Game promotion system and method based on data analysis

Abstract

The invention relates to the field of game promotion, and discloses a game promotion system and method based on data analysis, and the system comprises a data collection module which collects a player login frequency, a game duration, a checkpoint clearance rate, a payment frequency and an amount; regularly capturing the market scale and growth rate of games in each region and the popularity rank of the type to which the current game belongs from the game data platform; aiming at competitive games of the same type, analyzing a downloading quantity curve of the competitive games; the data analysis module obtains an interest index of each player based on the player behavior data, and performs grouping analysis on the players according to the interest index of each player; the promotion strategy generation module is used for customizing promotion strategies for different player groups according to the data analysis result; and the effect monitoring module calculates the promotion value index of the current game based on the market data and the competitive product data, comprehensively evaluates the promotion effect of the current game according to the promotion value index and the player interest index, and builds a visual billboard.

Description

Technical Field

[0001] The present invention relates to the field of game promotion, and in particular to a game promotion system and method based on data analysis. Background Art

[0002] With the rapid development of the gaming industry, market competition has become increasingly fierce. The number of games worldwide has grown exponentially, with thousands of new games launched every year, making game promotion more difficult and developers facing huge challenges.

[0003] The rise of data analysis technology has brought hope to the dilemma of game promotion. In the era of big data, the collection, storage and processing of massive data can be realized. With the help of professional data mining and machine learning algorithms, it is possible to deeply analyze player behavior and accurately track market trends, thereby providing a scientific and quantitative basis for the formulation and optimization of game promotion strategies;

[0004] However, how to continuously attract existing game players and convert them into active players is what is lacking in current game promotion. After most players are attracted by traditional game promotion strategies, the lack of follow-up promotion strategies in the subsequent process leads to a large number of player losses, resulting in serious waste of promotion resources invested in the early stage and causing losses. Therefore, it is urgent to build a game promotion system and method based on data analysis. Summary of the invention

[0005] The purpose of the present invention is to provide a game promotion system and method based on data analysis to solve the above technical problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A game promotion system based on data analysis, comprising:

[0008] The data acquisition module is used to collect multi-dimensional data, and the multi-dimensional data includes:

[0009] Player behavior data, including player login frequency, game duration, level completion rate, payment frequency and amount;

[0010] Market data: regularly capture the game market size, growth rate, and popularity ranking of current game types in each region from the game data platform;

[0011] Competitive product data: analyze the download curve of competitive games of the same type;

[0012] The data analysis module calculates the interest index of each player based on the player behavior data, and then performs group analysis on the players according to the interest index of each player, dividing the players into high-frequency, medium-frequency and low-frequency player groups;

[0013] Promotion strategy generation module, used to customize promotion strategies for different player groups according to data analysis results;

[0014] The effect monitoring module calculates the promotion value index of the current game based on market data and competitor data, and then comprehensively evaluates the promotion effect of the current game based on the promotion value index and player interest index, and builds a visual dashboard.

[0015] As a further technical solution, the process of calculating each player's interest index based on the player behavior data is as follows:

[0016] The obtained player behavior data is passed through the formula:

[0017]

[0018] Calculate the interest index F of the rth player r , i is the i-th player behavior data, 6 is the number of player behavior data items, q i is the parameter value of the i-th player behavior data, q imin ,q imax are the minimum and maximum values ​​of the i-th player behavior data, respectively. is the weight coefficient of the i-th player behavior data.

[0019] As a further technical solution, the process of performing group analysis on players according to each player's interest index is as follows:

[0020] The interest index F of the rth player r With the pre-set interest index interval [F r0 , F r1 ] for comparison:

[0021] If F r ∈[F r0 , F r1 ], then the current player is judged to be a medium-frequency player;

[0022] If F r >F r1 , then the current player is judged to be a high-frequency player;

[0023] If F r >F r1 , then the current player is judged to be a low-frequency player.

[0024] As a further technical solution, based on market data and competitor data, the process of calculating the promotion value index of the current game is as follows:

[0025] Market data and competitor data are combined through the formula:

[0026]

[0027] Calculate the promotion value index D of the current game;

[0028] Among them, t0 and t1 are the two time endpoints of a preset monitoring period, K(t) is the curve of the popularity ranking of the type to which the current game belongs during the monitoring period, f(x) is the judgment function about competing games, β is the game market size, and γ is the game market size growth rate.

[0029] As a further technical solution, the process of obtaining the judgment function f(x) about the competing game is:

[0030] like but

[0031] like but

[0032] Among them, g(t) is the download volume change curve of the competing game over time, g0(t) is the download volume reference change curve, Δθ is the reference value, is a constant and

[0033] As a further technical solution, the process of comprehensively evaluating the current game promotion effect based on the promotion value index and the player interest index is as follows:

[0034] By formula:

[0035]

[0036] The promotion evaluation coefficient H is calculated;

[0037] Among them, N B N is the actual number of players in the current game at the end of a statistical period. A N is the actual number of players in the current game at the start time of a statistical period. C It is the ratio of high-frequency players to the actual number of players of the current game at the end of a statistical period. D0 is the reference value of the promotion value index.

[0038] Compare the calculated promotion evaluation coefficient H with the preset promotion evaluation threshold H0:

[0039] If H≥H0, the promotion value of the current game is evaluated to be good;

[0040] If H<H0, the promotion value of the current game is evaluated to be poor.

[0041] As a further technical solution, the visual dashboard supports multi-terminal display, including computers, tablets and mobile phones.

[0042] A game promotion method based on data analysis, the method is implemented based on the game promotion system based on data analysis.

[0043] Beneficial effects of the present invention:

[0044] The present invention acquires multi-dimensional data with the help of a data acquisition module, and focuses on analyzing player behavior data by a data analysis module, thereby dividing players into three groups: high-frequency, medium-frequency, and low-frequency. The promotion focus is on converting low-frequency players into medium-frequency and high-frequency players, thereby increasing the popularity of the game, while focusing on attracting new high-frequency players and expanding the player base. Subsequently, exclusive promotion strategies are formulated according to different groups, and existing players are stabilized on the basis of traditional methods to seize market share. The promotion value index is then calculated based on market and competitor data, and the promotion effect is evaluated in combination with the player interest index. A visual dashboard is built to provide support for real-time optimization of promotion strategies and achieve overall promotion optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further described below in conjunction with the accompanying drawings.

[0046] Figure 1 It is a system logic block diagram of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 As shown, the present invention is a game promotion system based on data analysis, comprising:

[0049] The data acquisition module is used to collect multi-dimensional data, and the multi-dimensional data includes:

[0050] Player behavior data, including player login frequency, game duration, level completion rate, payment frequency and amount;

[0051] Market data: regularly capture the game market size, growth rate, and popularity ranking of current game types in each region from the game data platform;

[0052] Competitive product data: analyze the download curve of competitive games of the same type;

[0053] The data analysis module calculates the interest index of each player based on the player behavior data, and then performs group analysis on the players according to the interest index of each player, dividing the players into high-frequency, medium-frequency and low-frequency player groups;

[0054] Promotion strategy generation module, used to customize promotion strategies for different player groups according to data analysis results;

[0055] The effect monitoring module calculates the promotion value index of the current game based on market data and competitor data, and then comprehensively evaluates the promotion effect of the current game based on the promotion value index and player interest index, and builds a visual dashboard that supports multi-terminal display, including computers, tablets and mobile phones.

[0056] In this embodiment, after collecting multi-dimensional data through the data collection module, the player behavior data is analyzed in detail through the data analysis module, so as to divide the players into three groups: high frequency, medium frequency and low frequency. Obviously, low frequency players and medium frequency players are the top priorities of this promotion. The focus is on how to convert low frequency players into medium frequency or even high frequency players, which can significantly improve the popularity ranking of the game. The promotion focus for high frequency players is to attract new players, that is, to promote the current game to the surrounding areas and increase the number of game players. Different promotion strategies are formulated by the above three groups, and the existing players of the current game can be maintained on the basis of traditional promotion strategies, and finally the purpose of seizing market share can be achieved. Finally, the promotion value index of the current game is calculated based on market data and competitive product data, and then the promotion effect of the current game is comprehensively evaluated according to the promotion value index and the player interest index, and a visual dashboard is built to provide a judgment basis for the real-time optimization of the promotion strategy, thereby achieving overall promotion optimization. It should be noted that the existing traditional game promotion strategy is an existing technology, which will not be repeated here, such as highlighting the differences with competitive games, promoting through different channels, celebrity and Internet celebrity endorsements, interesting science popularization, hot topic association, and free trial.

[0057] The process of calculating each player's interest index based on player behavior data is as follows:

[0058] The obtained player behavior data is passed through the formula:

[0059]

[0060] Calculate the interest index F of the rth player r , i is the i-th player behavior data, 6 is the number of player behavior data items, q i is the parameter value of the i-th player behavior data, q imin ,q imax are the minimum and maximum values ​​of the i-th player behavior data, respectively. is the weight coefficient of the i-th player behavior data, determined based on historical data analysis;

[0061] The process of performing segmentation analysis on players based on each player's interest index is as follows:

[0062] The interest index F of the rth player r With the pre-set interest index interval [F r0 , F r1 ] for comparison:

[0063] If F r ∈[F r0 , F r1 ], then the current player is judged to be a medium-frequency player;

[0064] If F r >F r1 , then the current player is judged to be a high-frequency player;

[0065] If F r >F r1 , then the current player is judged to be a low-frequency player.

[0066] In this embodiment, a method for obtaining different interest indexes of each player is provided. Specifically, the collected behavior parameters of each player are first substituted into the formula Each player behavior parameter is processed by cumulative calculation, and finally the interest index of each player is obtained. Obviously, the higher the player login frequency, game duration, level completion rate, payment frequency and amount of each player, the higher the player's enthusiasm for the current game, that is, the more willing to promote the current game, the greater the player's stickiness. In addition, the slight changes in each player's behavior parameters can be found by cumulative multiplication, and then the player groups can be divided in real time and accurately, laying a solid foundation for the subsequent formulation of different promotion strategies. At the same time, a method for dividing player groups is provided. First, the interest index F of the rth player is calculated. r With the pre-set interest index interval [F r0 , F r1 ] for comparison, when F r ∈[F r0 , F r1 ], the current player is a medium-frequency player. r >F r1 When the current player is a high-frequency player, r >F r1 , the current player is a low-frequency player;

[0067] It should be noted that the promotion strategies designed for different groups of players are shown in the following examples:

[0068] For high frequency players:

[0069] 1. Exclusive gift package strategy: This type of players are highly engaged in the game and participate frequently. We customize limited edition premium game gift packages for them, which contain rare props, limited-time skins, and exclusive characters. Gift packages can not only enhance their gaming experience, but also stimulate their desire to show off through scarcity, prompting them to share in the gaming community and achieve word-of-mouth communication. For example, we launch a themed gift package for high-frequency players every month and push it with in-game announcements.

[0070] 2. Early access privileges: For new gameplay and new levels, give frequent players the opportunity to try them out in advance, unlocking them days or even weeks earlier than ordinary players. Let them feel the special treatment, stimulate their continued enthusiasm for the game, and collect their experience feedback to optimize the subsequent official online content; for example, before a large expansion pack is updated, invite frequent players to participate in the internal test;

[0071] 3. Community leader incentives: Identify opinion leaders among high-frequency players and give them special titles in the game, such as "Glory Pioneer" and "Chief Experience Officer", to enhance their prestige in the game community; encourage them to organize online and offline activities to promote the social atmosphere of the game, and give corresponding game points or physical peripheral rewards for each successful large-scale community activity.

[0072] For mid-range players:

[0073] 1. Growth support plan: Medium-frequency players have a certain degree of game participation, but may encounter bottlenecks in the process of advancement. We design personalized growth route guidance for them, with phased rewards. For example, when players reach a certain level or their character level is upgraded, we will issue corresponding upgrade resource packages, including experience value bonus props and skill upgrade materials, to help them break through bottlenecks and improve retention rates.

[0074] 2. Limited-time discounts: Regularly select a batch of popular props and fashions, and conduct limited-time discount promotions for medium-frequency players to create a sense of urgency and guide them to increase their payment frequency. You can push exclusive discount information at fixed times of the week, such as weekends, through in-game pop-ups and email notifications, with eye-catching discount labels and original price comparisons, to attract their consumption.

[0075] 3. Social team incentives: Given that mid-frequency players are fairly active, encourage them to participate more in social team play; set up team tasks and reward mechanisms. When a team completes a specified number of dungeons and battles, team members can receive additional rewards, such as gold coin bonuses and random treasure chests, to strengthen the social stickiness of the game and bring them closer to high-frequency players.

[0076] For low frequency players:

[0077] 1. Restart the game with a novice gift pack: Many low-frequency players may reduce their participation due to difficulties in getting started in the early stages. We will push optimized novice gift packs to them again, simplify the gift pack collection process, increase early resource support, and help them easily restart the game experience; the gift pack will include a novice guide short video link to quickly help them familiarize themselves with the basic game operations and core gameplay;

[0078] 2. Lightweight event invitations: Plan some lightweight events that are short in time and low in difficulty, such as limited-time sign-in draws and simple casual game challenges, to attract low-frequency players to participate in fragmented time; prizes can be highly versatile game currencies and basic props. Each event cycle is controlled within 1-3 days to lower the participation threshold and reawaken their interest;

[0079] 3. Nostalgic recall content: dig into classic elements of the game in the past, make them into sentimental-themed promotional posters and short videos, push them to low-frequency players, and evoke their past game memories; with return rewards, as long as you log in to the game again, you can receive a return gift pack containing replicas of popular props from the old version, stimulate emotional resonance, and attract them to return to the game.

[0080] Based on market data and competitor data, the process of calculating the promotion value index of the current game is as follows:

[0081] Market data and competitor data are combined through the formula:

[0082]

[0083] Calculate the promotion value index D of the current game;

[0084] Among them, t0 and t1 are the two time endpoints of a preset monitoring period, K(t) is the curve of the popularity ranking of the type to which the current game belongs during the monitoring period, f(x) is the judgment function about competing games, β is the game market size, and γ is the game market size growth rate.

[0085] The process of obtaining the judgment function f(x) about the competing game is:

[0086] like but

[0087] like but

[0088] Among them, g(t) is the download volume change curve of the competing game over time, g0(t) is the download volume reference change curve, Δθ is the reference value, is a constant and

[0089] The process of comprehensively evaluating the current game promotion effect based on the promotion value index and player interest index is as follows:

[0090] By formula:

[0091]

[0092] The promotion evaluation coefficient H is calculated;

[0093] Among them, N B N is the actual number of players in the current game at the end of a statistical period. A N is the actual number of players in the current game at the start time of a statistical period. C It is the ratio of high-frequency players to the actual number of players of the current game at the end of a statistical period. D0 is the reference value of the promotion value index, which is determined based on historical data and experimental data analysis.

[0094] Compare the calculated promotion evaluation coefficient H with the preset promotion evaluation threshold H0:

[0095] If H≥H0, the promotion value of the current game is evaluated to be good;

[0096] If H<H0, the promotion value of the current game is evaluated to be poor.

[0097] In this embodiment, in order to quickly determine the promotion value of the current game, specifically, firstly, the market data and the competitive product data are combined through the formula: The promotion value index D of the current game is calculated; wherein t0 and t1 are two time endpoints of a preset monitoring period, K(t) is the curve of the popularity ranking of the type to which the current game belongs changing with time during the monitoring period, f(x) is the judgment function of the competing game, β is the market size of the game, and γ is the growth rate of the market size of the game. It can be clearly seen from the above formula that the larger the product of the market size of the game and the growth rate, the better the market of the game is and the upward trend is. Therefore, it is more valuable to promote the current game. Therefore, the promotion value index of the current game is affected by the method of 1+β*γ, thereby improving the accuracy of the promotion value index of the current game. At the same time, Calculate the cumulative change of the current game popularity ranking. Obviously, the larger the cumulative change, the faster the current game popularity increases, so the promotion value of the current game is higher. Add the impact of competing games and compare the cumulative change of competing games in a monitoring period with the reference value. Obviously, if the cumulative change of the competing game is greater than 1, it means that the download volume of the competing game is on a downward trend, otherwise it means that the download volume of the competing game is on an upward trend. but like but This means that the download volume of competing games is on a downward trend, and the number of new players is relatively low. At this time, maintaining existing players is an important means to maintain the popularity of the current game, so the promotion value of the current game is higher;

[0098] In order to evaluate the current game promotion strategy, first use the formula:

[0099] The generalized evaluation coefficient H is calculated; obviously, if The larger the value, the more new players are added, and N C The larger the value, the higher the proportion of high-frequency players. Therefore, the better the overall promotion effect of the current game, the greater the promotion evaluation coefficient. If the ratio of the promotion value index of the current game to the reference value is The larger it is, the higher the promotion value of the current game. By combining the above two parameters to establish an evaluation model for the current game promotion strategy, the promotion situation of the current game in each statistical period can be accurately and quickly evaluated, so as to adjust the promotion strategy in a timely and effective manner. The calculated promotion evaluation coefficient H is then compared with the preset promotion evaluation threshold H0: if H≥H0, the promotion value of the current game is evaluated to be good; if H<H0, the promotion value of the current game is evaluated to be poor.

[0100] A game promotion method based on data analysis, the method is implemented based on the game promotion system based on data analysis.

[0101] It should be noted that the calculation formulas and various parameters involved in the calculation in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0102] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A game promotion system based on data analysis, characterized in that: include: The data acquisition module is used to collect multi-dimensional data, and the multi-dimensional data includes: Player behavior data, including player login frequency, game duration, level completion rate, payment frequency and amount; Market data: regularly capture the game market size, growth rate, and popularity ranking of current game types in each region from the game data platform; Competitive product data: analyze the download curve of competitive games of the same type; The data analysis module calculates the interest index of each player based on the player behavior data, and then performs group analysis on the players according to the interest index of each player, dividing the players into high-frequency, medium-frequency and low-frequency player groups; Promotion strategy generation module, used to customize promotion strategies for different player groups according to data analysis results; The effect monitoring module calculates the promotion value index of the current game based on market data and competitor data, and then comprehensively evaluates the promotion effect of the current game based on the promotion value index and player interest index, and builds a visual dashboard.

2. The game promotion system based on data analysis according to claim 1, characterized in that: The process of calculating each player's interest index based on player behavior data is as follows: The obtained player behavior data is passed through the formula: Calculate the interest index F of the rth player r , i is the i-th player behavior data, 6 is the number of player behavior data items, q i is the parameter value of the i-th player behavior data, q imin ,q imax are the minimum and maximum values ​​of the i-th player behavior data, respectively. is the weight coefficient of the i-th player behavior data.

3. The game promotion system based on data analysis according to claim 2, characterized in that: The process of performing segmentation analysis on players based on each player's interest index is as follows: The interest index F of the rth player r With the pre-set interest index interval [F r0 , F r1 ] for comparison: If F r ∈[F r0 , F r1 ], then the current player is judged to be a medium-frequency player; If F r >F r1 , then the current player is judged to be a high-frequency player; If F r >F r1 , then the current player is judged to be a low-frequency player.

4. The game promotion system based on data analysis according to claim 3, characterized in that: Based on market data and competitor data, the process of calculating the promotion value index of the current game is as follows: Market data and competitor data are combined through the formula: Calculate the promotion value index D of the current game; Among them, t0 and t1 are the two time endpoints of a preset monitoring period, K(t) is the curve of the popularity ranking of the type to which the current game belongs during the monitoring period, f(x) is the judgment function about competing games, β is the game market size, and γ is the game market size growth rate.

5. The game promotion system based on data analysis according to claim 4, characterized in that: The process of obtaining the judgment function f(x) about the competing game is as follows: like Then f(x)=1+θ; like Then f(x)=1-θ; Among them, g(t) is the download volume change curve of the competing game over time, g0(t) is the download volume reference change curve, Δθ is the reference value, is a constant and 6. The game promotion system based on data analysis according to claim 5, characterized in that: The process of comprehensively evaluating the current game promotion effect based on the promotion value index and player interest index is as follows: By formula: The promotion evaluation coefficient H is calculated; Among them, N B N is the actual number of players in the current game at the end of a statistical period. A N is the actual number of players in the current game at the start time of a statistical period. C It is the ratio of high-frequency players to the actual number of players of the current game at the end of a statistical period. D0 is the reference value of the promotion value index. Compare the calculated promotion evaluation coefficient H with the preset promotion evaluation threshold H0: If H≥H0, the promotion value of the current game is evaluated to be good; If H<H0, the promotion value of the current game is evaluated to be poor.

7. The game promotion system based on data analysis according to claim 1, characterized in that: The visual dashboard supports multi-terminal display, including computers, tablets and mobile phones.

8. A game promotion method based on data analysis, characterized in that: The method is implemented based on the game promotion system based on data analysis described in any one of claims 1-7.

Images