CN112717412A

CN112717412A - Data processing method, related device, equipment and storage medium

Info

Publication number: CN112717412A
Application number: CN202110089284.6A
Authority: CN
Inventors: 李旭冬; 袁明凯; 罗章龙; 严明
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-01-22
Filing date: 2021-01-22
Publication date: 2021-04-30
Anticipated expiration: 2041-01-22
Also published as: CN112717412B

Abstract

The application discloses a data processing method based on artificial intelligence technology, which comprises the following steps: acquiring a first array data set corresponding to a game to be analyzed; generating a second array capacity data set through a genetic algorithm based on the first array capacity data set; if the iteration frequency corresponding to the second formation data set reaches the iteration threshold, acquiring at least one of the occurrence frequency of each corresponding object name and the occurrence frequency of the skill name in each second formation data according to the second formation data set; and generating a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of appearance of the object name and the frequency of appearance of the skill name corresponding to each second formation data. The application also discloses a related device, equipment and a storage medium. The application is suitable for analyzing the games with formation combination, so that the reasonability of analyzing game data is improved, and the difficulty of adjusting the balance of the games is reduced.

Description

Data processing method, related device, equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a data processing method, a related apparatus, a device, and a storage medium.

Background

Simulation games (SLG) provide players with an environment that can mentally think of questions to deal with more complicated things, allowing players to freely control, manage and use people or things in the game, and achieving the goals required by the game through this free means and the players' brainstorming methods to fight against enemies.

SLG places great importance on the balance of the game, and game planners often need to make game balance adjustments before new versions of the game come online. At present, an abnormal hero and skill mining scheme based on a game configuration file can be adopted, namely whether the abnormal hero and the abnormal skill exist is judged through attributes and numerical values of the hero and the skill in the game configuration file.

However, the abnormal hero and skill mining scheme based on the game configuration file can only realize simple judgment, that is, only the rationality of a hero or a skill can be judged, and the rationality of the game form is difficult to analyze, so that the analysis of game data is single, and the difficulty in adjusting the balance of the game is increased.

Disclosure of Invention

The embodiment of the application provides a data processing method, a related device, equipment and a storage medium. The method and the device are suitable for analyzing the games with the formation combination, and the abnormal hero and skill are excavated from the formation of a plurality of high strengths, so that the reasonability of game data analysis is improved, and the difficulty of adjusting the balance of the games is reduced.

In view of the above, an aspect of the present application provides a data processing method, including:

acquiring a first array data set corresponding to a game to be analyzed, wherein the first array data set comprises M first array data, each first array data comprises R gene information, the R gene information comprises at least one of an object name and a skill name, and M and R are integers greater than 1;

generating a second array capacity data set through a genetic algorithm based on the first array capacity data set, wherein the second array capacity data set comprises M second array capacity data, and each second array capacity data comprises R pieces of gene information;

if the iteration frequency corresponding to the second formation data set reaches the iteration threshold, acquiring at least one of the occurrence frequency of the object name and the occurrence frequency of the skill name in each second formation data according to the second formation data set;

and generating a game analysis result corresponding to the game to be analyzed according to at least one of the object name occurrence frequency and the skill name occurrence frequency in each second formation data.

Another aspect of the present application provides a data processing apparatus, including:

the game analysis device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a first array data set corresponding to a game to be analyzed, the first array data set comprises M first array data, each first array data comprises R pieces of gene information, the R pieces of gene information comprise at least one of object names and skill names, and both M and R are integers larger than 1;

the generating module is used for generating a second array capacity data set through a genetic algorithm based on the first array capacity data set, wherein the second array capacity data set comprises M second array capacity data, and each second array capacity data comprises R pieces of gene information;

the obtaining module is further configured to obtain at least one of an occurrence frequency of an object name and an occurrence frequency of a skill name in each second lineup data according to the second lineup data set if the iteration number corresponding to the second lineup data set reaches an iteration threshold;

and the generating module is further used for generating a game analysis result corresponding to the game to be analyzed according to at least one of the object name occurrence frequency and the skill name occurrence frequency in each second formation data.

In one possible design, in another implementation of another aspect of an embodiment of the present application,

the generating module is specifically used for acquiring a cross-array capacity data set through a genetic algorithm based on the first array capacity data set, wherein the cross-array capacity data set comprises N cross-array capacity data, each cross-array capacity data comprises R pieces of gene information, and N is an integer greater than 1;

acquiring a variant lineup data set through a genetic algorithm based on a cross lineup data set, wherein the variant lineup data set comprises N variant lineup data, and each variant lineup data comprises R pieces of gene information;

performing interactive processing on each variant lineup data and a reference lineup data set to obtain the fitness corresponding to each variant lineup data, wherein the reference lineup data set comprises P reference lineup data, each reference lineup data comprises R pieces of gene information, and P is an integer greater than or equal to 1;

and acquiring a second array capacity data set from the first array capacity data set and the variant array capacity data set according to the fitness corresponding to each first array capacity data in the first array capacity data set and the fitness corresponding to each variant array capacity data in the variant array capacity data set.

the acquisition module is further used for acquiring a configuration information set corresponding to the game to be analyzed before the generation module carries out interactive processing on each variant lineup data and the reference lineup data set to obtain the fitness corresponding to each variant lineup data, wherein the configuration information set comprises at least two groups of configuration information, and each group of configuration information comprises at least one of an object name and a skill name;

the generating module is further configured to generate a reference lineup data set according to the configuration information set, where the reference lineup data set includes P reference lineup data, each reference lineup data includes R pieces of gene information, and P is an integer greater than or equal to 1.

the generating module is further used for generating an initial formation data set according to the configuration information set after the configuration information set corresponding to the game to be analyzed is acquired by the acquiring module, wherein the initial formation data set comprises M initial formation data, and each initial formation data comprises R pieces of gene information;

and the generating module is further used for generating a third array capacity data set through a genetic algorithm based on the initial array capacity data set, wherein the third array capacity data set comprises M third array capacity data, each third array capacity data comprises R pieces of gene information, and the iteration frequency corresponding to the third array capacity data set is less than or equal to the iteration frequency corresponding to the first array capacity data set.

the generating module is specifically configured to obtain a first array data subset from the first array data set, where the first array data subset includes Q first array data, and Q is an integer greater than 1 and smaller than M;

selecting parent lineup data and parent lineup data from the first lineup data subset, wherein the parent lineup data is one of the Q first lineup data, and the parent lineup data is the other of the Q first lineup data;

randomly obtaining T gene positions, wherein the T gene positions correspond to T gene information, the gene positions and the gene information have one-to-one correspondence, the T gene information comprises at least one of an object name and a skill name, and T is an integer which is greater than or equal to 1 and smaller than R;

exchanging T gene information corresponding to T gene positions in the father lineup data with T gene information corresponding to T gene positions in the mother lineup data to obtain first cross lineup data and second cross lineup data, wherein the first cross lineup data and the second cross lineup data both belong to a cross lineup data set.

the generating module is specifically configured to determine, according to the fitness corresponding to each first array data in the first array data set and the fitness sum corresponding to the first array data set, a selection probability corresponding to each first array data in the first array data set;

determining the cumulative probability corresponding to each first array data in the first array data set according to the selection probability corresponding to each first array data in the first array data set;

generating Q random numbers;

and acquiring a first array data subset from the first array data set according to the Q random numbers and the cumulative probability corresponding to each first array data in the first array data set.

the generating module is specifically used for generating a random numerical value corresponding to each gene information in each cross-array capacity data aiming at each cross-array capacity data in the cross-array capacity data set;

for each cross array capacity data in the cross array capacity data set, if the random value corresponding to the gene information is less than or equal to the variation probability, updating the gene information to obtain target gene information;

for each cross array capacity data in the cross array capacity data set, if a random value corresponding to the gene information is greater than the variation probability, determining the gene information as original gene information;

and acquiring variant lineup data corresponding to each cross lineup data in the cross lineup data set, wherein the variant lineup data comprises at least one of target gene information and original gene information.

for each cross array capacity data in the cross array capacity data set, if the random value corresponding to the gene information is less than or equal to the variation probability corresponding to the gene information, performing replacement processing on the gene information to obtain target gene information;

for each cross array capacity data in the cross array capacity data set, if a random numerical value corresponding to the gene information is greater than a mutation probability corresponding to the gene information, determining the gene information as original gene information;

the generating module is specifically used for performing interactive processing on each variant lineup data and the reference lineup data set to obtain the number of winning plays, the number of tie plays and the total number of plays corresponding to each variant lineup data;

determining the optimal average rate corresponding to each variable array capacity data according to the number of winning orders, the number of putting orders and the total number corresponding to each variable array capacity data;

and determining the optimal rate corresponding to each variable formation capacity data as the fitness corresponding to each variable formation capacity data.

the generating module is specifically configured to sort, according to a sequence from high fitness to low fitness, the M first array capacity data in the first array capacity data set and the N variant array capacity data in the variant array capacity data set to obtain (M + N) array capacity data;

performing deduplication processing on the (M + N) pieces of array capacity data to obtain a target array capacity data set, wherein the deduplication processing is to reserve the same array capacity with the maximum fitness in at least two pieces of same array capacity data and delete the remaining array capacity data of the at least two pieces of same array capacity data, the target array capacity data set comprises Y pieces of array capacity data, and Y is an integer which is greater than 1 and less than or equal to (M + N);

grouping the target formation data set to obtain at least two second formation data subsets, wherein each second formation data subset comprises at least one formation data;

and sequentially selecting the formation data with the maximum fitness from each second formation data subset until the selection times threshold is reached, and obtaining a second formation data set.

the generating module is specifically used for acquiring the total occurrence frequency of the object names according to the occurrence frequency of the object names in each second lineup data;

acquiring the total occurrence frequency of the skill names according to the occurrence frequency of the skill names in each second formation data;

if the total frequency of the object names is greater than or equal to the first maximum frequency, generating a first analysis result, wherein the first analysis result belongs to a game analysis result corresponding to the game to be analyzed;

if the total frequency of the object names is less than or equal to the first minimum frequency, generating a second analysis result, wherein the second analysis result belongs to a game analysis result corresponding to the game to be analyzed;

if the total occurrence frequency of the skill names is greater than or equal to the second maximum frequency, generating a third analysis result, wherein the third analysis result belongs to the game analysis result corresponding to the game to be analyzed;

and if the total occurrence frequency of the skill names is less than or equal to the second minimum frequency, generating a fourth analysis result, wherein the fourth analysis result belongs to the game analysis result corresponding to the game to be analyzed.

the generating module is specifically configured to obtain the common occurrence frequency corresponding to the first object name and the second object name according to the occurrence frequency of the object name in each second lineup data, where the first object name and the second object name are derived from the same second lineup data;

and if the common occurrence frequency is greater than or equal to the third maximum frequency, generating a fifth analysis result, wherein the fifth analysis result belongs to the game analysis result corresponding to the game to be analyzed.

the generating module is specifically configured to obtain the common occurrence frequency corresponding to the first skill name and the second skill name according to the occurrence frequency of the skill names in each second lineup data, where the first skill name and the second skill name are derived from the same second lineup data;

and if the common occurrence frequency is greater than or equal to the fourth maximum frequency, generating a sixth analysis result, wherein the sixth analysis result belongs to the game analysis result corresponding to the game to be analyzed.

the generating module is specifically used for acquiring the common occurrence frequency of the target object name and the target skill name according to the occurrence frequency of the object name and the occurrence frequency of the skill name in each second lineup data, wherein the target object name and the target skill name are derived from the same second lineup data;

and if the common occurrence frequency is greater than or equal to the fifth maximum frequency, generating a seventh analysis result, wherein the seventh analysis result belongs to the game analysis result corresponding to the game to be analyzed.

Another aspect of the present application provides a computer device, comprising: a memory, a processor, and a bus system;

wherein, the memory is used for storing programs;

a processor for executing the program in the memory, the processor for performing the above-described aspects of the method according to instructions in the program code;

the bus system is used for connecting the memory and the processor so as to enable the memory and the processor to communicate.

Another aspect of the present application provides a computer-readable storage medium having stored therein instructions, which when executed on a computer, cause the computer to perform the method of the above-described aspects.

In another aspect of the application, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided by the above aspects.

According to the technical scheme, the embodiment of the application has the following advantages:

in the embodiment of the application, a data processing method is provided, which includes the steps of firstly obtaining a first array data set corresponding to a game to be analyzed, then generating a second array data set through a genetic algorithm based on the first array data set, if the iteration frequency corresponding to the second array data set reaches an iteration threshold, obtaining at least one of the occurrence frequency of an object name and the occurrence frequency of a skill name in each second array data according to the second array data set, and finally generating a game analysis result corresponding to the game to be analyzed according to the at least one of the occurrence frequency of the object name and the occurrence frequency of the skill name in each second array data. Through the mode, but utilize genetic algorithm automatic generation second lineup data set, if present iteration number reaches the iteration threshold value, then think that second lineup data set is the lineup of a plurality of high strengths, based on this, this application is applicable to the recreation that the analysis has the lineup combination, excavates unusual hero and skill from the lineup of a plurality of high strengths, promotes the rationality of analysis recreation data from this, is favorable to reducing the degree of difficulty of adjustment recreation equilibrium.

Drawings

FIG. 1 is a schematic diagram of an architecture of a game data analysis system according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of the game data analysis based on genetic algorithm in the embodiment of the present application;

FIG. 3 is a schematic diagram of an embodiment of a data processing method in an embodiment of the present application;

FIG. 4 is a schematic view of a scene of a game to be analyzed in the embodiment of the present application;

FIG. 5 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 6 is a schematic flow chart of the embodiment of the present application for generating a high-strength array capacity set based on a genetic algorithm;

FIG. 7 is a diagram illustrating the generation of a high-intensity lattice volume set based on a genetic algorithm in an embodiment of the present application;

FIG. 8 is a schematic flow chart of genetic algorithm-based genetic information crossover implementation in an embodiment of the present application;

FIG. 9 is a schematic diagram of a process for performing genetic information mutation based on genetic algorithm in the present embodiment;

FIG. 10 is a schematic flow chart of implementing formation data evolution based on genetic algorithm in the embodiment of the present application;

FIG. 11 is a schematic diagram of an interface showing the results of game analysis in the embodiment of the present application;

FIG. 12 is a schematic diagram of another interface showing the results of game analysis in the embodiment of the present application;

FIG. 13 is a schematic view of another interface showing the results of game analysis in the embodiment of the present application;

FIG. 14 is a schematic diagram of another interface showing the results of game analysis in the embodiment of the present application;

FIG. 15 is a schematic diagram of an embodiment of a data processing apparatus according to the present embodiment;

fig. 16 is a schematic structural diagram of a computer device in an embodiment of the present application.

Detailed Description

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "corresponding" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The game balance test is a very important part in the game test, and the balance of the game is often considered in the process of game development and planning. For the confrontational game, whether single confrontation or multi-confrontation, as long as a plurality of strategies are available for the players to choose, the balance among the strategies is a problem to be considered. However, it is not simple to evaluate the balance of the game, and on the one hand, the number of strategies involved in the game is usually large, because there is sufficient play and selection space, resulting in a large amount of time and effort for manual evaluation. On the other hand, the strategy in the game is also dynamically changed, and as the developer modifies the game content (for example, strengthen or weaken a certain virtual object, push a new virtual object, etc.), the balance of the current game may be impacted.

Based on the above, the application provides a data processing method, which can automatically select the high-strength lineup in the game, analyze the high-strength lineup, and based on the game analysis result, a developer can adjust the value in the game or online the game. Referring to fig. 1, fig. 1 is a schematic structural diagram of a game data analysis system according to an embodiment of the present application, and as shown in the drawing, the game data analysis system may include a terminal device and a server, a developer inputs configuration information of a game to be analyzed through the terminal device, and the configuration information forms a configuration file. In the data analysis stage, the server or the terminal equipment can generate an initial lineup data set and a reference lineup data set according to the configuration file, and each initial lineup data in the initial lineup data set can compete with the reference lineup data set, so that the fitness of each initial lineup data is obtained. And processing the initial formation capacity data set by adopting a genetic algorithm to obtain a next generation formation capacity data set, then continuously processing the next generation formation capacity data set by adopting the genetic algorithm to obtain a formation capacity data set of the next generation, and so on until the iteration times reach an iteration threshold value, thereby obtaining a plurality of high-strength formation capacities.

The server related to the application can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, safety service, Content Delivery Network (CDN), big data and an artificial intelligence platform. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a palm computer, a personal computer, a smart television, a smart watch, and the like. The terminal device and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein. The number of servers and terminal devices is not limited.

It should be noted that the process of selecting a high-strength lineup can be implemented based on an Artificial Intelligence (AI) technology, and the purpose of automatic selection can be achieved without manual participation. AI is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, AI is an integrated technique of computer science that attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence. AI is to study the design principles and implementation methods of various intelligent machines, so that the machine has the functions of perception, reasoning and decision making.

The AI technology is a comprehensive subject, and relates to the field of extensive technology, both hardware level technology and software level technology. The AI base technologies generally include technologies such as sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technologies, operating/interactive systems, mechatronics, and the like. The AI software technology mainly includes several directions, such as computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.

For ease of understanding, the process of analyzing game data will be described with reference to fig. 2, please refer to fig. 2, and fig. 2 is a schematic flow chart of analyzing game data based on genetic algorithm in the embodiment of the present application, and as shown in the figure, specifically:

in step S1, the configuration file of the current game version is first read.

In step S2, an initial lineup data set is generated by acquiring the selectable object name and skill name from the configuration file, where the initial lineup data set includes M initial lineup data.

In step S3, a next generation lineup data set of the initial lineup data set is then generated using a genetic algorithm, wherein the next generation lineup data set also includes M lineup data.

In step S4, after multiple rounds of evolution, when the number of iterations reaches an iteration threshold, a high-strength array capacity data set is obtained, where the high-strength array capacity data set includes M high-strength array capacity data.

In step S5, the high-intensity formation data set is statistically analyzed to generate a game analysis result.

In step S6, the object name and skill name are finally mined based on the game analysis result whether there is an abnormality.

With reference to fig. 3, a data processing method in the present application will be described below, and an embodiment of the data processing method in the embodiment of the present application includes:

101. acquiring a first array data set corresponding to a game to be analyzed, wherein the first array data set comprises M first array data, each first array data comprises R gene information, the R gene information comprises at least one of an object name and a skill name, and M and R are integers greater than 1;

in this embodiment, the data processing device determines a game to be analyzed, and obtains a first array data set corresponding to the game to be analyzed, where the first array data set includes M first array data, and each first array data includes R pieces of genetic information, for example, M is equal to 300, and R is equal to 9. The R pieces of genetic information include at least one of object names and skill names, wherein the object names represent names of virtual objects, the virtual objects may refer to game characters in the game to be analyzed, one virtual object corresponds to a unique object name, and one virtual object corresponds to at least one skill name.

Specifically, taking the game to be analyzed as a simulation-like game (SLG) as an example for convenience of understanding, please refer to fig. 4, fig. 4 is a schematic diagram of a scenario of the game to be analyzed in the embodiment of the present application, and as shown in the figure, it is assumed that the game to be analyzed adopts a battle mode of 3 pairs (VS) 3, that is, each party can generate three cards, wherein the object name of the first card is "charming Tun", the skill name of the first card is "solstice" and "revitalization rest", the object name of the second card is "canadian", the skill name of the first card is "backwater-fighting" and "hard rock", the object name of the third card is "charming houyangtou", the skill name of the third card is "no purpose" and "who goes to leave me".

From these cards, a formation data may be generated, which comprises R pieces of genetic information, for example, with 9 pieces of genetic information, as in fig. 4, and these 9 pieces of genetic information comprise object names and skill names, which may be expressed as [ charcot Tun, solo lang, medicina, canadum, backland-water warfare, prankpan, charhou yuo, no intention, who she. It is understood that the amount of genetic information included in each piece of formation data, and the content included in the R pieces of genetic information may be set according to actual conditions, for example, the formation data may also be expressed as [ charm Tun, cao nao, charm yuan ], or expressed as [ solemn champion, revitalization, backland warfare, strong as rock, no purpose of going out enemies, who goes out of mystery ], which is described in the embodiment of the present application by taking the R pieces of genetic information including object names and skill names, but this should not be construed as a limitation to the present application.

It should be noted that the data processing apparatus may be disposed in a computer device, and the computer device may be a terminal device, a server, or a game data analysis system formed by the terminal device and the server, which is not limited herein.

102. Generating a second array capacity data set through a genetic algorithm based on the first array capacity data set, wherein the second array capacity data set comprises M second array capacity data, and each second array capacity data comprises R pieces of gene information;

in this embodiment, the data processing apparatus processes the first array content data set by using a genetic algorithm to obtain a second array content data set. The second array capacity data set comprises M second array capacity data, namely the total amount of the array capacity data included in the second array capacity data set is equal to the total amount of the array capacity data included in the first array capacity data set, and the total amount of the array capacity data included in the second array capacity data set is M. And the total amount of the genetic information included in each second array data is equal to the total amount of the genetic information included in each first array data, and is R.

Specifically, each piece of gene information corresponds to a gene position, and for the first array data and the second array data, the corresponding gene positions have the same gene information type, for example, the gene information at the gene position 0 in the first array data is an object name, the gene information at the gene position 0 in the second array data is also an object name, and for example, the gene information at the gene position 1 in the first array data is a skill name, and the gene information at the gene position 1 in the second array data is also a skill name.

For convenience of description, please refer to table 1, in which R is equal to 9, and R pieces of gene information include object names and skill names, and table 1 is an illustration of the R pieces of gene information.

TABLE 1

In the example shown in table 1 and fig. 4, the genetic information of gene position No. 0 is "object name 1", and "object name 1" may be "summer Tun", the genetic information of gene position No. 1 is "skill name 1", and "skill name 1" may be "solstice", the genetic information of gene position No. 2 is "skill name 2", and "skill name 2" may be "health maintenance". The genetic information of gene position No. 3 is "object name 2", and "object name 2" may be "caochun", the genetic information of gene position No. 4 is "skill name 3", and "skill name 3" may be "backland war", the genetic information of gene position No. 5 is "skill name 4", and "skill name 4" may be "strong rock". The genetic information of gene position No. 6 is "object name 3", and "object name 3" may be "summer houyuan", the genetic information of gene position No. 7 is "skill name 5", and "skill name 5" may be "enemy", the genetic information of gene position No. 8 is "skill name 6", and "skill name 6" may be "who left him/herself".

It follows that it is assumed that each lineup data contains three virtual objects, i.e. has three object names, and that each dummy your object carries two skills. Then a lattice data can be encoded as a 9-bit gene using symbolic encoding, i.e., [ HSSHSSHSS ], where H denotes the object name and S denotes the skill name. Different object names or skill names can be filled in each gene position, namely different object names can be filled in hero positions, and different skill names can be filled in skill positions. Alternatively, other gene coding schemes may be used to represent the lattice data.

It should be noted that Genetic Algorithm (GA) refers to a computational model of a biological evolution process that simulates natural selection and Genetic mechanism of darwinian biological evolution theory, i.e., a method for searching an optimal solution by simulating a natural evolution process. The genetic algorithm adopts a probabilistic optimization method, can automatically acquire and guide an optimized search space without a determined rule, and adaptively adjusts the search direction.

103. If the iteration frequency corresponding to the second formation data set reaches the iteration threshold, acquiring at least one of the occurrence frequency of the object name and the occurrence frequency of the skill name in each second formation data according to the second formation data set;

in this embodiment, after the data processing apparatus generates the second array capacity data set, it is further required to determine whether the current iteration number reaches an iteration threshold, where the current iteration number is an iteration number corresponding to the second array capacity data set, and assuming that the second array capacity data set is obtained when the iteration is 100 times, the iteration number corresponding to the second array capacity data set is 100. It should be noted that the iteration threshold may be set to 120, or 150, or another value, which is not limited herein.

Specifically, if the iteration number corresponding to the second lineup data set reaches the iteration threshold, it is determined that the second lineup data set is the high-strength lineup data set, and then the second lineup data set may be counted and analyzed, so as to obtain the occurrence frequency of the object name in each second lineup data or the occurrence frequency of the skill name in each second lineup data, and also obtain the occurrence frequency of the object name in each second lineup data and the occurrence frequency of the skill name in each second lineup data.

104. And generating a game analysis result corresponding to the game to be analyzed according to at least one of the object name occurrence frequency and the skill name occurrence frequency in each second formation data.

In this embodiment, the data processing device generates a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data. Based on this, by counting a plurality of high-intensity formation data, it is possible to more efficiently and accurately mine the abnormal object name and skill name.

With reference to the introduction of steps 101 to 104, the following will be further described with reference to fig. 5, please refer to fig. 5, where fig. 5 is a schematic flow chart of a data processing method in an embodiment of the present application, and as shown in the figure, specifically:

in step a1, the configuration file of the current game version is read first to obtain all object names and skill names in the game, then an initial formation data set and a reference formation data set are generated, and finally the optimal rate of each initial formation data in the initial formation data set is calculated.

In step a2, the initial formation data set is subjected to multiple rounds of operations of crossing, mutation, evaluation and evolution by using a genetic algorithm, so as to obtain a high-strength formation data set of the current game version.

In step a3, the high-intensity formation data set is statistically analyzed to obtain game analysis results.

In step a4, it is determined whether or not an abnormal object name or skill name exists based on the game analysis result, and if so, step a5 is executed, and if not, the flow of game data analysis is ended.

In step a5, if there is an abnormality in the frequency of occurrence of a certain object name or skill name in the high-strength lineup data set, it is determined that there is an abnormal object name or skill name, and a corresponding warning prompt is output.

In the embodiment of the application, a data processing method is provided, and through the mode, the second formation data set can be automatically generated by using a genetic algorithm, if the current iteration times reach the iteration threshold value, the second formation data set is considered to be the formation of a plurality of high strengths, and based on the method, the method is suitable for analyzing games with formation combinations, abnormal hero and skill are mined from the formation of the plurality of high strengths, the reasonability of game data analysis is improved, and the difficulty of adjusting the balance of the games is favorably reduced.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, the generating a second formation data set by a genetic algorithm based on the first formation data set specifically includes:

acquiring a cross-array capacity data set through a genetic algorithm based on the first array capacity data set, wherein the cross-array capacity data set comprises N cross-array capacity data, each cross-array capacity data comprises R pieces of gene information, and N is an integer greater than 1;

In this embodiment, a manner of obtaining the second set of array capacity numbers by using a genetic algorithm is described. Referring now to fig. 6, and referring to fig. 6, fig. 6 is a schematic flow chart of generating a high-strength array capacity set based on a genetic algorithm according to an embodiment of the present application, and specifically as shown in the figure:

in step B1, a first set of array data is input, where the first set of array data includes M first array data, for example, M equals 300, i.e., the first set of array data includes 300 first array data. It is understood that the first array data set may be obtained after the initial array data set is iterated for a plurality of times, or the first array data set is the initial array data set. In addition, a reference formation data set needs to be input, and the reference formation data set is used for calculating the fitness of each first formation data.

In step B2, any two first data arrays are selected from the first data arrays for cross processing to obtain cross-array data, and when a plurality of pairs of first data arrays are cross-processed, a cross-array data set is obtained, where the cross-array data set includes N cross-array data, where N may be equal to M, e.g., N is equal to 300, and each cross-array data includes R pieces of genetic information, e.g., R is equal to 9.

Wherein, the cross processing means cutting off the gene information at one or more identical gene positions in two chromosomes (i.e. two first array data), and then respectively combining the two strings of the first and second chromosomes in a cross way to form two new chromosomes (i.e. two cross array data), and this process is also called gene recombination or hybridization.

In step B3, performing mutation processing on each of the cross-lineup data to obtain variant lineup data, so that N variant lineup data can be obtained based on the N cross-lineup data, and each of the variant lineup data includes R pieces of genetic information. And if the variation of certain cross-lineup data is not successful, the generated variant lineup data is the cross-lineup data.

The mutation process means that some replication errors may occur (with a small probability) during replication, and the mutation generates a new chromosome (i.e., mutation array data) and shows a new trait.

In step B4, each variant lineup data and a reference lineup data set are processed interactively to obtain the fitness corresponding to each variant lineup data, wherein the reference lineup data set is obtained in advance, the reference lineup data set includes P reference lineup data, and each reference lineup data includes R pieces of genetic information.

The interactive processing represents that the variant lineup data and the reference lineup data are adopted for fighting, and if the reference lineup data set comprises 5000 reference lineup data, a certain variant lineup data is respectively matched with the 5000 reference lineup data to obtain a fighting result (such as victory, tie or failure).

In step B5, after obtaining the fitness corresponding to each first array data and the fitness corresponding to each variant array data, it is necessary to preferentially select array data with higher fitness, where these array data are the second array data set, and the selection process is the evolution process. Wherein the second set of lineup data comprises M second lineup data.

In step B6, it is determined whether the iteration number corresponding to the second lattice volume data set reaches an iteration threshold, if so, step B7 is executed, otherwise, if not, step B2 is skipped, i.e., the next iteration is performed.

In step B7, if the iteration threshold is reached, the second set of capacity data is determined to be the high-strength set of capacity data, and the high-strength set of capacity data is output.

Secondly, in the embodiment of the application, a mode of acquiring a second lineup quantity set by using a genetic algorithm is provided, and by the above mode, a plurality of high-strength lineup data can be generated by using the genetic algorithm, and then the occurrence frequency of object names and skill names in the high-strength lineup data is analyzed, so that whether abnormal object names and skill names exist in the current game version is judged, and therefore the effects of virtual objects and skill types in lineup can be effectively analyzed in a short time, and the abnormal object names and skill names can be found more accurately.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, before performing interactive processing on each variant lineup data and the reference lineup data set to obtain the fitness corresponding to each variant lineup data, the method may further include:

acquiring a configuration information set corresponding to a game to be analyzed, wherein the configuration information set comprises at least two groups of configuration information, and each group of configuration information comprises at least one of an object name and a skill name;

and generating a reference lineup data set according to the configuration information set, wherein the reference lineup data set comprises P reference lineup data, each reference lineup data comprises R pieces of gene information, and P is an integer greater than or equal to 1.

In this embodiment, a way of reading a configuration file to generate a reference lineup data set is described. Before processing the array data by using the genetic algorithm, the configuration file of the game to be analyzed may also be read, where the configuration file is usually stored in a file form, for example, in a form of spreadsheet (Excel), a configuration information set is stored in the configuration file, and the configuration information set includes at least two sets of configuration information, each set of configuration information includes at least one of an object name and a skill name, and in addition, other attributes of the virtual object may also be included, and for convenience of understanding, please refer to table 2, where table 2 is one illustration of the configuration information set.

TABLE 2

Table 2 shows nine sets of configuration information, each set of configuration information includes an object name, a skill name, a marketing, and basic attributes, it should be noted that table 2 only shows two skill names, and each virtual object may have other numbers of skills in practical applications.

A set of reference lineup data may be generated based on the set of configuration information, and taking as an example that each reference lineup data includes 9 pieces of genetic information, the 9 pieces of genetic information in the reference lineup data are arranged in the same manner as the 9 pieces of genetic information in the first lineup data, which may be denoted as [ HSSHSSHSS ]. Typically, the number of lineups included in the reference lineup data set is greater than the number of lineups included in the first lineup data set, e.g. the reference lineup data set includes 5000 reference lineup data, i.e. P may be equal to 5000. It should be noted that the reference lineup data set does not include repeated reference lineup data.

In the embodiment of the application, a mode of reading the configuration file to generate the reference formation data set is provided, and through the mode, the reference formation data set can be generated by combining the configuration file of the game to be analyzed, and the fitness can be determined by using the reference formation data set, so that the feasibility and the operability of the scheme are improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, after obtaining the configuration information set corresponding to the game to be analyzed, the method may further include:

generating an initial lineup data set according to the configuration information set, wherein the initial lineup data set comprises M initial lineup data, and each initial lineup data comprises R pieces of gene information;

and generating a third array capacity data set through a genetic algorithm based on the initial array capacity data set, wherein the third array capacity data set comprises M third array capacity data, each third array capacity data comprises R pieces of gene information, and the iteration times corresponding to the third array capacity data set are less than or equal to the iteration times corresponding to the first array capacity data set.

In this embodiment, a way of reading a configuration file to generate an initial lineup data set is described. Before the array capacity data is processed by using a genetic algorithm, the configuration file of a game to be analyzed can be read, an initial array capacity data set can be generated based on a configuration information set stored in the configuration file, the generation mode of the initial array capacity data set is similar to that of a reference array capacity data set, a corresponding object name or skill name at each gene position is randomly selected, and each gene information in the same array capacity data is ensured to be different in the random process. Note that the initial lineup data set does not include repeated initial lineup data.

The initial formation data set is an initial population of the genetic algorithm, and a third formation data set of a next round is generated after the genetic algorithm, where the number of formation included in the third formation data set is equal to the number of formation included in the initial formation data set, for example, the third formation data set includes 300 third formation data, that is, M may be equal to 300. And the iteration times corresponding to the third array capacity data set are less than or equal to the iteration times corresponding to the first array capacity data set, and the initial array capacity data set forms a high-strength array capacity data set after multiple rounds of evolution.

For easy understanding, please refer to fig. 7, fig. 7 is a schematic diagram of generating a high-strength lineup set based on a genetic algorithm in the embodiment of the present application, and as shown in the figure, an initial lineup data set is first obtained, for example, an initial lineup data set is [ liu bei, bang, sinkiang and water break, xiao ji, dun ai, furious dispute, magic clever ] in the river. And then, performing cross processing on the initial array capacity data in the initial array capacity data set, performing mutation processing on the array capacity data set after the cross processing, and then evaluating and evolving the array capacity data set after the mutation processing. The evaluation mode is that each array capacity data (namely current array capacity data) after the mutation treatment is matched with each reference array capacity data in the reference array capacity data set, the reference array capacity data set is used for evaluating the fitness of the array capacity data, based on the fitness, M array capacity data with higher strength are screened out, and after multiple iterations, a high-strength array capacity data set is generated.

Furthermore, in the embodiment of the application, a mode of reading the configuration file to generate the initial lineup data set is provided, and through the mode, the initial lineup data set can be generated by combining the configuration file of the game to be analyzed, and then the initial lineup data set is subjected to iterative processing by using a genetic algorithm, so that the lineup data set with higher intensity can be continuously screened out.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, the obtaining, based on the first array-content data set, the cross array-content data set by a genetic algorithm specifically includes:

acquiring a first array data subset from the first array data set, wherein the first array data subset comprises Q first array data, and Q is an integer which is larger than 1 and smaller than M;

In this embodiment, a method for generating a cross-lattice data set is described. Taking the example that the first array-capacity data set includes 300 first array-capacity data, that is, M is equal to 300, a cross array-capacity data set is generated based on the first array-capacity data set, and the cross array-capacity data set may also include 300, that is, N is equal to 300.

For ease of understanding, please refer to fig. 8, fig. 8 is a schematic flow chart of implementing gene information crossing based on genetic algorithm in the embodiment of the present application, as shown in the figure, specifically;

in step C1, a first set of fitting data is obtained.

In step C2, a first sub-set of data is then obtained from the first sub-set of data, and since the first data in the first sub-set of data originates from the first sub-set of data, the first sub-set of data includes a smaller amount of data than the first set of data, i.e., Q is smaller than M, e.g., Q is equal to 150.

In step C3, the parent and parent lineup data are selected from the first subset of lineup data, for example, two different first lineup data are randomly selected from 150 first lineup data as the parent and parent lineup data. It can be understood that, in practical applications, multiple random selections need to be performed from the first array capacity data subset, that is, multiple pairs of parent array capacity data and parent array capacity data are obtained.

In step C4, gene information is interleaved between the parent and parent lattice content data. Suppose that two cross-matrix data are generated in a three-point cross (i.e. T is equal to 3) manner, then three different gene positions need to be randomly acquired, gene information at the three gene positions in the parent-matrix data and the parent-matrix data is exchanged, and the matrix data after the two genes are exchanged is generated as the cross-matrix data.

Exemplarily, it is assumed that the parent array data is [ liu bei, chang purple, war hack, dong zhao, sinqiao water break, owl in the river, dun ai, fierce wuxiong, miraculous calculations ], the parent array data is [ caoguo, qigong, wei sha huaxia, yao fei, renshi wujiang, huangtian chess, grand shang xiang, nam chu kou ji, suspen huji ], three randomly acquired gene positions are [0, 4, 6], the first skill corresponding to the parent array data and the first hero, the second hero, and the third hero array, based on which two cross array data are obtained, the first cross array data and the second cross array data are respectively, wherein the first cross array data is [ caoguo, chang purple, chang tai, dun lang, zhao, ben, wu shang jian, wu jiangchu, wu xiao xian, naojian xiao, the second cross formation data is [ Liu Bei, Long Dan Qi, Wei Sha Huaxia, Zhang Fei, bridge sinking and water stopping, Huangtian chess, Deng ai, Wen Zhong Kui, and Xuan Ji Shi Ji ].

It should be noted that, in addition to generating two cross-array capacity data by a three-point cross, two cross-array capacity data may be generated by a single-point cross (i.e., T is equal to 1) or a two-point cross (i.e., T is equal to 2), or by other cross, where T is an integer smaller than R.

In step C5, it is determined whether N pieces of cross-array data have been generated, if so, the process proceeds to step C6, otherwise, the process proceeds to step C3.

In step C6, if N cross-lineup data have been generated, a set of cross-lineup data is obtained.

In the embodiment of the application, a mode of generating a cross-array capacity data set is provided, and through the mode, partial gene information in two first array capacity data is exchanged by using a cross mechanism of a genetic algorithm, so that more new individuals are generated, a subsequent series of operations are facilitated, and the feasibility and operability of a scheme are improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in this embodiment of the present application, the obtaining a first array data subset from the first array data set specifically includes:

determining the selection probability corresponding to each first array data in the first array data set according to the fitness corresponding to each first array data in the first array data set and the fitness sum corresponding to the first array data set;

generating Q random numbers;

In this embodiment, a way of selecting a subset of the first array data based on the roulette algorithm is described. Firstly, the fitness corresponding to each first array data in the first array data set is obtained, wherein the fitness of the first array data is the optimal average rate of the first array data. And then, summing the fitness of each first array data to obtain the fitness sum corresponding to the first array data set. Based on this, the fitness of the first fitting data is divided by the sum of the fitness, and the selection probability of the first fitting data can be obtained. And then, determining the cumulative probability corresponding to the first array data according to the selection probability corresponding to the first array data.

Specifically, for ease of understanding, please refer to table 3, where table 3 illustrates one relationship between fitness, selection probability, and cumulative probability.

TABLE 3

In table 3, 5 pieces of first array data are taken as an example for introduction, and in practical application, selection probabilities and cumulative probabilities corresponding to M pieces of first array data may be generated. Based on this, a random number is generated, and assuming that the random number is 0.81, the number 3 first array data is selected into the first array data subset. Similarly, after generating Q random numbers, selecting the first array data from the first array data set based on each random number, and finally obtaining a first array data subset.

It should be noted that, in practical applications, in addition to the first sub-set of the array data obtained based on the roulette algorithm, the first sub-set of the array data obtained based on the roulette algorithm may also be obtained in other ways, such as random selection or sorting selection.

Further, in the embodiment of the present application, a way of selecting the first sub-set of the formation data based on the roulette algorithm is provided, by which formation data with a larger fitness can be extracted more easily by using the roulette algorithm, the roulette algorithm is a choice of putting back, that is, formation data that has already been selected can be selected again, and the selection probability of the formation data is equal to the fitness of the formation data divided by the sum of the fitness of all the formation data, because the higher the fitness of the formation data is, the stronger the formation data is, and therefore, the selection probability of the formation data is proportional to the fitness of the formation data.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, the obtaining a variant lineup data set through a genetic algorithm based on the cross lineup data set specifically includes:

generating a random numerical value corresponding to each gene information in each cross array capacity data aiming at each cross array capacity data in the cross array capacity data set;

In this embodiment, a way of generating a variant lineup data set is described. After the cross-array capacity data set is obtained, each cross-array capacity data needs to be subjected to mutation processing, and finally the mutation array capacity data corresponding to each cross-array capacity data is obtained.

For the convenience of understanding, the mutation processing of one cross-matrix data is described as an example, and the other cross-matrix data also obtains corresponding variant-matrix data in a similar manner. Referring to fig. 9, fig. 9 is a schematic flow chart of implementing genetic information variation based on genetic algorithm in the embodiment of the present application, as shown in the figure, specifically:

in step D1, a cross-lineup data set is input.

In step D2, for each cross-lineup data in the cross-lineup data set, a random value corresponding to each genetic information in each cross-lineup data is generated, where the random value is a value greater than or equal to 0 and less than or equal to 1.

In step D3, it is determined whether each genetic information in each cross-array data needs mutation, and if the random value corresponding to the genetic information is less than or equal to the mutation probability, the genetic information needs to be updated (i.e., mutated) to obtain the target genetic information. On the contrary, if the random value corresponding to the genetic information is greater than the mutation probability, the genetic information is directly determined as the original genetic information without carrying out mutation processing on the genetic information.

The mutation probability may be set to 0.05, or may be set to other values, which is not limited herein.

In step D4, if the gene information needs to be updated, the gene information that needs to be mutated is randomly replaced with other gene information (i.e., the object name or the skill name), and it is ensured that there is no duplicate object name and skill name in the mutated formation data. And generating variant array capacity data corresponding to the cross array capacity data according to at least one of the target gene information and the original gene information.

In step D5, it is determined whether all the cross-array capacity data in the cross-array capacity data set have been processed through steps D2 to D4, if yes, step D6 is executed, otherwise, step D2 is skipped.

In step D6, the cross-lineup data set is output.

In the embodiment of the application, a method for generating a variant lineup data set is provided, and by the method, genetic information can be subjected to variant processing according to a fixed probability, so that the variant lineup data set is generated, and feasibility and operability of a scheme are improved.

In this embodiment, another way of generating the variant lineup data set is described. After the cross-array capacity data set is obtained, each cross-array capacity data needs to be subjected to mutation processing, and finally the mutation array capacity data corresponding to each cross-array capacity data is obtained.

For the convenience of understanding, the mutation processing of one cross-matrix data is described as an example, and the other cross-matrix data also obtains corresponding variant-matrix data in a similar manner. Referring again to fig. 9, specifically:

in step D1, a cross-lineup data set is input.

In step D3, it is determined whether each genetic information in each cross-lineup data needs to be mutated, where each genetic information may correspond to a preset mutation probability. If the random value corresponding to the first genetic information is less than or equal to the first mutation probability, the first genetic information needs to be updated (i.e., mutated) to obtain the target genetic information. On the contrary, if the random value corresponding to the first genetic information is greater than the first mutation probability, the first genetic information is directly determined as the original genetic information without performing mutation processing on the first genetic information.

If the random value corresponding to the second genetic information is less than or equal to the second mutation probability, the second genetic information needs to be updated (i.e., mutated) to obtain the target genetic information. On the contrary, if the random value corresponding to the second genetic information is greater than the second mutation probability, the second genetic information is directly determined as the original genetic information without performing mutation processing on the second genetic information. Similarly, other genetic information may have different mutation probabilities.

It should be noted that the first variation probability may be set to 0.05, the second variation probability may be set to 0.08, and the first variation probability and the second variation probability may also be set to other values, which is not limited herein.

In step D4, if the genetic information needs to be updated, the genetic information that needs to be mutated is randomly replaced with other genetic information (i.e., object name or skill name), and it is ensured that there is no duplicate object name and skill name in the mutated formation data. And generating variant array capacity data corresponding to the cross array capacity data according to at least one of the target gene information and the original gene information.

In step D6, the cross-lineup data set is output.

In the embodiment of the application, another way of generating a variant lineup data set is provided, and by the way, the genetic information can be subjected to variant processing according to different probabilities, so that the variant lineup data set is generated, and the feasibility and the flexibility of the scheme are improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in the embodiment of the present application, each variant lineup data and the reference lineup data set are processed interactively to obtain a fitness corresponding to each variant lineup data, and the method specifically includes:

performing interactive processing on each variable array capacity data and the reference array capacity data set to obtain the number of winning plays, the number of ties and the total number of plays corresponding to each variable array capacity data;

In this embodiment, a method for determining fitness is described. The fitness corresponding to the array capacity data represents the dominance degree of the array capacity data in population survival, namely the fitness is used for distinguishing the good and the bad of the array capacity data. In the application, the fitness of the initial formation capacity data, the fitness of the first formation capacity data, the fitness of the second formation capacity data, the fitness of the third formation capacity data and the fitness of the variant formation capacity data are optimal-average rates, and how to calculate the optimal-average rate of the formation capacity data will be described below.

Specifically, taking the calculation of the goodness-average rate of a certain variant lineup data as an example, the variant lineup data and each reference lineup data in the reference lineup data set are first processed interactively, that is, a battle is performed. Then counting the result of each battle to obtain the number of winning plays, the number of peaches and the total number of peaches, and finally calculating the optimal average rate by adopting the following formula:

the average rate is (number of winning rounds + number of average rounds)/total number of rounds;

assuming that the reference lineup data set comprises 5000 reference lineup data, the variant lineup data is respectively matched with the 5000 reference lineup data, wherein the variant lineup data wins 3000 fields, namely the number of winning plays is 3000, the number of tie plays is 1000, namely the number of tie plays is 1000, 5000 fields are matched in total, namely the total number of ties is 5000, and based on the result, the optimal average rate of the variant lineup data is 0.8.

In the embodiment of the application, a method for determining the fitness is provided, and through the method, the optimal average rate corresponding to the formation capacity data is used as the fitness of the formation capacity data, so that the advantage degree of the individual in population generation is obtained, namely, the higher the optimal average rate is, the greater advantage of the corresponding formation capacity data is shown, and therefore the feasibility of the scheme is improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided in this application, the obtaining the second array capacity data set from the first array capacity data set and the variant array capacity data set according to the fitness corresponding to each first array capacity data in the first array capacity data set and the fitness corresponding to each variant array capacity data in the variant array capacity data set specifically includes:

sequencing M first array capacity data in the first array capacity data set and N variant array capacity data in the variant array capacity data set according to the sequence of the fitness from high to low to obtain (M + N) array capacity data;

In this embodiment, a manner of generating the second lineup data set is described. The process of generating the second array capacity data set is an evolution process, that is, M array capacity data with higher fitness are selected as the second array capacity data set from M first array capacity data of the previous generation and N newly generated variant array capacity data.

For easy understanding, please refer to fig. 10, fig. 10 is a schematic flow chart of implementing formation data evolution based on genetic algorithm in the embodiment of the present application, and as shown in the figure, specifically:

in step E1, a first array data set and a variant array data set are first obtained, where the first array data set includes M first array data and the variant array data set includes N variant array data.

In step E2, the first array data set and the variant array data set are then merged, and the array data are sorted in the order of high fitness to low fitness, so as to obtain (M + N) array data.

In step E3, since there may be repeated array capacity data in the (M + N) array capacity data, only the array capacity data with the maximum fitness is retained, and the remaining repeated array capacity data are removed, and finally a target array capacity data set after deduplication is obtained, where the target array capacity data set includes Y array capacity data, Y is an integer greater than 1 and less than or equal to (M + N).

In step E4, the target lineup data set is grouped to obtain at least two second lineup data subsets, for example, the deduplicated lineups are grouped according to the difference of the first object name, and each second lineup data subset includes at least one lineup data.

In step E5, the formation data with the maximum fitness is sequentially selected from each second formation data subset until reaching a selection time threshold M (that is, a second formation data set is obtained, where the selection time threshold is M.

In step E6, the second set of lineup data is output.

In the embodiment of the present application, a manner of generating the second lineup data set is provided, and by the manner, lineup data with higher intensity can be selected from the previous-generation lineup data set and the lineup data set generated by the current generation to serve as the next-generation lineup data set, so that feasibility of the scheme is improved.

Optionally, on the basis of the embodiment corresponding to fig. 3, in another optional embodiment provided by the embodiment of the present application, a game analysis result corresponding to the game to be analyzed is generated according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data, and specifically includes:

acquiring the total occurrence frequency of the object names according to the occurrence frequency of the object names in each second lineup data;

In this embodiment, a mode of generating a game analysis result is described. If the second lineup data set is a high-intensity lineup data set, the total occurrence frequency of each object name can be counted according to the occurrence frequency of the object name in each second lineup data, and the total occurrence frequency of each skill name can be acquired according to the occurrence frequency of the skill name in each second lineup data.

Specifically, it is assumed that the second lineup data set includes 300 second lineup data, and then the 300 second lineup data need to be counted, that is, the total frequency of occurrence of each object name and the total frequency of occurrence of each skill name are counted respectively. For easy understanding, please refer to fig. 11, fig. 11 is a schematic interface diagram showing the game analysis result in the embodiment of the present application, and it is assumed that the first maximum frequency is 90, the first minimum frequency is 10, the second maximum frequency is 45, and the second minimum frequency is 5.

Illustratively, taking the object name "lubrican" as an example, if the total frequency of occurrence of "lubrican" is 100, the total frequency of occurrence is greater than the first maximum frequency, thereby generating a first analysis result, i.e., "the hero may be too strong", indicating that there is an abnormal object name.

Illustratively, taking the object name "dunai" as an example, if the total frequency of occurrence of "dunai" is 3, the total frequency of occurrence is less than the first minimum frequency, thereby generating a second analysis result, i.e., "the hero may be too weak", indicating that there is an abnormal object name.

Illustratively, taking the skill name "orphan gallbladder seventeen" as an example, if the total frequency of occurrence of "orphan gallbladder seventeen" is 50, the total frequency of occurrence is greater than the second maximum frequency, thereby generating a third analysis result, i.e., "the skill may be too strong", indicating that there is an abnormal skill name.

Illustratively, taking the skill name "take the place of the revitalization rest" as an example, if the total frequency of occurrence of the "revitalization rest" is 1, the total frequency of occurrence is less than the second minimum frequency, thereby generating a fourth analysis result, i.e., "the skill may be too weak", indicating that there is an abnormal skill name.

Secondly, in the embodiment of the application, a mode for generating a game analysis result is provided, and through the mode, whether a certain virtual object or a certain skill is too strong or not can be analyzed by combining a high-strength formation data set, and whether a certain virtual object or a certain skill is too weak or not can be analyzed, so that abnormal information can be mined quickly and accurately, a game developer can adjust the balance of the game before a new version of the game is online conveniently, and the method is suitable for a strategy simulation game with formation formed by combining the virtual object and the skill.

acquiring the common occurrence frequency corresponding to the first object name and the second object name according to the occurrence frequency of the object name in each second lineup data, wherein the first object name and the second object name are derived from the same second lineup data;

In this embodiment, another way of generating the game analysis result is described. If the second lineup data set is a high-intensity lineup data set, the frequency of the common occurrence of at least two objects (e.g., the first object name and the second object name) in one second lineup data may be counted according to the occurrence frequency of the object name in each second lineup data.

In particular, it is assumed that the second lineup data set includes 300 second lineup data, and then the 300 second lineup data need to be counted, that is, the common occurrence frequency of at least two object names is counted respectively, for example, the common occurrence frequency of the first object name and the second object name in the second lineup data set is counted. For ease of understanding, referring to fig. 12, fig. 12 is another interface diagram showing the game analysis result in the embodiment of the present application, and as shown, it is assumed that the third maximum frequency is 60.

Illustratively, taking the first object name "summer time Tun" and the second object name "grand shang xiang" as an example, if the co-occurrence frequency of "summer time Tun" and "grand shang xiang" is 70, the co-occurrence frequency is greater than the third maximum frequency, thereby generating a fifth analysis result, i.e., "the two hero combinations may be too strong", indicating that there is an abnormal object name.

Illustratively, taking the first object name as "cao" and the second object name as "dun", if the co-occurrence frequency of "cao" and "dun" is 65, the co-occurrence frequency is greater than the third maximum frequency, thereby generating a fifth analysis result, i.e., "the two hero combinations may be too strong", indicating that there is an abnormal object name.

Secondly, in the embodiment of the application, another mode for generating a game analysis result is provided, and through the mode, whether the combination of some virtual objects is too strong or not and whether the combination of some virtual objects is too weak or not can be analyzed by combining a high-strength formation data set, so that abnormal information is quickly and accurately mined, a game developer can conveniently adjust the balance of the game before a new version of the game is online, and the method is suitable for a strategy simulation game with formation formed by combining virtual objects and skills.

acquiring the common occurrence frequency corresponding to the first skill name and the second skill name according to the occurrence frequency of the skill name in each second lineup data, wherein the first skill name and the second skill name are derived from the same second lineup data;

In this embodiment, another way of generating the game analysis result is described. If the second lineup data set is a high-intensity lineup data set, the frequency with which at least two skills (e.g., a first skill name and a second skill name) commonly appear in one second lineup data may be counted according to the frequency of occurrence of the skill name in each second lineup data.

In particular, assuming that the second lineup data set includes 300 second lineup data, then the 300 second lineup data need to be counted, i.e. the co-occurrence frequency of at least two skill names is counted respectively, for example, the frequency of the co-occurrence of the first skill name and the second skill name in the second lineup data set is counted. For easy understanding, please refer to fig. 13, fig. 13 is another interface diagram showing the game analysis result in the embodiment of the present application, and as shown, it is assumed that the fourth maximum frequency is 30.

Illustratively, taking the first skill name "orphan gallbladder seventy" and the second skill name "restorative rest" as an example, if the co-occurrence frequency of the "orphan gallbladder seventy" and the "restorative rest" is 35, the co-occurrence frequency is greater than the fourth maximum frequency, thereby generating a sixth analysis result, i.e., "the two skill combinations may be too strong", indicating that there is an abnormal skill name.

Illustratively, taking the first skill name of "billow catamaran" and the second skill name of "great south club" as an example, if the co-occurrence frequency of "billow catamaran" and "great south club" is 40, the co-occurrence frequency is greater than the fourth maximum frequency, thereby generating a sixth analysis result, i.e., "the two skill combinations may be too strong", indicating that there is an abnormal skill name.

Secondly, in the embodiment of the application, another mode for generating game analysis results is provided, and through the mode, whether the combination of some skills is too strong or not and whether the combination of some skills is too weak or not can be analyzed by combining a high-strength formation data set, so that abnormal information can be mined quickly and accurately, a game developer can adjust the balance of the game before a new version of the game is online conveniently, and the method is suitable for a strategy simulation game with formation formed by combining virtual objects and skills.

acquiring the common occurrence frequency of the target object name and the target skill name according to the occurrence frequency of the object name and the occurrence frequency of the skill name in each second lineup data, wherein the target object name and the target skill name are derived from the same second lineup data;

In this embodiment, another way of generating the game analysis result is described. If the second lineup data sets are high-intensity lineup data sets, the frequency with which skills and virtual objects (e.g., target object names and target skill names) appear together in one second lineup data may be counted according to the frequency of occurrence of the skill names and the frequency of occurrence of the skill names in each second lineup data.

Specifically, assuming that the second lineup data set includes 300 second lineup data, then the 300 second lineup data need to be counted, that is, the co-occurrence frequency of the virtual object and the skill name is counted respectively, for example, the frequency of the co-occurrence of the target object name and the target skill name in the second lineup data set is counted. For ease of understanding, referring to fig. 14, fig. 14 is another interface diagram showing the game analysis result in the embodiment of the present application, and as shown, it is assumed that the fifth maximum frequency is 45.

Illustratively, taking the target object name "summer time Tun" and the target skill name "take the example of" take care of health ", if the co-occurrence frequency of" summer time Tun "and" take care of health "is 50, the co-occurrence frequency is greater than the fifth maximum frequency, thereby generating a seventh analysis result, i.e.," this combination of hero and skill may be too strong ", indicating that there is an abnormal object name and skill name.

Illustratively, taking the target object name "grand shang xiang" and the target skill name "suspen kettle jie" as an example, if the co-occurrence frequency of "grand shang xiang" and "suspen kettle jie" is 55, the co-occurrence frequency is greater than the fifth maximum frequency, thereby generating a seventh analysis result, i.e., "this combination of hero and skill may be too strong", indicating that there is an abnormal object name and skill name.

Secondly, in the embodiment of the application, another mode for generating a game analysis result is provided, and through the above mode, whether the combination of a certain virtual object and a certain skill is too strong or not can be analyzed by combining a high-strength formation data set, and whether the combination of the certain virtual object and the certain skill is too weak or not can be analyzed, so that abnormal information can be mined quickly and accurately, a game developer can adjust the balance of the game before a new version of the game is online conveniently, and the method is suitable for a strategy simulation game with formation formed by combining the virtual object and the skill.

Referring to fig. 15, fig. 15 is a schematic diagram of an embodiment of a data processing apparatus in an embodiment of the present application, and the data processing apparatus 20 includes:

an obtaining module 201, configured to obtain a first array data set corresponding to a game to be analyzed, where the first array data set includes M first array data, each first array data includes R pieces of genetic information, each R piece of genetic information includes at least one of an object name and a skill name, and both M and R are integers greater than 1;

a generating module 202, configured to generate a second lineup data set through a genetic algorithm based on the first lineup data set, where the second lineup data set includes M second lineup data, and each second lineup data includes R pieces of genetic information;

the obtaining module 201 is further configured to, if the iteration number corresponding to the second lineup data set reaches an iteration threshold, obtain at least one of an occurrence frequency of an object name and an occurrence frequency of a skill name in each second lineup data according to the second lineup data set;

the generating module 202 is further configured to generate a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data.

Alternatively, on the basis of the embodiment corresponding to fig. 15, in another embodiment of the data processing apparatus 20 provided in the embodiment of the present application,

the generating module 202 is specifically configured to obtain a cross-lattice data set through a genetic algorithm based on the first lattice data set, where the cross-lattice data set includes N cross-lattice data, each cross-lattice data includes R pieces of gene information, and N is an integer greater than 1;

the obtaining module 201 is further configured to obtain a configuration information set corresponding to the game to be analyzed before the generating module 202 performs interactive processing on each variant lineup data and the reference lineup data set to obtain a fitness corresponding to each variant lineup data, where the configuration information set includes at least two sets of configuration information, and each set of configuration information includes at least one of an object name and a skill name;

the generating module 202 is further configured to generate a reference lineup data set according to the configuration information set, where the reference lineup data set includes P reference lineup data, each reference lineup data includes R pieces of gene information, and P is an integer greater than or equal to 1.

the generating module 202 is further configured to generate an initial lineup data set according to the configuration information set after the obtaining module 201 obtains the configuration information set corresponding to the game to be analyzed, where the initial lineup data set includes M initial lineup data, and each initial lineup data includes R pieces of gene information;

the generating module 202 is further configured to generate a third array data set through a genetic algorithm based on the initial array data set, where the third array data set includes M third array data, each third array data includes R pieces of gene information, and the number of iterations corresponding to the third array data set is less than or equal to the number of iterations corresponding to the first array data set.

the generating module 202 is specifically configured to obtain a first array data subset from the first array data set, where the first array data subset includes Q first array data, and Q is an integer greater than 1 and smaller than M;

a generating module 202, configured to determine, according to a fitness corresponding to each first array data in the first array data set and a fitness sum corresponding to the first array data set, a selection probability corresponding to each first array data in the first array data set;

generating Q random numbers;

a generating module 202, configured to specifically generate, for each cross-lineup data in the cross-lineup data set, a random numerical value corresponding to each genetic information in each cross-lineup data;

a generating module 202, configured to perform interactive processing on each variant lineup data and the reference lineup data set to obtain a number of winning plays, a number of tie plays, and a total number of plays corresponding to each variant lineup data;

the generating module 202 is specifically configured to sort, according to a sequence from high fitness to low fitness, the M first array data in the first array data set and the N variant array data in the variant array data set to obtain (M + N) array data;

the generating module 202 is specifically configured to obtain the total occurrence frequency of the object names according to the occurrence frequency of the object names in each second lineup data;

the generating module 202 is specifically configured to obtain a common occurrence frequency corresponding to the first object name and the second object name according to the occurrence frequency of the object name in each second lineup data, where the first object name and the second object name are derived from the same second lineup data;

the generating module 202 is specifically configured to obtain the common occurrence frequency corresponding to the first skill name and the second skill name according to the occurrence frequency of the skill name in each second lineup data, where the first skill name and the second skill name are derived from the same second lineup data;

the generating module 202 is specifically configured to obtain the common occurrence frequency of the target object name and the target skill name according to the occurrence frequency of the object name and the occurrence frequency of the skill name in each second lineup data, where the target object name and the target skill name are derived from the same second lineup data;

The data processing device provided by the application can be deployed in computer equipment. Referring to fig. 16, fig. 16 is a schematic structural diagram of a computer device 30 according to an embodiment of the present disclosure. Computer device 30 may include an input device 310, an output device 320, a processor 330, and a memory 340. The output device in the embodiments of the present application may be a display device. Memory 340 may include both read-only memory and random-access memory, and provides instructions and data to processor 330. A portion of Memory 340 may also include Non-Volatile Random Access Memory (NVRAM).

Memory 340 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof:

and (3) operating instructions: including various operational instructions for performing various operations.

Operating the system: including various system programs for implementing various basic services and for handling hardware-based tasks.

Processor 330 controls the operation of computer device 30, and processor 330 may also be referred to as a Central Processing Unit (CPU). Memory 340 may include both read-only memory and random-access memory, and provides instructions and data to processor 330. A portion of the memory 340 may also include NVRAM. In particular applications, the various components of computer device 30 are coupled together by a bus system 350, where bus system 350 may include a power bus, a control bus, a status signal bus, and the like, in addition to a data bus. For clarity of illustration, however, the various buses are labeled in the figures as bus system 350.

The method disclosed in the embodiments of the present application can be applied to the processor 330, or implemented by the processor 330. The processor 330 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 330. The processor 330 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 340, and the processor 330 reads the information in the memory 340 and performs the steps of the above method in combination with the hardware thereof.

The related description of fig. 16 can be understood with reference to the related description and effects of the method portion of fig. 3, and will not be described in detail herein.

Embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method described in the foregoing embodiments.

Embodiments of the present application also provide a computer program product including a program, which, when run on a computer, causes the computer to perform the methods described in the foregoing embodiments.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A method of data processing, comprising:

acquiring a first array data set corresponding to a game to be analyzed, wherein the first array data set comprises M first array data, each first array data comprises R pieces of gene information, the R pieces of gene information comprise at least one of object names and skill names, and M and R are integers greater than 1;

if the iteration frequency corresponding to the second formation data set reaches an iteration threshold, acquiring at least one of the occurrence frequency of the object name and the occurrence frequency of the skill name in each second formation data according to the second formation data set;

and generating a game analysis result corresponding to the game to be analyzed according to at least one of the object name occurrence frequency and the skill name occurrence frequency in each second lineup data.

2. The method of claim 1, wherein generating a second set of formation data by a genetic algorithm based on the first set of formation data comprises:

acquiring a cross-array capacity data set through the genetic algorithm based on the first array capacity data set, wherein the cross-array capacity data set comprises N cross-array capacity data, each cross-array capacity data comprises R pieces of gene information, and N is an integer greater than 1;

acquiring a variant lineup data set through the genetic algorithm based on the cross lineup data set, wherein the variant lineup data set comprises N variant lineup data, and each variant lineup data comprises R pieces of gene information;

and acquiring the second array capacity data set from the first array capacity data set and the variant array capacity data set according to the fitness corresponding to each first array capacity data in the first array capacity data set and the fitness corresponding to each variant array capacity data in the variant array capacity data set.

3. The method according to claim 2, wherein before the performing the interactive processing on each variant lineup data and the reference lineup data set to obtain the fitness corresponding to each variant lineup data, the method further comprises:

acquiring a configuration information set corresponding to the game to be analyzed, wherein the configuration information set comprises at least two groups of configuration information, and each group of configuration information comprises at least one of an object name and a skill name;

and generating the reference lineup data set according to the configuration information set, wherein the reference lineup data set comprises P reference lineup data, each reference lineup data comprises R pieces of gene information, and P is an integer greater than or equal to 1.

4. The method of claim 3, wherein after obtaining the set of configuration information corresponding to the game to be analyzed, the method further comprises:

and generating a third array capacity data set through the genetic algorithm based on the initial array capacity data set, wherein the third array capacity data set comprises M third array capacity data, each third array capacity data comprises R pieces of gene information, and the iteration times corresponding to the third array capacity data set are less than or equal to the iteration times corresponding to the first array capacity data set.

5. The method of claim 2, wherein obtaining a cross-lattice data set by the genetic algorithm based on the first lattice data set comprises:

acquiring a first array data subset from the first array data set, wherein the first array data subset comprises Q first array data, and Q is an integer which is greater than 1 and smaller than M;

randomly obtaining T gene positions, wherein the T gene positions correspond to T gene information, the gene positions and the gene information have a one-to-one correspondence relationship, the T gene information comprises at least one of an object name and a skill name, and T is an integer which is greater than or equal to 1 and smaller than R;

exchanging T gene information corresponding to the T gene positions in the parent array capacity data with T gene information corresponding to the T gene positions in the parent array capacity data to obtain first cross array capacity data and second cross array capacity data, wherein the first cross array capacity data and the second cross array capacity data both belong to the cross array capacity data set.

6. The method of claim 5, wherein obtaining a first subset of the first array data from the first set of array data comprises:

determining the selection probability corresponding to each first array data in the first array data set according to the fitness corresponding to each first array data in the first array data set and the sum of the fitness corresponding to the first array data set;

generating Q random numbers;

and acquiring the first array data subset from the first array data set according to the Q random numbers and the cumulative probability corresponding to each first array data in the first array data set.

7. The method of claim 2, wherein obtaining a variant lineup data set through the genetic algorithm based on the cross-lineup data set comprises:

generating a random numerical value corresponding to each gene information in each cross-array capacity data aiming at each cross-array capacity data in the cross-array capacity data set;

for each cross array capacity data in the cross array capacity data set, if a random value corresponding to gene information is less than or equal to variation probability, updating the gene information to obtain target gene information;

for each cross array capacity data in the cross array capacity data set, if a random value corresponding to gene information is greater than the variation probability, determining the gene information as original gene information;

and acquiring variant lineup data corresponding to each cross lineup data in the cross lineup data set, wherein the variant lineup data comprises at least one of the target gene information and the original gene information.

8. The method of claim 2, wherein obtaining a variant lineup data set through the genetic algorithm based on the cross-lineup data set comprises:

for each cross array capacity data in the cross array capacity data set, if a random numerical value corresponding to gene information is less than or equal to the variation probability corresponding to the gene information, performing replacement processing on the gene information to obtain target gene information;

for each cross array capacity data in the cross array capacity data set, if a random numerical value corresponding to gene information is greater than a variation probability corresponding to the gene information, determining the gene information as original gene information;

9. The method according to claim 2, wherein the performing interactive processing on each variant lineup data and a reference lineup data set to obtain a fitness corresponding to each variant lineup data comprises:

performing interactive processing on each variable array capacity data and a reference array capacity data set to obtain the number of winning plays, the number of ties and the total number of plays corresponding to each variable array capacity data;

determining the optimal average rate corresponding to each variable lineup data according to the number of winning orders, the number of tiebacks and the total number corresponding to each variable lineup data;

10. The method of claim 2, wherein obtaining the second set of lineup data from the first set of lineup data and the variant set of lineup data according to the fitness of each of the first set of lineup data and the fitness of each of the variant set of lineup data comprises:

sequencing the M first array capacity data in the first array capacity data set and the N variant array capacity data in the variant array capacity data set according to the sequence of the fitness from high to low to obtain (M + N) array capacity data;

performing deduplication processing on the (M + N) pieces of lineup data to obtain a target lineup data set, wherein the deduplication processing is to reserve the same lineup with the largest fitness in at least two pieces of same lineup data, and delete the remaining lineup data of the at least two pieces of same lineup data, the target lineup data set includes Y pieces of lineup data, and Y is an integer greater than 1 and less than or equal to the (M + N);

grouping the target formation capacity data set to obtain at least two second formation capacity data subsets, wherein each second formation capacity data subset comprises at least one formation capacity data;

and sequentially selecting the formation data with the maximum fitness from each second formation data subset until reaching a selection time threshold value to obtain the second formation data set.

11. The method according to claim 1, wherein the generating a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data comprises:

acquiring the total occurrence frequency of the skill names according to the occurrence frequency of the skill names in each second lineup data;

if the total frequency of the object names is greater than or equal to a first maximum frequency, generating a first analysis result, wherein the first analysis result belongs to a game analysis result corresponding to the game to be analyzed;

if the total frequency of the object names is less than or equal to the first minimum frequency, generating a second analysis result, wherein the second analysis result belongs to the game analysis result corresponding to the game to be analyzed;

12. The method according to claim 1, wherein the generating a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data comprises:

acquiring the common occurrence frequency corresponding to a first object name and a second object name according to the occurrence frequency of the object name in each second lineup data, wherein the first object name and the second object name are derived from the same second lineup data;

if the common occurrence frequency is greater than or equal to a third maximum frequency, generating a fifth analysis result, wherein the fifth analysis result belongs to the game analysis result corresponding to the game to be analyzed;

or, the generating a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data includes:

acquiring the common occurrence frequency corresponding to a first skill name and a second skill name according to the occurrence frequency of the skill names in each second lineup data, wherein the first skill name and the second skill name are derived from the same second lineup data;

if the common occurrence frequency is greater than or equal to a fourth maximum frequency, generating a sixth analysis result, wherein the sixth analysis result belongs to a game analysis result corresponding to the game to be analyzed;

and if the common occurrence frequency is greater than or equal to a fifth maximum frequency, generating a seventh analysis result, wherein the seventh analysis result belongs to the game analysis result corresponding to the game to be analyzed.

13. A data processing apparatus, comprising:

the game analysis device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a first array data set corresponding to a game to be analyzed, the first array data set comprises M first array data, each first array data comprises R pieces of gene information, the R pieces of gene information comprise at least one of object names and skill names, and the M and the R are integers larger than 1;

a generating module, configured to generate a second lineup data set through a genetic algorithm based on the first lineup data set, where the second lineup data set includes M second lineup data, and each second lineup data includes R pieces of genetic information;

the generating module is further configured to generate a game analysis result corresponding to the game to be analyzed according to at least one of the frequency of occurrence of the object name and the frequency of occurrence of the skill name in each second lineup data.

14. A computer device, comprising: a memory, a processor, and a bus system;

wherein the memory is used for storing programs;

the processor for executing the program in the memory, the processor for performing the method of any one of claims 1 to 12 according to instructions in program code;

15. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the method of any of claims 1 to 12.