Player game data analysis method

Abstract

The invention discloses a player game data analysis method. The player game data analysis method comprises the steps of data acquisition, data preprocessing, feature extraction, data analysis and result presentation. Various types of behavior data of players in games are comprehensively collected, after preprocessing and feature extraction, various data analysis algorithms and deep learning algorithms are used for analysis, and finally analysis results are presented in a visual mode. According to the method, player behavior data can be deeply mined, valuable decision basis is provided for game developers and operators, game content optimization and operation efficiency is improved, and player experience and game benefits are improved.

Description

Technical Field

[0001] The present application relates to the field of game data analysis, and in particular to a method for analyzing player game data. Background Art

[0002] With the rapid development of the game industry, the number of game players continues to increase, and the amount of game data has also exploded. Game developers and operators need to have a deep understanding of player behavior and needs in order to optimize game content, enhance player experience, and increase game revenue. However, traditional game data analysis methods have many shortcomings. On the one hand, data collection is not comprehensive and cannot cover all the behavioral data of players in the game; on the other hand, the data analysis method is single and it is difficult to dig out the deep information behind the player's behavior. For example, traditional methods can often only perform simple statistical analysis on basic data such as player game time and level, and cannot accurately grasp the player's game preferences and potential needs. Therefore, a new method for analyzing player game data is urgently needed to solve the problems existing in the existing technology. Summary of the invention

[0003] The present invention mainly aims at the above-mentioned problems existing in the prior art and provides a method for analyzing player game data, which can deeply mine player behavior data and provide valuable decision-making basis for game developers and operators.

[0004] The purpose of the present invention is mainly achieved through the following solutions: A method for analyzing player game data, comprising the following steps: S1. Data collection step: Collect various behavioral data of players during the game, including but not limited to game operation records, game time, social interaction information, and props usage; S2, data preprocessing step: clean the collected data, remove noise data and duplicate data, and fill or delete missing values; S3, feature extraction step: extracting features for analysis from the preprocessed data, including but not limited to player activity features, game skill proficiency features, and social influence features; S4, data analysis step: using data analysis algorithms to analyze the extracted features, including but not limited to cluster analysis, association rule analysis, and time series analysis, to obtain player behavior patterns, game preferences, and potential game needs; S5. Result presentation step: present the analysis results in a visual manner, including but not limited to charts and reports, so that game developers and operators can intuitively understand player data.

[0005] Preferably, in the data collection step, player data is collected in real time through a data collection module built into the game client, and the data is transmitted to a server for storage.

[0006] Preferably, in the data preprocessing step, a noise data recognition algorithm based on a statistical method and a duplicate data detection algorithm based on a hash table are adopted.

[0007] Preferably, in the feature extraction step, the player behavior data is trained by a machine learning algorithm to automatically extract effective features.

[0008] Preferably, in the data analysis step, a deep learning algorithm is used to perform predictive analysis on player game data to predict player churn rate and willingness to pay.

[0009] Preferably, in the result presentation step, an interactive visualization tool is used to allow game developers and operators to customize data presentation methods according to their needs.

[0010] In summary, compared with the prior art, the present invention has the following beneficial technical effects: (1) The present invention comprehensively collects player data, which can cover all the player's behavior data in the game, providing a rich data basis for in-depth analysis; (2) The present invention adopts advanced data preprocessing and feature extraction methods to improve data quality and feature effectiveness, and enhance the accuracy of analysis results; (3) The present invention uses a variety of data analysis algorithms and deep learning algorithms to dig out the deep information behind player behavior and accurately grasp the player's game preferences and potential needs; (4) The present invention uses interactive visualization tools to present analysis results, making it easier for game developers and operators to intuitively understand player data and provide strong support for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0012] The technical solution of the present invention is further described in detail below through specific embodiments and in conjunction with the accompanying drawings. It should be understood that the implementation of the present invention is not limited to the following embodiments, and any form of modification and / or change made to the present invention will fall within the protection scope of the present invention.

[0013] like Figure 1 As shown, the present invention discloses a technical solution, a method for analyzing player game data, comprising the following steps: S1. Data collection step: Collect various behavioral data of players during the game, including but not limited to game operation records, game time, social interaction information, and props usage; S2, data preprocessing step: clean the collected data, remove noise data and duplicate data, and fill or delete missing values; S3, feature extraction step: extracting features for analysis from the preprocessed data, including but not limited to player activity features, game skill proficiency features, and social influence features; S4, data analysis step: using data analysis algorithms to analyze the extracted features, including but not limited to cluster analysis, association rule analysis, and time series analysis, to obtain player behavior patterns, game preferences, and potential game needs; S5. Result presentation step: present the analysis results in a visual manner, including but not limited to charts and reports, so that game developers and operators can intuitively understand player data.

[0014] Specifically, in the data collection step, the player data is collected in real time through the data collection module built into the game client, and the data is transmitted to the server for storage.

[0015] Specifically, in the data preprocessing step, a noise data recognition algorithm based on a statistical method and a duplicate data detection algorithm based on a hash table are adopted.

[0016] Specifically, in the feature extraction step, the player behavior data is trained through a machine learning algorithm to automatically extract effective features.

[0017] Specifically, in the data analysis step, deep learning algorithms are used to conduct predictive analysis on player game data to predict player churn rate and willingness to pay.

[0018] Specifically, in the result presentation step, interactive visualization tools are used to allow game developers and operators to customize data presentation methods according to their needs.

[0019] Taking a multiplayer online role-playing game as an example, the specific implementation steps are as follows: Data collection: A data collection module is built into the game client to collect real-time game operation records of players, such as the number of skill releases, attack frequency, etc.; game time, including daily game time, cumulative game time, etc.; social interaction information, such as the number of friends, the number of team formations, etc.; item usage, such as the type of item used, the frequency of use, etc. These data are transmitted to the server in real time for storage.

[0020] Data preprocessing: Clean the collected data, use a noise data identification algorithm based on statistical methods to identify and remove noise data such as abnormal operation records; use a duplicate data detection algorithm based on hash tables to remove duplicate social interaction information, etc. For missing game time data, use the mean filling method to fill it.

[0021] Feature extraction: Player behavior data is trained through machine learning algorithms to extract player activity features, such as the number of daily logins, online time distribution, etc.; game skill proficiency features, such as skill hit rate, skill cooldown time utilization efficiency, etc.; social influence features, such as the number of speeches in social groups, the number of times invited to form a team, etc.

[0022] Data analysis: Use cluster analysis algorithms to cluster players according to their game preferences and behavior patterns, and divide them into combat players, social players, exploration players, etc. Use association rule analysis to find the correlation between item use and player level upgrades; use time series analysis to predict the daily trend of online player numbers. At the same time, use deep learning algorithms to predict player churn rate and willingness to pay.

[0023] Results presentation: Interactive visualization tools are used to present the analysis results in the form of bar graphs, line graphs, pie charts, etc. For example, a bar graph can be used to show the number distribution of different types of players; a line graph can be used to show the daily trend of the number of players online; a pie chart can be used to show the proportion of props types used, etc. Game developers and operators can customize the data presentation method according to their needs, so as to intuitively understand player data and provide a basis for game optimization and operation decisions.

[0024] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for analyzing player game data, characterized in that: The following steps are involved: S1. Data collection step: Collect various behavioral data of players during the game, including but not limited to game operation records, game time, social interaction information, and props usage; S2, data preprocessing step: clean the collected data, remove noise data and duplicate data, and fill or delete missing values; S3, feature extraction step: extracting features for analysis from the preprocessed data, including but not limited to player activity features, game skill proficiency features, and social influence features; S4, data analysis step: using data analysis algorithms to analyze the extracted features, including but not limited to cluster analysis, association rule analysis, and time series analysis, to obtain player behavior patterns, game preferences, and potential game needs; S5. Result presentation step: present the analysis results in a visual manner, including but not limited to charts and reports, so that game developers and operators can intuitively understand player data.

2. A method for analyzing player game data according to claim 1, characterized in that: In the data collection step, the player data is collected in real time through the data collection module built into the game client, and the data is transmitted to the server for storage.

3. The method for analyzing player game data according to claim 1, characterized in that: In the data preprocessing step, a noise data recognition algorithm based on a statistical method and a duplicate data detection algorithm based on a hash table are adopted.

4. The method for analyzing player game data according to claim 1, characterized in that: In the feature extraction step, the player behavior data is trained through a machine learning algorithm to automatically extract effective features.

5. The method for analyzing player game data according to claim 1, characterized in that: In the data analysis step, a deep learning algorithm is used to perform predictive analysis on player game data to predict player churn rate and willingness to pay.

6. The method for analyzing player game data according to claim 1, characterized in that: In the result presentation step, an interactive visualization tool is used to allow game developers and operators to customize data presentation methods according to their needs.

Images