METHOD AND SYSTEM FOR PROPHESYING BEHAVIOR OF ONLINE GAMER, AND COMPUTER PROGRAM PRODUCT THEREOF

Abstract

A method and a system for prophesying a behavior of an online gamer, and a computer program product thereof are provided. In the present method, a gamer descriptor of a specific gamer of an online game accumulated before a time point is obtained firstly. Then, the gamer descriptor is divided into a plurality of sub-traces according to the time. Thereafter, at least one feature is derived from each of the sub-traces, and all features derived from the sub-traces are used for determining a possibility that the specific gamer quits the online game within a specific time period in the future.

Description

CROSS-REFERENCE TO RELATED APPLICATION

This application claims the priority benefit of Taiwan application serial no. 98142520, filed on Dec. 11, 2009. The entirety of the above-mentioned patent application is hereby incorporated by reference herein and made a part of specification.

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates to a method for prophesying a behavior. More particularly, the present invention relates to a method and a system for prophesying a behavior of an online gamer, and a computer program product thereof.

2. Description of Related Art

With widespread of the Internet, people are gradually used to obtain information from the Internet or contact others through the Internet, and more and more people take Internet surfing as a major leisure activity, which leads to a growth of online game industry. Different to a conventional personal computer (PC) game, an online game can achieve interactivities of the gamers, and the gamers can setup their own guilds to perform group activities and compete with each other, so that a variation degree and a sense of freshness of the game are greatly increased. According to statistics, in recent years, a market of the online game is still increasingly growing.

Generally, a fee-charging model of the online game includes a monthly fee model, an hour-based fee model, and a virtual treasure sale model. Regardless of the fee-charging model, the amount of players directly influences a profit of a game company, especially those hard-core players who will spend a lot of time and money on the game can greatly influence the profit of the game company. Therefore, how to trace a perception and a loyalty of each player to the game is undoubtedly an important issue for the game company who wants to enhance the output value.

However, present studies of player behaviors of the online game mostly take the behaviors of a group of players as an analysing unit. For example, the studies are mainly focused on number variations of the players in a same server, or the number of the players influenced by stability of the network, etc. These studies are mostly used to deduce increase or decrease of the number of the players in the future, and cannot be used to prophesy the players who will quit the game for a long time, so that the information provided to the online game company is insufficient.

SUMMARY OF THE INVENTION

Accordingly, the present invention is directed to a method for prophesying a behavior of an online gamer, by which one gamer is taken as a unit to determine whether the gamer will quit the online game for a long time within a period time in the future.

The present invention is directed to a system for prophesying a behavior of an online gamer, which may prophesy a behavior that a single gamer is going to quit the online game.

The present invention is directed to a computer program product comprising a plurality of program instructions, which is loaded to a computer system to prophesy a behavior of an online gamer.

The present invention provides a method for prophesying a behavior of an online gamer, which is used for prophesying a behavior of a specific gamer of an online game at a certain time point. In the present method, a gamer descriptor of the specific gamer accumulated before the time point is obtained. The gamer descriptor is divided into a plurality of sub-traces according to the time. At least one feature value is derived from each of the sub-traces, and a possibility that the specific gamer quits the online game within a specific time period in the future is determined according to the at least one feature value derived from each of the sub-traces.

In an embodiment of the present invention, the gamer descriptor at least includes one of a game related record of the specific gamer and a life related record of the specific gamer.

In an embodiment of the present invention, the game related record at least includes one of an online/offline record, a character profile information, and a character behavior information.

In an embodiment of the present invention, when the gamer descriptor includes the online/offline record, the step of deriving the at least one feature value from each of the sub-traces includes respectively deducing at least one of an average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime corresponding to each of the sub-traces according to each of the sub-traces, so as to serve as the at least one feature value.

In an embodiment of the present invention, the life related record at least includes one of a gamer profile information and a gamer behavior information.

In an embodiment of the present invention, the step of determining the possibility that the specific gamer quits the online game within the specific time period in the future according to the at least one feature value derived from each of the sub-traces includes using a machine learning mechanism to process the feature values derived from the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future. Wherein, the machine learning mechanism may be a supervised learning classification or a non-supervised learning classification, and the supervised learning classification includes a support vector machine (SVM).

The present invention provides a system for prophesying a behavior of an online gamer. The system includes an input/output interface, a storage unit, a feature deriving unit and a prophesying unit. The storage unit is used for storing gamer descriptors of a plurality of gamers of an online game. The feature deriving unit is coupled to the input/output interface and the storage unit, and after the input/output interface obtains a specific gamer and a time point, the feature deriving unit is used for obtaining the gamer descriptor of the specific gamer that is accumulated before the time point from the storage unit, dividing the gamer descriptor into a plurality of sub-traces according to time, and respectively deriving at least one feature value from each of the sub-traces. The prophesying unit is coupled to the input/output interface and the feature deriving unit, and is used for determining a possibility that the specific gamer quits the online game within a specific time period in the future according to the at least one feature value derived from each of the sub-traces, and outputting the possibility through the input/output interface.

In an embodiment of the present invention, the gamer descriptor at least includes one of a game related record of the specific gamer and a life related record of the specific gamer.

In an embodiment of the present invention, the game related record at least includes one of an online/offline record, a character profile information, and a character behavior information.

In an embodiment of the present invention, when the gamer descriptor includes the online/offline record, the feature deriving unit respectively deduces at least one of a average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime corresponding to each of the sub-traces according to each of the sub-traces, so as to serve as the at least one feature value.

In an embodiment of the present invention, the life related record at least includes one of a gamer profile information and a gamer behavior information.

In an embodiment of the present invention, the prophesying unit uses a machine learning mechanism to process the at least one feature value derived from each of the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future. Wherein, the machine learning mechanism includes a supervised learning classification or a non-supervised learning classification, and the supervised learning classification includes a SVM.

The present invention provides a computer program product including a plurality of program instructions, after the program instructions are loaded to a computer system, the aforementioned method for prophesying a behavior of an online gamer is executed.

According to the above descriptions, in the present invention, a gamer descriptor of a single specific gamer is obtained, and a plurality of feature values are derived from the gamer descriptor, so as to determine a possibility that the specific gamer quits the online game for a long time within a specific time period in the future according to the above feature values. Therefore, before the gamer completely lose an enthusiasm to the game, it has a chance to improve a playability of the game to enhance a willingness of the gamer to continually play the game.

In order to make the aforementioned and other features and advantages of the present invention comprehensible, several exemplary embodiments accompanied with figures are described in detail below.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

FIG. 1 is a block diagram illustrating a system for prophesying a behavior of an online gamer according to an embodiment of the present invention.

FIG. 2 is a flowchart illustrating a method for prophesying a behavior of an online gamer according to an embodiment of the present invention.

FIG. 3 is a flowchart illustrating a method for prophesying a behavior of an online gamer according to another embodiment of the present invention.

DESCRIPTION OF THE EMBODIMENTS

Since a perception of a gamer for an online game may be reflected by a related record of the gamer, if a behavior of the gamer can be deduced by analysing the related record, a game content can be improved when a satisfactory of the gamer is decreased, so as to maintain an enthusiasm of the gamer to the game. Therefore, a method and a system for prophesying a behavior of an online gamer, and a computer program product thereof are provided according to the above concept. To fully convey the concept of the present invention, embodiments are provided below for describing the present invention in detail.

FIG. 1 is a block diagram illustrating a system for prophesying a behavior of an online gamer according to an embodiment of the present invention. Referring to FIG. 1, the system 100 for prophesying a behavior of an online gamer includes an input/output interface 110, a storage unit 120, a feature deriving unit 130 and a prophesying unit 140. The system 100 is used for prophesying a behavior of a single gamer of an online game, especially for prophesying a behavior of the gamer intended to quit the online game.

In the present embodiment, the input/output interface 110 is, for example, a combination of a keyboard and a screen, or a touch screen, etc., which is used for receiving an input of a prophesying target and outputting a prophesying result. The storage unit 120 is, for example, any storage unit such as a memory, a memory card or a hard disk, etc., which is not limited by the present invention. In the present embodiment, the storage unit 120 stores a continuously accumulated gamer descriptor of each of the gamers of the online game.

The feature deriving unit 130 is coupled to the input/output interface 110 and the storage unit 120. After the input/output interface 110 obtains a specific gamer serving as the prophesying target, the feature deriving unit 130 obtains the related gamer descriptor from the storage unit 120, and derives a plurality of feature values from the gamer descriptor.

The prophesying unit 140 is coupled to the input/output interface 110 and the feature deriving unit 130, which is used for performing a prophesying operation according to the feature values derived by the feature deriving unit 130, and displaying a prophesying result on the input/output interface 110.

Another embodiment is provided below to further describe an operation flow of the system 100 for prophesying the behavior of the online gamer. FIG. 2 is a flowchart illustrating a method for prophesying a behavior of an online gamer according to an embodiment of the present invention.

Referring to FIG. 1 and FIG. 2, after a specific gamer serving as the prophesying target and a time point corresponding to the prophesying operation are obtained through the input/output interface 110, in step 210, the feature deriving unit 130 obtains a gamer descriptor of the specific gamer that is accumulated before the time point from the storage unit 120. In the present embodiment, the gamer descriptor of the specific gamer at least includes one of a game related record and a life related record of the specific gamer, though the present invention is not limited thereto. In detail, the game related record at least includes one of an online/offline record, a character profile information, and a character behavior information. The life related record at least includes one of a gamer profile information and a gamer behavior information.

Next, in step 220, the feature deriving unit 130 divides the gamer descriptor into a plurality of sub-traces according to time. For example, the feature deriving unit 130 may equally divide the gamer descriptor into K sub-traces according to the time, wherein K may be 10 or other positive integers, which is not limited by the present invention.

Next, in step 230, the feature deriving unit 130 respectively derives one or a plurality of feature values from each of the sub-traces. It should be noticed that types of the feature values derived by the feature deriving unit 130 may be different as contents of the gamer descriptors are different. For example, when the gamer descriptor includes the online/offline record of the specific gamer, the feature deriving unit 130 may deduce at least one of a average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime according to the content of each of the sub-traces, so as to serve as the feature values corresponding to each of the sub-traces.

When the gamer descriptor includes the character profile information, the feature deriving unit 130 may take information such as a race, a level, a level-up speed or equipments, etc. of the character played by the specific gamer in the online game as the feature values. When the gamer descriptor includes the character behavior information, the feature deriving unit 130 may obtain the feature values according to a consumption status of the character played by the specific gamer in the game, or interactive relationships with other characters in the game. Moreover, when the gamer descriptor includes the gamer profile information, the feature deriving unit 130 takes the information (for example, sex, education, occupation, residence, or income, etc.) of the gamer as the feature values. When the gamer descriptor includes the gamer behavior information, the feature deriving unit 130 may analyses actual behaviors (for example, a payment approach or whether there is a delay in payment, etc.) of the gamer in the real life to obtain the feature values.

It should be noticed that the gamer descriptor and the types of the feature values are only examples of the present invention, and when the system 100 performs the prophesying, determination may be performed not only based on the aforementioned gamer descriptor and the feature values. In detail, any static or dynamic information related to the gamer may serve as the gamer descriptor, and the feature deriving unit 130 may derive different feature values according to different gamer descriptors.

Finally, in step 240, the prophesying unit 140 determines a possibility that the specific gamer quits the online game within a specific time period in the future (for example, within 10 days in the future, or with in one month in the future, etc.) according to the feature values derived from each of the sub-traces. In the present embodiment, the prophesying unit 140 uses a machine learning mechanism to process the feature values derived from the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future. Wherein, the machine learning mechanism may be a supervised learning classification or a non-supervised learning classification, and the supervised learning classification is, for example, a support vector machine (SVM), which is used for classifying the feature values to obtain the prophesying result.

In the present embodiment, the prophesying unit 140 determines whether the specific gamer will quit the online game within a specific time period in the future, or calculates a possibility that the specific gamer quits the online game within the specific time period in the future. The prophesying result is outputted through the input/output interface 110.

Accordingly, an online game company may use the system 100 for prophesying the behavior of the online gamer to trace each of the gamers of the online game, so that at any time point, the system 100 may prophesy whether a certain gamer will quit the online game within a specific time period in the future according to the gamer descriptor accumulated before the time point. Once it is prophesied that the gamer will quit the online game for a long time, an immediate investigation may be performed to positively improve a content of the online game, so as to reduce a decreasing rate of the gamers. Moreover, the online game company may further analyse the gamers intended to quit the game according to the prophesying results of the system 100, so as to determine whether these gamers are all connected to a specific server, and if yes, it may be deduced that a connection problem of the server that cause the gamers losing their enthusiasm is probably occurred. Therefore, the server is tested and inspected to enhance hardware or network equipments thereof.

FIG. 3 is a flowchart illustrating a method for prophesying a behavior of an online gamer according to another embodiment of the present invention. In the following embodiment, the gamer descriptor includes the online/offline record of the specific gamer. Referring to FIG. 3, when a specific gamer of the online game is prophesied at any time point, in step 310, the online/offline record of the specific gamer that is accumulated before the time point is obtained, wherein the online/offline record includes a daily online/offline time record of the specific gamer from a time point that the specific gamer start to play the online game to the time point when the prophesying is performed.

In step 320, the online/offline record of the specific gamer is divided (for example, equally divided) into a plurality of sub-traces according to the time. For example, if the specific gamer has played the online game for 100 days when the prophesying is performed, according to the step 320, a first to a 33rd days, a 34th to a 66th days, and a 67th to a 100th days are respectively divided into a sub-trace.

Next, in step 330, an average daily playtime and a playing density are respectively derived from each of the sub-traces to serve as the feature values of each sub-trace. In detail, the average daily playtime represents a ratio between a total session time of the specific gamer and days covered by the sub-trace. The playing density represents a ratio between days that the specific gamer plays the online game and days covered by the sub-trace.

After the average daily playtime and the playing density corresponding to each of the sub-traces are calculated, in a final step 340, a possibility that the specific gamer quits the online game within a specific time period in the future is determined according to the average daily playtime and the playing density corresponding to each of the sub-traces. In the present embodiment, all of the calculated average daily playtimes and game playing densities are, for example, input to the trained classifier for a classification processing, so as to prophesy whether the specific gamer will quit the online game within a specific time period in the future.

In the present embodiment, to increase a prophesying accuracy, the other gamer descriptors (for example, the gamer profile information, the gamer behavior information, the character profile information, or the character behavior information etc.) of the specific gamer may also be added to derive more feature values. Then, all of the derived feature values are input to the prophesying unit to obtain the prophesying result.

The present invention provides a computer program product, which is used for executing the method for prophesying a behavior of an online gamer. The computer program product is basically formed by a plurality of program instructions (for example, setting program instruction or deployment program instruction, etc.). After these program instructions are loaded to the computer system for execution, the aforementioned steps for prophesying a behavior of an online gamer are then implemented, so that the computer system may prophesy a possibility that a gamer quits the online game within a specific time period in the future by analysing a gamer descriptor of the single gamer.

In summary, in the present invention, the method and the system for prophesying a behavior of an online gamer, and the computer program product thereof are used for prophesying a behavior of a single gamer. Therefore, when the gamers intend to quit the online game, the online game company is capable of finding a reason why the gamers lose enthusiasm to the game through a questionnaire survey, so as to suitably modify the game. Moreover, regarding all of the gamers intended to quit the game, the online game company is capable of analysing session status of these gamers, so as to determine whether the relevant server operation is abnormal, and accordingly enhance the related software and hardware to achieve the purpose of consolidating the number of the gamers.

It will be apparent to those skilled in the art that various modifications and variations may be made to the structure of the present invention without departing from the scope or spirit of the invention. In view of the foregoing, it is intended that the present invention cover modifications and variations of this invention provided they fall within the scope of the following claims and their equivalents.

Claims

1. A method for prophesying behavior of an online gamer, suitable for prophesying a behavior of a specific gamer of an online game at a time point, comprising:

obtaining a gamer descriptor of the specific gamer accumulated before the time point;

dividing the gamer descriptor into a plurality of sub-traces according to time;

respectively deriving at least one feature value from each of the sub-traces; and

determining a possibility that the specific gamer quits the online game within a specific time period in the future according to the at least one feature value derived from each of the sub-traces.

2. The method for prophesying the behavior of the online gamer as claimed in claim 1, wherein the gamer descriptor at least comprises one of a game related record of the specific gamer and a life related record of the specific gamer.

3. The method for prophesying the behavior of the online gamer as claimed in claim 2, wherein the game related record at least comprises one of an online/offline record, a character profile information, and a character behavior information.

4. The method for prophesying the behavior of the online gamer as claimed in claim 3, wherein when the gamer descriptor comprises the online/offline record, the step of respectively deriving the at least one feature value from each of the sub-traces comprises:

respectively deducing at least one of an average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime corresponding to each of the sub-traces according to each of the sub-traces, so as to serve as the at least one feature value.

5. The method for prophesying the behavior of the online gamer as claimed in claim 2, wherein the life related record at least comprises one of a gamer profile information and a gamer behavior information.

6. The method for prophesying the behavior of the online gamer as claimed in claim 1, wherein the step of determining the possibility that the specific gamer quits the online game within the specific time period in the future according to the at least one feature value derived from each of the sub-traces comprises:

using a machine learning mechanism to process the at least one feature value derived from each of the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future.

7. The method for prophesying the behavior of the online gamer as claimed in claim 6, wherein the machine learning mechanism comprises one of a supervised learning classification and a non-supervised learning classification.

8. The method for prophesying the behavior of the online gamer as claimed in claim 7, wherein the supervised learning classification comprises a support vector machine (SVM).

9. A system for prophesying a behavior of an online gamer, comprising:

an input/output interface;

a storage unit, configured to store gamer descriptors of a plurality of gamers of an online game;

a feature deriving unit, coupled to the input/output interface and the storage unit, wherein after the input/output interface obtains a specific gamer and a time point, the feature deriving unit is configured to obtain the gamer descriptor of the specific gamer that is accumulated before the time point from the storage unit, divide the gamer descriptor into a plurality of sub-traces according to time, and respectively derive at least one feature value from each of the sub-traces; and

a prophesying unit, coupled to the input/output interface and the feature deriving unit, the prophesying unit is configured to determine a possibility that the specific gamer quits the online game within a specific time period in the future according to the at least one feature value derived from each of the sub-traces, and output the possibility through the input/output interface.

10. The system for prophesying the behavior of the online gamer as claimed in claim 9, wherein the gamer descriptor at least comprises one of a game related record of the specific gamer and a life related record of the specific gamer.

11. The system for prophesying the behavior of the online gamer as claimed in claim 10, wherein the game related record at least comprises one of an online/offline record, a character profile information, and a character behavior information.

12. The system for prophesying the behavior of the online gamer as claimed in claim 11, wherein when the gamer descriptor comprises the online/offline record, the feature deriving unit respectively deduces at least one of an average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime corresponding to each of the sub-traces according to each of the sub-traces, so as to serve as the at least one feature value.

13. The system for prophesying the behavior of the online gamer as claimed in claim 10, wherein the life related record at least comprises one of a gamer profile information and a gamer behavior information.

14. The system for prophesying the behavior of the online gamer as claimed in claim 9, wherein the prophesying unit uses a machine learning mechanism to process the at least one feature value derived from each of the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future.

15. The system for prophesying the behavior of the online gamer as claimed in claim 14, wherein the machine learning mechanism comprises one of a supervised learning classification and a non-supervised learning classification.

16. The system for prophesying the behavior of the online gamer as claimed in claim 15, wherein the supervised learning classification comprises a support vector machine (SVM).

17. A computer program product comprising a plurality of program instructions, the program instructions being loaded to a computer system to execute following steps:

obtaining a gamer descriptor of a specific gamer of an online game that is accumulated before a time point;

dividing the gamer descriptor into a plurality of sub-traces according to time;

respectively deriving at least one feature value from each of the sub-traces; and

determining a possibility that the specific gamer quits the online game within a specific time period in the future according to the at least one feature value derived from each of the sub-traces.

18. The computer program product as claimed in claim 17, wherein the gamer descriptor at least comprises one of a game related record of the specific gamer and a life related record of the specific gamer.

19. The computer program product as claimed in claim 18, wherein the game related record at least comprises one of an online/offline record, a character profile information, and a character behavior information.

20. The computer program product as claimed in claim 19, wherein the program instructions respectively deduce at least one of an average daily playtime, a playing density, an average session time point, an average of each session time, and a variation of daily playtime corresponding to each of the sub-traces according to each of the sub-traces, so as to serve as the at least one feature value if the gamer descriptor comprises the online/offline record.

21. The computer program product as claimed in claim 18, wherein the life related record at least comprises one of a gamer profile information and a gamer behavior information.

22. The computer program product as claimed in claim 17, wherein the program instructions use a machine learning mechanism to process the at least one feature value derived from each of the sub-traces, so as to calculate the possibility that the specific gamer quits the online game within the specific time period in the future.

23. The computer program product as claimed in claim 22, wherein the machine learning mechanism comprises one of a supervised learning classification and a non-supervised learning classification.

24. The computer program product as claimed in claim 23, wherein the supervised learning classification comprises a support vector machine (SVM).