A method and device for determining a recommended game, and equipment and a medium

Abstract

The present disclosure provides a method and device for determining a recommended game, equipment and medium, and relates to the technical field of network games. The method comprises: obtaining game preference indicators of multiple historical periods based on user information of a target game; determining historical game preference indicators corresponding to each candidate game based on game preference indicators of the multiple historical periods and corresponding game progress decay parameters of each candidate game; determining multiple candidate games based on the historical game preference indicators of multiple candidate games; and obtaining the recommended game from the multiple candidate games based on the correlation between the target game and the multiple candidate games. The method for determining a recommended game provided by the present disclosure can improve the user retention rate.

Description

Technical Field

[0001] This invention relates to the field of online game technology, and in particular to a method, apparatus, device, and medium for determining recommended games. Background Technology

[0002] When popular IP games are removed from app stores, a significant loss of users often occurs. Therefore, effectively managing the user base of these games, migrating users before the hype fades, and improving the retention rate of new users are urgent issues that need to be addressed. Summary of the Invention

[0003] According to one aspect of this disclosure, a method for determining recommended games is provided, the method comprising:

[0004] Game preference metrics for multiple historical periods were obtained based on user information of the target game.

[0005] Based on the game preference index and corresponding game progress decay parameter of each candidate game in the multiple historical periods, the historical game preference index of the candidate game is determined.

[0006] Multiple candidate games were determined based on various historical game preference indicators of the candidate games;

[0007] Based on the correlation between the target game and the multiple candidate games, the recommended game is obtained from the multiple candidate games.

[0008] According to another aspect of this disclosure, a device for determining recommended games is provided, the device comprising:

[0009] The acquisition module is used to obtain game preference indicators for multiple historical time periods based on user information of the target game;

[0010] The determination module is used to determine the historical game preference index corresponding to the candidate game based on the game preference index of each candidate game in the multiple historical periods and the corresponding game progress decay parameter;

[0011] The determining module is also used to determine multiple candidate games based on various historical game preference indicators of the candidate games;

[0012] The acquisition module is also used to acquire the recommended game from the multiple candidate games based on the correlation between the target game and the multiple candidate games.

[0013] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0014] Processor; and,

[0015] Memory for stored programs;

[0016] The program includes instructions that, when executed by the processor, cause the processor to perform a method provided according to exemplary embodiments of the present disclosure.

[0017] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform a method provided according to an exemplary embodiment of this disclosure.

[0018] One or more technical solutions provided in this disclosure obtain game preference indicators for multiple historical time periods based on user information of the target game. Then, based on the game preference indicators of each candidate game in multiple historical time periods and the corresponding game progress decay parameters, the historical game preference indicators of the corresponding candidate game are determined. It can be seen that the method of this exemplary embodiment introduces game progress decay parameters for different historical time periods into the calculation of historical game preference indicators. Since the game progress decay parameters can reflect the game progress of the corresponding historical time period, and considering that game preference indicators for historical time periods closer to the current time have greater reference significance, while those farther from the current time have less reference significance, the game progress decay parameters can assign different weights to the game preference indicators for their corresponding historical time periods, allowing the historical game preference indicators of the corresponding candidate game to better represent the user's game preference for the current candidate game.

[0019] Based on this, multiple candidate games that match the user's game preferences can be selected from a variety of candidate games using historical game preference metrics. Then, based on the correlation between the target game and multiple candidate games, recommended games are obtained from multiple candidate games to ensure that the obtained recommended games have a high degree of correlation with the target game. When the obtained recommended games are recommended to users, the recommended games can meet the user's game preferences, reduce the problem of user churn on the game platform, and improve the user retention rate. Attached Figure Description

[0020] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A schematic flowchart illustrating a method for determining recommended games according to exemplary embodiments of the present disclosure is shown;

[0022] Figure 2 A schematic flowchart illustrating a method for obtaining game preference metrics for multiple historical time periods according to an exemplary embodiment of the present disclosure is shown;

[0023] Figure 3 A schematic flowchart illustrating a method for determining game preference metrics for multiple historical time periods according to an exemplary embodiment of the present disclosure is shown;

[0024] Figure 4 A schematic flowchart illustrating a method for obtaining user behavior data for multiple historical time periods according to an exemplary embodiment of the present disclosure is shown;

[0025] Figure 5 A schematic flowchart illustrating a method for determining the degree of association according to an exemplary embodiment of the present disclosure is shown;

[0026] Figure 6 This illustrates a user U1 in the i-th historical time period T according to an exemplary embodiment of this disclosure. i Game undirected graph;

[0027] Figure 7 This illustrates user U2 in the i-th historical time period T according to an exemplary embodiment of this disclosure. i Game undirected graph;

[0028] Figure 8 The i-th historical time period T according to an exemplary embodiment of this disclosure is shown. i An undirected graph of the games of all users;

[0029] Figure 9 A schematic block diagram of the functional modules of a device for determining recommended games according to an exemplary embodiment of the present disclosure is shown;

[0030] Figure 10 A schematic block diagram of a chip according to an exemplary embodiment of the present disclosure is shown;

[0031] Figure 11 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0032] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0033] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0034] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0035] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0036] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0037] Before introducing the embodiments of this disclosure, the relevant terms involved in the embodiments of this disclosure are first defined as follows:

[0038] Collaborative filtering is a classic and commonly used recommendation algorithm. It is a recommendation algorithm that relies entirely on the behavioral relationship between users and items. As its name suggests, "collaborative filtering" reveals its underlying principle: "Collaborating feedback, evaluations, and opinions from everyone to filter massive amounts of information and select information that the user may be interested in."

[0039] Machine learning is a multidisciplinary field that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and many other disciplines. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance.

[0040] Deep learning learns the inherent patterns and hierarchical representations of sample data. The information gained during this learning process greatly aids in interpreting data such as text, images, and sound. Its ultimate goal is to enable machines to possess analytical and learning capabilities like humans, allowing them to recognize data such as text, images, and sound.

[0041] An undirected graph is a graph in which every edge has no direction.

[0042] Confidence level, also known as reliability, confidence level, or confidence coefficient, refers to the uncertainty of the conclusions drawn when estimating population parameters through sampling due to the randomness of the sample.

[0043] Support, simply put, is the degree of support. It represents the frequency with which a preceding and following item appear together in a dataset.

[0044] In related technologies, emerging platforms often adopt the method of attracting new users by developing games based on other copyright backgrounds in order to quickly absorb users and occupy the market. However, they inevitably face the embarrassment of a large number of users being lost and low retention rates after the popularity fades or the games developed based on other copyright backgrounds are taken off the shelves, which makes the operation face great challenges.

[0045] Taking games as an example, gamers exhibit higher loyalty to their chosen games, repeatedly clicking on unfinished levels. This demonstrates multiple sessions with a single game over a long timeframe, while browsing data for other game products is relatively scarce. Consequently, the number of player behavioral data categories is significantly smaller, more singular, and sparse. In this unique scenario, effectively managing user operations for games developed under different copyright backgrounds, proactively migrating users before their initial hype fades, seizing the window of opportunity to cultivate user habits, and improving the retention rate of "new" users are urgent issues that need to be addressed.

[0046] Current game scene recommendation algorithms mainly include collaborative filtering, machine learning, and deep learning algorithms. Traditional collaborative filtering algorithms based on item or user similarity perform poorly in game scene recommendations, primarily because game players have high engagement and experience fatigue with similar games; furthermore, the limited variety of player game category data results in insufficient personalization of player user profiles, leading to unsatisfactory recommendation results.

[0047] Machine learning and deep learning algorithms require training on a large amount of user attributes and historical behavior data to mine user preferences. However, they are difficult to implement in this scenario of "nearly new" users who are almost in a cold start, and the recommendation effect is even worse than that of ordinary popular recommendations.

[0048] To address the aforementioned issues, this exemplary embodiment provides a method for determining recommended games. Compared to collaborative filtering, machine learning, and deep learning algorithms, the method for determining recommended games in this exemplary embodiment determines recommended games by using historical game preference metrics for each candidate game and the correlation between the target game and multiple candidate games. This improves the accuracy of staff recommendations and increases the retention rate of game platform users.

[0049] Figure 1 A schematic flowchart illustrating a method for determining recommended games according to exemplary embodiments of the present disclosure is shown. Figure 1 As shown, the method for determining the recommended game includes:

[0050] Step 101: Obtain game preference metrics for each candidate game from multiple historical time periods based on the target game's user information. The target game's user information here can be a single user profile, partial user information, or even all user information. It should be understood that candidate games may or may not include the target game.

[0051] In terms of the game's status, the target games mentioned above can be games that are about to be removed from the platform or games that may be removed in the future; in terms of game classification, the target games here can be games developed based on other copyright backgrounds or original games.

[0052] In practical applications, users in each historical time period can include all users of the target game, or only a subset of them. Game preference metrics can be used to characterize user preferences for different games. By acquiring game preference metrics from multiple historical time periods, these metrics can be used to represent user preferences for games during those different historical periods. For example, user U1 is considering game C... m Game preference metrics can include the user's U1 preference for game C. m The ratio of user U1's total preference value for all candidate games.

[0053] When the user information of the target game is the user information of a user U1 in the target game, then user U1 is the user information of the selected game C. m The preference index can be the game preference value of user U1. When the user information of the target game is the user information of multiple users of the target game, if the multiple users include user U1 and user U2 respectively, then user U1 is the user of the selected game C. m Game preference metrics can be user U1's choice of game C m The preference value of user U1 for all candidate games C m The ratio of total preference values, user U2's choice of game C m Game preference metrics can be user U2's selection of games C m The preference value accounts for the user's U2 for all candidate games C m The ratio of the total preference value.

[0054] Step 102: Based on the game preference indicators and corresponding game progress decay parameters for each candidate game across multiple historical time periods, determine the historical game preference indicators for the corresponding candidate game. As can be seen, the method of this exemplary embodiment incorporates game progress decay parameters for different historical time periods into the calculation of historical game preference indicators. Since game progress decay parameters can reflect the game progress of the corresponding historical time period, and considering that game preference indicators closer to the current time period have greater reference value than those further away, different weights can be assigned to the corresponding historical time period's game preference indicators through the game progress decay parameters. This allows the historical game preference indicators for the corresponding candidate game to better represent the user's game preference for the current candidate game. Finally, the game preference indicators for each candidate game across multiple historical time periods with different weights are summed to obtain the historical game preference indicator for each candidate game.

[0055] The aforementioned game progress decay parameter is positively correlated with the game progress of the corresponding candidate game in the corresponding historical period, and negatively correlated with the order of the corresponding candidate game in the corresponding historical period. Therefore, the formula for this game progress decay parameter can be:

[0056] In the formula,

[0057] H∈(0,100] represents the game progress of the corresponding candidate game in the corresponding historical period;

[0058] i represents the order of historical time periods in the direction away from the current time. When i = 0, the historical time period of the candidate game is considered to be the 0th position in the corresponding historical time period, i.e., T0. At this time, the game progress decay parameter corresponding to the historical time period is 1.

[0059] Step 103: Identify multiple candidate games based on historical game preference metrics of various candidate games. It should be understood that candidate games here refer to other games played by the user who played the target game alongside the target game. As such, candidate games also align with the game preferences of the user who played the target game. Therefore, by selecting multiple candidate games from the candidate games for recommendation, the accuracy of the recommendation can be improved, ensuring that the recommended games to users on the gaming platform better match their game preferences, thereby increasing user retention on the gaming platform.

[0060] Step 104: Based on the correlation between the target game and multiple candidate games, obtain recommended games from the candidate games. It should be understood that the correlation here can include the support level of the candidate games for the target game and the confidence level of the candidate games for the target game. By determining the correlation between multiple candidate games and the target game—that is, identifying the hidden patterns between them—candy games with high correlation to the target game be selected as recommended games and recommended to users. This satisfies users' game preferences while improving recommendation accuracy, reducing user churn on the game platform, and increasing user retention.

[0061] As one possible implementation method, Figure 2 A schematic flowchart illustrating a method for obtaining game preference metrics for multiple historical time periods according to an exemplary embodiment of this disclosure is shown. Figure 2 As shown, the aforementioned indicators of user preference for each candidate game across multiple historical time periods, obtained based on user information of the target game, may include:

[0062] Step 201: Obtain user behavior information for multiple candidate games based on user information of the target game. When a candidate game is another game played by a user who is playing the target game, recommend games based on the games the user has played. The recommended games will better match the user's game preferences, the recommendation accuracy will be higher, and it will be easier to improve user retention.

[0063] In practical applications, user behavior information can be determined based on the playtime of users of the target game, specifically when those users are simultaneously playing multiple candidate games within that playtime. It should be understood that this user behavior information can include behavioral data with multiple attributes, which can be selected based on the actual situation. For example, this behavioral data may include, but is not limited to, the user's playtime for the corresponding game, the number of shares, comments, favorites, and searches.

[0064] Step 202: Based on the user behavior information and corresponding behavior evaluation parameters for each candidate game, determine the game preference indicators for that candidate game across multiple historical time periods. It should be understood that "correspondence" here means that different user behavior information for each candidate game has corresponding behavior evaluation parameters, allowing different user behavior information to be evaluated using different behavior evaluation parameters. These behavior evaluation parameters may include multiple parameters, each used to measure the importance of the corresponding attribute behavior data.

[0065] By assigning different behavioral evaluation parameters to different user behavior information, the game preference indicators of the finally determined candidate games in multiple historical periods can better represent users' game preferences for different candidate games and are more meaningful for reference. When candidate games are determined and recommended to users based on their game preferences, the accuracy of the recommendations is higher, thereby resulting in a higher customer retention rate.

[0066] In some alternative methods, Figure 3 A schematic flowchart illustrating a method for determining game preference metrics across multiple historical time periods according to exemplary embodiments of the present disclosure is shown. Figure 3 As shown, the above-mentioned game preference indicators for each candidate game are determined based on user behavior information and corresponding behavior evaluation parameters for each candidate game over multiple historical periods, including:

[0067] Step 301: Obtain user behavior data for each candidate game across multiple historical time periods based on user behavior information for each candidate game. By segmenting user behavior information into multiple historical time periods according to duration, it is possible to determine user game preferences by analyzing user behavior data in the current time period, while also providing a reference for user behavior data from historical time periods prior to the current time period.

[0068] In practical applications, the duration of user behavior information for each candidate game can be divided according to the length of historical time periods to determine the user behavior data of the corresponding candidate game in multiple historical time periods.

[0069] Step 302: Based on user behavior data and corresponding behavioral evaluation parameters for multiple candidate games across various historical time periods, determine the game preference values ​​for each candidate game across these periods. By evaluating user behavior data from different historical time periods using behavioral evaluation parameters—that is, assigning different fixed weights to different user behavior data according to their reference significance—the determined game preference values ​​for multiple historical time periods can more accurately represent users' game preferences for that game. This makes the candidate games determined based on these preferences more aligned with users' play preferences, thereby improving user retention rates on the game platform.

[0070] For example, for candidate game C m User U j In the i-th historical period T i The game preference value can be represented as: B′(U j C m ,T i )=B(U j ,T i C m ,behave)*wb; where,

[0071] B(U j ,T i C m (,behave) indicates that for the candidate game C m User U j In the i-th historical period T i User behavior data matrix;

[0072] wb represents user U j In the i-th historical period T i The behavior evaluation parameters for each user behavior data point, where wb = (wb1, wb2, wb3, ..., wb n ), that is, each behavior evaluation parameter corresponds to a user behavior data, and n represents the user behavior category number.

[0073] For example, when the above user is a user U j At that time, for the candidate game C m The candidate game C m In the i-th historical period T i User behavior data may include: game duration 2.7 hours, 2 shares, 0 comments, 0 favorites, and 1 search. Let the behavioral evaluation parameters for game duration (wb1=1), share count (wb2=1), comment count (wb3=1), favorite count (wb4=1), and search count (wb5=1), then the candidate game C... m In the i-th historical period T i Game preference value B′(U j C m ,T i = 5.7.

[0074] For example, when the aforementioned users include user U1 and user U2, for the candidate game C... m The candidate game C m In the i-th historical period T i User behavior data can be found in Table 1.

[0075] Table 1 shows the users U1 and U2 in the i-th historical time period T. i User behavior data summary table

[0076]

[0077] At this point, let wb = (1,1,1,1,1), then we get the candidate game C. m In the i-th historical period T i User U1's preference value is B′(U1,C m ,Ti =5.7, Game C to be selected m In the i-th historical period T i User U2's preference value B′(U2,C) m ,T i = 2.7. Therefore, the candidate game C... m In the i-th historical period T i Preference value

[0078] Step 303: Based on the game preference values ​​of multiple candidate games in multiple historical periods, determine the game preference index of each candidate game in multiple historical periods.

[0079] The game preference index for each of the above candidate games in each historical period is positively correlated with the game preference value of the corresponding candidate game in the same historical period. The game preference index for each candidate game in each historical period is negatively correlated with the sum of the game preference values ​​of all candidate games in the same historical period. Let the user be U. j The candidate game is C. m Then the candidate game C m In T i Historical game preference metrics can be expressed as: In the formula,

[0080] B"(U j C m ,T i ) represents user U j Game C m In the i-th historical period T i The percentage of game preferences;

[0081] B′(U j C m ,T i ) represents user U j Game C m In the i-th historical period T i Game preference value;

[0082] Indicates user U j For each candidate game: game:{C0,C1,C2,..,C m} in the i-th historical period T i The sum of game preference values.

[0083] For example, when there is only one user, let user U be the user. j The game C0 is selected in the i-th historical period T. i Game preference value B′(U j ,C0,T i=5.7, where game C1 is in the i-th historical period T. i Game preference value B′(U j ,C1,T i If ) = 5.1, then the candidate game C0 is in the i-th historical time period T. i Game Preference Index B"(U j ,C0,T i ) = 0.53, the candidate game C1 in the i-th historical time period T i Game Preference Index B"(U j ,C1,T i = 0.47.

[0084] For example, when there are multiple users, the game preference index for each of the above candidate games in each historical period is the sum of the game preference indices of multiple users in the corresponding historical period. In this case, we can assume that all users are... Then all users Game C m In the i-th historical period T i The game preference index can be expressed as: In the formula,

[0085] Represents all users Game C m In the i-th historical period T i The sum of user preference percentages.

[0086] For example, suppose all users include user U1 and user U2, and the candidate games include candidate game C0 and candidate game C1. For candidate game C0 in the i-th historical time period T... i User U1's preference value is 5.7, and the candidate game C0 is in the i-th historical time period T. i User U2's preference value is 2.7, and the candidate game C1 is in the i-th historical time period T. i User U1's preference value is 5.1, and the candidate game C1 is in the i-th historical time period T. i If user U2's preference value is 19.4, then user U1's preference value for the selected game C0 in the i-th historical time period T is... i User preference percentage B"(U1,C0,T i = 0.53, user U1 is the player selecting game C1 in the i-th historical time period T. i User preference percentage B"(U1,C1,T i = 0.47, user U2 is in the i-th historical time period T of the selected game C0. i User preference percentage B"(U2,C0,T i= 0.12, user U2 is in the i-th historical time period T of the selected game C1. i User preference percentage B"(U2,C1,T i ) = 0.88. Therefore, users U1 and U2 have the same game C0 in the i-th historical time period T. i The game preference index is 0.65. Users U1 and U2 are considering game C1 in the i-th historical time period T. i The game preference index is 1.35.

[0087] Figure 4 A schematic flowchart illustrating a method for acquiring user behavior data across multiple historical time periods according to exemplary embodiments of the present disclosure is shown. Figure 4 As shown, the above-mentioned acquisition of user behavior data for each candidate game across multiple historical time periods based on user behavior information includes:

[0088] Step 401: Obtain historical behavior data for each candidate game across multiple historical time periods based on user behavior information for each candidate game.

[0089] In practical applications, user behavior information for each candidate game can be segmented according to the duration of historical time periods to obtain historical behavior data for each candidate game across multiple historical time periods.

[0090] For example, user behavior information for multiple candidate games can be obtained based on user behavior information of the target game. This target game user behavior information can include the user's playtime in the target game. Specifically, the target game user behavior information can include the user's earliest game record time, i.e., the earliest time the user entered the game platform and started playing the target game, recorded as 'start'. The current and last playtime of the target game is recorded as 'end'. Let the target game be C0. Then, the user's playtime 't' is the time difference between the earliest time the user entered the game platform and started playing the target game and the current and last playtime, which can be expressed as t = [start, end], i.e., user behavior information for multiple candidate games.

[0091] Then, the user behavior information t of the candidate games can be divided into multiple historical time periods according to t′ as the segmentation length, resulting in multiple historical time periods T:{T i ,0≤i≤k}. It should be understood that t′ is the segmentation length, and its segmentation unit can be selected according to the actual situation. For example, the user's playtime t can be segmented by hour, day, week, etc., and is not limited to these.

[0092] Step 402: If the historical behavior data meets the behavior data filtering criteria, determine that the historical behavior data is user behavior data. It should be understood that the behavior data filtering criteria here may include the presence of user behavior data for the target game in the historical behavior data for the corresponding historical period. That is, by determining that user behavior data for the target game exists in the historical behavior data for each historical period, the correlation between the candidate game and the target game can be obtained.

[0093] The aforementioned behavioral data filtering criteria may also include matching the duration of the historical time period corresponding to the historical behavioral data with a preset duration. It should be understood that the preset duration here can be the segmented duration of dividing the user behavior information of the candidate game into multiple historical time periods; this segmented duration can be set according to actual circumstances.

[0094] Because some historical behavioral data from multiple historical time periods may not contain user behavior data for the target game during those periods—meaning users didn't log into the game platform or logged in but didn't click on the target game—these historical periods are considered meaningless. Therefore, to improve processing speed and reduce interference from irrelevant information, these periods can be removed. Similarly, historical periods whose duration doesn't match the preset duration can also be removed to reduce computational load.

[0095] For example, let the target game be C0, and user U... j If the user entered the game platform on January 1st and started playing game C0, and the last time they played was June 1st, then t = 150 days. Dividing the user's playtime t into weeks, we obtain multiple historical time periods T:{T i Let T1 represent the 7 days between May 26th and June 1st, T2 represent the 7 days between May 19th and May 25th, and so on. This allows us to segment the user behavior information for each candidate game into historical behavior data for multiple historical time periods. Since k = 150 / 7 = 21.4, segmenting the user behavior information t for each candidate game using weeks as the unit yields 21 historical time periods. The remaining four days do not satisfy the segmentation time length t′, and since they are too far removed from the current time, they have little reference value and can be directly deleted. Then, we can determine whether the remaining 21 historical time periods contain user behavior data for the target game C0. Historical time periods containing user behavior data for the target game C0 are retained, while those not containing such data are deleted.

[0096] As one possible approach, when determining multiple candidate games based on historical game preference metrics of various candidate games, it is necessary to screen these multiple candidate games. That is, the multiple candidate games need to meet the game screening criteria, and the candidate games that meet the game screening criteria are determined as candidate games.

[0097] The game selection criteria mentioned above may include: if the historical game preference index of a candidate game is greater than the preset historical game preference index, the candidate game is determined as a candidate game. It should be understood that the preset historical game preference index can be determined according to the actual situation and is not limited here.

[0098] For example, a preset historical preference index can be set to 0.7. Historical preference indices greater than 0.7 can be selected from a variety of candidate games, and the selected games can be identified as candidate games.

[0099] The above game selection criteria may also include: sorting the candidate games in descending order of their historical game preference indices, and determining the top M candidate games, where M represents the total number of candidate games.

[0100] For example, the candidate games can be sorted in descending order of their historical game preference index, and the top M games can be selected as candidate games. Alternatively, the bottom 20% of the candidate games can be removed, and the remaining candidate games can be selected as candidate games.

[0101] As one possible implementation method, Figure 5 A schematic flowchart illustrating a method for determining the degree of association according to an exemplary embodiment of this disclosure is shown. Figure 5 As shown, the above method also includes:

[0102] Step 501: Obtain user game information from multiple historical time periods based on the target game's user information. Each historical time period includes the target game and candidate games played during that period. By obtaining the user game information for both the target and candidate games for each historical time period, a correlation between the target and candidate games can be established. This allows for the recommendation of candidate games that match user preferences and have a high degree of relevance to the target game when it is about to be removed from the platform, thereby improving user retention on the gaming platform.

[0103] Step 502: Based on the user's game playing information for each historical time period, determine the undirected graph of the target game for the corresponding historical time period. It's important to note that when there is only one user, the undirected graph for that user in each historical time period can be determined based on that single user's game playing information. When there are multiple users, the undirected graph for each user in each historical time period can be determined first, and then these graphs can be merged to determine the undirected graph for all users in each historical time period.

[0104] Figure 6 This illustrates a user U1 in the i-th historical time period T according to an exemplary embodiment of this disclosure. i Game undirected graph, Figure 7 This illustrates user U2 in the i-th historical time period T according to an exemplary embodiment of this disclosure. i An undirected graph of a game. For example... Figure 6 and Figure 7 As shown, let user U1 be in the i-th historical time period T i The game list is {C0, C1, C3, C5}, and user U2 is in the i-th historical time period T. i If the game list is {C0, C1, C2}, then the corresponding undirected game graph can be constructed using this game list as the nodes. Here, the degree of each node in the undirected game graph is set to the number of games minus 1, and the edge weight is 1.

[0105] Figure 8 The i-th historical time period T according to an exemplary embodiment of this disclosure is shown. i An undirected graph of the games of all users. For example... Figure 8 As shown, Figure 6 and Figure 7 The game's undirected graph will be merged, and soon... Figure 7 Add nodes and edges to Figure 6 In the context of edge e(C0,C1), for the same edge e(C0,C1), the weight of edge e(C0,C1) is w(C0,C1)+1=2; for the newly added point C2, in Figure 6 Add point C2, and in Figure 7 The edges e(C2,C0) and e(C2,C1) connected to C2 are updated to... Figure 8 .

[0106] Step 503: Based on the undirected game graph of each target game's users in the corresponding historical time period and the corresponding game progress decay parameter, determine the game association graph of the target game's users. By assigning different weights to the undirected game graphs in different historical time periods through the game progress decay parameter, the game association graph can better represent the correlation between the candidate game and the target game, reducing data computation.

[0107] In practical applications, the game association graph of users of different target games can be obtained by multiplying the undirected graph of each target game user in the corresponding historical period with its game progress decay parameter.

[0108] For example, such as Figure 8 As shown, when f(i) = 1, the weight of edge e(C0,C1) is 2 and the weight of other edges is 1. Multiplying each edge by the progress decay coefficient f(i) determines that in the updated undirected game graph, the weight of edge e(C0,C1) is 2 and the weight of other edges is 1.

[0109] Step 504: Determine the association degree between the target game and multiple candidate games based on the edge weight information of the game association graph of the target game's users, that is, calculate the support degree between the target game and multiple candidate games, as well as the confidence degree between the target game and multiple candidate games.

[0110] For example, the support of the target game among multiple candidate games is inversely proportional to the sum of the weights of all edges in the game association graph of the target game's users, and directly proportional to the weights of the candidate games and the target game. This can be expressed by the formula:

[0111] In the formula:

[0112] w(C m1 (C0) represents candidate game C m1 The weight of the target game C0;

[0113] w(G) represents the sum of the weights of all edges in the game association graph of the users in the target game C0.

[0114] The confidence score between the target game and multiple candidate games is inversely proportional to the sum of the weights of all edges between the target game and each candidate game in the game association graph of the target game's users, and directly proportional to the weights of the candidate games and the target game. This can be expressed by the formula:

[0115] In the formula,

[0116] w(C m1 (C0) represents candidate game C m1 The weight of the target game C0;

[0117] ∑ C∈game w(C0,C) represents the sum of the weights of all edges between the target game and each candidate game in the game association graph.

[0118] After determining the correlation between the target game and multiple candidate games, recommended games can be obtained from the candidate games based on this correlation. Specifically, obtaining recommended games can include: First, based on the confidence level of the candidate games towards the target game, selecting candidate games with a confidence level greater than a preset confidence level as pre-recommended games. It should be understood that this preset confidence level can be adjusted in a timely manner according to actual circumstances and is not limited here. After obtaining the pre-recommended games, they can be directly ranked according to their correlation with the target game, or they can be ranked based on the support level of the candidate games towards the target game, and then the ordered recommended games can be recommended to the user.

[0119] The recommended game determination method of this exemplary embodiment determines the recommended game by using the user's historical game preference index for different candidate games and the correlation between different candidate games and the target game. This makes the obtained recommended games more in line with the user's game preferences. When the recommended game is recommended to the user, the user can accept the recommended game more quickly and play it, thereby avoiding the problem of a large number of users being lost due to the removal of the target game.

[0120] The foregoing primarily describes the solutions provided by the embodiments of this disclosure from the perspective of the server. It is understood that, in order to implement the above functions, the server includes the corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0121] This disclosure embodiment can divide the server into functional units according to the above method example. For example, it can divide each function into a separate functional module, or it can integrate two or more functions into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0122] In the case of dividing each functional module according to its corresponding function, an exemplary embodiment of this disclosure provides a device for determining recommended games, which can be a server or a chip applied to a server. Figure 9A schematic block diagram of the functional modules of a game recommendation determination device according to an exemplary embodiment of the present disclosure is shown. Figure 9 As shown, the device 900 for determining the recommended game includes:

[0123] The acquisition module 901 is used to acquire game preference indicators for multiple historical time periods based on user information of the target game.

[0124] The determination module 902 is used to determine the historical game preference index of the corresponding candidate game based on the game preference index of each candidate game in multiple historical periods and the corresponding game progress decay parameter.

[0125] The determination module 902 is also used to determine multiple candidate games based on historical game preference indicators of various candidate games.

[0126] The acquisition module 901 is also used to acquire recommended games from multiple candidate games based on the correlation between the target game and multiple candidate games.

[0127] As one possible implementation, the above-mentioned acquisition of game preference indicators for multiple historical time periods based on user information of the target game includes:

[0128] The acquisition module 901 is used to acquire user behavior information of multiple candidate games based on the user information of the target game;

[0129] The determination module 902 is used to determine the game preference index of the corresponding candidate game in multiple historical periods based on the user behavior information and corresponding behavior evaluation parameters of each candidate game.

[0130] In some alternative approaches, the aforementioned user behavior information includes multiple attribute behavior data, and the behavior evaluation parameters include multiple behavior evaluation parameters, each of which is used to measure the importance of the corresponding attribute behavior data.

[0131] In some alternative methods, the above-mentioned determination of game preference indicators for each candidate game across multiple historical time periods is based on user behavior information and corresponding behavior evaluation parameters for each candidate game, including:

[0132] The acquisition module 901 is used to acquire user behavior data of the corresponding candidate game in multiple historical time periods based on the user behavior information of each candidate game.

[0133] Module 902 is used to determine the game preference value of a candidate game in multiple historical periods based on user behavior data and corresponding behavior evaluation parameters of multiple candidate games in multiple historical periods. Based on the game preference values ​​of multiple candidate games in multiple historical periods, the game preference index of each candidate game in multiple historical periods is determined.

[0134] In some alternative methods, the above-mentioned acquisition of user behavior data for each candidate game across multiple historical time periods based on user behavior information for each candidate game includes:

[0135] The acquisition module 901 is used to acquire historical behavior data of each candidate game in multiple historical time periods based on the user behavior information of each candidate game.

[0136] If the historical behavior data meets the behavior data filtering criteria, module 902 is used to determine that the historical behavior data is user behavior data.

[0137] In some optional methods, the above behavioral data filtering criteria include: historical behavioral data containing user behavior data of the target game during the corresponding historical period; and / or,

[0138] The duration of the historical time period corresponding to the historical behavior data matches the preset duration.

[0139] In some alternative approaches, the game preference index for each of the above candidate games in each historical period is positively correlated with the game preference value of the corresponding candidate game in the corresponding historical period.

[0140] The game preference index for each candidate game in each historical period is negatively correlated with the sum of the game preference values ​​of each candidate game in the corresponding historical period.

[0141] In some alternative methods, the aforementioned game progress decay parameter is positively correlated with the game progress of the corresponding candidate game in the corresponding historical period, and negatively correlated with the order of the historical periods of the corresponding candidate game in the corresponding historical period.

[0142] As one possible implementation, the above method identifies multiple candidate games based on historical game preference metrics of various candidate games, including:

[0143] If the historical game preference index of the candidate game is greater than the preset historical game preference index, the determination module 902 is used to determine the candidate game as a candidate game.

[0144] As one possible implementation, the above-mentioned method of identifying multiple candidate games based on historical game preference indicators of various candidate games also includes:

[0145] The candidate games are sorted in descending order of their historical game preference indices. Module 902 is also used to determine the top M candidate games, where M represents the total number of games less than the number of candidate games.

[0146] As one possible implementation, the above method also includes:

[0147] The acquisition module 901 is used to acquire user game information for multiple historical time periods based on the user information of the target game. The user game information for each historical time period includes the target game and candidate games for playing in the corresponding historical time period.

[0148] Module 902 is used to determine the undirected game graph of the target game's users in the corresponding historical time period based on user game information for each historical time period. Based on the undirected game graph of the target game's users in the corresponding historical time period and the corresponding game progress decay parameters, it determines the game association graph of the target game's users. Based on the edge weight information of the target game's user game association graph, it determines the association degree between the target game and multiple candidate games.

[0149] In some alternative approaches, the aforementioned correlation includes the support level of the candidate game for the target game and the confidence level of the candidate game for the target game; based on the correlation between the target game and multiple candidate games, recommended games are obtained from multiple candidate games, including:

[0150] The acquisition module 901 is used to obtain candidate games with a confidence level greater than a preset confidence level from multiple candidate games based on the confidence level of the candidate games against the target game, and to pre-recommend the candidate games.

[0151] The aforementioned device for determining recommended games also includes a sorting module 903, which sorts the pre-recommended games based on the degree of support of the candidate games for the target game.

[0152] Figure 10 A schematic block diagram of a chip according to an exemplary embodiment of the present disclosure is shown. Figure 10 As shown, the chip 1000 includes one or more (including two) processors 1001 and a communication interface 1002. The communication interface 1002 can support the server in performing the data transmission and reception steps in the above-described image processing method, and the processor 1001 can support the server in performing the data processing steps in the above-described image processing method.

[0153] Optional, such as Figure 10 As shown, the chip 1000 also includes a memory 1003, which may include read-only memory and random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include non-volatile random access memory (NVRAM).

[0154] In some implementations, such as Figure 10As shown, processor 1001 executes corresponding operations by calling operation instructions stored in memory (which may be stored in the operating system). Processor 1001 controls the processing operations of any terminal device; processor can also be called a central processing unit (CPU). Memory 1003 may include read-only memory and random access memory, and provides instructions and data to processor 1001. A portion of memory 1003 may also include NVRAM. For example, in applications, memory, communication interfaces, and other components are coupled together via a bus system, which may include, in addition to a data bus, a power bus, a control bus, and a status signal bus, etc. However, for clarity, in... Figure 10 The general labeled all buses as Bus System 1004.

[0155] The methods disclosed in the embodiments of this disclosure can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0156] Exemplary embodiments of this disclosure also provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the electronic device to perform a method according to an embodiment of this disclosure.

[0157] Exemplary embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to embodiments of this disclosure.

[0158] Exemplary embodiments of this disclosure also provide a computer program product, including a computer program, wherein, when executed by a processor of a computer, the computer program is used to cause the computer to perform a method according to an embodiment of this disclosure.

[0159] refer to Figure 11 The present invention describes a structural block diagram of an electronic device 1100 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0160] like Figure 11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of the device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0161] Multiple components in electronic device 1100 are connected to I / O interface 1105, including: input unit 1106, output unit 1107, storage unit 1108, and communication unit 1109. Input unit 1106 can be any type of device capable of inputting information to electronic device 1100. Input unit 1106 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 1107 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1108 may include, but is not limited to, disk and optical disk. Communication unit 1109 allows electronic device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0162] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above. For example, in some embodiments, the methods of the exemplary embodiments of this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1100 via ROM 1102 and / or communication unit 1109. In some embodiments, the computing unit 1101 can be configured to perform the methods of the exemplary embodiments of this disclosure by any other suitable means (e.g., by means of firmware).

[0163] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0164] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0165] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0167] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0168] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0169] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this disclosure are performed, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center integrating one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); or it can be a semiconductor medium, such as a solid-state drive (SSD).

[0170] Although this disclosure has been described in conjunction with specific features and embodiments, it will be apparent that various modifications and combinations can be made therein without departing from the spirit and scope of this disclosure. Accordingly, this specification and drawings are merely exemplary illustrations of the disclosure as defined by the appended claims and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this disclosure. It is obvious that those skilled in the art can make various alterations and modifications to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include any such modifications and modifications that fall within the scope of the claims of this disclosure and their equivalents.

Claims

1. A method for determining recommended games, characterized in that, The method includes: Based on the user information of the target game, obtain user behavior information for multiple candidate games; Based on user behavior information and corresponding behavior evaluation parameters for each candidate game, game preference indicators for the candidate game in multiple historical periods are determined. Based on the game progress decay parameter corresponding to the game preference index of each of the candidate games in the plurality of historical time periods, a weight is assigned to the game preference index of each of the plurality of historical time periods, and the game preference indices of the plurality of historical time periods with different weights are added together to determine the historical game preference index of the candidate game. The game progress decay parameter is positively correlated with the game progress of the candidate game in the corresponding historical time period, and the game progress decay parameter is negatively correlated with the order of the historical time periods of the candidate game in the corresponding historical time periods. Multiple candidate games were determined based on various historical game preference indicators of the candidate games; The recommended game is obtained from the multiple candidate games based on the correlation between the target game and the multiple candidate games.

2. The method according to claim 1, characterized in that, The process of determining game preference indicators for each candidate game across multiple historical time periods based on user behavior information and corresponding behavior evaluation parameters for each candidate game includes: Based on the user behavior information of each candidate game, obtain the user behavior data of the corresponding candidate game in multiple historical time periods; Based on user behavior data and corresponding behavior evaluation parameters of various candidate games in multiple historical periods, determine the game preference value of the corresponding candidate game in multiple historical periods; Based on the game preference values ​​of the various candidate games in multiple historical periods, a game preference index for each candidate game in multiple historical periods is determined.

3. The method according to claim 2, characterized in that, The step of obtaining user behavior data for each candidate game across multiple historical time periods based on user behavior information for each candidate game includes: Based on the user behavior information of each of the candidate games, obtain historical behavior data of each of the candidate games in multiple historical time periods; If the historical behavior data meets the behavior data filtering criteria, the historical behavior data is determined to be the user behavior data.

4. The method according to claim 3, characterized in that, The behavioral data filtering criteria include: The historical behavior data includes user behavior data of the target game during the corresponding historical time period; and / or The duration of the historical time period corresponding to the historical behavior data matches a preset duration; and / or, The user behavior information includes multiple attribute behavior data, and the behavior evaluation parameters include multiple behavior evaluation parameters, each of which is used to measure the importance of the corresponding attribute behavior data; and / or, The game preference index of each candidate game in each historical period is positively correlated with the game preference value of the corresponding candidate game in the corresponding historical period. The game preference index of each candidate game in each historical period is negatively correlated with the sum of the game preference values ​​of each candidate game in the corresponding historical period.

5. The method according to any one of claims 1 to 4, characterized in that, The process involves determining multiple candidate games based on historical game preference metrics of the candidate games, including: If the historical game preference index of the candidate game is greater than the preset historical game preference index, the candidate game is determined as a candidate game; and / or, The process of determining multiple candidate games based on historical game preference indicators of the candidate games also includes: The candidate games are sorted in descending order of their historical game preference indices, and the top M games are determined, where M represents the total number of games with indices less than the top M games; and / or, The method further includes: Based on the user information of the target game, obtain user game information for multiple historical time periods. The user game information for each historical time period includes the target game and candidate games for playing in the corresponding historical time period. Based on the user's game information for each historical period, determine the undirected graph of the target game's users' games in the corresponding historical period; Based on the undirected game graph of each user of the target game in the corresponding historical time period and the corresponding game progress decay parameter, the game association graph of the users of the target game is determined. The correlation between the target game and multiple candidate games is determined based on the edge weight information of the game association graph of the target game's users.

6. The method according to claim 5, characterized in that, The correlation includes the support level of the candidate games for the target game and the confidence level of the candidate games for the target game; the step of obtaining the recommended game from the multiple candidate games based on the correlation between the target game and the multiple candidate games includes: Based on the confidence level of the candidate games against the target game, candidate games with a confidence level greater than a preset confidence level are selected from multiple candidate games as pre-recommended games; The pre-recommended games are ranked based on the degree of support the candidate games have for the target game.

7. A device for determining recommended games, characterized in that, The device includes: The acquisition module is used to obtain user behavior information for multiple candidate games based on the user information of the target game; The determination module is used to determine the game preference index of the candidate game in multiple historical time periods based on the user behavior information and corresponding behavior evaluation parameters of each candidate game; The determining module is further configured to assign weights to the game preference indicators of each of the multiple historical periods based on the game progress decay parameter corresponding to the game preference indicator of each of the multiple historical periods for each of the candidate games, and to add the game preference indicators of the multiple historical periods with different weights to determine the historical game preference indicator corresponding to the candidate game. The game progress decay parameter is positively correlated with the game progress of the corresponding candidate game in the corresponding historical period, and the game progress decay parameter is negatively correlated with the order of the historical periods of the corresponding candidate game in the corresponding historical periods. The determining module is also used to determine multiple candidate games based on various historical game preference indicators of the candidate games; The acquisition module is also used to acquire the recommended game from the multiple candidate games based on the correlation between the target game and the multiple candidate games.

8. An electronic device, characterized in that, include: processor; as well as, Memory for stored programs; The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method according to any one of claims 1-6.

Images