阅读说明：本技术 一种游戏角色的推荐方法及终端 (Game role recommendation method and terminal ) 是由 刘德建 高杨 杨灿 陈宏展 于 2019-09-09 设计创作，主要内容包括：本发明公开一种游戏角色的推荐方法及终端,通过对符合角色推荐的玩家喜欢使用的英雄的特征数据与游戏中所有其他玩家使用的英雄的特征数据的比对,找出与玩家喜欢使用的英雄最相似的前几个英雄,作为候选英雄列表,并对候选英雄列表进行过滤,通过对玩家大量游戏数据的分析,挖掘出不同游戏中不同英雄的玩法,根据玩家的玩法习惯,为玩家推荐类似操作风格的新英雄供玩家选择,能够充分挖掘出游戏中隐藏的玩家会感兴趣的角色,并且能够让玩家更多的接触相似风格的非同类型的英雄角色,从而让玩家在玩游戏的过程中更多元化,提升玩家的游戏娱乐性。(The invention discloses a method and a terminal for recommending game roles, wherein the first heroes most similar to heroes preferred by players are found out as a candidate hero list by comparing characteristic data of the heroes preferred by the players and the characteristic data of the heroes used by all other players in a game according to role recommendation, the candidate hero list is filtered, playing methods of different heroes in different games are mined by analyzing a large amount of game data of the players, new heroes with similar operation styles are recommended for the players to select according to the playing habits of the players, roles which are hidden in the game and can be interesting to the players can be fully mined, and the players can be more contacted with the non-same type hero roles with similar styles, so that the players can be more diversified in the game playing process, and the game entertainment of the players is improved.)

1. A method for recommending a game character, comprising the steps of:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

2. The method of claim 1, wherein the step S1 includes:

and determining the players with the daily playing times exceeding the preset times and the playing time length of each time exceeding the preset time length in the player database as the players according with the character recommendation.

3. The method of claim 1, wherein the step S2 includes:

for each player meeting the character recommendation, extracting hero meeting one of the following conditions in a preset time period as hero preferred by the player, and generating a first hero list:

hero with the winning rate exceeding the preset winning rate;

hero whose use frequency of player exceeds preset frequency;

hero whose ratio of using times of player exceeds preset ratio.

4. The method of claim 1, wherein the first hero characteristic data and the second hero characteristic data each comprise a plurality of game features representing the same operational habits and operational levels of the player;

each game feature includes the average and median of all game feature data values generated by each player in each tournament using each hero.

5. The method of claim 4, wherein the step S3 further comprises:

amplifying the maximum value of each game feature in all hero feature data consisting of the first hero feature data and the second hero feature data by a preset amount, and normalizing all game feature data values in each game feature according to the minimum value and the amplified maximum value in each game feature.

6. A game character recommendation terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

7. The terminal for recommending game characters according to claim 6, wherein said step S1 includes:

and determining the players with the daily playing times exceeding the preset times and the playing time length of each time exceeding the preset time length in the player database as the players according with the character recommendation.

8. The terminal for recommending game characters according to claim 6, wherein said step S2 includes:

for each player meeting the character recommendation, extracting hero meeting one of the following conditions in a preset time period as hero preferred by the player, and generating a first hero list:

hero with the winning rate exceeding the preset winning rate;

hero whose use frequency of player exceeds preset frequency;

hero whose ratio of using times of player exceeds preset ratio.

9. The terminal of claim 6, wherein the first hero characteristic data and the second hero characteristic data each comprise a plurality of game features representing the same operation habits and operation levels of the player;

each game feature includes the average and median of all game feature data values generated by each player in each tournament using each hero.

10. The terminal for recommending a game character according to claim 9, wherein said step S3 further comprises:

amplifying the maximum value of each game feature in all hero feature data consisting of the first hero feature data and the second hero feature data by a preset amount, and normalizing all game feature data values in each game feature according to the minimum value and the amplified maximum value in each game feature.

Technical Field

The invention relates to the field of game recommendation, in particular to a game role recommendation method and a terminal.

Background

At present, hero, loading and unloading sequence and playing method in the PVP game are designed by a game designer in the early stage of the game to guide a player to select, the player is guided to select by the method, the player often plays, the hero or the playing method selected by the player is too single, and other hero or playing method hidden in the game and possibly interesting the player cannot be fully excavated, so that the game experience of the player is not good enough.

Disclosure of Invention

The technical problem to be solved by the invention is as follows: the method and the terminal for recommending the game role can fully dig out the role which is hidden in the game and is interesting to the player, and improve user experience.

In order to solve the technical problems, the invention adopts a technical scheme that:

a method for recommending game characters comprises the following steps:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

In order to solve the technical problem, the invention adopts another technical scheme as follows:

a game character recommendation terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

The invention has the beneficial effects that: the first few heros most similar to the heros preferred by the players are found out by comparing the characteristic data of the heros preferred by the players according with the character recommendation with the characteristic data of the heros used by all other players in the game to serve as a candidate hero list, the candidate hero list is filtered, playing methods of different heros in different games are mined by analyzing a large amount of game data of the players, new heros with similar operation styles are recommended to the players for the players to select according to the playing habits of the players, the characters which the hidden players can be interested in the game can be fully mined, and the players can be more contacted with non-same types of heros with similar styles, so that the players can be more diversified in the game playing process, and the game entertainment of the players is improved.

Drawings

FIG. 1 is a flow chart illustrating steps of a method for recommending game characters according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a game character recommending terminal according to an embodiment of the present invention;

description of reference numerals:

1. a recommendation terminal for game roles; 2. a memory; 3. a processor.

Detailed Description

In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.

Referring to fig. 1, a method for recommending game characters includes the steps of:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

From the above description, the beneficial effects of the present invention are: the first few heros most similar to the heros preferred by the players are found out by comparing the characteristic data of the heros preferred by the players according with the character recommendation with the characteristic data of the heros used by all other players in the game to serve as a candidate hero list, the candidate hero list is filtered, playing methods of different heros in different games are mined by analyzing a large amount of game data of the players, new heros with similar operation styles are recommended to the players for the players to select according to the playing habits of the players, the characters which the hidden players can be interested in the game can be fully mined, and the players can be more contacted with non-same types of heros with similar styles, so that the players can be more diversified in the game playing process, and the game entertainment of the players is improved.

Further, the step S1 includes:

and determining the players with the daily playing times exceeding the preset times and the playing time length of each time exceeding the preset time length in the player database as the players according with the character recommendation.

Further, the step S2 includes:

for each player meeting the character recommendation, extracting hero meeting one of the following conditions in a preset time period as hero preferred by the player, and generating a first hero list:

hero with the winning rate exceeding the preset winning rate;

hero whose use frequency of player exceeds preset frequency;

hero whose ratio of using times of player exceeds preset ratio.

According to the description, the player meeting the preset conditions is determined as the player meeting the role recommendation, the hero meeting certain conditions in the hero used by the player is set as the hero which the player likes to use, a hero list is generated, the reliability and effectiveness of quantity sources for data analysis are guaranteed, meaningless analysis is avoided, resources are wasted, and the effectiveness and reliability of the role recommendation are improved.

Further, the first hero characteristic data and the second hero characteristic data both comprise a plurality of game characteristics which represent the same operation habits and operation levels of the player;

each game feature includes the average and median of all game feature data values generated by each player in each tournament using each hero.

As is apparent from the above description, the hero characteristic data includes a plurality of game characteristics representing player's operation habits and operation levels, and each game characteristic includes the average number and the median number of the game data generated during the game for each hero used by each player, and the extraction of the average number and the median number ensures the reasonableness of the comparative analysis, improving the accuracy of character recommendation.

Further, the step S3 further includes:

amplifying the maximum value of each game feature in all hero feature data consisting of the first hero feature data and the second hero feature data by a preset amount, and normalizing all game feature data values in each game feature according to the minimum value and the amplified maximum value in each game feature.

As can be seen from the above description, by appropriately amplifying the maximum value of each game feature and normalizing all game feature data values in each game feature based on the minimum value and the amplified maximum value in each game feature, the uniformity of each data during data analysis is ensured, and the accuracy of the recommended character obtained through data analysis is further improved.

Referring to fig. 2, a recommendation terminal for a game character includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the following steps:

s1, determining the player according with the role recommendation;

s2, extracting a first hero list which is liked to be used by the player and accords with the character recommendation;

s3, determining corresponding first hero characteristic data according to the first hero list, and extracting second hero characteristic data of all other players in the game;

s4, determining the preset number of heros most similar to the heros the player likes to use in the second hero characteristic data according to the first hero characteristic data and the second hero characteristic data, and generating a candidate hero recommendation list;

and S5, filtering the hero which the player likes to use and the hero which is different from the hero which the player likes to use from the candidate hero recommendation list, and generating a hero recommendation list.

From the above description, the beneficial effects of the present invention are: the first few heros most similar to the heros preferred by the players are found out by comparing the characteristic data of the heros preferred by the players according with the character recommendation with the characteristic data of the heros used by all other players in the game to serve as a candidate hero list, the candidate hero list is filtered, playing methods of different heros in different games are mined by analyzing a large amount of game data of the players, new heros with similar operation styles are recommended to the players for the players to select according to the playing habits of the players, the characters which the hidden players can be interested in the game can be fully mined, and the players can be more contacted with non-same types of heros with similar styles, so that the players can be more diversified in the game playing process, and the game entertainment of the players is improved.

Further, the step S1 includes:

and determining the players with the daily playing times exceeding the preset times and the playing time length of each time exceeding the preset time length in the player database as the players according with the character recommendation.

Further, the step S2 includes:

for each player meeting the character recommendation, extracting hero meeting one of the following conditions in a preset time period as hero preferred by the player, and generating a first hero list:

hero with the winning rate exceeding the preset winning rate;

hero whose use frequency of player exceeds preset frequency;

hero whose ratio of using times of player exceeds preset ratio.

According to the description, the player meeting the preset conditions is determined as the player meeting the role recommendation, the hero meeting certain conditions in the hero used by the player is set as the hero which the player likes to use, a hero list is generated, the reliability and effectiveness of quantity sources for data analysis are guaranteed, meaningless analysis is avoided, resources are wasted, and the effectiveness and reliability of the role recommendation are improved.

Further, the first hero characteristic data and the second hero characteristic data both comprise a plurality of game characteristics which represent the same operation habits and operation levels of the player;

each game feature includes the average and median of all game feature data values generated by each player in each tournament using each hero.

As is apparent from the above description, the hero characteristic data includes a plurality of game characteristics representing player's operation habits and operation levels, and each game characteristic includes the average number and the median number of the game data generated during the game for each hero used by each player, and the extraction of the average number and the median number ensures the reasonableness of the comparative analysis, improving the accuracy of character recommendation.

Further, the step S3 further includes:

amplifying the maximum value of each game feature in all hero feature data consisting of the first hero feature data and the second hero feature data by a preset amount, and normalizing all game feature data values in each game feature according to the minimum value and the amplified maximum value in each game feature.

As can be seen from the above description, by appropriately amplifying the maximum value of each game feature and normalizing all game feature data values in each game feature based on the minimum value and the amplified maximum value in each game feature, the uniformity of each data during data analysis is ensured, and the accuracy of the recommended character obtained through data analysis is further improved.