Game promotion interaction method and system based on big data

Abstract

The invention discloses a game promotion interaction method and system based on big data, and relates to the technical field of game promotion interaction.The method comprises the steps that game behavior data of users are collected through multiple channels, promotion interaction features of game types of different dimensions are calculated, promotion interaction feature vectors are constructed, and the promotion interaction feature vectors are obtained; calculating the feature difference degree of the promotion interaction feature vectors corresponding to other users, and calculating the user difference degree according to the feature difference degree; and sorting the other users in an ascending order according to the user difference degree, selecting games of which recently participated energy characteristics are greater than a preset value of the other users according to the order until a preset number is met, generating a game promotion table, and carrying out game promotion on the users according to the game promotion table. According to the method, personalized game recommendation is pushed in real time through calculation of promotion interaction characteristics and a user difference degree calculation method based on a local space density adjustment coefficient, so that user requirements are accurately captured, the promotion accuracy, personalization and real-time response capability are improved, and the game promotion effect is remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of game promotion interaction, and specifically to a game promotion interaction method and system based on big data. Background Art

[0002] With the popularization of smart devices and the rapid development of the Internet, online games have become entertainment activities widely participated in globally. Especially the rapid expansion of the mobile game market has made the accumulation of user behavior data an important resource in game operation. Game companies and promotion platforms hope to formulate precise game promotion strategies by analyzing users' game behavior data to improve user stickiness, retention rate, and payment conversion rate of games.

[0003] Currently, existing game promotion methods mainly conduct promotion recommendations based on users' historical data, basic information, and certain simplified game behavior characteristics. However, the existing methods generally have the following problems: inaccurate promotion effects, existing promotion strategies usually make recommendations through simple rule matching, unable to effectively consider the multi-dimensional behavior differences of users, resulting in the inability to maximize the promotion effect; lack of personalized analysis, most game promotion methods focus on single-dimensional user behavior characteristics (such as game duration, consumption amount, etc.), fail to comprehensively analyze users' behavior patterns, and ignore the differences between users in different game types and behaviors; inaccurate calculation of user differences, traditional methods often rely on simple similarity calculations (such as Euclidean distance, cosine similarity, etc.) to compare users, fail to consider the complexity and non-linear characteristics of user behavior, and lack precise measurement based on local spatial density; poor real-time performance of promotion strategies, existing technologies are difficult to obtain users' latest behavior data in real time and conduct timely analysis, and promotion strategies are usually lagging, unable to quickly respond to market changes and users' dynamic needs.

[0004] Therefore, there is an urgent need in this field for a new game promotion interaction method that can accurately evaluate the differences between users based on multi-dimensional user behavior data, combine complex feature calculation models, and generate personalized game promotion recommendations to improve the efficiency and effect of promotion. Summary of the Invention

[0005] Based on the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a game promotion interaction method and system based on big data to solve the above technical problems.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A game promotion interaction method based on big data, including:

[0007] S1: Collect users' game behavior data through multiple channels, and clean, denoise, and fill in missing values for the game behavior data;

[0008] S2: Based on the collected game behavior data, calculate the promotion interaction features of different dimensions of game types according to the preset game type vector, and construct a promotion interaction feature vector according to the promotion interaction features;

[0009] S3: Calculate the feature difference degree between the promotion interaction feature vector corresponding to other users according to the promotion interaction feature vectors of different dimensions of the user's game types, and calculate the user difference degree according to the feature difference degrees of the promotion interaction feature vectors of all different dimensions of game types;

[0010] S4: Sort other users in ascending order according to the user difference degree, select the games in which the recent participation energy feature of other users is greater than the preset value in order until the preset quantity is satisfied, generate a game promotion list, and promote games for the user according to the game promotion list.

[0011] The present invention is further configured that the game behavior data includes game duration, monthly active days, real consumption amount, game currency consumption amount, virtual item consumption amount, social interaction behavior frequency, and social relationship depth. The social interaction behaviors include liking, commenting, collecting, and sharing. The game types include action, role-playing, adventure, strategy, simulation, competitive, puzzle, and casual. The above game types form a game type vector in any order. In the game type vector, each dimension represents a different game type.

[0012] The present invention is further configured that the promotion interaction features include participation energy feature, game driving feature, and relationship interaction feature;

[0013] Calculate the participation energy feature according to the game duration and the monthly active days;

[0014] Calculate the game driving feature according to the real consumption amount, the game currency consumption amount, and the virtual item consumption amount;

[0015] Calculate the relationship interaction feature according to the social interaction behavior frequency and the social relationship depth.

[0016] The present invention is further configured that the calculation logic of the participation energy feature is: Wherein, A active (u) is the participation energy feature of user u, L d (u) is the game duration of user u on the dth day, D active (u) is the monthly active days of user u, and α and δ are adjustment parameters.

[0017] The present invention is further configured that the calculation logic of the game driving feature is: B purchase (u) = (Pbuy (u) + β·ln(1 + G swend (u)))·U item (u), where B purchase (u) is the game driving feature of user u, P buy (u) is the actual consumption amount of user u, G swend (u) is the in-game currency consumption amount of user u, U item (u) is the consumption amount of virtual items of user u, and β is the weight coefficient.

[0018] The present invention is further configured such that the calculation logic of the relationship interaction feature is: where S social (u) is the relationship interaction feature of user u, M is the number of types of social interaction behaviors, and social interaction behaviors include liking, commenting, collecting, and sharing. I social,j (u) is the frequency of the j-th social interaction behavior of user u, is the weight coefficient of the j-th social interaction behavior, and R connect (u) is the depth of the social relationship, specifically the number of monthly interaction people, and γ and θ are adjustment coefficients.

[0019] The present invention is further configured to construct a promotion interaction feature vector for the participation energy feature, the game driving feature, and the relationship interaction feature in any order. Among them, in the promotion interaction feature vector, each dimension represents a different promotion interaction feature.

[0020] The present invention is further configured such that step S3 includes:

[0021] Quantify the feature difference degree of the promotion interaction feature vectors between users by calculating a function based on the adjustment coefficient of local spatial density for all the promotion interaction feature vectors in the game type vector according to a preset difference metric;

[0022] Perform a weighted sum of the feature difference degrees of all the promotion interaction feature vectors in the game type vector to obtain the user difference degree.

[0023] The present invention is further configured such that the calculation logic of the difference metric calculation function is: where Δ local (F i , F j ) is the feature difference degree of the promotion interaction feature vectors F i and F j of user i and user j, f ik is the k-th promotion interaction feature in the promotion interaction feature vector F i of user i, and f jkThe promotion interaction feature vector F for user j i The k-th promotion interaction feature in k The normalization factor for the k-th promotion interaction feature, λ k (F i , F j ) is the adjustment coefficient based on local neighborhood density, and the calculation logic is as follows: where α is the local sensitivity factor.

[0024] The present invention also provides a game promotion interaction system based on big data for implementing the above-mentioned game promotion interaction method based on big data. The system includes:

[0025] Data collection module: Collect the game behavior data of users through multiple channels, and clean, denoise, and fill in the missing values of the game behavior data;

[0026] First calculation module: Based on the collected game behavior data, calculate the promotion interaction features of different dimensions of game types according to the preset game type vector, and construct a promotion interaction feature vector according to the promotion interaction features;

[0027] Second calculation module: Calculate the feature difference degree between the promotion interaction feature vector corresponding to other users and the promotion interaction feature vector of different dimensions of game types of the user, and calculate the user difference degree according to the feature difference degrees of all promotion interaction feature vectors of different dimensions of game types;

[0028] Promotion interaction module: Sort other users in ascending order according to the user difference degree, select the games whose recently participated energy features of other users are greater than a preset value in sequence until the preset quantity is satisfied, generate a game promotion list, and promote games for users according to the game promotion list.

[0029] The present invention provides a game promotion interaction method and system based on big data. The method collects the game behavior data of users through multiple channels, cleans, denoises, and fills in the missing values of the game behavior data; based on the collected game behavior data, calculates the promotion interaction features of different dimensions of game types according to the preset game type vector, and constructs a promotion interaction feature vector according to the promotion interaction features; calculates the feature difference degree between the promotion interaction feature vector corresponding to other users and the promotion interaction feature vector of different dimensions of game types of the user, and calculates the user difference degree according to the feature difference degrees of all promotion interaction feature vectors of different dimensions of game types; sorts other users in ascending order according to the user difference degree, selects the games whose recently participated energy features of other users are greater than a preset value in sequence until the preset quantity is satisfied, generates a game promotion list, and promotes games for users according to the game promotion list. The beneficial effects produced include:

[0030] 1. Comprehensive promotion interaction feature calculation: Based on user behavior features, further calculate participation energy features, game drive features, and relationship interaction features to form promotion interaction feature vectors in multiple dimensions. These feature vectors not only reflect the user's participation in the game but also comprehensively consider the user's consumption habits, social behaviors, and the depth of their social relationships. Through the comprehensive analysis of these features, the present invention can better capture the true needs and interests of users and improve the accuracy of promotion;

[0031] 2. Innovative user difference calculation method: Through the difference calculation method based on the adjustment coefficient of local spatial density, it can more accurately measure the differences between users in promotion interaction feature vectors. By combining the local sensitivity factor to adjust the feature difference degree, compared with traditional similarity calculation methods, it can more accurately reflect the differences and complexities of user behaviors, thus realizing more accurate user classification and promotion strategies;

[0032] 3. Real-time personalized game recommendation: Through the real-time calculation of user difference degrees, sort them in ascending order according to user differences, and select eligible games for recommendation. This mechanism ensures the personalization and real-time nature of promotion recommendations, can quickly respond to changes in user needs, and timely push suitable games to users, thereby enhancing user activity.

[0033] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically presents the specific implementation manners of this application. Brief Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0035] Figure 1 It is a flowchart of a game promotion interaction method based on big data shown in an exemplary embodiment of the present invention;

[0036] Figure 2 It is a schematic structural diagram of a game promotion interaction system based on big data shown in an exemplary embodiment of the present invention. Detailed Description of the Invention

[0037] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, rather than for limiting the protection scope of the present invention.

[0038] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0039] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0040] Embodiment 1

[0041] A game promotion interaction method based on big data, as Figure 1 shown, includes:

[0042] S1: Collect game behavior data of users through multiple channels, and clean, denoise, and fill in missing values for the game behavior data;

[0043] S2: Based on the collected game behavior data, calculate the promotion interaction features of different dimensions of game types according to the preset game type vectors, and construct a promotion interaction feature vector according to the promotion interaction features;

[0044] S3: Calculate the feature difference degree between the promotion interaction feature vector corresponding to other users according to the promotion interaction features of different dimensions of game types of the user, and calculate the user difference degree according to the feature difference degrees of all promotion interaction feature vectors of different dimensions of game types;

[0045] S4: Sort other users in ascending order according to the user difference degree, select games whose recently participated energy features of other users are greater than a preset value in sequence until the preset quantity is satisfied, generate a game promotion list, and promote games to users according to the game promotion list.

[0046] The present invention is further configured such that the game behavior data includes game duration, monthly active days, real consumption amount, in-game currency consumption amount, virtual item consumption quantity, social interaction behavior frequency, and depth of social relationship. The social interaction behaviors include liking, commenting, collecting, and sharing. The game types include action, role-playing, adventure, strategy, simulation, competitive, puzzle, and casual. The above game types form a game type vector in any order. In the game type vector, each dimension represents a different game type.

[0047] The present invention is further configured such that the promotion interaction features include participation energy feature, game drive feature, and relationship interaction feature;

[0048] Calculate the participation energy feature according to the game duration and the monthly active days. The present invention is further configured such that the calculation logic of the participation energy feature is: Wherein, A active (u) is the participation energy feature of user u, L d (u) is the game duration of user u on the d-th day, D active (u) is the monthly active days of user u, and α and δ are adjustment parameters; specifically, the participation energy feature aims to measure the participation and activity of users, reflecting the behavioral activity level of users within a specific time period. In order to accurately measure the participation energy feature, the calculation process involves processing the daily game duration and combining it with the monthly active days to form a more refined participation energy calculation logic; first, the game duration L d (u) of the user on each day will be logarithmically transformed and then incremented by 1. This process can compress the distribution range of the duration, thereby reducing the impact of long-term play. This logarithmic transformation can not only avoid the excessive impact of extreme values (such as overly long game duration) on the overall feature, but also enhance the sensitivity to small changes. Then, the game durations (the results of logarithmic transformation) of the user in the past 30 days are accumulated. Since the monthly active days D active (u) represent the number of days when the user is at least active within a month, using the accumulated sum can better reflect the overall participation of the user during the active days. The accumulated result will be exponentially transformed to enhance its responsiveness to the activity level; the monthly active days D active(u)'s role in the participation energy feature is a key indicator of how many days the user has played the game in the past 30 days. By combining the accumulated game duration feature and the monthly active days, the final participation energy feature is obtained; the value range of the adjusted parameter δ is from 1 to 5, and the value range of the adjusted parameter α is from 0.1 to 2; by performing a logarithmic transformation on the daily game duration, the influence of long-term game players is reduced, making the feature calculation smoother and avoiding the excessive influence of outliers; through the complex calculation of combining monthly active days and game duration, the long-term nature and frequency of user participation can be comprehensively reflected, and the sensitivity of user activity can be improved;

[0049] Calculate the game driving feature according to the real consumption amount, the game currency consumption amount and the virtual item consumption amount; the present invention is further set that the calculation logic of the game driving feature is: B purchase (u)=(P buy (u)+β·ln(1 + G swend (u)))·U item (u), where B purchase (u) is the game driving feature of user u, P buy (u) is the real consumption amount of user u, G swend (u) is the game currency consumption amount of user u, U item (u) is the virtual item consumption amount of user u, and β is the weight coefficient; specifically, the game driving feature aims to measure the comprehensive relationship between the user's consumption behavior in the game and the use of virtual items. This feature evaluates the user's consumption drive and economic behavior in the game by integrating the user's real consumption amount, in-game currency consumption amount and virtual item consumption amount, and quantifies the user's game drive and stickiness; first, a basic component for calculating the game driving feature is the real consumption amount P buy (u) and the game currency consumption amount G swend (u). The real consumption amount directly reflects the amount of money the user invests in real currency, while the game currency consumption amount represents the amount of virtual currency the user uses in the game. To integrate this two-part information, the game currency consumption amount is logarithmically transformed and weighted to more finely quantify the user's participation in the virtual economy. Next, the game driving feature also involves the user's virtual item consumption amount U item(u), the consumption of virtual items directly reflects the user's deep engagement in the game and is usually used to purchase, upgrade, or enhance virtual items. This item is combined with the above part through simple weighting to represent the overall intensity of the user's virtual item usage in the game; combining the above two steps, the calculated game driving characteristics integrate the user's real consumption, virtual currency consumption, and virtual item usage, and can more comprehensively reflect the user's driving and stickiness in the game; the weight coefficient, the value range of β is from 1 to 10, by combining real consumption, in-game currency consumption, and virtual item usage, the game driving characteristics can comprehensively reflect the user's consumption patterns and economic participation both inside and outside the game;

[0050] Calculate the relationship interaction characteristics according to the social interaction behavior frequency and the social relationship depth. The present invention is further set such that the calculation logic of the relationship interaction characteristics is: Among them, S social (u) is the relationship interaction characteristic of user u, M is the number of types of social interaction behaviors, and social interaction behaviors include liking, commenting, collecting, and sharing, I social,j (u) is the frequency of the j-th social interaction behavior of user u, is the weight coefficient of the j-th social interaction behavior, R connect (u) is the social relationship depth, specifically the number of monthly interaction users, and γ and θ are adjustment coefficients; specifically, the relationship interaction characteristic is a characteristic that quantifies the user's social behavior and the user's game viscosity. It reflects the user's participation degree and interaction intensity in the social network by integrating the user's social interaction frequency and social relationship depth. This characteristic can more comprehensively describe the user's activity level in the social environment and the breadth of their social network by weighted summing the weights of different types of social behaviors and combining the social relationship depth; first, calculate the frequency weighted sum of the user on different types of social interaction behaviors. Social interaction behaviors include liking, commenting, collecting, and sharing. The frequency of each behavior is weighted according to its corresponding weight coefficient, and finally, the weighted results of all social behaviors are summed. Next, calculate the influence of the social relationship depth. The social relationship depth is mainly determined by the interaction frequency between the user and other users in their social network, usually measured by the "number of monthly interaction users". The social relationship depth is closely related to the breadth and connection strength of the user's social network and can reflect the user's core position and interaction density in the social network. The sum of the weight coefficients of social interaction behaviors is 1, that is The value range of the adjustment coefficient γ is from 0.5 to 2, and the value range of the adjustment coefficient θ is from 0 to 5. The relationship interaction characteristic integrates the social behavior frequency, the weight of social behavior, the social relationship depth, and the corresponding adjustment coefficients, and can reflect the social breadth of the user in the social network and the user's game viscosity;

[0051] The present invention is further configured to construct a promotion interaction feature vector for the participation energy feature, the game drive feature, and the relationship interaction feature in any order, where in the promotion interaction feature vector, each dimension represents a different promotion interaction feature.

[0052] The present invention is further configured that step S3 includes:

[0053] Quantifying the feature difference degree of the promotion interaction feature vectors between users by calculating a function based on an adjustment coefficient of local space density for all the promotion interaction feature vectors in the game type vector according to a preset difference metric; The present invention is further configured that the calculation logic of the difference metric calculation function is: where, Δ local (F i , F j ) is the feature difference degree of the promotion interaction feature vectors F i and F j of user i and user j, f ik is the k-th promotion interaction feature in the promotion interaction feature vector F i of user i, f jk is the k-th promotion interaction feature in the promotion interaction feature vector F i of user j, σ k is the normalization factor of the k-th promotion interaction feature, λ k (F i , F j ) is the adjustment coefficient based on local neighborhood density, and the calculation logic is: where, α is the local sensitivity factor; Specifically, by designing the difference metric calculation function, considering the differences in the interaction features between users, and combining the adjustment coefficient of local space density to improve the accuracy and credibility of the calculation results, by comprehensively considering the differences in the promotion interaction features between users and the adjustment of local space density, it is possible to more accurately quantify the similarities and differences in user behavior, thereby optimizing the personalized recommendation strategy and improving the accuracy and effectiveness of promotion; The local sensitivity factor and the normalization factor make the algorithm have strong self-adaptability and can flexibly handle the differences in different types of user data; By quantifying the user feature differences, the present invention can generate personalized recommendation content for each user, avoid overgeneralization, enhance the user experience, and improve the conversion rate of advertisements and the activity of games;

[0054] Performing a weighted sum of the feature difference degrees of all the promotion interaction feature vectors in the game type vector to obtain the user difference degree.

[0055] 4. By further calculating the participation energy features, game drive features, and relationship interaction features based on user behavior features, promotion interaction feature vectors in multiple dimensions are formed. These feature vectors not only reflect the user's participation in the game but also comprehensively consider the user's consumption habits, social behaviors, and the depth of their social relationships. Through the comprehensive analysis of these features, the present invention can better capture the real needs and interests of users and improve the accuracy of promotion. Through the difference calculation method of the adjustment coefficient based on local spatial density, the differences between users in the promotion interaction feature vectors can be measured more accurately. By combining the local sensitivity factor to adjust the feature difference degree, compared with the traditional similarity calculation method, it can more accurately reflect the differences and complexities of user behaviors, thereby realizing more accurate user classification and promotion strategies. By calculating the user difference degree in real time, sorting the users in ascending order according to their differences, and selecting eligible games for recommendation. This mechanism ensures the personalization and real-time nature of promotion recommendations, can quickly respond to changes in user needs, and timely push suitable games to users, thereby enhancing user activity.

[0056] Embodiment 2

[0057] Please refer to Figure 2 , the exemplary big data-based game promotion interaction system for implementing the above-mentioned big data-based game promotion interaction method, the system includes:

[0058] Data collection module: Collect the game behavior data of users through multiple channels, and clean, denoise, and fill in the missing values of the game behavior data;

[0059] First calculation module: Based on the collected game behavior data, calculate the promotion interaction features of different dimensions of game types according to the preset game type vector, and construct a promotion interaction feature vector according to the promotion interaction features;

[0060] Second calculation module: Calculate the feature difference degree between the promotion interaction feature vector corresponding to other users and the promotion interaction feature vector of the user according to the promotion interaction feature vectors of different dimensions of game types of the user, and calculate the user difference degree according to the feature difference degrees of all promotion interaction feature vectors of different dimensions of game types;

[0061] Promotion interaction module: Sort other users in ascending order according to the user difference degree, select games with the recently participated energy feature greater than the preset value of other users in sequence until the preset quantity is satisfied, generate a game promotion list, and promote games to users according to the game promotion list.

[0062] It should be noted that the game promotion interaction system based on big data provided in the above embodiments and the game promotion interaction method based on big data provided in the above embodiments belong to the same concept. The specific ways in which each module and unit perform operations have been described in detail in the method embodiments, and will not be elaborated here. In practical applications, the game promotion interaction system based on big data provided in the above embodiments can, according to needs, allocate the above functions to different functional modules to complete, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above. This is not limited here either.

[0063] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0064] It should be understood that the term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. Specifically, it can be understood by referring to the context before and after.

[0065] In this application, "at least one" means one or more, and "a plurality of" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0066] It should be understood that in various embodiments of this application, the magnitude of the serial numbers of the above - mentioned processes does not mean the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0067] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0068] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0069] In several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0070] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0072] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0073] As described above, the above are only specific implementation manners of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A game promotion interactive method based on big data, characterized in that: include: S1: Collecting the game behavior data of users through multiple channels, and cleaning, denoising and filling missing values ​​of the game behavior data; S2: Based on the collected game behavior data, the promotion interaction features of game types of different dimensions are calculated according to the preset game type vectors, and a promotion interaction feature vector is constructed according to the promotion interaction features; S3: Calculate the feature difference between the promotion interaction feature vectors of different dimensional game types of the user and the promotion interaction feature vectors corresponding to other users, and calculate the user difference based on the feature difference between the promotion interaction feature vectors of all different dimensional game types; S4: Sort other users in ascending order according to user difference, select games whose recent participation energy characteristics are greater than a preset value in order until a preset number is met, generate a game promotion table, and promote games to users according to the game promotion table.

2. The game promotion interactive method based on big data according to claim 1, characterized in that: Game behavior data includes game duration, monthly active days, real consumption amount, game currency consumption amount, virtual props consumption, social interaction behavior frequency and social relationship depth. Social interaction behavior includes likes, comments, collections and shares. Game types include action, role-playing, adventure, strategy, simulation, competition, puzzle and leisure. The above game types are constructed into a game type vector in any order. In the game type vector, each dimension represents a different game type.

3. The game promotion interactive method based on big data according to claim 2 is characterized in that: The promotion interaction features include participation energy features, game driving features and relationship interaction features; Calculate the participation energy feature according to the game duration and the monthly active days; Calculate the game driving characteristics according to the actual consumption amount, the game currency consumption amount and the consumption of virtual props; The relationship interaction feature is calculated according to the social interaction behavior frequency and the social relationship depth.

4. The game promotion interactive method based on big data according to claim 3 is characterized in that: The calculation logic of the participating energy characteristics is: Among them, A active (u) is the participation energy characteristic of user u, L d (u) is the game time of user u on day d, D active (u) is the number of monthly active days of user u, and α and δ are adjustment parameters.

5. The game promotion interactive method based on big data according to claim 4 is characterized in that: The calculation logic of the game driving feature is: purchase (u)=(P buy (u)+β·ln(1+Gswendu)·Uitemu, where Bpurchaseu is the game driving feature of user u, Pbuyu is the actual consumption amount of user u, G swend (u) is the game currency consumption amount of user u, U item (u) is the virtual item consumption of user u, and β is the weight coefficient.

6. The game promotion interactive method based on big data according to claim 5 is characterized in that: The calculation logic of the relationship interaction feature is: Among them, S social (u) is the relationship interaction feature of user u, M is the number of types of social interaction behaviors, and social interaction behaviors include likes, comments, favorites, and shares. social，j (u) is the frequency of the jth social interaction behavior of user u, is the weight coefficient of the jth social interaction behavior, R connect (u) is the depth of social relationship, specifically the number of monthly interactions, and γ and θ are adjustment coefficients.

7. The game promotion interactive method based on big data according to claim 6 is characterized in that: A promotion interaction feature vector is constructed for the participation energy feature, the game driving feature and the relationship interaction feature in any order, wherein each dimension in the promotion interaction feature vector represents a different promotion interaction feature.

8. The game promotion interactive method based on big data according to claim 7 is characterized in that: Step S3 includes: For all promotion interaction feature vectors in the game type vector, the feature difference between the promotion interaction feature vectors between users is quantified according to a preset difference measurement calculation function by using an adjustment coefficient based on local space density; The feature differences of all promotion interaction feature vectors in the game type vector are weighted summed to obtain the user difference.

9. The game promotion interactive method based on big data according to claim 8, characterized in that: The calculation logic of the difference metric calculation function is: Among them, ΔlocalFi,Fj is the feature difference between the promotion interaction feature vectors Fi and Fj of user i and user j, f ik is the promotion interaction feature vector F of user i i The kth generalized interaction feature, f jk is the promotion interaction feature vector F of user j i The kth generalized interaction feature in k is the normalization factor of the kth generalized interaction feature, λ k (F i , F j ) is the adjustment coefficient based on the local neighborhood density, and the calculation logic is: Among them, α is the local sensitivity factor.

10. A game promotion interactive system based on big data, used to implement the game promotion interactive method based on big data according to any one of claims 1 to 9, characterized in that: include: Data collection module: collects users' game behavior data through multiple channels, and cleans, denoises and fills missing values ​​in the game behavior data; The first calculation module: based on the collected game behavior data, calculates the promotion interaction features of game types of different dimensions according to the preset game type vector, and constructs a promotion interaction feature vector according to the promotion interaction features; The second calculation module: calculates the feature difference between the promotion interaction feature vectors of different dimensional game types of the user and the promotion interaction feature vectors corresponding to other users, and calculates the user difference based on the feature difference between the promotion interaction feature vectors of all different dimensional game types; Promotion interaction module: Sort other users in ascending order according to user difference, select games whose recent participation energy characteristics are greater than a preset value in order until a preset number is met, generate a game promotion table, and promote games to users according to the game promotion table.

Images