A team composition consists of multiple heroes, and each hero has multiple skills.

[0040] Advantage / Draw Ratio: After a lineup plays against other lineups, the number of wins and draws of that lineup is counted. The ratio of the sum of the number of wins and draws of that lineup to the total number of matches played is called the advantage / draw ratio.

[0041] Ladder lineups (i.e. target ladder lineups): include multiple lineups, such as 100 lineups. Each lineup in the ladder lineup has a high advantage / disadvantage ratio, and there is low overlap of heroes between different lineups.

[0042] The following description of several optional embodiments illustrates the technical solutions provided in this application and the technical effects produced by these solutions. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0043] Figure 1 This is a schematic diagram illustrating the application environment of the data processing method provided in this application embodiment. The application environment may include an operation server 101, a game server 102, and an operation terminal 103. Specifically, the operation terminal 103 sends a target ranked team generation instruction to the operation server 101. The operation server 101 obtains an initial team set from the game server 102. The operation server 101 performs at least one team optimization operation on the initial team set until a preset termination condition is met. Based on the optimized initial team set, at least one target ranked team is determined. The operation server 101 sends the generated target ranked team to the operation terminal 103.

[0044] In the above scenario, the target ranking lineup is generated by the operation server 101. In other scenarios, the target ranking lineup can be generated by the game server 102, or the game lineup can be generated by the operation terminal 103. Those skilled in the art will understand that the above scenario is merely an example and does not limit the application scenarios of the data processing method of this application.

[0045] Those skilled in the art will understand that a server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server or server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0046] The terminal (also known as a user terminal or user equipment) can be a smartphone, tablet, laptop, desktop computer, intelligent voice interaction device (such as a smart speaker), wearable electronic device (such as a smartwatch), in-vehicle terminal, smart home appliance (such as a smart TV), AR / VR device, etc., but is not limited thereto. The terminal and the server can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0047] Figure 2 This illustration shows a flowchart of a data processing method provided in an embodiment of this application. This method can be executed by an operations server, a game server, or an operations terminal, such as... Figure 2 As shown, taking the operating server as the executing entity as an example, the data processing method provided in this application may include the following steps: Step S201: Obtain the initial lineup set.

[0048] The initial lineup set includes multiple initial game lineups; each initial game lineup includes at least two lineup units, and each lineup unit includes at least two lineup elements.

[0049] Among them, lineup elements can include virtual characters or virtual attributes possessed by virtual characters.

[0050] For example, a virtual character could be a game character present in the initial game roster.

[0051] Virtual attributes can be the combat ability attributes of a virtual character. For example, virtual attributes can include a character's skill attributes, talent attributes, combat ability point allocation, and so on.

[0052] Specifically, step S201, obtaining the initial lineup set, may include: According to the lineup configuration rules, the preset virtual characters are combined, and corresponding virtual attributes are set for each virtual character to generate an initial lineup set.

[0053] The lineup configuration rules can include which different virtual characters can form a lineup, and which virtual attributes can be assigned to different virtual characters, etc.

[0054] For example, an initial game lineup can include three virtual characters. First, determine the types of units that can be combined to form the initial game lineup. Then, select three corresponding virtual characters based on the types of units. Next, set virtual attributes for each virtual character, such as randomly selecting two equipment skills for each virtual character. Finally, set different combat ability point allocations for each virtual character.

[0055] Step S202: Perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and determine at least one target ladder lineup based on the optimized initial lineup set.

[0056] Among them, lineup optimization operations can be genetic evolution operations, that is, searching for the optimal solution by simulating the natural evolution process, or they can include determining fitness for screening, that is, screening based on lineup strength, or performing crossover or mutation operations, that is, performing exchange or replacement operations.

[0057] The preset termination condition can be that the number of iterations reaches a preset number, or that the initial lineup set obtained in the current iteration is the same as the initial lineup set obtained in the previous iteration; there are no specific restrictions.

[0058] The lineup optimization operations include: (1) For each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined by the trained strength prediction model based on the initial game lineup.

[0059] Among them, lineup strength can be used to represent the combat power of the corresponding initial game lineup. The stronger the combat power, the greater the lineup strength.

[0060] In the specific implementation process, multiple sample game lineups and the strength of each sample game lineup can be obtained first, and then the strength prediction model can be trained.

[0061] (2) Select multiple first game lineups from the initial lineup set based on the determined strength of each lineup.

[0062] Specifically, an initial game lineup whose strength exceeds a first preset threshold can be used as the first game lineup.

[0063] (3) Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least some of the lineups in multiple first game lineups.

[0064] In some implementations, a swap operation can be performed on all lineups in multiple first game lineups. If a swap operation is performed on all lineups, then all first game lineups after the swap operation are used as second game lineups.

[0065] In other implementations, a swap operation can be performed on a portion of the lineups within multiple first game lineups. The portion of the first game lineups that have undergone the swap operation and the portion of the first game lineups that have not undergone the swap operation are both used as second game lineups. In other words, during the swap operation, the number of game lineups can remain unchanged from the first game lineup to the second game lineup.

[0066] Specifically, the process of the exchange operation may include: Two lineups to be swapped are randomly selected from multiple first-game lineups. The two lineups to be swapped are treated as chromosomes that are paired with each other, and each lineup unit is treated as a gene on a chromosome. Two chromosomes to be exchanged exchange some genes with each other, generating two new chromosomes, that is, generating two first game lineups.

[0067] It is important to note that the above-mentioned exchange operation is performed on a lineup unit basis. In other words, at least two lineup elements within a lineup unit are bound together. When a virtual character is crossed or exchanged, at least one virtual attribute of that virtual character is also exchanged. Binding at least two lineup elements together for the exchange operation can effectively control the range of changes in the initial game lineup.

[0068] (4) Determine a new initial lineup set based on multiple second game lineups.

[0069] In some implementations, the second game lineup can be directly used as the new initial lineup set. That is, after performing the lineup unit swapping operation, the result of this lineup optimization operation can be obtained.

[0070] In other implementations, the second game lineup can be further updated. The process of determining a new initial lineup set based on multiple second game lineups will be described in more detail below.

[0071] In the above embodiments, when optimizing some lineups in multiple first game lineups, the exchange operation is carried out on a lineup unit basis. That is, at least two lineup elements in a lineup unit are bound to be exchanged. The first game lineups are already strong game lineups selected through lineup strength screening. This exchange operation method can further optimize the first game lineups while controlling the change range, avoiding the lineups from not being optimized due to too large a change range during the optimization process. It can more efficiently discover target ladder lineups.

[0072] Furthermore, by using a trained strength prediction model to determine the strength of the initial game lineup, it is not necessary to play against multiple reference lineups in real time to determine the strength of the lineup. This can effectively improve the prediction efficiency of lineup strength, especially when there are a large number of initial game lineups. It can effectively reduce the time spent calculating the lineup strength, thereby more efficiently discovering the target ladder lineup.

[0073] The following will describe the specific process of determining the strength of a lineup with reference to specific embodiments.

[0074] In some possible implementations, for each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined based on the initial game lineup using a trained strength prediction model, which may include: a. For each initial game lineup, obtain the lineup characteristics of the initial game lineup.

[0075] Among them, lineup characteristics include the element characteristics of each lineup element contained in the game lineup.

[0076] Specifically, lineup characteristics can include the characteristics of multiple virtual characters in the game lineup and the characteristics of the virtual attributes corresponding to each virtual character.

[0077] For example, each initial game lineup has 3 virtual characters, each virtual character has 2 equipped skills, and each virtual character has different point allocations in four dimensions: Strength, Defense, Strategy, and City Conquest (the sum of the point allocations for each general in the four dimensions is fixed). Each lineup has 1 troop type, therefore the lineup code is designed as: [Troop ID, Virtual Character 1_ID, Virtual Character 2_ID, Virtual Character 3_ID, Virtual Character 1_Skill 1_ID, Virtual Character 1_Skill 2_ID, Virtual Character 2_Skill 1_ID, ...] Virtual Character 2_Skill 2_ID, Virtual Character 3_Skill 1_ID, Virtual Character 3_Skill 2_ID, Virtual Character 1_Strength_Points, Virtual Character 1_Defense_Points, Virtual Character 1_Strategy_Points, Virtual Character 1_City Conquest_Points, Virtual Character 2_Strength_Points, Virtual Character 2_Defense_Points, Virtual Character 2_Strategy_Points, Virtual Character 2_City Conquest_Points, Virtual Character 3_Strength_Points, Virtual Character 3_Defense_Points, Virtual Character 3_Strategy_Points, Virtual Character 3_City Conquest_Points).

[0078] The above feature encoding can be transformed, for example, by performing one-hot encoding transformation to obtain the lineup features.

[0079] b. Input the lineup features into the trained strength prediction model to obtain the lineup strength of the initial game lineup.

[0080] The intensity prediction model is trained based on multiple sample game lineups and the intensity of the sample lineups corresponding to each sample game lineup.

[0081] In practice, the intensity prediction model is trained in the following way: (1) Obtain multiple sample game lineups.

[0082] In the actual implementation process, the preset virtual characters can be combined according to the lineup configuration rules, and corresponding virtual attributes can be set for each virtual character to generate an initial lineup set.

[0083] Specifically, the initial lineup set can include all lineups generated according to the lineup configuration rules. Sample game lineups can be a part of the initial lineup set.

[0084] For example, based on the lineup configuration rules, 100 million different initial game lineups can be generated. Different game lineups refer to those containing any different virtual characters, or any virtual character having different virtual attributes. 100,000 can be selected from the 100 million initial game lineups as sample game lineups. In this way, the strength of a large number of initial game lineups other than the sample game lineups can be predicted through the strength prediction model process.

[0085] (2) For each sample game lineup, the sample game lineup is compared with multiple preset reference lineups, and the sample lineup strength is determined based on the results of the comparison.

[0086] The reference lineup can be generated based on specified information input from the terminal. For example, if experienced developers or operators believe that certain lineups are relatively strong, they can be designated as reference lineups.

[0087] (3) Obtain the sample lineup features of each sample game lineup.

[0088] Specifically, the process of obtaining the features of the sample lineup can be referred to the above process of obtaining the lineup features, and will not be repeated here.

[0089] (4) Based on the sample lineup features and corresponding sample lineup strength of each sample game lineup, the initial prediction model is trained to obtain the strength prediction model.

[0090] Specifically, the sample prediction intensity of the sample lineup features can be generated based on the initial prediction model, the training loss can be generated based on the sample prediction intensity and the sample lineup intensity, the parameters of the initial prediction model can be adjusted based on the training loss, and the steps of generating sample prediction intensity and determining training loss can be repeated until the training termination condition is met to obtain the intensity prediction model.

[0091] like Figure 3 As shown, the process of predicting the lineup strength in this application will be further explained in detail below with examples.

[0092] like Figure 3 As shown in the example, the process of predicting the strength of an initial game lineup may include the following steps: Multiple sample game lineups are generated based on preset lineup configuration rules; that is, the lineup to be evaluated is generated based on business rules as shown in the figure. Obtain multiple reference lineups; that is, the lineups that are used more frequently based on data from various user terminals, or the lineups recommended by operations planners based on experience, as shown in the figure, to determine the candidate lineups; For each sample game lineup, the sample game lineup is put into battle against multiple preset reference lineups, as shown in the figure, through battle suit clusters. The sample lineup strength of each sample game lineup is generated based on the battle results, as shown in the figure, which generates a training set based on the battle results. The sample game lineups are encoded to obtain the sample lineup features; that is, one-hot encoding extraction is performed as shown in the figure. The initial prediction model is trained based on the characteristics and strength of the sample lineup. As shown in the figure, the DNN (Deep Neural Network) regression model is trained and written using the Tensorflow deep learning framework to obtain the trained strength prediction model. The lineup characteristics of the initial game lineup to be predicted are input into the strength prediction model to predict the lineup strength.

[0093] The above embodiments illustrate the specific process of predicting lineup strength. The following will further illustrate the specific process of determining a new initial lineup set in conjunction with the embodiments.

[0094] In some possible implementations, determining a new initial lineup set based on multiple second game lineups may include: Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups; The update operation includes at least one of the element swapping operation or element replacement operation, and the lineup elements targeted by one update operation are the same lineup elements.

[0095] Specifically, lineup elements may include virtual characters or at least one virtual attribute possessed by virtual characters.

[0096] Specifically, the update operation can also be a genetic evolution operation, which can include determining fitness for selection, i.e., selecting based on lineup strength, performing crossover or mutation operations, i.e., performing exchange or replacement operations.

[0097] In the specific implementation process, virtual characters can be replaced in at least some of the lineups in multiple second game lineups, and virtual attributes can be replaced or exchanged in at least some of the lineups in multiple second game lineups.

[0098] In the above embodiments, by performing lineup optimization and update operations at different levels, at least one lineup optimization operation is first performed on the initial lineup set at the lineup unit level to obtain multiple second game lineups. This allows the range of changes during the lineup optimization process to be controlled within a reasonable range. Then, at least one update operation is performed on at least some of the multiple second game lineups at the lineup element level. This allows for further adjustments to the second game lineups, further optimizing them and thus more accurately identifying the target ladder lineups.

[0099] In some possible implementations, lineup elements include virtual characters; update operations include element replacement operations; A new initial lineup set is obtained by performing at least one update operation on at least some of the lineups in multiple second game lineups, which may include: (1) For virtual characters in at least some of the lineups in multiple second game lineups, obtain the replaceable characters corresponding to the virtual characters; (2) A new initial lineup set is obtained by replacing at least one virtual character in at least part of the lineups of multiple second game lineups with replaceable characters.

[0100] Among them, the replaceable character can be an equivalent character with the same position as the virtual character. For example, if the virtual character is a warrior, then the replaceable character is also a warrior; if the virtual character is a mage, then the replaceable character is also a mage.

[0101] In the specific implementation process, such as Figure 4 As shown, the process of obtaining the target ladder lineup based on the initial lineup set can include: Determine the strength of each initial game lineup; Based on the strength of each initial game lineup, multiple first game lineups are selected from the initial lineup set, i.e., a roulette operation is performed. Multiple second game lineups are obtained through cross operations, i.e., swap operations, which are based on lineup units. Replace at least one virtual character in at least some of the game lineups in multiple game lineups, i.e. perform a mutation operation. If the preset termination condition is met, the target ladder lineup is obtained; if the termination condition is not met, a new initial lineup set is obtained. In some possible implementations, lineup elements include at least one virtual attribute possessed by the virtual character; update operations include element swapping operations; The update process includes the following steps: Determine the strength of each game lineup before the current update operation; the game lineup before the first update operation is the second game lineup; the game lineup before each update operation other than the first one is the game lineup obtained from the previous update operation. Based on the determined lineup strength, several first-update lineups were identified from the game lineups before multiple update operations. By performing an element swap operation on a virtual attribute of at least some of the multiple first update lineups, multiple second update lineups obtained in the current update operation are obtained. The multiple second-update lineups obtained from the current update operation are used as the game lineups before the next update operation. An initial lineup set is obtained based on the multiple second-update lineups obtained from the last update operation.

[0102] In the specific implementation process, the exchange operation can be carried out separately for different virtual attributes, that is, cross operation. Before each exchange operation, the lineup strength can be used for screening, that is, roulette operation.

[0103] like Figure 5 As shown in one example, virtual attributes include the allocation of virtual character skills and combat ability points. Therefore, the process of determining the target ladder lineup may include: Determine the strength of each initial game lineup; Based on the strength of each initial game lineup, multiple first game lineups are selected from the initial lineup set, i.e., a roulette operation is performed. Multiple second game lineups are obtained through cross operations, i.e., swap operations, which are based on lineup units. Based on the strength of the lineups, multiple first-update lineups are determined from multiple second-game lineups, i.e., a roulette operation is performed. The virtual character skills in at least some of the multiple first-update lineups are swapped, i.e., cross-operated, to obtain the second-update lineup; Use the second updated lineup as the game lineup before the next update operation, and perform the roulette operation again to get the new first updated lineup; Cross-operation is performed on the combat ability point allocation of at least some of the lineups in the new first update lineup to obtain the initial lineup set.

[0104] The update operation in the above embodiments only includes the exchange operation for virtual attributes. In some possible implementations, the update operation also includes the element replacement operation.

[0105] By performing an element swap operation on at least some of the virtual attributes of multiple first-update lineups, multiple second-update lineups obtained from the current update operation can be obtained, including: Perform an element swap operation on a virtual attribute of at least some of the multiple first-update lineups to obtain multiple third-update lineups; Perform element replacement operations on virtual attributes in at least some of the multiple third-update lineups to obtain multiple second-update lineups.

[0106] like Figure 6 As shown, in Figure 5 Based on this, in each update operation, after performing cross operations on virtual attributes, a swap operation can be performed, that is, a mutation operation, to obtain a new initial lineup set.

[0107] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by the virtual characters, wherein the virtual characters possess at least one virtual attribute. Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups, including: Multiple third game lineups are obtained by performing an update operation on at least one virtual character in at least some of the multiple second game lineups; Determine the strength of multiple third game lineups, and then determine multiple fourth game lineups from the multiple third game lineups based on the determined lineup strengths. A new initial lineup set is obtained by updating at least one virtual attribute in at least some of the multiple fourth game lineups; at least one virtual attribute belongs to the same virtual attribute.

[0108] In some implementations, the process of selecting a fourth game lineup based on lineup strength can be to select a third game lineup whose lineup strength is greater than a second threshold.

[0109] Specifically, update operations can be performed on virtual characters first, such as replacing game characters (mutation) to obtain a third game lineup; then the third game lineup can be filtered (rotary selection) to obtain a fourth game lineup; then update operations can be performed on virtual attributes, such as exchanging virtual attributes (crossing) and then performing mutation.

[0110] like Figure 7 As shown, in one example, virtual attributes include virtual character skills (also known as equipment skills) and combat ability point allocation (also known as point allocation). The process of determining the target ladder lineup based on the initial lineup set can include: Obtain the initial lineup set; that is, as shown in the figure, first set the lineup coding rules, and then initialize the lineup population; Determine the strength of each initial game lineup; that is, calculate the lineup strength fitness using a DNN model, as shown in the figure. Evolution of virtual characters, as shown in the image, can include: a. First, filter by lineup strength, that is, perform a roulette operation to obtain multiple first game lineups; b. Using lineup units as the unit, perform a cross operation on some lineups in multiple first game lineups to obtain multiple second game lineups; using lineup units as the unit, bind virtual characters and virtual attributes together and cross them together, that is, bind heroes, equipment skills, and point allocation as shown in the figure and cross them together; c. Perform virtual character update operations on at least some of the lineups in multiple second game lineups, that is, perform virtual character exchange operations, i.e. mutation operations, to obtain third game lineups; Updating virtual character skills within virtual attributes, i.e., the equipment skill evolution shown in the image, can include: d. Determine the strength of multiple third game lineups respectively, and determine multiple fourth game lineups from the multiple third game lineups based on the determined lineup strength; that is, perform the roulette operation again. By performing an update operation on at least one virtual attribute in at least some of the multiple fourth-game lineups: e. Perform cross-operation of virtual character skills for at least some of the lineups in multiple fourth game lineups; at this time, virtual character skills are not bound to virtual characters, and cross-operation is only performed on virtual character skills; f. Perform virtual character skill mutation operations on some of the multiple game lineups obtained in step e; Updating the point allocation in virtual attributes, i.e., the point allocation evolution shown in the diagram, can include: h. Determine the strength of the multiple game lineups obtained in step f, and filter them based on the lineup strength, that is, perform the roulette operation again. i. Perform cross-operation on point allocation for some lineups among the multiple game lineups obtained in step h; j. Perform a mutation operation on the point allocation of some of the multiple game lineups obtained in step i to obtain a new initial lineup set. If the preset termination condition is met, the target ladder lineup is obtained, as shown in the figure. If the preset termination condition is not met, the process returns to the steps of determining the strength of each initial game lineup and repeats step aj until the preset termination condition is met, thus obtaining the final target ladder lineup.

[0111] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters; The method also includes: Based on at least one target ladder lineup, calculate the evaluation value of each virtual character in the lineup element database; the evaluation value includes at least one of the virtual character's appearance count or frequency in at least one target ladder lineup; Adjust the virtual attributes of virtual characters whose evaluation values ​​exceed the reference range; Based on the adjusted lineup element database, generate multiple new initial game lineups; Perform at least one lineup optimization operation on multiple new initial game lineups to obtain the corresponding new target ladder lineups.

[0112] Specifically, we can calculate the evaluation value of each virtual character in the target ladder lineup. If the evaluation value is too high or too low, it means that the hero character is set too strong and needs to be adjusted accordingly.

[0113] like Figure 8 As shown, Figure 8 This is a numerical illustration of the evaluation in an example, which shows the frequency of virtual characters appearing in the target ranked lineup. By statistically analyzing the frequency distribution of each hero (i.e., virtual character) and skill in the target ranked lineup, adjustments are made to the virtual attributes of heroes with excessively high or low frequency of appearance.

[0114] like Figure 9 As shown, Figure 9 The evaluation values ​​are obtained after mining the target ladder lineup. After adjusting the lineup elements, a new initial game lineup can be generated. The lineup optimization operation is then repeated to obtain a new target ladder lineup and determine new evaluation values. This process continues until the new evaluation values ​​show that each virtual character is within a reasonable range, i.e., balance is achieved.

[0115] The data processing method provided in this application performs lineup optimization operations on a lineup unit basis when optimizing some lineups in multiple first-game lineups. That is, at least two lineup elements in a lineup unit are bound and exchanged. The first-game lineups are already strong lineups selected through lineup strength screening. This exchange operation method can further optimize the first-game lineups while controlling the change range, avoiding the lineups from not being optimized due to too large a change range during the optimization process. It can more efficiently discover target ladder lineups.

[0116] Furthermore, by using a trained strength prediction model to determine the strength of the initial game lineup, it is not necessary to play against multiple reference lineups in real time to determine the lineup strength. This can effectively improve the prediction efficiency of lineup strength, especially when the number of initial game lineups is large. It can effectively reduce the time spent calculating lineup strength, thereby more efficiently identifying target ladder lineups.

[0117] Furthermore, through different levels of lineup optimization and update operations, firstly, at least one lineup optimization operation is performed on the initial lineup set at the lineup unit level to obtain multiple second game lineups. This allows the range of changes during the lineup optimization process to be controlled within a reasonable range. Then, at least one update operation is performed on at least some of the multiple second game lineups at the lineup unit level. This allows for further adjustments to the second game lineups, further optimizing them and thus more accurately identifying the target ladder lineups.

[0118] Furthermore, this solution can more accurately and efficiently identify target team compositions in the game, allowing for timely numerical adjustments to virtual characters or skills that are used too frequently or too infrequently, thereby improving game balance and ultimately enhancing the player experience.

[0119] The beneficial effects of the data processing method of this application will be explained below with reference to the accompanying drawings.

[0120] like Figure 10 As shown in the figure, four schemes are compared: Traditional approach: Determine team strength based on real-time battles against reference teams, and optimize teams by directly performing cross-operations or mutations on various team elements. Only improve the evolution strategy: determine the strength of the lineup based on real-time battles with the reference lineup, and perform cross calculations on the lineup unit; Only improve the lineup evaluation method: determine the lineup strength through the strength prediction model, and directly perform cross-operation or mutation operation on each lineup element in the lineup when performing lineup optimization operation. This application proposes a method to determine the strength of a lineup by using a strength prediction model and performing cross-calculation on a lineup unit basis.

[0121] Depend on Figure 10 It can be seen that the computational efficiency of this application is high: the time taken for a single iteration is reduced by 150 seconds compared to determining the strength of a lineup based on real-time battles with a reference lineup, which is a relative reduction of 85.2%; Excellent convergence effect: It alleviates the problem of getting stuck in local optima, and the strength of the strongest lineup is increased by 12.1% compared to the joint evolution strategy.

[0122] In addition, such as Figure 11 As shown, Figure 11 The middle part represents the standard deviation of the occurrence frequency of lineup elements before and after adjusting the lineup elements based on the target ladder lineup. By analyzing the standard deviation of the occurrence frequency of all virtual characters and virtual character skills before and after the adjustment, it was found that the standard deviation of the occurrence frequency of virtual characters decreased by 67% and the standard deviation of the occurrence frequency of virtual character skills decreased by 45% compared with before the adjustment. The above results effectively verify the improvement of game balance.

[0123] In summary, this solution can more accurately and efficiently identify target team compositions in the game, allowing game designers to promptly adjust the numerical values ​​of virtual characters or their skills that are used too frequently or too infrequently, thereby improving game balance and ultimately enhancing the player experience.

[0124] like Figure 12As shown, in some possible embodiments, a data processing apparatus is provided, comprising: The acquisition module 1201 is used to acquire an initial lineup set; the initial lineup set includes multiple initial game lineups; each initial game lineup includes at least two lineup units, and each lineup unit includes at least two lineup elements; Optimization module 1202 is used to perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and to determine at least one target ladder lineup based on the initial lineup set after lineup optimization. Specifically, when performing lineup optimization operations, the optimization module 1202 is used for: For each initial game lineup in the initial lineup set, the lineup strength of the initial game lineup is determined by a trained strength prediction model based on the initial game lineup. Based on the determined strength of each lineup, multiple first-game lineups are selected from the initial lineup set; Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least a portion of the multiple first game lineups; A new initial lineup set is determined based on multiple second game lineups.

[0125] In some possible implementations, when the optimization module 1202 determines the strength of each initial game lineup in the initial lineup set using a trained strength prediction model based on the initial game lineup, it specifically performs the following: For each initial game lineup, obtain the lineup characteristics of the initial game lineup; where the lineup characteristics include the element characteristics of each lineup element contained in the game lineup; The lineup features are input into the trained strength prediction model to obtain the lineup strength of the initial game lineup; the strength prediction model is trained based on multiple sample game lineups and the sample lineup strength corresponding to each sample game lineup.

[0126] In some possible implementations, the intensity prediction model is trained based on the following method: Obtain multiple sample game lineups; For each sample game lineup, the sample game lineup is compared with multiple preset reference lineups, and the sample lineup strength is determined based on the results of the comparison. Obtain the sample lineup features for each sample game lineup; Based on the sample lineup features and corresponding sample lineup strength of each sample game lineup, the initial prediction model is trained to obtain the strength prediction model.

[0127] In some possible implementations, when determining a new initial lineup set based on multiple second game lineups, the optimization module 1202 is specifically used for: Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups; The update operation includes at least one of the element swapping operation or element replacement operation, and the lineup elements targeted by one update operation are the same lineup elements.

[0128] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by the virtual characters, wherein the virtual characters possess at least one virtual attribute. Optimization module 1202, when obtaining a new initial lineup set by performing at least one update operation on at least one lineup element in at least some of the multiple second game lineups, specifically uses the following: Multiple third game lineups are obtained by performing an update operation on at least one virtual character in at least some of the multiple second game lineups; Determine the strength of multiple third game lineups, and then determine multiple fourth game lineups from the multiple third game lineups based on the determined lineup strengths. A new initial lineup set is obtained by updating at least one virtual attribute in at least some of the multiple fourth game lineups; at least one virtual attribute belongs to the same virtual attribute.

[0129] In some possible implementations, lineup elements include virtual characters; update operations include element replacement operations; When optimizing module 1202 obtains a new initial lineup set by performing at least one update operation on at least some lineup elements in multiple second game lineups, it is specifically used for: For virtual characters in at least a portion of multiple second game lineups, obtain replaceable characters corresponding to the virtual characters; A new initial lineup set is obtained by replacing at least one virtual character in at least a portion of multiple second game lineups with a replaceable character.

[0130] In some possible implementations, lineup elements include at least one virtual attribute possessed by the virtual character; update operations include element swapping operations; The update process includes the following steps: Determine the strength of each game lineup before the current update operation; the game lineup before the first update operation is the second game lineup; the game lineup before each update operation other than the first one is the game lineup obtained from the previous update operation. Based on the determined lineup strength, several first-update lineups were identified from the game lineups before multiple update operations. By performing an element swap operation on a virtual attribute of at least some of the multiple first update lineups, multiple second update lineups obtained in the current update operation are obtained. The multiple second-update lineups obtained from the current update operation are used as the game lineups before the next update operation. An initial lineup set is obtained based on the multiple second-update lineups obtained from the last update operation.

[0131] In some possible implementations, the update operation also includes an element replacement operation; When the optimization module 1202 obtains multiple second-update lineups obtained from the current update operation by performing element swap operations on at least some of the virtual attributes of multiple first-update lineups, it is specifically used for: Perform an element swap operation on a virtual attribute of at least some of the multiple first-update lineups to obtain multiple third-update lineups; Perform element replacement operations on virtual attributes in at least some of the multiple third-update lineups to obtain multiple second-update lineups.

[0132] In some possible implementations, at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters; The device also includes an adjustment module for: Based on at least one target ladder lineup, calculate the evaluation value of each virtual character in the lineup element database; the evaluation value includes at least one of the virtual character's appearance count or frequency in at least one target ladder lineup; Adjust the virtual attributes of virtual characters whose evaluation values ​​exceed the reference range; Based on the adjusted lineup element database, generate multiple new initial game lineups; Perform at least one lineup optimization operation on multiple new initial game lineups to obtain the corresponding new target ladder lineups.

[0133] The data processing device of this application performs lineup optimization operations on a lineup unit basis when optimizing a portion of the lineups in multiple first game lineups. That is, at least two lineup elements in a lineup unit are bound together for exchange operations. The first game lineups are already strong game lineups selected through lineup strength screening. This exchange operation method can further optimize the first game lineups while controlling the range of change, avoiding the possibility that the lineups will not be optimized due to too large a range of change during the optimization process. It can more efficiently discover target ladder lineups.

[0134] Furthermore, by using a trained strength prediction model to determine the strength of the initial game lineup, it is not necessary to play against multiple reference lineups in real time to determine the lineup strength. This can effectively improve the prediction efficiency of lineup strength, especially when the number of initial game lineups is large. It can effectively reduce the time spent calculating lineup strength, thereby more efficiently identifying target ladder lineups.

[0135] Furthermore, through different levels of lineup optimization and update operations, firstly, at least one lineup optimization operation is performed on the initial lineup set at the lineup unit level to obtain multiple second game lineups. This allows the range of changes during the lineup optimization process to be controlled within a reasonable range. Then, at least one update operation is performed on at least some of the multiple second game lineups at the lineup unit level. This allows for further adjustments to the second game lineups, further optimizing them and thus more accurately identifying the target ladder lineups.

[0136] Furthermore, this solution can more accurately and efficiently identify target team compositions in the game, allowing for timely numerical adjustments to virtual characters or skills that are used too frequently or too infrequently, thereby improving game balance and ultimately enhancing the player experience.

[0137] The apparatus in this application embodiment can execute the method provided in this application embodiment. The implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0138] This application provides an electronic device, including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program stored in the memory, it can implement the method in any optional embodiment of this application.

[0139] Figure 13 A schematic diagram of the structure of an electronic device to which an embodiment of the present invention applies is shown, such as... Figure 13As shown, the electronic device can be a server or a user terminal, and it can be used to implement the methods provided in any embodiment of the present invention.

[0140] like Figure 13 As shown, the electronic device 1300 may primarily include at least one processor 1301. Figure 13 The diagram shows components such as a memory 1302, a communication module 1303, and an input / output interface 1304. Optionally, these components can be connected and communicate with each other via a bus 1305. It should be noted that... Figure 13 The structure of the electronic device 1300 shown is merely illustrative and does not constitute a limitation on the electronic devices to which the methods provided in the embodiments of this application are applicable.

[0141] The memory 1302 can be used to store operating systems and applications, etc. The applications can include computer programs that implement the methods shown in the embodiments of the present invention when invoked by the processor 1301, and can also include programs for implementing other functions or services. The memory 1302 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and computer programs, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disk storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0142] Processor 1301 is connected to memory 1302 via bus 1305 and implements corresponding functions by calling the application programs stored in memory 1302. Processor 1301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present invention disclosure. Processor 1301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0143] Electronic device 1300 can connect to a network via communication module 1303 (which may include, but is not limited to, components such as a network interface) to communicate with other devices (such as user terminals or servers) through the network and achieve data interaction, such as sending data to or receiving data from other devices. Communication module 1303 may include wired network interfaces and / or wireless network interfaces, meaning the communication module may include at least one of wired or wireless communication modules.

[0144] Electronic device 1300 can connect to required input / output devices, such as keyboards and display devices, via input / output interface 1304. Electronic device 1300 itself may have a display device, and other display devices can also be connected externally via interface 1304. Optionally, storage devices, such as hard drives, can also be connected via interface 1304 to store data from electronic device 1300, retrieve data from storage devices, or store data from storage devices into memory 1302. It is understood that input / output interface 1304 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to input / output interface 1304 can be a component of electronic device 1300 or an external device connected to electronic device 1300 when needed.

[0145] The bus 1305 used to connect the components may include a path for transmitting information between the components. The bus 1305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Depending on its function, the bus 1305 may be divided into an address bus, a data bus, a control bus, etc.

[0146] Optionally, for the solution provided in the embodiments of the present invention, the memory 1302 can be used to store a computer program that executes the solution of the present invention, and the processor 1301 runs the computer program. When the processor 1301 runs the computer program, it implements the operation of the method or apparatus provided in the embodiments of the present invention.

[0147] Based on the same principle as the method provided in the embodiments of this application, the embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0148] This application also provides a computer program product, which includes a computer program that, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0149] It should be noted that the terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0150] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0151] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A data processing method, characterized in that, include: Obtain the initial lineup set; the initial lineup set includes multiple initial game lineups; Each of the initial game lineups includes at least two lineup units, and each lineup unit includes at least two lineup elements, the lineup elements including virtual characters in the game or at least one virtual attribute possessed by virtual characters; Perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and determine at least one target ladder lineup based on the optimized initial lineup set. The lineup optimization operation includes: For each initial game lineup in the initial lineup set, the lineup features of the initial game lineup are obtained; the lineup features are input into the trained strength prediction model to obtain the lineup strength of the initial game lineup; wherein, the lineup features include the element features of each lineup element contained in the game lineup; the strength prediction model is trained based on multiple sample game lineups and the sample lineup strength corresponding to each sample game lineup; The initial game lineup with a lineup strength higher than a first preset threshold in the initial lineup set is taken as the first game lineup; Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least a portion of the multiple first game lineups, using lineup units as the unit. Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least a portion of the multiple second game lineups for at least one lineup element. Each update operation targets the same lineup element, and the update operation includes at least one of element swapping or element replacement.

2. The data processing method according to claim 1, characterized in that, The intensity prediction model was trained in the following manner: Obtain multiple sample game lineups; For each sample game lineup, the sample game lineup is compared with multiple preset reference lineups, and the sample lineup strength is determined based on the comparison results. Obtain the sample lineup features for each of the sample game lineups; Based on the sample lineup features and corresponding sample lineup strength of each sample game lineup, the initial prediction model is trained to obtain the strength prediction model.

3. The data processing method according to claim 1, characterized in that, The lineup elements include virtual characters; the update operation includes element replacement operation; The step of obtaining a new initial lineup set by performing at least one update operation on at least a portion of the plurality of second game lineups for at least one lineup element includes: For virtual characters in at least a portion of the multiple second game lineups, obtain replaceable characters corresponding to the virtual characters; A new initial lineup set is obtained by replacing at least one of the virtual characters in at least a portion of the plurality of second game lineups with the replaceable characters.

4. The data processing method according to claim 1, characterized in that, The lineup elements include at least one virtual attribute possessed by the virtual character; the update operation includes an element swapping operation; The update operation includes the following steps: Determine the strength of each game lineup before the current update operation; the game lineup before the first update operation is the second game lineup; the game lineup before each update operation other than the first one is the game lineup obtained from the previous update operation; Multiple first updated lineups are determined from the game lineups prior to the multiple update operations based on the determined lineup strength; By performing an element swap operation on at least a portion of the virtual attributes of the plurality of first updated lineups, a plurality of second updated lineups obtained in the current update operation are obtained. The multiple second-update lineups obtained from the current update operation are used as the game lineups before the next update operation, and the initial lineup set is obtained based on the multiple second-update lineups obtained from the last update operation.

5. The data processing method according to claim 4, characterized in that, The update operation also includes element replacement operations; The process of obtaining multiple second-updated lineups by performing an element swap operation on a virtual attribute of at least a portion of the multiple first-updated lineups to achieve the current update operation includes: Perform an element swap operation on a virtual attribute of at least some of the multiple first update lineups to obtain multiple third update lineups; The virtual attributes in at least a portion of the plurality of third-update lineups are replaced with elements to obtain the plurality of second-update lineups.

6. The data processing method according to claim 1, characterized in that, The at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters, wherein a virtual character possesses at least one virtual attribute; The step of obtaining a new initial lineup set by performing at least one update operation on at least a portion of the plurality of second game lineups for at least one lineup element includes: Multiple third game lineups are obtained by performing an update operation on at least one virtual character in at least a portion of the multiple second game lineups; The strength of multiple third game lineups is determined, and multiple fourth game lineups are determined from the multiple third game lineups based on the determined lineup strengths. A new initial lineup set is obtained by updating at least one virtual attribute of at least some of the multiple fourth game lineups; the at least one virtual attribute belongs to the same type of virtual attribute.

7. The data processing method according to claim 1, characterized in that, The at least two lineup elements include virtual characters and virtual attributes possessed by virtual characters; The method further includes: Based on the at least one target ladder lineup, the evaluation value of each virtual character in the lineup element database is calculated; the evaluation value includes at least one of the number of times or frequency of occurrence of the virtual character in the at least one target ladder lineup; Adjust the virtual attributes of virtual characters whose evaluation values ​​exceed the reference range; Based on the adjusted lineup element database, generate multiple new initial game lineups; Perform the lineup optimization operation at least once on the multiple new initial game lineups to obtain the corresponding new target ladder lineups.

8. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire an initial lineup set; the initial lineup set includes multiple initial game lineups; Each of the initial game lineups includes at least two lineup units, and each lineup unit includes at least two lineup elements, the lineup elements including virtual characters in the game or at least one virtual attribute possessed by virtual characters; The optimization module is used to perform at least one lineup optimization operation on the initial lineup set until a preset termination condition is met, and to determine at least one target ladder lineup based on the initial lineup set after lineup optimization. Specifically, when performing lineup optimization operations, the optimization module is used to: For each initial game lineup in the initial lineup set, the lineup features of the initial game lineup are obtained; the lineup features are input into the trained strength prediction model to obtain the lineup strength of the initial game lineup; wherein, the lineup features include the element features of each lineup element contained in the game lineup; the strength prediction model is trained based on multiple sample game lineups and the sample lineup strength corresponding to each sample game lineup; The initial game lineup with a lineup strength higher than a first preset threshold in the initial lineup set is taken as the first game lineup; Multiple second game lineups are obtained by performing lineup unit-based swapping operations on at least a portion of the multiple first game lineups, using lineup units as the unit. Using lineup elements as units, a new initial lineup set is obtained by performing at least one update operation on at least a portion of the multiple second game lineups for at least one lineup element. Each update operation targets the same lineup element, and the update operation includes at least one of element swapping or element replacement.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the data processing method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the data processing method according to any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the data processing method according to any one of claims 1-7.

Images