Game user retention analysis method and device applied to multi-dimensional data

Abstract

The invention discloses a game user retention analysis method and device applied to multi-dimensional data, by implementing the method and device, after user behavior data of a target game are collected, core index data of the target game can be intelligently determined based on the user behavior data; therefore, the behavior change data, the user retention information and / or the user loss information of the game user facing the target game are determined, and the capture accuracy of the user behavior change and the recognition efficiency of key nodes retained by the user and potential reasons of loss are improved. The user distribution condition of all game users can be obtained by performing secondary analysis on the user retention information and / or loss information according to the core index data, so that a game developer is helped to know the basic characteristics of a user group, the active law of the users is revealed, and data support is provided for game optimization; and a user analysis report can be generated based on a secondary analysis result, so that the viewing convenience of user retention and loss current situations and trends can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a game user retention analysis method and device applied to multi-dimensional data. Background Art

[0002] With the rapid development of Internet technology, the online game industry has ushered in an unprecedented prosperity. In order to effectively improve the competitiveness of games and user experience, game developers and operators need to conduct continuous and in-depth monitoring and analysis of games in operation. At present, the monitoring and analysis of games in the market is mainly achieved by collecting and analyzing the core indicator data of games.

[0003] Specifically, the core indicator data covers the indicators of the target game in different promotion channels (such as app stores, social media, advertising platforms, etc.). These data are crucial for understanding the market performance, user sources and user behavior of the game.

[0004] However, simply collecting this data is not enough to fully reveal the game's operating conditions and user behavior patterns. In-depth and effective data analysis is needed for these data. However, even though the existing technology has made certain progress in game data analysis, there is still room for further improvement. In particular, how to efficiently and accurately collect and analyze game core indicator data, and how to generate instructive reports based on these data, there is still room for optimization. It can be seen that in the face of the low effect of game data monitoring and analysis and low data utilization in game operations in the existing technology, it is particularly important to provide a corresponding solution. Summary of the invention

[0005] The present invention provides a game user retention analysis method and device applied to multi-dimensional data, which can improve the analysis precision of game data, improve the data utilization rate of collected game indicator data, and then improve the user retention rate of the game.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses a game user retention analysis method applied to multi-dimensional data, the method comprising:

[0007] Collecting user behavior data corresponding to one or more game users targeted by the target game, and determining core indicator data of the target game based on the user behavior data, wherein the core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms;

[0008] Determine the behavior change data of all the game users based on the user behavior data and in combination with the core indicator data; perform primary analysis on the behavior change data of all the game users to obtain the primary analysis results of the target game within the target specified time period; the primary analysis results include user retention information and / or user churn information;

[0009] According to the core indicator data, a secondary analysis is performed on the primary analysis result to obtain secondary analysis results corresponding to all the game users, wherein the secondary analysis results include user distribution and user activity of all the game users; the secondary analysis results are used to indicate the usage of different functions of the target game by all the game users;

[0010] A user analysis report for the target game is generated according to the secondary analysis results.

[0011] As an optional implementation, in the first aspect of the present invention, performing a primary analysis on the behavior change data of all the game users to obtain a primary analysis result of the target game within a target specified time period includes:

[0012] Determine one or more analysis periods to be analyzed, and determine all first periods with target recommendation strategies set and all second periods without the target recommendation strategies from all the analysis periods; the target recommendation strategies include an initial promotion strategy for adding new users and a return visit recommendation strategy set for returning users;

[0013] According to a preset grouping strategy, grouping is performed on all the analysis time periods to obtain grouping results corresponding to all the analysis time periods; the grouping results include at least one time period grouping set, each of the time period grouping sets matches a set time period; the set time period includes at least one of the first time period and at least one of the second time period;

[0014] For each analysis period, determining sub-change data corresponding to the analysis period according to the behavior change data corresponding to all the game users, wherein the sub-change data includes the number of new users, the number of returning users, and the number of lost users;

[0015] For each of the time period grouping sets, all the sub-change data corresponding to the time period grouping set are analyzed to obtain a set analysis result corresponding to the time period grouping set; and the set analysis results corresponding to all the time period grouping sets are determined as the first-level analysis results of the target game within the target setting time period; the target setting time period includes all the set time periods.

[0016] As an optional implementation manner, in the first aspect of the present invention, analyzing all the sub-change data corresponding to the time period grouping set to obtain a set analysis result corresponding to the time period grouping set includes:

[0017] Merge and integrate all the first time periods and all the second time periods in the time period grouping set to obtain a target integrated time period;

[0018] Merge and integrate the sub-change data corresponding to all the first time periods and all the second time periods in the time period grouping set to obtain first integrated data corresponding to all the first time periods and second integrated data corresponding to all the second time periods;

[0019] Compare the first integrated data and the second integrated data in the time period grouping set to obtain corresponding data comparison results as the set analysis results corresponding to the time period grouping set;

[0020] The first integrated data corresponding to the time period grouping set and all the first time periods include first user retention information and / or first user churn information within the target integration time period; the second integrated data corresponding to the time period grouping set and all the second time periods include second user retention information and / or second user churn information within the target integration time period;

[0021] The time period grouping combined with the corresponding data comparison result is used to indicate the strategy recommendation effect of setting the target recommendation strategy.

[0022] As an optional implementation manner, in the first aspect of the present invention, performing secondary analysis on the primary analysis results according to the core indicator data to obtain secondary analysis results corresponding to all the game users includes:

[0023] Determine multiple dimensional indicators, wherein the dimensional indicators include channel dimension, platform dimension, time dimension and geographical dimension;

[0024] According to all the dimensional indicators, the core indicator data is divided into dimensions to obtain a dimensional indicator interval corresponding to each dimensional indicator;

[0025] Analyze the primary analysis result to obtain user distribution of all the game users in each dimension indicator interval, wherein the user distribution includes multiple sub-distribution situations, and each sub-distribution situation corresponds to one dimension indicator interval;

[0026] Determine the application function corresponding to each dimension indicator interval;

[0027] For each of the dimensional indicator intervals, determining user participation information of all the game users for the application function in the dimensional indicator interval according to the user distribution as user activity;

[0028] All the dimension indicator intervals, the user distribution and the user activity are determined as secondary analysis results.

[0029] As an optional implementation manner, in the first aspect of the present invention, analyzing the primary analysis results to obtain the user distribution of all the game users in each dimension indicator interval includes:

[0030] Obtaining user tags set for all game users and their corresponding tag categories, each of the tag categories being associated with one or more of the user tags;

[0031] Taking each dimension index interval as a unit, calculate the number and proportion of each user tag in the dimension index interval;

[0032] According to the quantity and quantity proportion of each user tag in the dimension index interval, determine the user group proportion information corresponding to each tag classification in the dimension index interval;

[0033] The user group proportion information corresponding to each of the tag categories in all the dimensional index intervals is determined as the user distribution of all the game users in all the dimensional index intervals.

[0034] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0035] Determine retention influencing factors for the target game according to the user analysis report, wherein the retention influencing factors include game quality, game experience rating, and user stickiness rating;

[0036] According to the retention influencing factor, a plurality of characteristic gameplays are determined from a plurality of basic gameplays of the target game, wherein a game user rating corresponding to each of the characteristic gameplays is higher than a preset rating value;

[0037] Determine a plurality of user portraits according to the user analysis report, wherein the user portraits are associated with a preset user group classification;

[0038] According to the user analysis report, all the user portraits and all the characteristic gameplays are arranged and combined to obtain corresponding arrangement and combination results; and according to the arrangement and combination results, personalized recommendation information is generated for each of the user portraits, and the personalized recommendation information includes a personalized recommendation strategy for game promotion;

[0039] Among them, in the permutation and combination results, each of the user portraits matches at least one of the characteristic gameplays.

[0040] As an optional implementation, in the first aspect of the present invention, the core indicator data also includes event record information corresponding to each free event in the target game; each free event matches a game function of the target game, and the event record information corresponding to each free event includes the number of user usages, user usage frequency, time investment, and conversion rate;

[0041] The user usage frequency corresponding to each free event is used to indicate the number of times one or more game users repeatedly visit the free event within a preset recording time period; the time investment corresponding to each free event is the cumulative visit time of one or more game users visiting the free event; the conversion rate corresponding to each free event is used to indicate the probability of triggering a preset key behavior after the game user uses the free event;

[0042] The user tag includes at least one of an age group tag, a gender tag, an interest preference tag, and a consumption habit tag.

[0043] A second aspect of the present invention discloses a game user retention analysis device applied to multi-dimensional data, the device comprising:

[0044] A first determination module is used to collect user behavior data corresponding to one or more game users targeted by the target game, and determine core indicator data of the target game according to the user behavior data, wherein the core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms;

[0045] A second determination module is used to determine the behavior change data of all the game users based on the user behavior data and in combination with the core indicator data;

[0046] A primary analysis module, used to perform primary analysis on the behavior change data of all game users to obtain the primary analysis results of the target game within a target specified time period; the primary analysis results include user retention information and / or user churn information;

[0047] A secondary analysis module, for performing secondary analysis on the primary analysis results according to the core indicator data, to obtain secondary analysis results corresponding to all the game users, the secondary analysis results including user distribution and user activity of all the game users; the secondary analysis results are used to indicate the usage of different functions of the target game by all the game users;

[0048] A report generation module is used to generate a user analysis report for the target game according to the secondary analysis results.

[0049] As an optional implementation, in the second aspect of the present invention, the primary analysis module performs primary analysis on the behavior change data of all the game users, and the method of obtaining the primary analysis result of the target game within the target specified time period specifically includes:

[0050] Determine one or more analysis periods to be analyzed, and determine all first periods with target recommendation strategies set and all second periods without the target recommendation strategies from all the analysis periods; the target recommendation strategies include an initial promotion strategy for adding new users and a return visit recommendation strategy set for returning users;

[0051] According to a preset grouping strategy, grouping is performed on all the analysis time periods to obtain grouping results corresponding to all the analysis time periods; the grouping results include at least one time period grouping set, each of the time period grouping sets matches a set time period; the set time period includes at least one of the first time period and at least one of the second time period;

[0052] For each analysis period, determining sub-change data corresponding to the analysis period according to the behavior change data corresponding to all the game users, wherein the sub-change data includes the number of new users, the number of returning users, and the number of lost users;

[0053] For each of the time period grouping sets, all the sub-change data corresponding to the time period grouping set are analyzed to obtain a set analysis result corresponding to the time period grouping set; and the set analysis results corresponding to all the time period grouping sets are determined as the first-level analysis results of the target game within the target setting time period; the target setting time period includes all the set time periods.

[0054] As an optional implementation, in the second aspect of the present invention, the primary analysis module analyzes all the sub-change data corresponding to the time period grouping set to obtain a set analysis result corresponding to the time period grouping set, specifically including:

[0055] Merge and integrate all the first time periods and all the second time periods in the time period grouping set to obtain a target integrated time period;

[0056] Merge and integrate the sub-change data corresponding to all the first time periods and all the second time periods in the time period grouping set to obtain first integrated data corresponding to all the first time periods and second integrated data corresponding to all the second time periods;

[0057] Compare the first integrated data and the second integrated data in the time period grouping set to obtain corresponding data comparison results as the set analysis results corresponding to the time period grouping set;

[0058] The first integrated data corresponding to the time period grouping set and all the first time periods include first user retention information and / or first user churn information within the target integration time period; the second integrated data corresponding to the time period grouping set and all the second time periods include second user retention information and / or second user churn information within the target integration time period;

[0059] The time period grouping combined with the corresponding data comparison result is used to indicate the strategy recommendation effect of setting the target recommendation strategy.

[0060] As an optional implementation, in the second aspect of the present invention, the secondary analysis module performs secondary analysis on the primary analysis result according to the core indicator data, and the method of obtaining the secondary analysis result corresponding to all the game users specifically includes:

[0061] Determine multiple dimensional indicators, wherein the dimensional indicators include channel dimension, platform dimension, time dimension and geographical dimension;

[0062] According to all the dimensional indicators, the core indicator data is divided into dimensions to obtain a dimensional indicator interval corresponding to each dimensional indicator;

[0063] Analyze the primary analysis result to obtain user distribution of all the game users in each dimension indicator interval, wherein the user distribution includes multiple sub-distribution situations, and each sub-distribution situation corresponds to one dimension indicator interval;

[0064] Determine the application function corresponding to each dimension indicator interval;

[0065] For each of the dimensional indicator intervals, determining user participation information of all the game users for the application function in the dimensional indicator interval according to the user distribution as user activity;

[0066] All the dimension indicator intervals, the user distribution and the user activity are determined as secondary analysis results.

[0067] As an optional implementation, in the second aspect of the present invention, the secondary analysis module analyzes the primary analysis result to obtain the user distribution of all the game users in each dimension indicator interval, specifically including:

[0068] Obtaining user tags set for all game users and their corresponding tag categories, each of the tag categories being associated with one or more of the user tags;

[0069] Taking each dimension index interval as a unit, calculate the number and proportion of each user tag in the dimension index interval;

[0070] According to the quantity and quantity proportion of each user tag in the dimension index interval, determine the user group proportion information corresponding to each tag classification in the dimension index interval;

[0071] The user group proportion information corresponding to each of the tag categories in all the dimensional index intervals is determined as the user distribution of all the game users in all the dimensional index intervals.

[0072] As an optional implementation, in the second aspect of the present invention, the second determination module is further used to determine a retention impact factor for the target game according to the user analysis report, wherein the retention impact factor includes game quality, game experience rating, and user stickiness rating;

[0073] The second determination module is further configured to determine, according to the retention influencing factor, a plurality of characteristic gameplays from a plurality of basic gameplays of the target game, wherein a game user rating corresponding to each of the characteristic gameplays is higher than a preset rating value;

[0074] The second determination module is further used to determine a plurality of user portraits according to the user analysis report, wherein the user portraits are associated with a preset user group classification;

[0075] The device also includes:

[0076] A permutation and combination module, for performing permutations and combinations of all the user portraits and all the characteristic gameplays according to the user analysis report to obtain corresponding permutation and combination results; and generating personalized recommendation information for each user portrait according to the permutation and combination results, wherein the personalized recommendation information includes a personalized recommendation strategy for game promotion;

[0077] Among them, in the permutation and combination results, each of the user portraits matches at least one of the characteristic gameplays.

[0078] As an optional implementation, in the second aspect of the present invention, the core indicator data also includes event record information corresponding to each free event in the target game; each free event matches a game function of the target game, and the event record information corresponding to each free event includes the number of user usages, user usage frequency, time investment, and conversion rate;

[0079] The user usage frequency corresponding to each free event is used to indicate the number of times one or more game users repeatedly visit the free event within a preset recording time period; the time investment corresponding to each free event is the cumulative visit time of one or more game users visiting the free event; the conversion rate corresponding to each free event is used to indicate the probability of triggering a preset key behavior after the game user uses the free event;

[0080] The user tag includes at least one of an age group tag, a gender tag, an interest preference tag, and a consumption habit tag.

[0081] A third aspect of the present invention discloses another game user retention analysis device applied to multi-dimensional data, the device comprising:

[0082] A memory storing executable program code;

[0083] a processor coupled to the memory;

[0084] The processor calls the executable program code stored in the memory to execute the game user retention analysis method applied to multidimensional data disclosed in the first aspect of the present invention.

[0085] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the game user retention analysis method applied to multidimensional data disclosed in the first aspect of the present invention.

[0086] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0087] In an embodiment of the present invention, a game user retention analysis method applied to multidimensional data is provided, the method comprising: collecting user behavior data corresponding to one or more game users targeted by a target game, and determining core indicator data of the target game based on the user behavior data, the core indicator data comprising channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms; determining behavior change data of all game users based on the user behavior data in combination with the core indicator data; performing a primary analysis on the behavior change data of all game users to obtain a primary analysis result of the target game within a target specified time period; the primary analysis result comprises user retention information and / or user churn information; performing a secondary analysis on the primary analysis result based on the core indicator data to obtain a secondary analysis result corresponding to all game users, the secondary analysis result comprising user distribution and user activity of all game users; the secondary analysis result is used to indicate usage of different functions of the target game by all game users; and generating a user analysis report for the target game based on the secondary analysis result. It can be seen that by implementing the present invention, after collecting the user behavior data of one or more game users targeted by the target game, the core indicator data of the target game can be intelligently determined based on the user behavior data, thereby gradually determining the behavior change data, user retention information and / or user churn information of one or more game users targeted by the target game, which is conducive to improving the accuracy of capturing user behavior changes, and then helping game developers to timely identify the key nodes of user retention and potential causes of churn, and provide corresponding auxiliary data for formulating targeted operation strategies; further, it is also possible to perform a secondary analysis on the primary analysis results based on the core indicator data to obtain the user distribution of all game users. This in-depth analysis not only helps game developers understand the basic characteristics of the user group, but also reveals the active patterns of users, and then provides a scientific basis for optimizing the game experience and improving user stickiness; finally, it is possible to generate a user analysis report for the target game based on the secondary analysis results. The setting of the user analysis report is conducive to improving the convenience of viewing the current status and trends of user retention and churn for the target game. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0089] Figure 1 It is a flowchart of a method for analyzing game user retention applied to multi-dimensional data disclosed in an embodiment of the present invention;

[0090] Figure 2It is a flowchart diagram of another method for analyzing game user retention applied to multi-dimensional data disclosed in an embodiment of the present invention;

[0091] Figure 3 It is a structural schematic diagram of a game user retention analysis device applied to multi-dimensional data disclosed in an embodiment of the present invention;

[0092] Figure 4 It is a structural schematic diagram of another game user retention analysis device applied to multi-dimensional data disclosed in an embodiment of the present invention;

[0093] Figure 5 It is a structural schematic diagram of another game user retention analysis device applied to multi-dimensional data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0094] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0095] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0096] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0097] The present invention discloses a method and device for analyzing game user retention applied to multidimensional data. After collecting user behavior data of one or more game users facing the target game, the core indicator data of the target game can be intelligently determined based on the user behavior data, thereby determining the behavior change data, user retention information and / or user loss information of one or more game users facing the target game step by step, which is conducive to improving the accuracy of capturing user behavior changes, and then helping game developers to timely identify the key nodes of user retention and potential causes of loss, and provide corresponding auxiliary data for formulating targeted operation strategies; further, it is also possible to perform secondary analysis on the primary analysis results according to the core indicator data to obtain the user distribution of all game users. This deep analysis not only helps game developers understand the basic characteristics of user groups, but also reveals the active rules of users, and then provides a scientific basis for optimizing game experience and improving user stickiness; finally, it is possible to generate a user analysis report for the target game based on the secondary analysis results, and the setting of the user analysis report is conducive to improving the convenience of viewing the current status and trend of user retention and loss for the target game. The following are detailed descriptions.

[0098] Embodiment 1

[0099] See also Figure 1 , Figure 1 1 is a flowchart of a method for analyzing game user retention applied to multi-dimensional data disclosed in an embodiment of the present invention. Figure 1 The game user retention analysis method applied to multi-dimensional data described above can be applied to a game user retention analysis device applied to multi-dimensional data, and the embodiment of the present invention does not limit this. Figure 1 As shown, the game user retention analysis method applied to multi-dimensional data may include the following operations:

[0100] 101. Collect user behavior data corresponding to one or more game users targeted by the target game, and determine core indicator data of the target game based on the user behavior data.

[0101] In the embodiment of the present invention, the core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms.

[0102] In an embodiment of the present invention, game behavior data of one or more game users for a target game is first collected, and then based on the game behavior data, combined with a set analysis engine and analysis needs / business needs, multiple core indicator data for the target game are determined; the game behavior data includes the channels and paths through which game users download / access the target game.

[0103] In the embodiment of the present invention, the core indicator data not only covers the channel indicators of different channels (such as the download volume, installation volume, activation rate, etc. of each channel), but also includes the platform indicators of different platforms (such as the user ratio and payment rate of iOS and Android platforms). This comprehensive data collection strategy ensures the breadth of the analysis basis and the representativeness of the data, and provides a solid foundation for subsequent in-depth analysis.

[0104] 102. Based on user behavior data and combined with core indicator data, determine the behavior change data of all game users.

[0105] In an embodiment of the present invention, the behavior change data of the game user may record the continuous login time of the user logging into the target game (such as logging in for 7 consecutive days), the time of the most recent login (such as logging in 10 hours ago or 3 days ago), the login frequency (such as logging in to the game 3 times or 10 times a day, etc.), and the duration of each login of the game user (such as maintaining online for 2 hours per login).

[0106] 103. Perform a primary analysis on the behavior change data of all game users to obtain a primary analysis result of the target game within a target specified time period; the primary analysis result includes user retention information and / or user churn information.

[0107] In an embodiment of the present invention, the user retention information refers to the number of users who remain logged in to the target game, and the user churn information is obtained by calculating the cumulative number of new users minus the number of users who have not logged in for a long time (such as 7 days).

[0108] 104. Perform secondary analysis on the primary analysis results based on the core indicator data to obtain secondary analysis results corresponding to all game users.

[0109] In the embodiment of the present invention, the secondary analysis result includes the user distribution and user activity of all game users; the secondary analysis result is used to indicate the usage of different functions of the target game by all game users.

[0110] 105. Generate a user analysis report for the target game based on the secondary analysis results.

[0111] It can be seen that implementation Figure 1The described game user retention analysis method applied to multidimensional data can, after collecting user behavior data of one or more game users targeted by the target game, intelligently determine the core indicator data of the target game based on the user behavior data, thereby gradually determining the behavior change data, user retention information and / or user churn information of one or more game users targeted by the target game, which is conducive to improving the accuracy of capturing user behavior changes, and then helping game developers to timely identify key nodes of user retention and potential causes of churn, and provide corresponding auxiliary data for formulating targeted operation strategies; further, it is also possible to perform secondary analysis on the primary analysis results based on the core indicator data to obtain the user distribution of all game users. This in-depth analysis not only helps game developers understand the basic characteristics of the user group, but also reveals the active patterns of users, and then provides a scientific basis for optimizing the game experience and improving user stickiness; finally, it is possible to generate a user analysis report for the target game based on the secondary analysis results, and the setting of the user analysis report is conducive to improving the convenience of viewing the current status and trends of user retention and churn for the target game.

[0112] In an optional embodiment, the above step 103 performs a primary analysis on the behavior change data of all game users, and the method of obtaining the primary analysis result of the target game within the target specified time period specifically includes:

[0113] Determine one or more analysis periods to be analyzed, and determine all first periods with target recommendation strategies set and all second periods without target recommendation strategies set from all analysis periods; the target recommendation strategies include an initial promotion strategy for increasing new users and a return visit recommendation strategy set for returning users;

[0114] According to a preset grouping strategy, all analysis time periods are grouped to obtain grouping results corresponding to all analysis time periods; the grouping results include at least one time period grouping set, each time period grouping set matches a set time period; the set time period includes at least one first time period and at least one second time period;

[0115] For each analysis period, the sub-change data corresponding to the analysis period is determined based on the behavior change data corresponding to all game users. The sub-change data includes the number of new users, the number of returning users, and the number of lost users.

[0116] For each time period grouping set, all sub-change data corresponding to the time period grouping set are analyzed to obtain the set analysis results corresponding to the time period grouping set; and the set analysis results corresponding to all time period grouping sets are determined as the first-level analysis results of the target game within the target setting time period; the target setting time period includes all set time periods.

[0117] In this optional embodiment, one or more analysis time periods to be analyzed are determined, and on this basis, a first time period in which a target recommendation strategy is set and a second time period in which a target recommendation strategy is not set are further distinguished; this precise division of time periods is conducive to improving the accuracy of subsequent analysis of the impact of different recommendation strategies on user behavior.

[0118] In this optional embodiment, all analysis time periods are divided into multiple time period grouping sets through a preset grouping strategy. This grouping method takes into account both the continuity of time and the presence or absence of a recommended strategy, making the data in each time period grouping set more comparable and more valuable for analysis.

[0119] In this optional embodiment, for each analysis period, key indicators such as the number of new users, the number of returning users, and the number of lost users can be determined based on the behavioral change data of all game users; these indicators comprehensively reflect the behavioral characteristics of users in different time periods, and provide detailed data support for in-depth analysis of user retention and loss; specifically, by comparing the changes in the number of users who set a target recommendation strategy and the changes in the number of users who do not set a target recommendation strategy, the setting effect of the target recommendation strategy can be clearly compared, thereby assisting game operators to optimize and adjust the target recommendation strategy or continue to promote its application.

[0120] In this optional embodiment, all sub-change data within each time period grouping set are analyzed to obtain a set analysis result. While considering the user behavior changes within a single time period, the long-term trends and patterns of user behavior changes are revealed by comparing the data within the set time period. This analysis method that combines depth and breadth helps game developers to understand user behavior more comprehensively and provide a scientific basis for formulating more accurate operation strategies.

[0121] It can be seen that in this optional embodiment, through precise time period division, reasonable grouping strategy application and comprehensive data analysis, deep insight and accurate evaluation of user behavior changes are achieved, which is conducive to improving the accuracy and reliability of subsequent game operation strategy formulation.

[0122] In another optional embodiment, the above-mentioned method of analyzing all sub-change data corresponding to the time period grouping set to obtain the set analysis result corresponding to the time period grouping set specifically includes:

[0123] Merge and integrate all first time periods and all second time periods in the time period grouping set to obtain a target integrated time period;

[0124] Merge and integrate the sub-change data corresponding to all first time periods and all second time periods in the time period grouping set to obtain first integrated data corresponding to all first time periods and second integrated data corresponding to all second time periods;

[0125] Compare the first integrated data and the second integrated data in the time period grouping set to obtain corresponding data comparison results as the set analysis results corresponding to the time period grouping set;

[0126] The first integrated data corresponding to the time period grouping set and all the first time periods include first user retention information and / or first user churn information within the target integration time period; the second integrated data corresponding to the time period grouping set and all the second time periods include second user retention information and / or second user churn information within the target integration time period;

[0127] This time period grouping combined with the corresponding data comparison results is used to indicate the strategy recommendation effect of setting the target recommendation strategy.

[0128] In this optional embodiment, all the first time periods can be the first week and the third week of October; all the second time periods can be the second week and the fourth week of October; optionally, the first two weeks of October can be merged to obtain a corresponding collective time period of the first two weeks of October; the four weeks of October can also be merged to obtain a corresponding collective time period of the entire month of October. The specific merging method is not limited in this embodiment of the present invention.

[0129] It can be seen that in this optional embodiment, when analyzing all sub-change data corresponding to the time period grouping set, the set analysis results are obtained by merging and integrating time periods, merging and integrating data, and comparing data, which is conducive to improving the efficiency and accuracy of data analysis.

[0130] Embodiment 2

[0131] See also Figure 2 , Figure 2 1 is a flow chart of another method for analyzing game user retention applied to multi-dimensional data disclosed in an embodiment of the present invention. Figure 2 The game user retention analysis method applied to multi-dimensional data described above can be applied to a game user retention analysis device applied to multi-dimensional data, and the embodiment of the present invention does not limit this. Figure 2 As shown, the game user retention analysis method applied to multi-dimensional data may include the following operations:

[0132] 201. Collect user behavior data corresponding to one or more game users targeted by the target game, and determine core indicator data of the target game based on the user behavior data.

[0133] 202. Based on the user behavior data and combined with the core indicator data, determine the behavior change data of all game users.

[0134] 203. Perform primary analysis on the behavior change data of all game users to obtain primary analysis results of the target game within the target specified time period; the primary analysis results include user retention information and / or user churn information.

[0135] 204. Perform secondary analysis on the primary analysis results based on the core indicator data to obtain secondary analysis results corresponding to all game users.

[0136] 205. Generate a user analysis report for the target game based on the secondary analysis results.

[0137] In the embodiment of the present invention, for other descriptions of step 201 to step 205, please refer to other specific descriptions of step 101 to step 105 in embodiment 1, and the embodiment of the present invention will not be repeated here.

[0138] 206. Based on the user analysis report, determine the retention influencing factors for the target game. The retention influencing factors include game quality, game experience rating, and user stickiness rating.

[0139] In the embodiment of the present invention, the three retention influencing factors cover the core competitiveness of the game and the user behavior characteristics. By accurately identifying and analyzing these retention influencing factors, it is helpful to provide ideas for game developers to perform subsequent game optimization.

[0140] 207. Based on the retention impact factor, multiple characteristic gameplays are determined from multiple basic gameplays of the target game, and the game user rating corresponding to each characteristic gameplay is higher than the preset rating value.

[0141] 208. Based on the user analysis report, multiple user portraits are determined, and the user portraits are associated with a preset user group classification.

[0142] 209. According to the user analysis report, all user portraits and all feature gameplays are arranged and combined to obtain corresponding arrangement and combination results.

[0143] 210. Generate personalized recommendation information for each user portrait based on the permutation and combination results. The personalized recommendation information includes a personalized recommendation strategy for game promotion.

[0144] In the embodiment of the present invention, in the permutation and combination results, each user portrait matches at least one characteristic gameplay.

[0145] In the embodiment of the present invention, the method for generating personalized recommendation information can not only effectively improve the user's attention and participation in game promotion, but also further optimize the game promotion strategy and improve the competitiveness of the game by accurately matching user needs.

[0146] It can be seen that implementation Figure 2 The described game user retention analysis method applied to multi-dimensional data provides ideas for subsequent developers to optimize and operate the target game by accurately identifying retention influencing factors, efficiently screening characteristic gameplay, building user portraits, and generating personalized recommendation information, thereby helping to improve the user experience of users using the target game, and then greatly improve the user's game retention rate, and then improve the user's user experience of using the target game.

[0147] In an optional embodiment, the above step 204 performs secondary analysis on the primary analysis results according to the core indicator data, and the method of obtaining the secondary analysis results corresponding to all game users specifically includes:

[0148] Determine multiple dimensional indicators, including channel dimension, platform dimension, time dimension and geographical dimension;

[0149] According to all dimensional indicators, perform dimensional division on the core indicator data to obtain the dimensional indicator interval corresponding to each dimensional indicator;

[0150] Analyze the first-level analysis results to obtain the user distribution of all game users in each dimension indicator interval. The user distribution includes multiple sub-distributions, and each sub-distribution corresponds to a dimension indicator interval;

[0151] Determine the application function corresponding to each dimension indicator interval;

[0152] For each dimension indicator interval, based on the user distribution, determine the user participation information of all game users for the application function in the dimension indicator interval as the user activity;

[0153] All dimension indicator ranges, user distribution, and user activity are determined as secondary analysis results.

[0154] In this optional embodiment, the channel dimension is used to indicate the user's download channel for the target game (such as Google Play, App Store), and data segmentation can be performed through the channel identifier (Channel ID); platform dimension: by identifying the operating system and device type used by the user (through User-Agent string parsing), in order to analyze the device environment; time dimension: by timestamp (Timestamp), user behavior data is segmented into precise daily, weekly, and monthly time periods for time series analysis; regional dimension: the user's geographic location information is obtained through IP address or GPS data, and classified into regional levels (country, province, city).

[0155] In this optional embodiment, the above-mentioned method of performing dimension division on the core indicator data according to all dimensional indicators to obtain the dimensional indicator interval corresponding to each dimensional indicator specifically includes:

[0156] Determine a plurality of subdivision indicators corresponding to each dimensional indicator, and determine each subdivision indicator corresponding to the dimensional indicator as a dimensional indicator interval of the dimensional indicator;

[0157] And, the above-mentioned first-level analysis results are analyzed to obtain the user distribution of all game users in each dimension indicator range, specifically including:

[0158] For each dimensional indicator, all primary indicator data corresponding to the dimensional indicator are extracted from the core indicator data;

[0159] Taking each sub-indicator corresponding to the dimension indicator as the division basis, perform data division on all primary indicator data corresponding to the dimension indicator to obtain secondary indicator data corresponding to each sub-indicator in the dimension indicator;

[0160] Based on the secondary indicator data corresponding to each sub-indicator in each dimensional indicator, determine the user distribution of all game users in each dimensional indicator range.

[0161] Specifically, the core indicator data is divided into dimensions to obtain the dimensional indicator interval corresponding to each dimensional indicator, which can be used to perform preliminary unified integration and data collection for the data of the channel dimension, platform dimension, time dimension and regional dimension; then the data is divided according to the detailed indicators corresponding to each dimensional indicator in the dimensional indicator; taking the channel dimension as an example, all data related to the channel dimension in the core indicator data is collected, and then divided according to different download dimensions, such as Google Play, App Store, etc., to obtain the number of users who downloaded through Google Play and the number of users who downloaded through AppStore; similarly, the time dimension can be divided into data according to month, degree, year, etc. after data collection; the platform dimension is divided according to different platforms, and the region dimension is divided according to different regions; the specific division method can be adjusted according to actual needs, and the embodiment of the present invention is not limited thereto.

[0162] It can be seen that in this optional embodiment, through the division of multi-dimensional indicators, in-depth analysis of user distribution and accurate evaluation of user activity, the primary analysis results are further refined and deepened; not only the accuracy and comprehensiveness of data analysis are improved, but also strong data support and decision-making basis are provided for game developers, which is beneficial to improving the subsequent playability of the target game to a certain extent.

[0163] In another optional embodiment, the method of analyzing the first-level analysis results to obtain the user distribution of all game users in each dimension index interval specifically includes:

[0164] Obtain user tags set for all game users and their corresponding tag categories, where each tag category is associated with one or more user tags;

[0165] Taking each dimension index interval as a unit, calculate the number and proportion of each user tag in the dimension index interval;

[0166] According to the number and proportion of each user tag in the dimension index interval, determine the proportion information of the user group corresponding to each tag classification in the dimension index interval;

[0167] The user group proportion information corresponding to each label classification in all dimension indicator intervals is determined as the user distribution of all game users in all dimension indicator intervals.

[0168] In this optional embodiment, the user tags of all game users may include male, female, child, youth, middle-aged or elderly, etc.; wherein, the tag classification can be divided into low activity, medium activity or high activity according to the game activity; it can also be divided into novice players, old players; high-skilled players with high scores in the game, medium-skilled players or novice players, etc., which is not limited in this embodiment of the present invention.

[0169] In this optional embodiment, the core indicator data also includes event record information corresponding to each free event in the target game; each free event matches a game function of the target game, and the event record information corresponding to each free event includes the number of times the user uses it, the frequency of the user using it, the time investment, and the conversion rate;

[0170] In this optional embodiment, it should be noted that the user usage frequency corresponding to each free event is used to indicate the number of times one or more game users repeatedly visit the free event within a preset recording time period; the time investment corresponding to each free event is the cumulative access time of one or more game users visiting the free event; the conversion rate corresponding to each free event is used to indicate the probability of triggering a preset key behavior after the game user uses the free event;

[0171] The user tag includes at least one of an age group tag, a gender tag, an interest preference tag, and a consumption habit tag.

[0172] It can be seen that in this optional embodiment, the depth and breadth of the analysis of user behavior characteristics are further improved through precise user tags and tag classification, accurate quantity and proportion analysis, comprehensive user group proportion information and comprehensive user distribution.

[0173] Embodiment 3

[0174] See also Figure 3 , Figure 3 : is a schematic diagram of the structure of a game user retention analysis device applied to multi-dimensional data disclosed in an embodiment of the present invention. The game user retention analysis device applied to multi-dimensional data can be a game user retention analysis terminal, device, system or server applied to multi-dimensional data. The server can be a local server, a remote server, or a cloud server (also known as a cloud server). When the server is a non-cloud server, the non-cloud server can communicate with the cloud server, which is not limited in the embodiment of the present invention. Figure 3 As shown, the game user retention analysis device applied to multi-dimensional data may include a first determination module 301, a second determination module 302, a primary analysis module 303, a secondary analysis module 304 and a report generation module 305, wherein:

[0175] The first determination module 301 is used to collect user behavior data corresponding to one or more game users targeted by the target game, and determine core indicator data of the target game based on the user behavior data. The core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms.

[0176] The second determination module 302 is used to determine the behavior change data of all game users based on the user behavior data in combination with the core indicator data.

[0177] The primary analysis module 303 is used to perform primary analysis on the behavior change data of all game users to obtain the primary analysis results of the target game within the target specified time period; the primary analysis results include user retention information and / or user churn information.

[0178] The secondary analysis module 304 is used to perform secondary analysis on the primary analysis results according to the core indicator data to obtain secondary analysis results corresponding to all game users. The secondary analysis results include the user distribution and user activity of all game users. The secondary analysis results are used to indicate the usage of different functions of the target game by all game users.

[0179] The report generation module 305 is used to generate a user analysis report for the target game according to the secondary analysis results.

[0180] It can be seen that implementation Figure 3 The described game user retention analysis device applied to multi-dimensional data can, after collecting user behavior data of one or more game users targeted by the target game, intelligently determine the core indicator data of the target game based on the user behavior data, thereby gradually determining the behavior change data, user retention information and / or user churn information of one or more game users targeted by the target game, which is conducive to improving the accuracy of capturing user behavior changes, and then helps game developers to timely identify key nodes of user retention and potential causes of churn, and provide corresponding auxiliary data for formulating targeted operation strategies; further, it can also perform secondary analysis on the primary analysis results based on the core indicator data to obtain the user distribution of all game users. This in-depth analysis not only helps game developers understand the basic characteristics of the user group, but also reveals the active patterns of users, and then provides a scientific basis for optimizing the game experience and improving user stickiness; finally, it can generate a user analysis report for the target game based on the secondary analysis results. The setting of this user analysis report is conducive to improving the convenience of viewing the current status and trends of user retention and churn for the target game.

[0181] In an optional embodiment, the primary analysis module 303 performs primary analysis on the behavior change data of all game users, and obtains the primary analysis result of the target game within the target specified time period in a specific manner including:

[0182] Determine one or more analysis periods to be analyzed, and determine all first periods with target recommendation strategies set and all second periods without target recommendation strategies set from all analysis periods; the target recommendation strategies include an initial promotion strategy for increasing new users and a return visit recommendation strategy set for returning users;

[0183] According to a preset grouping strategy, all analysis time periods are grouped to obtain grouping results corresponding to all analysis time periods; the grouping results include at least one time period grouping set, each time period grouping set matches a set time period; the set time period includes at least one first time period and at least one second time period;

[0184] For each analysis period, the sub-change data corresponding to the analysis period is determined based on the behavior change data corresponding to all game users. The sub-change data includes the number of new users, the number of returning users, and the number of lost users.

[0185] For each time period grouping set, all sub-change data corresponding to the time period grouping set are analyzed to obtain the set analysis results corresponding to the time period grouping set; and the set analysis results corresponding to all time period grouping sets are determined as the first-level analysis results of the target game within the target setting time period; the target setting time period includes all set time periods.

[0186] It can be seen that in this optional embodiment, through precise time period division, reasonable grouping strategy application and comprehensive data analysis, deep insight and accurate evaluation of user behavior changes are achieved, which is conducive to improving the accuracy and reliability of subsequent game operation strategy formulation.

[0187] In another optional embodiment, the primary analysis module 303 analyzes all sub-change data corresponding to the time period grouping set to obtain a set analysis result corresponding to the time period grouping set, specifically including:

[0188] Merge and integrate all first time periods and all second time periods in the time period grouping set to obtain a target integrated time period;

[0189] Merge and integrate the sub-change data corresponding to all first time periods and all second time periods in the time period grouping set to obtain first integrated data corresponding to all first time periods and second integrated data corresponding to all second time periods;

[0190] Compare the first integrated data and the second integrated data in the time period grouping set to obtain corresponding data comparison results as the set analysis results corresponding to the time period grouping set;

[0191] The first integrated data corresponding to the time period grouping set and all the first time periods include first user retention information and / or first user churn information within the target integration time period; the second integrated data corresponding to the time period grouping set and all the second time periods include second user retention information and / or second user churn information within the target integration time period;

[0192] This time period grouping combined with the corresponding data comparison results is used to indicate the strategy recommendation effect of setting the target recommendation strategy.

[0193] It can be seen that in this optional embodiment, when analyzing all sub-change data corresponding to the time period grouping set, the set analysis results are obtained by merging and integrating time periods, merging and integrating data, and comparing data, which is conducive to improving the efficiency and accuracy of data analysis.

[0194] In another optional embodiment, the secondary analysis module 304 performs secondary analysis on the primary analysis results according to the core indicator data, and the method of obtaining the secondary analysis results corresponding to all game users specifically includes:

[0195] Determine multiple dimensional indicators, including channel dimension, platform dimension, time dimension and geographical dimension;

[0196] According to all dimensional indicators, perform dimensional division on the core indicator data to obtain the dimensional indicator interval corresponding to each dimensional indicator;

[0197] Analyze the first-level analysis results to obtain the user distribution of all game users in each dimension indicator interval. The user distribution includes multiple sub-distributions, and each sub-distribution corresponds to a dimension indicator interval;

[0198] Determine the application function corresponding to each dimension indicator interval;

[0199] For each dimension indicator interval, based on the user distribution, determine the user participation information of all game users for the application function in the dimension indicator interval as the user activity;

[0200] All dimension indicator ranges, user distribution, and user activity are determined as secondary analysis results.

[0201] It can be seen that in this optional embodiment, through the division of multi-dimensional indicators, in-depth analysis of user distribution and accurate evaluation of user activity, the primary analysis results are further refined and deepened; not only the accuracy and comprehensiveness of data analysis are improved, but also strong data support and decision-making basis are provided for game developers, which is beneficial to improving the subsequent playability of the target game to a certain extent.

[0202] In another optional embodiment, the secondary analysis module 304 analyzes the primary analysis results to obtain the user distribution of all game users in each dimension index interval in a manner that specifically includes:

[0203] Obtain user tags set for all game users and their corresponding tag categories, where each tag category is associated with one or more user tags;

[0204] Taking each dimension index interval as a unit, calculate the number and proportion of each user tag in the dimension index interval;

[0205] According to the number and proportion of each user tag in the dimension index interval, determine the proportion information of the user group corresponding to each tag classification in the dimension index interval;

[0206] The user group proportion information corresponding to each label classification in all dimension indicator intervals is determined as the user distribution of all game users in all dimension indicator intervals.

[0207] In this optional embodiment, the core indicator data also includes event record information corresponding to each free event in the target game; each free event matches a game function of the target game, and the event record information corresponding to each free event includes the number of times the user uses it, the frequency of the user using it, the time investment, and the conversion rate;

[0208] The user usage frequency corresponding to each free event is used to indicate the number of times one or more game users repeatedly access the free event within a preset recording time period; the time investment corresponding to each free event is the cumulative access time of one or more game users to the free event; the conversion rate corresponding to each free event is used to indicate the probability of triggering a preset key behavior after the game user uses the free event;

[0209] The user tag includes at least one of an age group tag, a gender tag, an interest preference tag, and a consumption habit tag.

[0210] It can be seen that in this optional embodiment, the depth and breadth of the analysis of user behavior characteristics are further improved through precise user tags and tag classification, accurate quantity and proportion analysis, comprehensive user group proportion information and comprehensive user distribution.

[0211] In another optional embodiment, the second determination module 302 is further used to determine the retention influencing factor for the target game according to the user analysis report, where the retention influencing factor includes game quality, game experience rating, and user stickiness rating;

[0212] The second determination module 302 is further used to determine a plurality of characteristic gameplays from a plurality of basic gameplays of the target game according to the retention impact factor, wherein the game user rating corresponding to each characteristic gameplay is higher than a preset rating value;

[0213] The second determination module 302 is further used to determine a plurality of user portraits according to the user analysis report, wherein the user portraits are associated with a preset user group classification;

[0214] The device also includes a permutation and combination module 306, wherein:

[0215] The permutation and combination module 306 is used to perform permutations and combinations on all user portraits and all characteristic gameplays according to the user analysis report to obtain corresponding permutation and combination results; and generate personalized recommendation information for each user portrait according to the permutation and combination results, wherein the personalized recommendation information includes a personalized recommendation strategy for game promotion;

[0216] Among them, in the permutation and combination results, each user portrait matches at least one characteristic gameplay.

[0217] It can be seen that in this optional embodiment, by accurately identifying retention influencing factors, efficiently screening characteristic gameplay, building user portraits, generating personalized recommendation information, etc., it provides ideas for subsequent developers to optimize and operate the target game, which is beneficial to improving the user experience of users using the target game, and then greatly improving the user's game retention rate, and then improving the user's user experience of using the target game.

[0218] Embodiment 4

[0219] See also Figure 5 , Figure 5 Schematic diagram of another structure of a game user retention analysis device for multi-dimensional data disclosed in an embodiment of the present invention. Figure 5 As shown, the game user retention analysis device applied to multi-dimensional data may include:

[0220] A memory 401 storing executable program codes;

[0221] a processor 402 coupled to the memory 401;

[0222] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the game user retention analysis method applied to multi-dimensional data described in the first embodiment of the present invention or the second embodiment of the present invention.

[0223] Embodiment 5

[0224] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the game user retention analysis method applied to multidimensional data described in Embodiment 1 or Embodiment 2 of the present invention.

[0225] Embodiment 6

[0226] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the game user retention analysis method applied to multidimensional data described in Example 1 or Example 2.

[0227] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0228] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0229] Finally, it should be noted that the game user retention analysis method and device applied to multi-dimensional data disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for analyzing game user retention applied to multidimensional data, characterized in that: The method comprises: Collecting user behavior data corresponding to one or more game users targeted by the target game, and determining core indicator data of the target game based on the user behavior data, wherein the core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms; Determine the behavior change data of all the game users based on the user behavior data and in combination with the core indicator data; perform primary analysis on the behavior change data of all the game users to obtain the primary analysis results of the target game within the target specified time period; the primary analysis results include user retention information and / or user churn information; According to the core indicator data, a secondary analysis is performed on the primary analysis result to obtain secondary analysis results corresponding to all the game users, wherein the secondary analysis results include user distribution and user activity of all the game users; the secondary analysis results are used to indicate the usage of different functions of the target game by all the game users; A user analysis report for the target game is generated according to the secondary analysis results.

2. The method for analyzing game user retention applied to multidimensional data according to claim 1, characterized in that: The performing of primary analysis on the behavior change data of all the game users to obtain the primary analysis result of the target game within the target specified time period includes: Determine one or more analysis periods to be analyzed, and determine all first periods with target recommendation strategies set and all second periods without the target recommendation strategies from all the analysis periods; the target recommendation strategies include an initial promotion strategy for adding new users and a return visit recommendation strategy set for returning users; According to a preset grouping strategy, grouping is performed on all the analysis time periods to obtain grouping results corresponding to all the analysis time periods; the grouping results include at least one time period grouping set, each of the time period grouping sets matches a set time period; the set time period includes at least one of the first time period and at least one of the second time period; For each analysis period, determining sub-change data corresponding to the analysis period according to the behavior change data corresponding to all the game users, wherein the sub-change data includes the number of new users, the number of returning users, and the number of lost users; For each of the time period grouping sets, all the sub-change data corresponding to the time period grouping set are analyzed to obtain a set analysis result corresponding to the time period grouping set; and the set analysis results corresponding to all the time period grouping sets are determined as the first-level analysis results of the target game within the target setting time period; the target setting time period includes all the set time periods.

3. The method for analyzing game user retention applied to multidimensional data according to claim 2, characterized in that: The analyzing all the sub-change data corresponding to the time period grouping set to obtain a set analysis result corresponding to the time period grouping set includes: Merge and integrate all the first time periods and all the second time periods in the time period grouping set to obtain a target integrated time period; Merge and integrate the sub-change data corresponding to all the first time periods and all the second time periods in the time period grouping set to obtain first integrated data corresponding to all the first time periods and second integrated data corresponding to all the second time periods; Compare the first integrated data and the second integrated data in the time period grouping set to obtain corresponding data comparison results as the set analysis results corresponding to the time period grouping set; The first integrated data corresponding to the time period grouping set and all the first time periods include first user retention information and / or first user churn information within the target integration time period; the second integrated data corresponding to the time period grouping set and all the second time periods include second user retention information and / or second user churn information within the target integration time period; The time period grouping combined with the corresponding data comparison result is used to indicate the strategy recommendation effect of setting the target recommendation strategy.

4. The method for analyzing game user retention applied to multidimensional data according to any one of claims 1 to 3, characterized in that: The performing of secondary analysis on the primary analysis result according to the core indicator data to obtain secondary analysis results corresponding to all the game users includes: Determine multiple dimensional indicators, wherein the dimensional indicators include channel dimension, platform dimension, time dimension and geographical dimension; According to all the dimensional indicators, the core indicator data is divided into dimensions to obtain a dimensional indicator interval corresponding to each dimensional indicator; Analyze the primary analysis result to obtain user distribution of all the game users in each dimension indicator interval, wherein the user distribution includes multiple sub-distribution situations, and each sub-distribution situation corresponds to one dimension indicator interval; Determine the application function corresponding to each dimension indicator interval; For each of the dimensional indicator intervals, determining user participation information of all the game users for the application function in the dimensional indicator interval according to the user distribution as user activity; All the dimension indicator intervals, the user distribution and the user activity are determined as secondary analysis results.

5. The method for analyzing game user retention applied to multi-dimensional data according to claim 4, characterized in that: Analyzing the primary analysis results to obtain the user distribution of all the game users in each dimension indicator interval includes: Obtaining user tags set for all game users and their corresponding tag categories, each of the tag categories being associated with one or more of the user tags; Taking each dimension index interval as a unit, calculate the number and proportion of each user tag in the dimension index interval; According to the quantity and quantity proportion of each user tag in the dimension index interval, determine the user group proportion information corresponding to each tag classification in the dimension index interval; The user group proportion information corresponding to each of the tag categories in all the dimensional index intervals is determined as the user distribution of all the game users in all the dimensional index intervals.

6. The method for analyzing game user retention applied to multidimensional data according to claim 1, 2, 3 or 5, characterized in that: The method further comprises: Determine retention influencing factors for the target game according to the user analysis report, wherein the retention influencing factors include game quality, game experience rating, and user stickiness rating; According to the retention influencing factor, a plurality of characteristic gameplays are determined from a plurality of basic gameplays of the target game, wherein a game user rating corresponding to each of the characteristic gameplays is higher than a preset rating value; Determine a plurality of user portraits according to the user analysis report, wherein the user portraits are associated with a preset user group classification; According to the user analysis report, all the user portraits and all the characteristic gameplays are arranged and combined to obtain corresponding arrangement and combination results; and according to the arrangement and combination results, personalized recommendation information is generated for each of the user portraits, and the personalized recommendation information includes a personalized recommendation strategy for game promotion; Among them, in the permutation and combination results, each of the user portraits matches at least one of the characteristic gameplays.

7. The method for analyzing game user retention applied to multidimensional data according to claim 5, characterized in that: The core indicator data also includes event record information corresponding to each free event in the target game; each free event matches a game function of the target game, and the event record information corresponding to each free event includes the number of times the user uses it, the frequency of the user's use, the time investment, and the conversion rate; The user usage frequency corresponding to each free event is used to indicate the number of times one or more game users repeatedly visit the free event within a preset recording time period; the time investment corresponding to each free event is the cumulative visit time of one or more game users visiting the free event; the conversion rate corresponding to each free event is used to indicate the probability of triggering a preset key behavior after the game user uses the free event; The user tag includes at least one of an age group tag, a gender tag, an interest preference tag, and a consumption habit tag.

8. A game user retention analysis device applied to multi-dimensional data, characterized in that: The device comprises: A first determination module is used to collect user behavior data corresponding to one or more game users targeted by the target game, and determine core indicator data of the target game according to the user behavior data, wherein the core indicator data includes channel indicators of the target game for different channels and / or platform indicators of the target game for different platforms; A second determination module is used to determine the behavior change data of all the users based on the user behavior data and in combination with the core indicator data; A primary analysis module, used to perform primary analysis on the behavior change data of all game users to obtain the primary analysis results of the target game within a target specified time period; the primary analysis results include user retention information and / or user churn information; A secondary analysis module, for performing secondary analysis on the primary analysis results according to the core indicator data, to obtain secondary analysis results corresponding to all the game users, the secondary analysis results including user distribution and user activity of all the game users; the secondary analysis results are used to indicate the usage of different functions of the target game by all the game users; A report generation module is used to generate a user analysis report for the target game according to the secondary analysis results.

9. A game user retention analysis device applied to multi-dimensional data, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the game user retention analysis method applied to multidimensional data as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, which, when called, are used to execute the game user retention analysis method applied to multidimensional data as described in any one of claims 1-7.

Images