CN109794065B

CN109794065B - Game role creating method and device, electronic equipment and storage medium

Info

Publication number: CN109794065B
Application number: CN201910080389.8A
Authority: CN
Inventors: 黄景文; 刘海平
Original assignee: Netease Hangzhou Network Co Ltd
Current assignee: Netease Hangzhou Network Co Ltd
Priority date: 2019-01-28
Filing date: 2019-01-28
Publication date: 2022-02-11
Anticipated expiration: 2039-01-28
Also published as: CN109794065A

Abstract

The disclosure provides a game role creating method, a game role creating device, electronic equipment and a computer readable storage medium, and belongs to the technical field of program development. The method comprises the following steps: acquiring initial attributes of a role to be created; according to the initial attributes, determining similar roles of the roles to be created in the existing game roles, and extracting configuration data of the similar roles, wherein the configuration data of the similar roles at least comprise equipment data of the similar roles; applying the configuration data of the similar role to the role to be created, and carrying out simulated game to obtain simulated game data of the role to be created; and adjusting the initial attribute of the character to be created according to the simulated game data to obtain the final attribute of the character to be created. The method and the device can solve the problem of cold start of configuration data during game role creation, simplify the creation process of the game role and improve the efficiency.

Description

Game role creating method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of program development technologies, and in particular, to a game character creating method, a game character creating apparatus, an electronic device, and a computer-readable storage medium.

Background

With the development of electronic devices such as mobile terminals, electronic games become an increasingly important entertainment mode. Game developers often need to continually update game content after a new game is released in order to maintain game viability and appeal to players. The creation of a new game role is an important updating mode, and the diversity of the game can be greatly increased and the freshness of the player can be improved by creating the new game role.

The existing game role creating method usually needs to set the basic information of a new role according to the historical experience of a tester, and then repeatedly adjust the basic information of the role to be created according to the result feedback of the game test and the judgment of the tester on the new role, so that the basic information can meet the expected standard. However, this method requires the tester to evaluate and feed back the test result of the character to be created, and repeatedly adjust the basic information according to the test result, which makes the operation flow more complicated, resulting in a longer test period and higher labor cost; in addition, the method depends on subjective judgment of testers, objectivity of game character evaluation cannot be guaranteed, created game characters are unbalanced, and game experience of players is affected.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure provides a game character creating method, a game character creating apparatus, an electronic device, and a computer-readable storage medium, which overcome, at least to some extent, the problems of complicated operation flow, high labor cost, and low accuracy in the conventional game character creating method.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to an aspect of the present disclosure, there is provided a game character creation method including: acquiring initial attributes of a role to be created; according to the initial attributes, determining similar roles of the roles to be created in the existing game roles, and extracting configuration data of the similar roles, wherein the configuration data of the similar roles at least comprise equipment data of the similar roles; applying the configuration data of the similar role to the role to be created, and carrying out simulated game to obtain simulated game data of the role to be created; and adjusting the initial attribute of the character to be created according to the simulated game data to obtain the final attribute of the character to be created.

In an exemplary embodiment of the present disclosure, the applying the configuration data of the similar character to the character to be created and performing a simulation game, and obtaining the simulation game data of the character to be created includes: applying the configuration data of the similar role to the role to be created, and carrying out a first simulation game to obtain first simulation game data of the role to be created; after obtaining the first simulated game data of the character to be created, the method further comprises: adjusting the configuration data of the character to be created according to the first simulation game data, and performing a second simulation game to obtain second simulation game data of the character to be created; sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after the nth simulated game is performed; the adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created comprises: adjusting the initial attribute of the character to be created according to the Nth simulated game data to obtain the final attribute of the character to be created; wherein N is a positive integer greater than 1, and i is any positive integer in [2, N ].

In an exemplary embodiment of the present disclosure, the similar role is a first similar role; the applying the configuration data of the similar role to the role to be created and performing a first simulation game to obtain first simulation game data of the role to be created includes: applying the configuration data of the first similar role to the role to be created, and carrying out a first simulation game to obtain first simulation game data of the role to be created; sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after performing the nth simulated game, wherein the steps comprise: sequentially, according to the ith-1 th simulated game data, determining the ith similar role of the role to be created in the existing game roles, applying the configuration data of the ith similar role to the role to be created, and carrying out the ith simulated game to obtain the ith simulated game data of the role to be created; and determining the (N + 1) th similar role of the role to be created in the existing game roles according to the nth simulation game data, wherein the (N + 1) th similar role is the same as the (N) th similar role.

In an exemplary embodiment of the present disclosure, the configuration data of the similar role is first-time configuration data; sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after performing the nth simulated game, wherein the steps comprise: sequentially inputting the (i-1) th simulated game data into a classification model to obtain ith configuration data of the character to be created, and performing ith simulated game according to the ith configuration data to obtain ith simulated game data of the character to be created; and inputting the nth simulation game data into the classification model to obtain the (N + 1) th configuration data of the character to be created, wherein the (N + 1) th configuration data is the same as the nth configuration data.

In an exemplary embodiment of the present disclosure, the configuration data includes a first type of configuration data and a second type of configuration data; sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after performing the nth simulated game, wherein the steps comprise: sequentially inputting the (i-1) th simulated game data into a classification model to obtain the ith first-class configuration data of the character to be created; determining the ith similar role of the role to be created in the existing game roles according to the ith-1 time simulation game data, and extracting the second type of configuration data of the ith similar role; applying the ith first type of configuration data and the ith second type of configuration data of the similar role to the role to be created, and performing the ith simulation game to obtain the ith simulation game data of the role to be created; and obtaining the data of the simulation game of the Nth time of the character to be created until the simulation game of the Nth time is carried out, wherein the data of the simulation game of the Nth time is converged relative to the data of the simulation game of the (N-1) th time.

In an exemplary embodiment of the present disclosure, the simulation game data includes initial simulation game data; the adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created comprises: performing initial adjustment on the initial attribute of the character to be created according to the initial simulation game data to obtain the intermediate attribute of the character to be created; performing a secondary simulation game on the character to be created according to the intermediate attribute to obtain secondary simulation game data of the character to be created; and if the re-simulation game data reach the expected condition, determining the intermediate attribute as the final attribute of the character to be created.

In an exemplary embodiment of the present disclosure, the determining, according to the initial attribute, a similar character of the character to be created among existing game characters includes: and mapping the character to be created to an attribute space according to the initial attribute, and determining the existing game character closest to the character to be created in the attribute space as a similar character of the character to be created.

In an exemplary embodiment of the present disclosure, the similar roles of the roles to be created include a plurality of similar roles; applying the configuration data of the similar role to the role to be created, and performing a simulation game, wherein obtaining simulation game data of the role to be created comprises: and generating the configuration data of the character to be created according to the average value of the configuration data of the similar characters, and carrying out simulated game on the character to be created to obtain the simulated game data of the character to be created.

According to an aspect of the present disclosure, there is provided a game character creation apparatus including: the initial attribute acquisition module is used for acquiring the initial attribute of the role to be created; and the similar role determining module is used for determining the similar role of the role to be created in the existing game roles according to the initial attribute and extracting the configuration data of the similar role, wherein the configuration data of the similar role at least comprises the equipment data of the similar role. And the simulation game processing module is used for applying the configuration data of the similar role to the role to be created, carrying out simulation game and obtaining the simulation game data of the role to be created. And the final attribute determining module is used for adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created.

In an exemplary embodiment of the present disclosure, the simulation game processing module includes: the first simulation unit is used for applying the configuration data of the similar role to the role to be created and carrying out a first simulation game to obtain first simulation game data of the role to be created; the second simulation unit is used for adjusting the configuration data of the character to be created according to the first simulation game data after the first simulation game data of the character to be created are obtained, and performing a second simulation game to obtain second simulation game data of the character to be created; the simulation unit is used for adjusting the configuration data of the character to be created according to the simulation game data of the (i-1) th time, performing simulation game of the (i) th time, obtaining simulation game data of the character to be created of the (i) th time, and reaching a preset convergence condition after performing simulation game of the (N) th time; the attribute adjusting unit is used for adjusting the initial attribute of the character to be created according to the Nth simulated game data to obtain the final attribute of the character to be created; wherein N is a positive integer greater than 1, and i is any positive integer in [2, N ].

In an exemplary embodiment of the present disclosure, the similar role is a first similar role; the first simulation unit is used for applying the configuration data of the first similar role to the role to be created and carrying out a first simulation game to obtain first simulation game data of the role to be created; the Nth simulation unit is used for determining the ith similar role of the role to be created in the existing game roles according to the ith-1 th simulation game data in sequence, applying the configuration data of the ith similar role to the role to be created, and carrying out the ith simulation game to obtain the ith simulation game data of the role to be created; and determining the (N + 1) th similar role of the role to be created in the existing game roles according to the nth simulation game data, wherein the (N + 1) th similar role is the same as the (N) th similar role.

In an exemplary embodiment of the present disclosure, the configuration data of the similar role is first-time configuration data; the Nth analog unit includes: the configuration data acquisition subunit is used for sequentially inputting the (i-1) th simulated game data into a classification model to obtain the ith configuration data of the character to be created, and performing the ith simulated game according to the ith configuration data to obtain the ith simulated game data of the character to be created; and the data judgment subunit is used for inputting the nth simulation game data into the classification model to obtain the (N + 1) th configuration data of the character to be created, wherein the (N + 1) th configuration data is the same as the nth configuration data.

In an exemplary embodiment of the present disclosure, the configuration data includes a first type of configuration data and a second type of configuration data; the Nth analog unit includes: the first data input subunit is used for sequentially inputting the (i-1) th simulated game data into a classification model to obtain the (i) th first-class configuration data of the character to be created; the configuration extraction subunit is used for determining the ith similar role of the role to be created in the existing game roles according to the ith-1 th simulation game data and extracting the second type of configuration data of the ith similar role; the configuration application subunit is used for applying the ith first type of configuration data and the ith second type of configuration data of the similar role to the role to be created, and performing the ith simulated game to obtain the ith simulated game data of the role to be created; and the data convergence subunit is used for obtaining the simulation game data of the Nth time of the character to be created until the simulation game of the Nth time is played, wherein the simulation game of the Nth time is converged relative to the simulation game data of the (N-1) th time.

In an exemplary embodiment of the present disclosure, the simulation game data includes initial simulation game data; the final attribute determination module includes: the attribute adjusting unit is used for carrying out primary adjustment on the initial attribute of the character to be created according to the primary simulation game data to obtain the intermediate attribute of the character to be created; the game simulation unit is used for carrying out a re-simulation game on the character to be created according to the intermediate attribute to obtain re-simulation game data of the character to be created; and the condition judging unit is used for determining the intermediate attribute as the final attribute of the character to be created if the re-simulation game data reaches the expected condition.

In an exemplary embodiment of the disclosure, according to the initial attribute, the similar role determination module is configured to map the to-be-created role to an attribute space according to the initial attribute, determine, in the attribute space, an existing game role that is closest to the to-be-created role as a similar role of the to-be-created role, and extract configuration data of the similar role, where the configuration data of the similar role at least includes equipment data of the similar role.

In an exemplary embodiment of the present disclosure, the similar roles of the roles to be created include a plurality of similar roles; the simulation game processing module is used for generating the configuration data of the character to be created according to the average value of the configuration data of the similar characters, and performing simulation game on the character to be created to obtain the simulation game data of the character to be created.

According to an aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of the above via execution of the executable instructions.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.

Exemplary embodiments of the present disclosure have the following advantageous effects:

the method comprises the steps of obtaining initial attributes of a character to be created, determining similar characters of the character to be created according to the initial attributes, extracting configuration data of the similar characters, applying the configuration data to the character to be created, carrying out a simulation game, and adjusting the initial attributes of the character to be created according to simulation game data to obtain final attributes of the character to be created. On one hand, by applying the configuration data of the similar character to the character to be created, effective configuration data can be obtained at the initial stage of creating the game character, the problem of cold start of the configuration data is solved, and compared with a mode of manually setting the configuration data, the configuration data acquisition process can be simplified, and the degree of matching between the configuration data and the character to be created is higher. On the other hand, the character to be created is evaluated and the initial attribute of the character is adjusted according to the simulated game data, so that the condition that the character to be created is repeatedly and artificially modified when the character to be created is not in accordance with the expectation is reduced, the adjustment of the initial attribute of the character to be created is more targeted and directional, the creating and testing period of the character is shortened, and the efficiency is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

FIG. 1 is a flowchart showing a game character creating method in the present exemplary embodiment;

FIG. 2 is a sub-flowchart showing a game character creating method in the present exemplary embodiment;

FIG. 3 shows a sub-flowchart of another game character creation method in the present exemplary embodiment;

FIG. 4 is a flowchart showing another game character creating method in the present exemplary embodiment;

FIG. 5 is a flowchart showing a further game character creating method in the present exemplary embodiment;

fig. 6 is a block diagram showing the configuration of a game character creation apparatus in the present exemplary embodiment;

fig. 7 shows an electronic device for implementing the above method in the present exemplary embodiment;

fig. 8 illustrates a computer-readable storage medium for implementing the above-described method in the present exemplary embodiment.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In one approach to the related art, a new character is created by manually configuring data, such as equipment or lineup, of the new character, and after configuring the equipment or lineup data, a test may be performed to determine whether the new character is as expected. However, such a solution greatly depends on whether the artificially configured equipment or lineup data is appropriate, and if not appropriate, the test results are affected, resulting in a failure to accurately create the game character.

In view of the above, exemplary embodiments of the present disclosure provide a game character creation method for creating a new character in a game. The present exemplary embodiment may be applied to a MOBA (Multiplayer Online Battle Arena) type Game or a combat Game for creating a new character, a new hero, and the like in the Game, may also be applied to a MMORPG (Massive Multiplayer Online Role-Playing Game) type Game for creating a new occupation, a new family, and the like in the Game, may also be applied to a racing type Game for creating a new model of racing car or plane, and the like in the Game. It should be understood that the above game types are for illustrative purposes only and the present disclosure is not limited thereto.

The exemplary embodiment is further described with reference to fig. 1, and as shown in fig. 1, the game character creating method may include the following steps S110 to S140:

step S110, obtaining the initial attribute of the role to be created.

The character to be created is a game character expected to need to be created, the initial attribute is initial basic information of the character to be created, and the initial basic information includes types, basic attributes, skill information and the like of the game character, for example, in a battle game, the initial attribute can be which type of a physical attack type, a legal attack type, a treatment type and an auxiliary type the game character belongs to, or can be basic attributes of the attack, life, defense, speed and the like of the game character, or can be skill attributes of the skill of the game character such as injury, effect, consumption value and the like; for another example, in a race game, the initial attributes may include basic attributes such as endurance, speed, steering sensitivity, etc. of the race game, and skill information such as turbo acceleration, drift, etc. The present disclosure is not limited to a particular type of initial attribute.

In this exemplary embodiment, the initial attribute may be set manually by a game developer, for example, after determining what type and location of a game character is expected to be created, the developer sets the initial attribute for the game character according to experience, or generates the initial attribute of the character to be created based on a certain rule, for example, specifies a total value of the initial attribute and a value interval of each attribute, and then randomly allocates a value of each attribute, or generates the initial attribute of the character to be created according to an attribute of an existing game character in a game, for example, after determining that the character to be created is a physical attack type character, a certain number of physical attack type characters may be found out from the existing game characters, and the attributes of the characters are averaged or weighted to obtain the initial attribute of the character to be created. Of course, not limited to the specific embodiments described above, other ways of obtaining the initial property that can be easily imagined by those skilled in the art should fall within the scope of the present disclosure.

Step S120, according to the initial attribute, determining the similar role of the role to be created in the existing game roles, and extracting the configuration data of the similar role, wherein the configuration data of the similar role at least comprises the equipment data of the similar role.

In general, a character does not directly play a game with an initial attribute, and it is necessary to configure certain equipment, a formation, a state, and the like for the character. In the exemplary embodiment, the configuration data of the role to be created can be determined according to the configuration data of the similar roles, so as to solve the problem of cold start of the configuration data.

The similar role may be an existing game role having the same or similar initial attribute as the role to be created, and may be the same as the type of the role to be created, for example, a physical attack type role or a therapeutic type role, or may have the same or similar basic attribute, skill information, and the like as the role to be created, for example, the basic attribute of the role to be created is attack 3323, life 10000, and individual injury with skill injury of 2000, and the attack and life of the similar role should be respectively in the vicinity of 3323 and 10000, and have the skill of about 2000 individual injury. In an exemplary embodiment, the basic attributes of the game character may be ranked, for example, from top to bottom, the basic attributes are "S" level, "a" level, "B" level, and the like, and then the similar character may be determined according to the levels of the basic attributes, for example, the basic attributes of the character to be created are attack S, life B, and defense a, and the character which is also attack S, life B, and defense a is searched for in the existing game character and determined as the similar character of the character to be created.

In an exemplary embodiment, similar roles may be determined by:

and mapping the character to be created to an attribute space according to the initial attribute, and determining the existing game character closest to the character to be created in the attribute space as the similar character of the character to be created.

The attributes usually include multiple indexes, such as the above-mentioned attack, life, defense, skill injury, and each index is used as a coordinate dimension, so that a multi-dimensional attribute space can be constructed. The attribute values of game characters are mapped into attribute space, and each character can be represented as a point in the attribute space or a vector connecting the point and an origin. Based on the mapping points of the game characters in the attribute space, the distance between the mapping points of every two game characters can be measured, and the distance can be Euclidean distance, Manhattan distance, Chebyshev distance and the like.

In addition, based on the mapping vectors of the game characters in the attribute space, the cosine similarity between the mapping vectors of every two game characters can be measured, and the larger the cosine similarity is, the higher the similarity is, so that the existing game character with the largest cosine similarity with the character to be created can be determined as the similar character of the character to be created.

In an exemplary embodiment, the similar character of the character to be created may also be determined through a KNN (K Nearest Neighbor, K Neighbor) algorithm, specifically, the positions of the initial attribute of the character to be created and the attributes of the existing game characters may be determined in an attribute space, the distance between the initial attribute and the attributes of each existing game character is calculated, and the K existing game characters with the smallest distance are selected, from which the most representative existing game characters are counted as the similar characters of the character to be created.

It should be noted that, when mapping a game character to the attribute space, it may be necessary to perform a numerical process on non-numerical attributes, for example, the attributes of the game character may include a character type, and when performing the numerical process, a physical attack type, a legal attack type, a treatment type, and an auxiliary type may be converted into 1, 2, 3, and 4, respectively. In addition, normalization processing can be carried out on attribute values of different dimensions, for example, attack of game characters is 1000-4000, life is 10000-20000, and the two attributes can be in the same value level through the normalization processing, so that an attribute space can be constructed conveniently. The digitization processing may be implemented by custom assignment, ASCII coding (American Standard Code for Information exchange Code), etc., and the normalization processing may be implemented by min-max (minimum-maximum value), Z-score (mean-Standard deviation), etc., which is not particularly limited in this disclosure.

After determining the similar characters, configuration data of the similar characters may be extracted, and as can be seen from the above, the configuration data may represent equipment, lineup, status, and the like, in this exemplary embodiment, the configuration data is in units of groups, for example, in a battle game, if equipment and lineup are required to be configured for a game character, a group of configuration data represents a set of complete equipment and lineup combination, further, if the equipment in the game totally includes three types of weapons, guards, and auxiliary props, and the game form is 5vs5, a group of configuration data may specifically include 7 data, where 3 represents three types of equipment, and 4 represents 4 teammate characters collocated in the lineup; in the case of a one-player fighting game, the configuration data can be equipment and state without configuring the formation for the game role, and a group of configuration data represents a complete set of equipment and state combination, and the like. Configuration data commonly used by similar characters can be extracted, for example, more equipment and formation combinations are used by players, if a plurality of groups of configuration data are included, all the configuration data can be extracted, and the optimal group of configuration data can be extracted, for example, the equipment and formation combination with the highest winning rate, and the like.

Step S130, the configuration data of the similar role is applied to the role to be created, and the simulation game is carried out to obtain the simulation game data of the role to be created.

As can be seen from the above, there may be one or more sets of configuration data of similar roles, and the multiple sets of configuration data indicate that the similar roles have various common equipment and formation combinations, etc., which may all be applied to the roles to be created, or one or more sets thereof may be selected to be applied to the roles to be created. For example, each set of configuration data may be scored, and the scoring criterion may be a ratio of a winning rate of the set of configuration data used by the similar character to a total price of the equipment in the set of configuration data (i.e., determining a cost performance of each equipment combination), and one or more sets of configuration data that are better are screened according to the scoring and applied to the character to be created, and then the simulated game is played.

The simulation game is to automatically perform game match on a server, and may randomly determine a game level, a game opponent, a game map, a match mode, and the like for a character to be created, and then control each game character by a program to perform game match, or automatically act after setting rules, and the like. The actual combat game data of the character to be created, that is, the simulation game data of the character to be created can be acquired through the simulation game. The simulated game data can truly reflect the fighting ability, defense ability, adaptability and the like of the character to be created, and the comprehensive ability of the character to be created and the difference between the comprehensive ability and the expected level of the character can be clearly determined through analyzing the data. The simulation game data may be the comprehensive performance of the character to be created in the simulation game, and may be embodied in the battle evaluation data, the victory ratio, and the like of the game character in the simulation game. For example, the number of wins may be a ratio of the number of wins to the total number of games after one hundred battles are performed, for example, the offensive ability (damage output, attack addition, etc.) and the enduring ability (life, shield, block, flash avoidance, etc.) of a game character in a battle game. The simulated game data can more directly reflect the performance of the character in the game than the initial attributes or configuration data of the character to be created.

In an exemplary embodiment, an ELK (data scheduling center consisting of three software, namely, Elasticsearch, logstand and Kibana) architecture can be adopted to obtain simulated game data, and simulated game data of a character to be created is counted from a simulated game by collecting analysis data through logstand, searching by an Elasticsearch engine and visualizing query results through Kibana.

Step S140, adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created.

In the present exemplary embodiment, if the simulated game data does not meet the requirements or criteria for the intended setting of the character to be created, the initial attribute of the character to be created can be adjusted. For example, in simulated game data, if the average injury output value of the character to be created in each game is significantly higher than the expected level, the attack attribute or skill injury value in the initial attribute may be reduced; if the average treatment value of the character to be created in each game is obviously higher than the expected level, the life attribute or skill treatment amount in the initial attribute can be reduced; if the winning rate of the character to be created is obviously higher or lower, resulting in game imbalance, the initial attributes can be increased or decreased as a whole, for example, all the initial attributes are multiplied by a specific coefficient according to the difference degree between the winning rate and the expected level, the coefficient is smaller than 1 when the winning rate is higher, the coefficient is smaller when the winning rate is lower, and the coefficient is larger than 1 when the winning rate is lower, and the like. After the final attributes are determined, the creation of the character to be created is completed, and a subsequent game developer can put the character into a new version of the game so that a player can use the character.

In an exemplary embodiment, the simulation game data may be initial simulation game data, and accordingly, as shown in fig. 2, the step S140 may be implemented by:

step S210, performing primary adjustment on the initial attribute of the character to be created according to the primary simulation game data to obtain the intermediate attribute of the character to be created;

step S220, performing a secondary simulation game on the character to be created according to the intermediate attribute to obtain secondary simulation game data of the character to be created;

in step S230, if the simulation game data again reaches the expected condition, the intermediate attribute is determined as the final attribute of the character to be created.

In the exemplary embodiment, the initial attributes of the character to be created are adjusted according to the simulation game data of the first simulation game to obtain a new set of attributes, and at this time, whether the set of attributes meet expectations or not is not determined yet, and the set of attributes can be regarded as intermediate attributes; the simulation game is again played based on the intermediate attributes, and the intermediate attributes are evaluated by data of the re-simulation game, and if the re-simulation game data reaches a desired level, the intermediate attributes are determined as final attributes of the character to be created. The expected condition may be a numerical interval set for the simulated game data, for example, an average injury output value, an average treatment value, a winning rate, and the like of the character to be created should be within a reasonable interval. If the simulation game data does not reach the expected level again, the intermediate attribute needs to be adjusted again, which can be regarded as secondary adjustment of the initial attribute, and a new round of simulation game is performed according to the adjusted attribute until the obtained simulation game data reaches the expected condition. It can be seen that, in the exemplary embodiment, the initial attribute may be adjusted any number of times, the simulated game data reaches the expected condition as a judgment standard, the attribute after the last adjustment is determined as the final attribute of the character to be created, and the character creation is completed.

Based on the above description, in the exemplary embodiment, the initial attribute of the character to be created is obtained, the similar character of the character to be created is determined according to the initial attribute, the configuration data of the similar character is extracted, the configuration data is applied to the character to be created, the simulation game is performed, and the initial attribute of the character to be created is adjusted according to the simulation game data, so that the final attribute of the character to be created is obtained. On one hand, by applying the configuration data of the similar character to the character to be created, effective configuration data can be obtained at the initial stage of creating the game character, the problem of cold start of the configuration data is solved, and compared with a mode of manually setting the configuration data, the configuration data acquisition process can be simplified, and the degree of matching between the configuration data and the character to be created is higher. On the other hand, the character to be created is evaluated and the initial attribute of the character is adjusted according to the simulated game data, so that the condition that the character to be created is repeatedly and artificially modified when the character to be created is not in accordance with the expectation is reduced, the adjustment of the initial attribute of the character to be created is more targeted and directional, the creating and testing period of the character is shortened, and the efficiency is improved.

In an exemplary embodiment, as shown with reference to fig. 3, step S130 may include the steps of:

step S310, applying the configuration data of the similar role to the role to be created, and carrying out a first simulation game to obtain first simulation game data of the role to be created;

further, after obtaining the first simulation game data of the character to be created at step S310, the game character creating method may further include the steps of:

step S320, adjusting the configuration data of the character to be created according to the first simulation game data, and performing a second simulation game to obtain second simulation game data of the character to be created;

step S330, sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching the preset convergence condition after the nth simulated game is performed;

accordingly, step S140 may include the steps of:

step S340, adjusting the initial attribute of the character to be created according to the Nth simulated game data to obtain the final attribute of the character to be created;

wherein N is a positive integer greater than 1, and i is any positive integer in [2, N ].

In steps S120 and S130, the similar character is determined by the initial attribute of the character to be created, and the configuration data of the similar character is applied to the character to be created, thereby obtaining the configuration data of the character to be created, which can be used for playing the simulation game. However, the initial attribute contains a small amount of information about the character to be created, the similar character determined by the initial attribute may not be the substantially most similar character, and the configuration data of the similar character may not be the configuration data most suitable for the character to be created. In the present exemplary embodiment, after the simulated game data is acquired, the feature information of the character to be created can be characterized by the simulated game data to adjust the configuration data of the character to be created, and since the information of the simulated game data is richer, the configuration data determined in this way is more suitable for the character to be created.

When the configuration data is adjusted according to the simulated game data, the values in the configuration data can be adjusted according to the imbalance condition of the simulated game data, for example, if the damage output value of the character to be created in the simulated game data is too high and the treatment value is too low, the attack added value in the configuration data can be reduced and the treatment added value can be improved. In addition, the adjustment may be performed in other specific manners, which will be specifically described in the following embodiments.

When the initial attribute of the character to be created is evaluated by using the simulation game data, for accurate evaluation, the simulation game data which can reflect the game performance of the character to be created most truly needs to be obtained, and the simulation game data is influenced by the configuration data. Therefore, in the exemplary embodiment, the configuration data may be adjusted according to the simulated game data, the adjusted configuration data is more suitable for the character to be created than before the adjustment, the adjusted configuration data is used for the simulated game, so that better simulated game data may be obtained, and the configuration data is adjusted according to the better simulated game data, so that the configuration data may be further optimized; therefore, the configuration data can be continuously optimized in a circular adjustment mode, better simulated game data can be obtained, and the like, the circulation is stopped until the simulated game data obtained by the N-th simulated game reaches the preset convergence condition, or the configuration data of the character to be created is adjusted according to the N-th simulated game data, and the configuration data is converged. Convergence means that the configuration data or the simulation game data cannot be further optimized through the loop, and the nth simulation game data obtained finally is the optimal simulation game data.

In order to facilitate calculation of the convergence condition of the simulated game data, the simulated game data may be converted into a feature vector by performing a digitization process. The configuration data of the character to be created may be adjusted to the expected level of the character based on the simulated game data. For example, in simulated game data, if the average injury output value of a character to be created in each round of the game is significantly higher than expected, the attributes of the configuration data (e.g., defense, injury, etc.) may be reduced. And then, adjusting the initial attribute of the character to be created according to the Nth simulation data to obtain the final attribute of the character to be created, namely, the initial attribute can be adjusted only once to obtain the final attribute. In addition, when determining whether or not the simulated game data or the configuration data converted into the feature vector converges, the convergence determination may be performed for each component in the feature vector, or whether or not the feature vector converges may be determined by performing calculation using a gaussian-seidel or jacobian iterative formula.

In the present exemplary embodiment, a convergence condition may be set to determine whether the loop is ended, for example, a threshold value regarding the simulated game data may be set, and when the similarity between the nth simulated game data and the N-1 st simulated game data reaches the threshold value, the simulated game data may be considered to be converged and the loop may be stopped. In addition, a maximum circulation frequency can be set for the simulation game circulation, when the circulation frequency reaches the threshold value, the circulation is stopped, and the initial attribute of the character to be created is adjusted according to the simulation game data obtained in the Nth time, so that the final attribute of the character to be created is obtained.

It should be noted that, when the configuration data of the character to be created is adjusted according to the simulated game data, the configuration data of the character to be created can be comprehensively considered according to the simulated game data and the initial attributes of the character to be created, and the configuration data of the character to be created can be determined more comprehensively to be adjusted by analyzing the richer data.

In an exemplary embodiment, the flow of the game character creating method may be as shown in fig. 4, including:

step S410, obtaining the initial attribute of the role to be created;

step S420, determining a similar role of the roles to be created;

step S430, using the configuration data of the similar role as the configuration data of the role to be created;

step S440, carrying out a simulation game on the character to be created;

step S450, after the simulation game is played, obtaining simulation game data;

step S460, determining whether the simulated game data is optimal by judging convergence;

step S461, if the simulation game data is not converged, returning to step S430, adjusting the configuration data of the character to be created, and performing steps S440-S460 again to form a loop between steps S430-S461, namely a process of adjusting the configuration data loop;

step S470, if the simulated game data is converged, judging whether the simulated game data meets the expected conditions;

step S471, if the expected condition is not reached, adjusting the initial attribute, and forming a loop through the steps S420 to S471 to iteratively adjust the attribute of the character to be created until the simulated game data reaches the expected condition;

step S480, the finally adjusted attribute is determined as the final attribute, and the creation flow of the role is ended.

When iteratively adjusting the attribute of the character to be created according to whether the simulated game data reaches the expected condition, a complete loop process of steps S420 to S471 can be adopted, that is, after adjusting the attribute each time, each step of steps S420 to S471 is passed, including a process of loop adjusting the configuration data between steps S430 to S461, and then whether the expected condition is reached is judged again in step S470; a simplified loop process of steps S440, S450 and then directly jumping to S470 may also be employed, which is not particularly limited by the present disclosure. Through the process, the cyclic adjustment optimization of the configuration data and the cyclic adjustment optimization of the attribute of the character to be created can be realized, the optimization of data of each link is realized in a double-cycle mode to obtain the optimal character attribute, and the accuracy of game character creation can be further improved.

In an exemplary embodiment, the similar role in step S120 is a first similar role, and step S310 may include the following steps:

applying the configuration data of the first similar role to the role to be created, and carrying out a first simulation game to obtain first simulation game data of the role to be created;

accordingly, step S330 may include the steps of:

sequentially, according to the (i-1) th simulated game data, determining the (i) th similar role of the role to be created in the existing game roles, applying the configuration data of the (i) th similar role to the role to be created, and carrying out the (i) th simulated game to obtain the (i) th simulated game data of the role to be created;

until the N +1 th similar role of the role to be created is determined in the existing game roles according to the nth simulation game data, wherein the N +1 th similar role is the same as the N th similar role.

When the configuration data of the character to be created is adjusted according to the simulation game data, the existing game character which is more similar to the character to be created can be determined again according to the simulation game data. And then applying the re-determined configuration data of the existing game role to the role to be created to obtain game simulation data, determining a similar role according to the game simulation data, and circulating the process until a convergence condition is reached, wherein the convergence condition can be that the (N + 1) th similar role is the same as the (N) th similar role, namely after the determined (N) th similar role passes through the simulation game, determining the (N + 1) th similar role in the existing game roles according to the simulation game data to be still the similar role, and showing that no similar role which is more in accordance with the condition than the (N) th similar role exists in the existing game roles according to the simulation game data, so that the configuration data of the (N) th similar role can be applied to the role to be created.

In an exemplary embodiment, the configuration data of the similar role is first time configuration data. Step S330 may include:

sequentially inputting the (i-1) th simulated game data into the classification model to obtain the ith configuration data of the character to be created, and performing the ith simulated game according to the ith configuration data to obtain the ith simulated game data of the character to be created;

and inputting the nth simulation game data into the classification model to obtain the (N + 1) th configuration data of the character to be created, wherein the (N + 1) th configuration data is the same as the nth configuration data.

The classification model can obtain the ith configuration data of the character to be created according to the (i-1) th simulation game data. The classification model may be used to represent the correspondence between the simulated game data and the configuration data, and determine what configuration data is obtained according to the feature data in the simulated game data. The classification model may be a machine learning model, such as a random forest, a decision tree, or a neural network, among others; or a mapping table or the like containing a large number of correspondences between the feature data and the configuration data. When the classification model is a machine learning model, the extracted feature data in the simulated game data can be used as the input of the classification model, and the corresponding configuration data can be obtained through calculation or by searching in the mapping table of the corresponding relationship.

In the exemplary embodiment, inputting the simulation game data into the classification model may obtain a set of configuration data corresponding thereto, applying the set of configuration data to the character to be created and performing the simulation game may obtain new simulation game data, and continuing to adjust the configuration data according to the new simulation game data until a convergence condition of the loop is reached, and stopping the loop. The convergence condition may be that when the nth time simulated game data of the character to be created is obtained, the configuration data determined by the simulated game data is the same as the configuration data determined by the N-1 times simulated game data, indicating that the configuration data determined from the simulated game data does not fit more to the configuration data of the character to be created than the nth time simulated game data in all the configuration data combinations, and thus the configuration data can be applied to the character to be created.

In an exemplary embodiment, the configuration data may include a first type of configuration data and a second type of configuration data. Step S330 may include the steps of:

sequentially inputting the (i-1) th simulated game data into the classification model to obtain the ith first-class configuration data of the character to be created;

determining an ith similar role of the role to be created in the existing game roles according to the ith-1 time simulation game data, and extracting second type configuration data of the ith similar role;

applying the ith first type of configuration data and the ith second type of configuration data of similar roles to the roles to be created, and performing simulation game for the ith time to obtain the ith simulation game data of the roles to be created;

and obtaining the data of the simulation game of the Nth time of the character to be created until the simulation game of the Nth time is performed, wherein the data of the simulation game of the Nth time is converged relative to the data of the simulation game of the N-1 st time.

The first type of configuration data and the second type of configuration data are different types of configuration data, and each type of configuration data can be determined or adjusted in different ways according to the characteristics of the data. For example, the first type of configuration data may be equipment data and the second type of configuration data may be lineup data. For example, in the present exemplary embodiment, the ith equipment data of the character to be created may be determined according to the (i-1) th simulated game data through a loop process, and meanwhile, the ith similar character may be determined according to the (i-1) th simulated game data, and the formation data of the similar character may be extracted. And then, the determined ith equipment data and the formation data of the ith similar role are applied to the role to be created together, the ith simulated game is carried out to obtain the ith simulated game data, and the (i + 1) th equipment data and the formation data of the (i + 1) th similar role can be determined according to the ith simulated game data. And repeating the circulation in the same way until the Nth simulated game converges relative to the (N-1) th simulated game data, wherein the simulated game data convergence can be realized by calculating a feature vector related to the simulated game data and setting a convergence condition, and when the calculation result meets the convergence condition, stopping the circulation and applying the equipment data and the formation data determined by the last circulation to the character to be created. An upper limit for the number of cycles may also be set for the cycle, and the cycle may be stopped when the number of cycles reaches the upper limit. Wherein the configuration data may be determined by a machine learning model, e.g. the equipment data may be determined by a random forest model, the formation data may be determined by a K-neighborhood algorithm model, etc.

It should be noted that the exemplary embodiment is not limited to the first type of configuration data and the second type of configuration data, and may also include third type of configuration data, fourth type of configuration data, and the like, for example, the third type of configuration data may be state data of a game character, and the fourth type of configuration data may be growth data of the game character, which is not particularly limited in this disclosure.

Based on the first type of configuration data and the second type of configuration data, in an exemplary embodiment, a game character creating method may be as shown in fig. 5, including the following steps:

step S510, obtaining initial attributes of the roles to be created;

step S520, determining similar roles of the roles to be created;

step S530, using the configuration data of the similar role as the configuration data of the role to be created, including the first type configuration data and the second type configuration data;

step S540, carrying out simulation game on the character to be created to obtain simulation game data;

step S541, determining whether the simulation game data is optimal or not by judging convergence;

step S542, if the simulated game data is not converged, adjusting the first type configuration data through the classification model;

step S543, when the first type of configuration data is adjusted, the second type of configuration data is adjusted through a clustering algorithm;

step S544, the adjusted first type configuration data and second type configuration data are used for the simulation game again to obtain simulation game data, if the simulation game data are not converged, the steps S540 to S543 are repeated until the simulation game data are converged;

step S545, if the simulated game data is converged, determining the simulated game data;

and step S550, adjusting the initial attribute according to the simulation game data to obtain the final attribute, thereby completing the creation of the game role.

The clustering algorithm may perform statistical classification on data with similarity, and may be specifically applied to determining other similar data such as similar roles, similar teams, or similar equipment, and then may determine the second type of configuration data according to the similar data, and the similar data may have other types, which is not particularly limited in this disclosure.

In an exemplary embodiment, the similar roles to create a role may include a plurality of similar roles. Step S230 may include:

and generating configuration data of the character to be created according to the average value of the configuration data of the similar characters, and carrying out simulated game on the character to be created to obtain simulated game data of the character to be created.

In the exemplary embodiment, a plurality of similar characters can be determined according to the initial attributes, configuration data corresponding to the similar characters can be correspondingly extracted, and different configuration data can be obtained when the different configuration data is applied to the character to be created to perform a simulation game. Because the types of the configuration data are different, before the average value is solved, the configuration data can be subjected to numerical conversion to generate the feature vectors of the configuration data, the average value of the feature vectors of the configuration data is calculated, the configuration data corresponding to the average value of the feature vectors is applied to the character to be created, and the simulated game is performed, so that the simulated game data of the character to be created can be obtained.

In addition, based on the configuration data of the multiple similar roles, a median or a mode may also be taken as the configuration data of the role to be created, for example, statistics may be performed on data of each item in the configuration data of the multiple similar roles, a mode may be taken for data of each item, and the configuration data of the role to be created is obtained, which is not particularly limited in this disclosure.

Exemplary embodiments of the present disclosure also provide a game character creation apparatus. Referring to fig. 6, the apparatus 600 may include an initial attribute acquisition module 610, a similar character determination module 620, a simulation game processing module 630, and a final attribute determination module 640. The initial attribute obtaining module 610 is configured to obtain an initial attribute of a role to be created; the similar role determination module 620 is configured to determine, according to the initial attribute, a similar role of a role to be created in existing game roles, and extract configuration data of the similar role, where the configuration data of the similar role at least includes equipment data of the similar role; the simulation game processing module 630 is configured to apply the configuration data of the similar role to the role to be created, perform a simulation game, and obtain simulation game data of the role to be created; and the final attribute determining module 640 is configured to adjust the initial attribute of the character to be created according to the simulated game data, so as to obtain a final attribute of the character to be created.

In an exemplary embodiment, the simulation game processing module may include: the first simulation unit is used for applying the configuration data of the similar roles to the roles to be created and carrying out first simulation game to obtain first simulation game data of the roles to be created; the game character creation apparatus further includes: the second simulation unit is used for adjusting the configuration data of the character to be created according to the first simulation game data after the first simulation unit obtains the first simulation game data of the character to be created, and performing a second simulation game to obtain second simulation game data of the character to be created; the simulation unit is used for adjusting the configuration data of the character to be created according to the simulation game data of the (i-1) th time, performing simulation game of the (i) th time, obtaining simulation game data of the character to be created, and reaching a preset convergence condition after performing simulation game of the (N) th time; the final attribute determination module may include: the attribute adjusting unit is used for adjusting the initial attribute of the character to be created according to the Nth simulated game data to obtain the final attribute of the character to be created; wherein N is a positive integer greater than 1, and i is any positive integer in [2, N ].

In an exemplary embodiment, the similar role is a first similar role; the first simulation unit may be configured to apply the configuration data of the first similar character to the character to be created, perform a first simulation game, and obtain first simulation game data of the character to be created; the Nth simulation unit can be used for sequentially determining the ith similar role of the role to be created in the existing game roles according to the ith-1 st simulation game data, applying the configuration data of the ith similar role to the role to be created, and carrying out the ith simulation game to obtain the ith simulation game data of the role to be created; and determining the (N + 1) th similar role of the role to be created in the existing game roles according to the nth simulation game data, wherein the (N + 1) th similar role is the same as the (N) th similar role.

In an exemplary embodiment, the configuration data of the similar role is first configuration data, and the nth simulation unit may include: the configuration data acquisition subunit is used for sequentially inputting the (i-1) th simulated game data into the classification model to obtain the ith configuration data of the character to be created, and performing the ith simulated game according to the ith configuration data to obtain the ith simulated game data of the character to be created; and the data judgment subunit is used for inputting the nth simulation game data into the classification model to obtain the (N + 1) th configuration data of the character to be created, wherein the (N + 1) th configuration data is the same as the nth configuration data.

In an exemplary embodiment, the configuration data includes a first type of configuration data and a second type of configuration data; the nth analog unit may include: the first data input subunit is used for sequentially inputting the (i-1) th simulated game data into the classification model to obtain the (i) th first-class configuration data of the character to be created; configuring an extraction subunit: the system comprises a simulation module, a first class configuration module, a second class configuration module and a third class configuration module, wherein the simulation module is used for determining an ith similar role of a role to be created in the existing game roles according to the ith-1 time simulation game data and extracting second class configuration data of the ith similar role; the configuration application subunit is used for applying the ith first type of configuration data and the ith second type of configuration data of a similar role to the role to be created, and performing the ith simulation game to obtain the ith simulation game data of the role to be created; and the data convergence subunit is used for obtaining the simulation game data of the Nth time of the character to be created until the simulation game of the Nth time is played, wherein the simulation game of the Nth time is converged relative to the simulation game data of the (N-1) th time.

In an exemplary embodiment, the simulation game data includes initial simulation game data; the final attribute determination module may include: the attribute adjusting unit is used for carrying out primary adjustment on the initial attribute of the character to be created according to the primary simulation game data to obtain the intermediate attribute of the character to be created; the game simulation unit is used for performing a secondary simulation game on the character to be created according to the intermediate attribute to obtain secondary simulation game data of the character to be created; and the condition judging unit is used for determining the intermediate attribute as the final attribute of the character to be created if the simulation game data reaches the expected condition again.

In an exemplary embodiment, according to the initial attribute, the similar role determination module may be configured to map the to-be-created role to an attribute space according to the initial attribute, determine, in the attribute space, an existing game role closest to the to-be-created role as a similar role of the to-be-created role, and extract configuration data of the similar role, where the configuration data of the similar role at least includes equipment data of the similar role.

In an exemplary embodiment, the similar roles of the roles to be created include a plurality of similar roles; the simulation game processing module can be used for generating the configuration data of the character to be created according to the average value of the configuration data of the similar characters, and performing simulation game on the character to be created to obtain the simulation game data of the character to be created.

The specific details of each module/unit have been described in detail in the corresponding method embodiment, and therefore are not described herein again.

Exemplary embodiments of the present disclosure also provide an electronic device capable of implementing the above method.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 700 according to such an exemplary embodiment of the present disclosure is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 7, electronic device 700 is embodied in the form of a general purpose computing device. The components of the electronic device 700 may include, but are not limited to: the at least one processing unit 710, the at least one memory unit 720, a bus 730 connecting different system components (including the memory unit 720 and the processing unit 710), and a display unit 740.

Where the memory unit stores program code, the program code may be executed by the processing unit 710 such that the processing unit 710 performs the steps according to various exemplary embodiments of the present disclosure as described in the above-mentioned "exemplary methods" section of this specification. For example, the processing unit 710 may execute steps S110 to S140 shown in fig. 1, or may execute steps S210 to S230 shown in fig. 2, or the like.

The storage unit 720 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)721 and/or a cache memory unit 722, and may further include a read only memory unit (ROM) 723.

The memory unit 720 may also include programs/utilities 724 having a set (at least one) of program modules 725, such program modules 725 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 730 may be any representation of one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 700 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 700, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 700 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 750. Also, the electronic device 700 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 760. As shown, the network adapter 760 communicates with the other modules of the electronic device 700 via the bus 730. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary embodiments of the present disclosure.

Exemplary embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the above-mentioned "exemplary methods" section of this specification, when the program product is run on the terminal device.

Referring to fig. 8, a program product 800 for implementing the above method according to an exemplary embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit according to an exemplary embodiment of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims

1. A game character creation method, comprising:

acquiring initial attributes of a role to be created;

according to the initial attributes, determining similar roles of the roles to be created in the existing game roles, and extracting configuration data of the similar roles, wherein the configuration data of the similar roles at least comprise equipment data of the similar roles;

applying the configuration data of the similar role to the role to be created, and carrying out simulated game to obtain simulated game data of the role to be created;

and adjusting the initial attribute of the character to be created according to the simulated game data to obtain the final attribute of the character to be created.

2. The method of claim 1, wherein the applying the configuration data of the similar character to the character to be created and performing a simulation game, and obtaining simulation game data of the character to be created comprises:

applying the configuration data of the similar role to the role to be created, and carrying out a first simulation game to obtain first simulation game data of the role to be created;

after obtaining the first simulated game data of the character to be created, the method further comprises:

adjusting the configuration data of the character to be created according to the first simulation game data, and performing a second simulation game to obtain second simulation game data of the character to be created;

sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after the nth simulated game is performed;

the adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created comprises:

adjusting the initial attribute of the character to be created according to the Nth simulated game data to obtain the final attribute of the character to be created;

3. The method of claim 2, wherein the similar role is a first similar role;

the applying the configuration data of the similar role to the role to be created and performing a first simulation game to obtain first simulation game data of the role to be created includes:

sequentially, adjusting the configuration data of the character to be created according to the (i-1) th simulated game data, performing the ith simulated game, obtaining the ith simulated game data of the character to be created, and reaching a preset convergence condition after performing the nth simulated game, wherein the steps comprise:

sequentially, according to the ith-1 th simulated game data, determining the ith similar role of the role to be created in the existing game roles, applying the configuration data of the ith similar role to the role to be created, and carrying out the ith simulated game to obtain the ith simulated game data of the role to be created;

and determining the (N + 1) th similar role of the role to be created in the existing game roles according to the nth simulation game data, wherein the (N + 1) th similar role is the same as the (N) th similar role.

4. The method of claim 2, wherein the configuration data of the similar role is first time configuration data;

sequentially inputting the (i-1) th simulated game data into a classification model to obtain ith configuration data of the character to be created, and performing ith simulated game according to the ith configuration data to obtain ith simulated game data of the character to be created;

5. The method of claim 2, wherein the configuration data comprises a first type of configuration data and a second type of configuration data;

sequentially inputting the (i-1) th simulated game data into a classification model to obtain the ith first-class configuration data of the character to be created;

determining the ith similar role of the role to be created in the existing game roles according to the ith-1 time simulation game data, and extracting the second type of configuration data of the ith similar role;

applying the ith first type of configuration data and the ith second type of configuration data of the similar role to the role to be created, and performing the ith simulation game to obtain the ith simulation game data of the role to be created;

and obtaining the data of the simulation game of the Nth time of the character to be created until the simulation game of the Nth time is carried out, wherein the data of the simulation game of the Nth time is converged relative to the data of the simulation game of the (N-1) th time.

6. The method of claim 1, wherein the simulated game data comprises primary simulated game data;

performing initial adjustment on the initial attribute of the character to be created according to the initial simulation game data to obtain the intermediate attribute of the character to be created;

performing a secondary simulation game on the character to be created according to the intermediate attribute to obtain secondary simulation game data of the character to be created;

and if the re-simulation game data reach the expected condition, determining the intermediate attribute as the final attribute of the character to be created.

7. The method of claim 1, wherein the determining, from the initial attributes, a similar character of the character to be created among existing game characters comprises:

and mapping the character to be created to an attribute space according to the initial attribute, and determining the existing game character closest to the character to be created in the attribute space as a similar character of the character to be created.

8. The method of claim 1, wherein the similar roles of the to-be-created role comprise a plurality of similar roles;

applying the configuration data of the similar role to the role to be created, and performing a simulation game, wherein obtaining simulation game data of the role to be created comprises:

and generating the configuration data of the character to be created according to the average value of the configuration data of the similar characters, and carrying out simulated game on the character to be created to obtain the simulated game data of the character to be created.

9. A game character creation apparatus, comprising:

the initial attribute acquisition module is used for acquiring the initial attribute of the role to be created;

a similar role determination module, configured to determine, according to the initial attribute, a similar role of the role to be created in an existing game role, and extract configuration data of the similar role, where the configuration data of the similar role at least includes equipment data of the similar role;

the simulation game processing module is used for applying the configuration data of the similar role to the role to be created, carrying out simulation game and obtaining simulation game data of the role to be created;

and the final attribute determining module is used for adjusting the initial attribute of the character to be created according to the simulation game data to obtain the final attribute of the character to be created.

10. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the method of any of claims 1-8 via execution of the executable instructions.

11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 8.