Information processing method and device, electronic equipment, storage medium and program product

Abstract

The invention discloses an information processing method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of games. The method comprises the following steps: acquiring game data corresponding to a user in a first historical duration in a target game; wherein the game data comprises resource acquisition information and game interaction behavior information; determining a state evaluation value corresponding to the user according to the resource acquisition information; wherein the state evaluation value is used for representing an adverse state of the resource acquisition behavior of the user; according to the game interaction behavior information, the retention probability of the target game by the user is determined; and determining an intervention level for the user according to the state evaluation value and the retention probability, and triggering a corresponding game interaction function for the user according to the intervention level. According to the technical scheme, the effects that the intervention level of the user is determined according to the state evaluation value of the user and the retention probability multi-dimensional index, and the game interaction function is triggered based on intervention level differentiation are achieved.

Description

Technical Field

[0001] This invention relates to the field of game technology, and in particular to an information processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In the gaming industry, acquiring high-value items with a high probability of success is a crucial source of core player enjoyment. Conversely, failing to obtain such items for an extended period can lead to a lack of positive feedback for players, ultimately causing churn.

[0003] In related technologies, existing player retention solutions typically determine whether a player is at risk of churn by counting the number of consecutive times a player fails to draw a high-value reward, and then award corresponding achievement titles to churned players, giving them a sense of accomplishment from another perspective. However, this player retention method may suffer from problems such as a single judgment dimension, rewards lacking substantial value and targeted care, thus failing to accurately respond to players' core needs to achieve effective retention. Summary of the Invention

[0004] This invention provides an information processing method, apparatus, electronic device, storage medium, and program product to determine the user's intervention level based on multi-dimensional indicators such as the user's status assessment value and retention probability, and to trigger game interaction functions based on the differentiated intervention level.

[0005] According to one aspect of the present invention, an information processing method is provided, the method comprising:

[0006] Acquire game data corresponding to a user in a target game within a first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information; the resource acquisition information includes the resource acquisition behavior participated in by the user in the target game and / or the resource feedback result information received; the game interaction behavior information includes the specified game behavior information performed by the user in the target game;

[0007] Based on the resource acquisition information, a status evaluation value is determined for the user; wherein the status evaluation value characterizes the unfavorable state of the user's resource acquisition behavior; and,

[0008] Based on the game interaction behavior information, determine the user's retention probability of the target game;

[0009] Based on the status assessment value and the retention probability, the intervention level for the user is determined, and the corresponding game interaction function for the user is triggered according to the intervention level.

[0010] According to another aspect of the present invention, an information processing apparatus is provided, the apparatus comprising:

[0011] An information acquisition module is used to acquire game data corresponding to a user in a target game within a first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information; the resource acquisition information includes the resource acquisition behavior participated in by the user in the target game and / or the resource feedback result information received; the game interaction behavior information includes the specified game behavior information performed by the user in the target game;

[0012] A status assessment value determination module is used to determine a status assessment value corresponding to the user based on the resource acquisition information; wherein, the status assessment value is used to characterize the unfavorable state of the user's resource acquisition behavior; and,

[0013] The retention probability determination module is used to determine the user's retention probability of the target game based on the game interaction behavior information.

[0014] The intervention level determination module is used to determine the intervention level for the user based on the status evaluation value and the retention probability, and to trigger the corresponding game interaction function for the user based on the intervention level.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the information processing method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the information processing method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the information processing method described in any embodiment of the present invention.

[0021] The technical solution of this invention acquires game data corresponding to a user in a target game within a first historical time period. This game data includes resource acquisition information and game interaction behavior information, providing core data support for subsequent matching of differentiated incentive processing strategies. Furthermore, by determining the user's corresponding state evaluation value based on resource acquisition information, it achieves precise quantification of the user's unfavorable state in resource acquisition behavior within the target game. Further, by determining the user's retention probability in the target game based on game interaction behavior information, it achieves precise quantification of the user's retention intention within the target game. Furthermore, by determining the intervention level for the user based on the state evaluation value and retention probability, and triggering corresponding game interaction functions for the user based on the intervention level, it achieves precise targeted incentives based on the user's unfavorable state in resource acquisition behavior and retention intention. Through the matching of differentiated game interaction functions, it not only specifically reduces the player's negative experience but also effectively reduces the risk of churn, while simultaneously improving the utilization efficiency of game incentive resources and player retention rate. The technical solution of this invention solves the problems existing in related technologies, such as a single judgment dimension, lack of substantial value in rewards and no targeted care, which makes it impossible to accurately respond to the core needs of players and achieve effective retention. It realizes the accurate quantification of the user's status evaluation value and retention intention based on the dual-dimensional information of the user's resource acquisition behavior and game interaction behavior. Through the targeted triggering of differentiated game interaction functions, it accurately responds to the user's substantial needs, which not only improves the user's game experience and retention rate, but also optimizes the allocation efficiency of game incentive resources.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of an information processing method provided according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of an information processing method provided according to an embodiment of the present invention;

[0026] Figure 3 This is a flowchart of an information processing method provided according to an embodiment of the present invention;

[0027] Figure 4 This is a flowchart of an information processing method provided according to an embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of an information processing device according to an embodiment of the present invention;

[0029] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the information processing method of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] It's important to note that for massively multiplayer online role-playing games (MMORPGs), a genre that relies on long-term player interaction and emotional investment, player retention is directly related to the experience of receiving high-value, low-probability items (such as rare characters and top-tier equipment). In these games, obtaining low-probability, high-value rewards is a key mechanism for triggering core player enjoyment and a sense of return on investment. When players fail to obtain their desired items for an extended period in probabilistic gameplay, such as gacha games, their investment fails to translate into the expected positive feedback, easily leading to negative emotions and becoming a core factor causing player churn.

[0033] Existing player retention solutions mainly fall into two categories: one is an incentive mechanism that awards achievement titles based on the number of consecutive times a player fails to obtain high-value items, and the other is a compensation mechanism that provides high-value items to returning players after churning. However, the former only provides honorary rewards and does not specifically address players with a high churn risk, while the latter intervenes too late and is unable to bridge the gap in player progress. Furthermore, neither solution combines "status assessment value" (quantifying the accumulated state of not obtaining high-value resources, commonly known as "unlucky score") and "player stickiness" to build a personalized intervention mechanism, thus failing to accurately solve the player churn problem. Therefore, a dynamically adaptable personalized care system is urgently needed to improve the retention rate of players at high churn risk.

[0034] To address the aforementioned issues, this invention provides an information processing method that precisely quantifies players' "accumulated resource unacquired value" and "player stickiness" in probabilistic gameplay, constructing a dynamically adaptable personalized care system. This allows intervention mechanisms to be deeply integrated into the game's emotional experience, thereby enhancing the player's gaming experience and increasing player retention.

[0035] Figure 1 This is a flowchart of an information processing method provided by an embodiment of the present invention. This embodiment is applicable to situations where corresponding game interactive functions are matched to a user in a target game. This method can be executed by an information processing device, which can be implemented in hardware and / or software, and can be configured in a terminal and / or server. Figure 1 As shown, the method includes:

[0036] S110. Obtain the game data corresponding to the user in the target game within the first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information.

[0037] The target game can be an electronic game product with resource extraction gameplay and scene interaction functions. The target game can be the platform through which players perform resource extraction and scene interaction operations. Optionally, the target game includes, but is not limited to, massively multiplayer online role-playing games (MMORPGs), card games, competitive games, and other digital virtual interactive products. Users can be players in the target game, and these players can be the subjects of retention analysis. Users can include all players with interaction records in the target game, including at least one of registration records, login records, and interaction operation records; or, users can also include selected players in the target game who need to be analyzed for retention. The first historical duration can refer to a preset time period for collecting user operation data. The first historical duration can be used to limit the data collection scope, ensuring that the game data used for analysis is timely and relevant. The first historical duration can be set by the game operator based on gameplay characteristics or user lifecycle. Optionally, the first historical duration includes 7 days, 15 days, 30 days, and 90 days. Game data refers to the complete set of data generated by a user within a specific historical timeframe within a target game, directly related to their gameplay. Game data can include resource acquisition information and game interaction behavior information.

[0038] Resource acquisition information refers to the set of related data generated by a user within a first historical timeframe in a probabilistic resource acquisition scenario within the target game. A probabilistic resource acquisition scenario can be understood as a core gameplay module or functional scenario set up in the target game, based on a preset probability distribution model to randomly allocate incentive resources. It is a specific game interaction scenario where a user initiates a resource acquisition operation and receives feedback information. The core characteristic of a probabilistic resource acquisition scenario is that the resource acquisition result is not deterministic, but rather randomly and dynamically determined by the game system's preset probability rules (such as the drop rate of rare resources, the distribution ratio of item quality, etc.). Players actively trigger resource acquisition operations to obtain target incentive resources. For example, probabilistic resource acquisition scenarios include, but are not limited to, in-game card acquisition systems (such as character card pools, item card pools), treasure chest / gift pack opening functions, dungeon drop trigger mechanisms, random result mechanisms for resource synthesis / unlocking, and limited-time item acquisition events. The incentive resources obtainable in probabilistic resource acquisition scenarios cover core value items within the target game, including but not limited to high-rarity characters / pets, top-tier equipment, limited-edition appearances, advancement materials, game currency, and other virtual items with usable or collectible value. In this embodiment, resource acquisition information can be used to characterize the resource extraction operations input by the user in the target game and / or the extraction feedback information received. Resource acquisition information includes the resource acquisition behaviors the user participates in in the target game and / or the resource feedback result information received. Resource acquisition behavior can refer to trigger operation data initiated by the user to acquire in-game incentive resources (such as card acquisition operations, item unlocking operations, dungeon drop trigger operations, etc., including operation timestamps, number of operations, type and quantity of game resources consumed per operation, etc.). Resource acquisition behavior can refer to interactive operations actively triggered by the user through the game interface with the goal of acquiring in-game incentive resources. Resource feedback result information can refer to the result response data returned by the game system for the user's resource acquisition behavior, used to characterize the final resource acquisition result of the resource acquisition behavior, and is the direct basis for determining whether the expected acquisition result has been achieved. Resource acquisition information can include multiple pieces of information related to resource acquisition behavior and / or resource feedback result information. Optionally, resource acquisition information can include at least one of the following: number of failed resource acquisitions, resource consumption corresponding to the resource acquisition behavior, acquisition probability deviation value, and remaining threshold for guaranteed triggers.

[0039] The number of failed resource acquisitions refers to the cumulative number of times a user, within the first historical timeframe, initiated a resource acquisition action in a probabilistic resource acquisition scenario, and the feedback result was that the user failed to obtain the target incentive resource. In other words, the number of failed resource acquisitions can be considered the total frequency of resource acquisition actions that did not achieve the expected acquisition result. The number of failed resource acquisitions can be used to quantify the frequency of negative feedback from users in probabilistic gameplay. The resource consumption corresponding to the resource acquisition action can refer to the cumulative total of incentive resources transferred by the user to the game system within the first historical timeframe in order to initiate a resource acquisition action targeting the target incentive resource. The transferred incentive resources can include, but are not limited to, in-game incentive resources (such as game currency), special draw items, and advancement materials—virtual items with in-game value. The total amount of resources transferred to acquire the target incentive resource can be used to characterize the scale of cost invested by the user in acquiring the target incentive resource. The target incentive resource can be the object that the user expects to acquire in the probabilistic resource acquisition scenario of the target game. The target incentive resource can be a high-value resource preset by the game system (such as high-rarity characters, items, etc.), or an incentive resource that meets the player's expected resource acquisition needs. The probability deviation value refers to the quantitative difference between the probability of a user obtaining the target incentive resource and the average probability of obtaining the target incentive resource on the server during the same period. The probability deviation value characterizes the degree of negative deviation between the user's resource acquisition probability and the server's average resource acquisition probability during the same period. The larger the probability deviation value, the greater the negative deviation between the user's resource acquisition probability and the server's average resource acquisition probability during the same period (i.e., the user's luck is worse than the server average). The remaining threshold for the guaranteed trigger refers to the quantitative difference (or remaining percentage) between the number of times a user has currently attempted to obtain the target incentive resource and the guaranteed trigger threshold (i.e., the minimum number of attempts required to trigger the guaranteed trigger mechanism). In other words, the remaining threshold for the guaranteed trigger characterizes the closeness between the number of times a user has currently attempted to obtain the target resource and the guaranteed trigger threshold. For example, if the guaranteed trigger threshold for the target resource is 100 times (i.e., it is guaranteed to be obtained after 100 attempts), and the user has failed to obtain it after 85 attempts, then the remaining threshold for the guaranteed trigger is 15 times (or the remaining percentage is 15%). This is used to characterize how close the user is to "certainly obtaining the target incentive resource". The smaller the remaining threshold, the stronger the user's "expectation disappointment".

[0040] Game interaction behavior information refers to the set of active operation data generated by users in various core gameplay scenarios (such as dungeon challenges, social interactions, daily tasks, competitive battles, etc.) of the target game within the first historical time period. Game interaction behavior information includes specific game behavior information performed by users in the target game. Specific game behavior information refers to non-resource acquisition operations initiated by users in the virtual scene of the target game (such as logging into the game, participating in dungeons, teaming up with other players, completing daily tasks, sending social messages, etc.), which is a core component of scene interaction information and reflects the user's level of participation and dependence on the game. For example, game interaction behavior information may include the number of game friends, guild contribution ranking, team duration, message sending frequency, number of team members, character's overall cultivation value, cultivation increase amount, cultivation increase times, equipment rating, pet rating, rare appearance collection rate, achievement points, number of gameplay types participated in, number of days participated in each gameplay type, participation frequency of each gameplay type, total resource transfer amount, number of resource transfers, and resource transfer frequency, etc.

[0041] In one implementation, for users in the target game, resource acquisition information and game interaction behavior information of users within a first historical period can be obtained based on the user's game logs in the target game. Furthermore, the user retention status in the target game can be analyzed based on the resource acquisition information and game interaction behavior information.

[0042] S120. Determine the corresponding status evaluation value for the user based on the resource acquisition information.

[0043] The status evaluation value can be understood as a dynamic, cumulative parameter determined based on resource acquisition information, used to quantify the user's failure to achieve the expected acquisition result. The status evaluation value can be used to characterize the unfavorable state of a user's resource acquisition behavior. In other words, the status evaluation value can be used to characterize the cumulative state of negative feedback in probabilistic gameplay. The status evaluation value can be used to quantify the cumulative state of not obtaining high-value resources, commonly known as the "unlucky value." The expected acquisition result can be understood as the acquisition result that satisfies the user's resource acquisition needs, such as obtaining high-value rare items.

[0044] In this embodiment, the user's resource acquisition information within the first historical time period can characterize the user's resource acquisition status within that period. Furthermore, to further summarize and quantify the user's resource acquisition status within the first historical time period, the resource acquisition information can be processed according to a preset state evaluation value determination method to obtain a state evaluation value corresponding to the user. The state evaluation value determination method may include at least one of the following: weighted summation; processing the resource acquisition information using a state evaluation value determination model; or cumulative calculation.

[0045] Optionally, the resource acquisition information includes the number of resource acquisition failures, the resource consumption corresponding to the resource acquisition behavior, the acquisition probability deviation value, and the remaining threshold for the minimum trigger. Based on the resource acquisition information, a status evaluation value corresponding to the user is determined, including: determining a first weight corresponding to the number of resource acquisition failures, a second weight corresponding to the resource consumption, a third weight corresponding to the acquisition probability deviation value, and a fourth weight corresponding to the remaining threshold for the minimum trigger. The number of resource acquisition failures, the first weight, the resource consumption, the second weight, the acquisition probability deviation value, the third weight, the remaining threshold for the minimum trigger, and the fourth weight are calculated through a weighted summation operation to obtain the status evaluation value corresponding to the user.

[0046] The first weight can refer to a quantitative coefficient preset by the game system to adjust the contribution of the number of failed resource acquisitions in the state evaluation value calculation. The value of the first weight can be set by the game system according to the "negative impact of the number of failed resource acquisitions on the player" (e.g., the higher the number of failed resource acquisitions, the greater the negative impact, and the higher the first weight). The core function of the first weight is to adapt the quantitative data of the number of failed resource acquisitions to the comprehensive evaluation logic through weight scaling, avoiding an excessively high proportion of a single dimension. The first weight can be any value, such as 0.1, 0.2, or 0.3. The second weight can refer to a quantitative coefficient preset by the game system to adjust the contribution of the resource consumption corresponding to the resource acquisition behavior in the state evaluation value calculation. The value of the second weight can be set by the game system according to the "impact of resource consumption on the player's perceived return on investment" (e.g., the higher the resource consumption, the stronger the negative feedback from the player, and the higher the second weight). The core function of the second weight is to balance the influence weights of the investment cost dimension and other dimensions, ensuring that the calculation results comprehensively reflect the player's investment experience. The second weight can be any value, such as 0.1, 0.2, or 0.3. The third weight can refer to a quantitative coefficient preset by the game system to adjust the contribution of the acquisition probability deviation value in the state evaluation value calculation. The value of the third weight can be set by the game system according to the "impact of the acquisition probability deviation value on the player's game experience" (e.g., the larger the acquisition probability deviation value, the worse the player's game experience, and the higher the third weight). The core function of the third weight is to highlight the impact of the player's differentiated acquisition probability on the unacquired accumulated state, and improve the differentiated adaptability of the calculation results. The third weight can be any value, selectable, such as 0.1, 0.2, or 0.3, etc. The fourth weight can refer to a quantitative coefficient preset by the game system to adjust the contribution of the remaining threshold of the guaranteed trigger in the state evaluation value calculation. The value of the fourth weight can be set by the game system according to the "intensity of expected negative feedback close to the guaranteed trigger" (e.g., the smaller the remaining threshold of the guaranteed trigger, the stronger the expected negative feedback, and the higher the fourth weight). The core function of the fourth weight is to quantify the user's emotional experience into a calculable weight factor, making the results more consistent with the user's psychological state. The fourth weight can be any value, selectable, such as 0.1, 0.2, or 0.3, etc.

[0047] It should be noted that the sum of the first weight, the second weight, the third weight, and the fourth weight can be one.

[0048] In practical applications, determining a user's status assessment value typically involves statistically analyzing the number of resource acquisition failures within the first historical timeframe and using the results as the user's status assessment value. However, this method, relying solely on the number of resource acquisition failures, may result in low accuracy of the status assessment value and discrepancies between the determined value and the user's actual game state.

[0049] To address the above issues, this embodiment utilizes multi-dimensional data, including the number of failed resource acquisitions, the resource consumption corresponding to the acquisition behavior, the acquisition probability deviation, and the remaining threshold for the guaranteed trigger, to determine the user's status assessment value. This improves the accuracy of the status assessment value, making it more closely reflect the user's actual game state.

[0050] In one implementation, a first weight corresponding to the number of resource acquisition failures, a second weight corresponding to the resource consumption, a third weight corresponding to the acquisition probability deviation, and a fourth weight corresponding to the remaining threshold for the guaranteed trigger can be determined. Further, the number of resource acquisition failures, the total amount of resources transferred to acquire the target incentive resource, the acquisition probability deviation, and the remaining threshold for the guaranteed trigger can be normalized to obtain normalized resource acquisition failures, resource consumption, acquisition probability deviation, and the remaining threshold for the guaranteed trigger. Further, the product between the normalized number of resource acquisition failures and the first weight can be determined to obtain a first value; the product between the normalized resource consumption and the second weight can be determined to obtain a second value; the product between the normalized acquisition probability deviation and the third weight can be determined to obtain a third value; and the product between the normalized remaining threshold for the guaranteed trigger and the fourth weight can be determined to obtain a fourth value. Further, the first, second, third, and fourth values ​​can be added together, and the sum can be used as the status evaluation value corresponding to the user.

[0051] Optionally, based on the resource acquisition information, the corresponding state evaluation value for the user is determined, including: providing the resource acquisition information to the state evaluation value determination model to obtain the output state evaluation value corresponding to the user.

[0052] The state evaluation value determination model can refer to an algorithmic model or data processing module used to quantitatively calculate state evaluation values ​​based on resource acquisition information. The state evaluation value determination model can automatically calculate and output a comprehensive quantitative value for evaluating the unfavorable states of a user's resource acquisition behavior after receiving resource acquisition information, through built-in algorithmic logic. The state evaluation value determination model can include at least one of the following: a pre-trained neural network model, a conversational language model, and an intelligent agent.

[0053] In another implementation, after obtaining the user's resource acquisition information within a first historical time period, the resource acquisition information can be provided to the state evaluation value determination model. Then, the state evaluation value determination model can process and calculate the resource acquisition information to obtain an output state evaluation value corresponding to the user.

[0054] S130. Based on game interaction behavior information, determine the user retention probability of the target game.

[0055] Retention probability, determined based on user interaction behavior, quantifies the likelihood that a user will continue using the target game within a predetermined period. It characterizes a user's dependence on the target game and their willingness to remain. A high retention probability indicates high user satisfaction with the target game, while a low retention rate indicates low user satisfaction. Retention probability can be understood as player stickiness, i.e., the probability that a player will remain active in the target game for a future period.

[0056] In this embodiment, the user's game interaction behavior information within the first historical time period can be used to characterize the user's player interaction operations inputted towards the target game within the first historical time period, which is the user's player behavior data within the first historical time period. Furthermore, in order to predict the likelihood of the user continuing to be active in the target game in the future, the game interaction behavior information can be processed according to a preset retention probability determination method to predict the user's retention probability for the target game.

[0057] Optionally, the preset retention probability determination method may include at least one of the following: determining the user's retention probability for the target game based on the retention probability prediction model and game interaction behavior information; calculating the user's retention probability for the target game using a statistical analysis algorithm; or determining the user's retention probability for the target game based on a predetermined mapping rule and game interaction behavior information.

[0058] In one embodiment, at least one game interaction feature corresponding to a user can be determined based on game interaction behavior information. Further, this at least one game interaction feature can be provided to a retention probability prediction model, which then processes it. Finally, the model prediction result output by the retention probability prediction model can be used as the user's retention probability for the target game.

[0059] S140. Based on the status assessment value and retention probability, determine the intervention level for the user, and trigger the corresponding game interaction function for the user according to the intervention level.

[0060] Intervention level can be understood as a graded identifier assigned to users after classification based on a two-parameter quantitative analysis of state assessment value and retention probability. Intervention level can be used to clarify the priority of different players' needs and the appropriate intervention strategy type. Intervention level can be set to 3, 4, or 5 levels, etc., depending on the gameplay requirements of the target game. Optionally, intervention level includes at least one of the following: First intervention level (e.g., S level, 1 level, or core care level), Second intervention level (e.g., A level, 2 level, or potential retention level), Third intervention level (e.g., B level, 3 level, or routine maintenance level), and Fourth intervention level (e.g., C level, 4 level, or routine maintenance level). The priority of the first intervention level can be higher than the priority of the second intervention level, the priority of the second intervention level can be higher than the priority of the third intervention level, and the priority of the third intervention level can be higher than the priority of the fourth intervention level. In this embodiment, the division of intervention level directly depends on the two-parameter quantitative results of state assessment value and retention probability. Furthermore, the intervention level can also serve as a direct basis for matching subsequent game interaction functions. Different intervention levels correspond to preset differentiated game interaction functions (such as high priority corresponding to high-value incentive resources, medium priority corresponding to medium-low value incentive resources, and low priority corresponding to maintaining the normal experience).

[0061] Game interaction features can refer to pre-defined in-game functional modules or services designed to improve unfavorable user resource acquisition situations and / or enhance retention rates. Game interaction features can provide precisely tailored feedback and incentives based on the user's specific state, avoiding resource waste or insufficient player experience caused by standardized resources. Optionally, game interaction features may include at least one of the following: displaying interactive prompts to the user corresponding to their intervention level; directly distributing substantial incentive resources related to the target incentive resources to the user; reducing the amount of resources the user needs to transfer to subsequently acquire the target incentive resources, or returning a portion of the total transferred resources.

[0062] In this embodiment, after determining the user's status assessment value and retention probability, the user's status assessment value and retention probability can be processed according to a preset intervention level assessment method to determine the intervention level corresponding to the user.

[0063] Optionally, the user's status assessment value and retention probability are processed according to a preset intervention level assessment method to determine the intervention level corresponding to the user, including at least one of the following: processing the user's status assessment value and retention probability according to a preset intervention level mapping rule to determine the intervention level corresponding to the user; providing the user's status assessment value and retention probability to the intervention level assessment model to obtain the output intervention level corresponding to the user. One of the determination methods will be explained in detail below.

[0064] Optionally, based on the status assessment value and retention probability, the intervention level corresponding to the user is determined, including: if the status assessment value is greater than a first preset threshold and the retention probability is greater than a second preset threshold, the intervention level for the user is determined to be the first intervention level; if the status assessment value is greater than the first preset threshold and the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be the second intervention level; if the status assessment value is not greater than the first preset threshold and the retention probability is greater than the second preset threshold, the intervention level for the user is determined to be the third intervention level; if the status assessment value is not greater than the first preset threshold and the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be the fourth intervention level.

[0065] The first preset threshold refers to a quantitative judgment standard preset by the game system to divide the high and low intervals of the status evaluation value. The first preset threshold is used to match the determination of the status evaluation value dimension and is a critical value to distinguish the severity of the player's "unfavorable status in resource acquisition behavior". A status evaluation value greater than the first preset threshold indicates a severe unfavorable status of the user not obtaining the target incentive resources; a status evaluation value not greater than the first preset threshold also indicates a severe unfavorable status of the user not obtaining the target incentive resources. The first preset threshold provides a clear quantitative basis for the interval division of status evaluation values. The first preset threshold can be dynamically adjusted by the operator based on player operation data and gameplay characteristics. The first preset threshold can be any value. Optionally, when the value range is 0-1, the first preset threshold can be 0.3, 0.4, 0.5, and 0.6, etc.; when the value range is 0-100, the first preset threshold can be 30, 40, 50, and 60, etc.

[0066] The second preset threshold refers to a quantitative criterion preset by the game system to divide the retention probability into high and low intervals. This threshold is used to match the retention probability dimension and serves as a critical value to distinguish the strength of a player's "willingness to retain." A retention probability greater than the second preset threshold indicates a high user willingness to retain (a high probability of continuing to play); a retention probability less than the second preset threshold indicates a weak user willingness to retain (a low probability of continuing to play). The second preset threshold provides a clear quantitative basis for dividing the retention probability intervals. It can be dynamically adjusted by the operator based on player lifecycle data and churn warning models. The second preset threshold can be any value. Optionally, when the value range is 0-1, the second preset threshold can be 0.3, 0.4, 0.5, or 0.6, etc.; when the value range is 0-100%, the first preset threshold can be 30%, 40%, 50%, or 60%, etc.

[0067] The intervention levels are as follows: Level 1: The first level corresponds to users who have not received the target incentive resources for a long time (i.e., those with a strong negative experience due to the lack of target incentive resources) but have a high retention intention (e.g., loyal players who have not received target incentive resources for a long time). This level corresponds to the priority care level, where high-value, targeted incentive programs can be provided. Level 2: The second level corresponds to users who have not received the target incentive resources for a long time (i.e., those with a strong negative experience due to the lack of target incentive resources) but have a weak retention intention (e.g., players at high risk of churn who have not received target incentive resources for a long time). This level corresponds to the core retention level, where highly stimulating, high-priority intervention programs can be provided to prevent player churn. Level 3: The third level corresponds to users who have experienced a relatively weak cumulative failure to achieve their expected results (i.e., those with a relatively weak negative experience due to the lack of target incentive resources) but have a high retention intention (e.g., loyal players with a relatively weak negative experience due to the lack of target incentive resources). This level corresponds to the routine maintenance level, where game interaction functions that maintain a normal gaming experience can be provided. The fourth intervention level can be understood as the intervention level corresponding to user groups whose cumulative state of not achieving the expected results is relatively weak (i.e., the negative experience caused by not obtaining target incentive resources for a long time is relatively weak) and whose retention intention is relatively weak (such as players with low churn risk but insufficient retention intention). Generally, in order to save operational resources and avoid the system excessively disturbing such users, solutions that maintain a normal game experience can be matched for users at the third and fourth intervention levels.

[0068] In one implementation, after obtaining the user's status assessment value and retention probability, the status assessment value can be compared with a first preset threshold, and the retention probability can be compared with a second preset threshold. Further, if the status assessment value is greater than the first preset threshold and the retention probability is greater than the second preset threshold, the intervention level for the user is determined to be a first intervention level; if the status assessment value is greater than the first preset threshold but the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be a second intervention level; if the status assessment value is not greater than the first preset threshold but the retention probability is greater than the second preset threshold, the intervention level for the user is determined to be a third intervention level; and if the status assessment value is not greater than the first preset threshold and the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be a fourth intervention level.

[0069] In this embodiment, after determining the intervention level corresponding to the user, the corresponding game interaction function for the user can be triggered according to the preset strategy mapping rules and the intervention level corresponding to the user.

[0070] The technical solution of this invention acquires game data corresponding to a user in a target game within a first historical time period. This game data includes resource acquisition information and game interaction behavior information, providing core data support for subsequent matching of differentiated incentive processing strategies. Furthermore, by determining the user's corresponding state evaluation value based on resource acquisition information, it achieves precise quantification of the user's unfavorable state in resource acquisition behavior within the target game. Further, by determining the user's retention probability in the target game based on game interaction behavior information, it achieves precise quantification of the user's retention intention within the target game. Furthermore, by determining the intervention level for the user based on the state evaluation value and retention probability, and triggering corresponding game interaction functions for the user based on the intervention level, it achieves precise targeted incentives based on the user's unfavorable state in resource acquisition behavior and retention intention. Through the matching of differentiated game interaction functions, it not only specifically reduces the player's negative experience but also effectively reduces the risk of churn, while simultaneously improving the utilization efficiency of game incentive resources and player retention rate. The technical solution of this invention solves the problems existing in related technologies, such as a single judgment dimension, lack of substantial value in rewards and no targeted care, which makes it impossible to accurately respond to the core needs of players and achieve effective retention. It realizes the accurate quantification of the user's status evaluation value and retention intention based on the dual-dimensional information of the user's resource acquisition behavior and game interaction behavior. Through the targeted triggering of differentiated game interaction functions, it accurately responds to the user's substantial needs, which not only improves the user's game experience and retention rate, but also optimizes the allocation efficiency of game incentive resources.

[0071] Figure 2 This is a flowchart of an information processing method provided by an embodiment of the present invention. Based on the foregoing embodiments, S130 is further refined. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0072] S210. Obtain the game data corresponding to the user in the target game within the first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information.

[0073] S220. Based on the resource acquisition information, determine the corresponding status evaluation value for the user.

[0074] S230. Determine at least one game interaction feature corresponding to the user based on game interaction behavior information.

[0075] Among them, game interaction features can refer to quantitative indicators determined based on game interaction behavior information, used to characterize user game participation, dependence, and retention potential. Optionally, game interaction features may include at least one of the following: social network depth features; character development engagement features; gameplay participation breadth features; and resource transfer health features.

[0076] In this embodiment, determining at least one game interaction feature corresponding to a user based on game interaction behavior information includes at least one of the following: providing game interaction behavior information to a feature extraction model to obtain at least one game interaction feature corresponding to the user; and using a feature integration algorithm to integrate the game interaction behavior information to obtain at least one game interaction feature corresponding to the user. The feature extraction model may include at least one of a machine learning model, a conversational language model, and an intelligent agent.

[0077] For example, suppose that game interaction behavior information may include the number of game friends, guild contribution ranking, team existence duration, message sending frequency, number of team members, character's overall cultivation value, cultivation increase amount, cultivation increase times, equipment rating, pet rating, rare appearance collection progress, achievement points, number of gameplay types participated in, number of days of participation in each gameplay type, participation frequency of each gameplay type, total resource transfer amount, number of resource transfers, and resource transfer frequency, etc. Furthermore, the social network depth characteristics corresponding to the user can be determined based on at least one of the following: number of game friends, guild contribution ranking, team duration, message sending frequency, and number of team members; the character's overall cultivation value, cultivation increase amount, cultivation increase times, equipment rating, pet rating, rare appearance collection rate, and achievement points can be determined based on at least one of the following: the breadth of gameplay participation corresponding to the user can be determined based on at least one of the following: number of gameplay types participated in, number of days participated in each gameplay type, and frequency of participation in each gameplay type; and the resource transfer health characteristics corresponding to the user can be determined based on at least one of the following: total resource transfer amount, number of resource transfers, and frequency of resource transfers.

[0078] In one implementation, game interaction behavior information can be provided to a pre-trained feature extraction model, and the feature extraction model can extract features from the game interaction behavior information to obtain at least one game interaction feature corresponding to the user.

[0079] S240. Provide at least one game interaction feature to the retention probability prediction model to obtain the output user retention probability of the target game.

[0080] The retention probability prediction model can refer to a pre-trained algorithmic model or data processing module used to quantify and output the probability of user retention based on game interaction characteristics. Optionally, the retention probability prediction model can be at least one of machine learning models, conversational language models, and intelligent agents. For example, when the retention probability prediction model includes a machine learning model, it can include at least one machine learning model such as the Light GBM gradient boosting tree model, logistic regression model, random forest model, and long short-term memory network model. In this embodiment, the retention probability prediction model can be obtained by training a pre-built machine learning model based on the player's sample game interaction behavior information and the actual retention probability.

[0081] In this embodiment, before applying the retention probability prediction model, a pre-built machine learning model can be trained in a supervised or unsupervised manner. Before training the machine learning model, multiple training samples can be constructed to train the model based on these samples. To improve the prediction accuracy of the retention probability prediction model, as many and rich training samples as possible can be constructed. Optionally, the training process of the retention probability prediction model may include: acquiring sample game interaction behavior information of sample users in the target game within a second historical time period, and the actual retention probability of the sample users within the predicted time period; determining at least one sample game interaction feature corresponding to the sample user based on the sample game interaction behavior information, and constructing training samples based on the at least one sample game interaction feature and the actual retention probability; inputting at least one sample game interaction feature from the training samples into the pre-built machine learning model to obtain the output predicted retention probability; determining the loss value based on the predicted retention probability and the actual retention probability, and adjusting the model parameters of the machine learning model based on the loss value; and determining the trained machine learning model as the retention probability prediction model when a preset training termination condition is met.

[0082] Here, "sample users" refers to the historical user group used to construct training samples. Sample users can be existing and / or churned users of the target game, and their historical interaction behavior and actual retention results can serve as reference samples for model learning. There can be multiple sample users. Sample users can include positive and / or negative sample users. Positive sample users are those with an actual retention probability of 1 corresponding to the predicted duration, i.e., users who log in to the target game every day within the predicted duration; negative sample users are those with an actual retention probability of 0 corresponding to the predicted duration, i.e., users who have not logged in to the target game for a consecutive preset number of days within the predicted duration. The second historical duration can refer to the time range used to collect sample user game interaction behavior information, i.e., tracing back the historical behavior cycle of sample users. Optionally, the second historical duration includes 7 days, 15 days, 30 days, and 90 days, etc. Sample game interaction behavior information can refer to the quantitative data set of all interactive operations related to game scenes or game functions generated by sample users in the target game within the second historical duration. Sample game interaction behavior information is used to characterize the interactive operations input by sample users in the target game. For example, sample game interaction behavior information may include the number of game friends, guild contribution ranking, team duration, message sending frequency, number of team members, character's overall cultivation value, cultivation increase amount, cultivation increase times, equipment rating, pet rating, rare appearance collection rate, achievement points, number of gameplay types participated in, number of days of participation in each gameplay type, participation frequency of each gameplay type, total resource transfer amount, number of resource transfers, and resource transfer frequency. The predicted duration can be the retention probability prediction period corresponding to the training labels in the training samples. Generally, the actual retention probability of sample users within the predicted duration is the true known retention result. Furthermore, the predicted duration can be the time interval after the historical time node used to determine the second historical duration. And the time interval corresponding to the predicted duration is usually a historical time interval. Optionally, the predicted duration can be 7 days, 15 days, 30 days, or 90 days after the historical time node, etc. The actual retention probability can refer to the quantitative value of the actual retention result of sample users within the predicted duration, which is the training label for model training.

[0083] The sample game interaction features can be quantitative indicators determined based on sample game interaction behavior information, used to characterize the game participation, dependence, and retention potential of sample users. Optionally, the sample game interaction features can include at least one of the following: social network depth features; development engagement features; gameplay participation breadth features; resource transfer health features. The pre-built machine learning model can refer to an initial model built based on a preset algorithm framework before training, which has not been trained with data (model parameters are initial values ​​or default values). The model structure of the machine learning model can include at least one of the following: Light GBM gradient boosting tree model, logistic regression model, random forest model, and long short-term memory network model. The predicted retention probability can refer to the retention probability prediction value output by the model after inputting the sample game interaction features from the training samples into the pre-built machine learning model (the prediction result output by the model). The loss value can refer to the quantitative value of the deviation between the predicted retention probability and the actual retention probability calculated based on a preset loss function. The preset loss function can include at least one of the following: logarithmic loss function and mean squared error loss function. The preset training termination condition can refer to the quantitative or rule-based criteria for determining whether the model training is complete. Optionally, the preset training termination condition may include at least one of the following: the loss value drops to a preset threshold; the loss value no longer decreases for several consecutive rounds; the preset loss function converges; the number of training rounds of the model reaches a preset upper limit.

[0084] In one implementation, sample game interaction behavior information of multiple sample users in the target game within a second historical time period, as well as the actual retention probability of multiple sample users within the predicted time period, can be obtained. Further, for multiple sample users, at least one sample game interaction feature corresponding to each sample user can be determined based on the sample game interaction behavior information, and training samples can be constructed based on the at least one sample game interaction feature and the actual retention probability. Thus, multiple training samples can be obtained. Further, for multiple training samples, at least one sample game interaction feature from the training samples can be input into a pre-built machine learning model to obtain the output predicted retention probability. Further, a loss function can be applied to the predicted retention probability and the actual retention probability to obtain a loss value. Further, the model parameters in the machine learning model can be corrected based on the loss value. Then, the training error of the loss function in the machine learning model, i.e., the loss parameter, can be used as a condition to detect whether the preset loss function has reached convergence, such as whether the training error is less than the preset error, whether the error change trend tends to stabilize, or whether the current model iteration number is equal to the preset number, etc. If the convergence condition is met—for example, the training error of the loss function is less than the preset error or the error change tends to stabilize—it indicates that the machine learning model training is complete, and iterative training can be stopped. If the convergence condition has not yet been met, other training samples can be obtained to train the machine learning model until the training error of the preset loss function is within the preset range. When the training error of the preset loss function converges, the trained machine learning model can be used as the retention probability prediction model.

[0085] In this embodiment, after obtaining the trained retention probability prediction model, at least one game interaction feature corresponding to the user can be provided to the retention probability prediction model. Furthermore, the retention probability prediction model can process the received at least one game interaction feature to obtain the output user retention probability for the target game.

[0086] S250. Based on the status assessment value and retention probability, determine the intervention level for the user, and trigger the corresponding game interaction function for the user according to the intervention level.

[0087] The technical solution of this invention determines at least one game interaction feature corresponding to a user based on game interaction behavior information; further, it provides at least one game interaction feature to a retention probability prediction model to obtain the output user retention probability of the target game. This realizes the transformation of the user's original game interaction data into a quantitative feature that the model can parse, and accurately outputs the user retention probability through the retention probability prediction model, providing reliable retention dimension data support for the subsequent two-parameter determination of the intervention level, thereby improving the accuracy and efficiency of retention probability assessment.

[0088] Figure 3 This is a flowchart of an information processing method provided by an embodiment of the present invention. Based on the foregoing embodiments, S140 is further refined. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 3 As shown, the method includes:

[0089] S310. Obtain the game data corresponding to the user in the target game within the first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information.

[0090] S320. Based on the resource acquisition information, determine the corresponding status evaluation value for the user.

[0091] S330. Based on game interaction behavior information, determine the user retention probability of the target game.

[0092] S340. Based on the status assessment value and retention probability, determine the intervention level for the user, determine the interactive prompt information to be displayed to the user based on the intervention level, and display the corresponding interactive prompt information to the user.

[0093] Interactive prompts can be understood as a set of visual and / or textual information displayed to players, designed to guide them in inputting specific game interaction operations. In this embodiment, different interactive prompts can be displayed to users based on different intervention levels. Typically, for users at the first intervention level who have a strong negative experience due to a prolonged lack of target incentive resources and have a high retention intention, incentive prompts that guide them to acquire high-value target incentive resources can be displayed. For users at the second intervention level who have a strong negative experience due to a prolonged lack of target incentive resources and have a weak retention intention, since these players have a relatively weaker retention intention and a higher risk of churn compared to users at the first intervention level, interactive prompts that guide them to acquire second-highest value incentive resources can be displayed to quickly provide positive feedback. Optionally, interactive prompts may include incentive progress prompts and / or incentive acquisition prompts.

[0094] In this embodiment, different incentive prompts can correspond to different intervention levels. The incentive prompts corresponding to different intervention levels will be explained below.

[0095] Optionally, the interactive prompt information includes status assessment value interactive information; the interactive prompt information to be displayed to the user is determined according to the intervention level, and the corresponding interactive prompt information is displayed to the user, including: when the intervention level is the first intervention level, the interactive prompt information to be displayed to the user is determined to be status assessment value interactive information, and the status assessment value interactive information is displayed to the user.

[0096] The status evaluation value interaction information can be understood as guidance information related to the user's status evaluation value. This guidance information can be used to guide the user to perform a specified interactive operation to increase the status evaluation value. The status evaluation value interaction information at least indicates the specified interactive operation to be performed to increase the user's status evaluation value. In other words, the user can obtain the specified interactive operation to be performed to increase the status evaluation value based on the displayed status evaluation value interaction information. The status evaluation value interaction information may include at least one of the following: the current status evaluation value; the specified interactive operation to be performed; the expected increase in the evaluation value after the operation is completed; and the increase progress prompt information. Optionally, the status evaluation value interaction information may include text prompt information and / or graphic prompt information. Text prompt information can be used to indicate the specified interactive operation to be performed to increase the user's status evaluation value; graphic prompt information can be used to indicate the progress information of the increase in the user's status evaluation value, such as using a progress bar.

[0097] It should be noted that for users at the first intervention level, showing them interactive information about their status assessment value can provide them with the most substantial incentives, effectively improving their retention rate. Furthermore, progress prompts provide clear expectation management, transforming the uncertainty of obtaining the first incentive resources into a visualized and definite goal, thereby further enhancing the user's engagement with the game.

[0098] In one implementation, when the user's intervention level is the first intervention level, the interactive prompt information to be displayed to the user can be determined to be a status evaluation value interactive information, so that the user can perform a specified interactive operation based on the displayed status evaluation value interactive information to increase the user's status evaluation value.

[0099] Optionally, after displaying the status evaluation value interactive information to the user, the method further includes: responding to the completion of the specified interactive operation, determining the adjustment progress of the status evaluation value based on the operation execution information of the specified interactive operation, and determining the target display information of the status evaluation value based on the adjustment progress, so as to display the user's status evaluation value based on the target display information; and displaying a first incentive acquisition prompt when the displayed status evaluation value reaches a preset threshold; wherein the first incentive acquisition prompt is used to acquire a first incentive resource.

[0100] The specified interactive operation can refer to a specific game operation that the user must perform in the target game to increase their status evaluation value, as explicitly indicated in the status evaluation value interaction information. For example, the specified interactive operation may include at least one of the following: completing a specified daily task; performing a resource acquisition action targeting a specific resource; refining game equipment; or reaching a preset threshold number of consecutive days logged into the target game. Operation execution information can refer to a set of quantitative data representing the operation execution status collected during and after the user performs the specified interactive operation. Optionally, operation execution information may include at least one of the following: whether the operation was completed; the number of times the operation was completed; the quality of the operation completion; and the operation execution time. The adjustment progress of the status evaluation value can refer to the contribution ratio or quantitative growth rate of the user's current operation to the status evaluation value, determined based on the operation execution information, and is a visual representation of the change in the status evaluation value. The adjustment progress can be expressed in at least one of the following forms: percentage (e.g., increasing by 5% upon completing one refining); numerical value (e.g., increasing by 5 points upon completing one refining); or progress bar nodes (e.g., advancing the progress bar by 2 bars upon completing one refining). The target display information can refer to a structured set of information generated based on the adjustment progress to show the user the latest status evaluation value. It is a visual representation of the adjusted status evaluation value determined according to the adjustment progress. Optionally, the target display information may include at least one of the following: the specific value of the current status evaluation value; a visual indicator of the adjustment progress (such as a progress bar); the difference from a preset threshold (such as "30% away from obtaining the reward"). The preset threshold may refer to a pre-set quantitative standard for determining whether the status evaluation value has reached the incentive acquisition condition, and is a critical value that triggers the incentive acquisition prompt. The preset threshold may be represented in at least one of the following ways: corresponding to the specific value of the status evaluation value (such as the cumulative status evaluation value reaching 200 points), or the percentage of adjustment progress (such as a progress bar of 100%).

[0101] In this embodiment, determining the adjustment progress of the state evaluation value based on the operation execution information of the specified interactive operation includes at least one of the following: determining the adjustment progress of the state evaluation value based on preset operation evaluation value correspondence information and the operation execution information of the specified interactive operation, wherein the operation evaluation value correspondence information is used to characterize the correspondence between the operation execution information of the specified interactive operation and the adjustment progress; determining the adjustment progress of the state evaluation value based on a preset evaluation value increment determination algorithm and the operation execution information of the specified interactive operation.

[0102] In one implementation, after displaying interactive information about the state evaluation value to the user, a specified interactive operation can be performed on the target game to increase the user's state evaluation value. Further, upon detecting the completion of the specified interactive operation, operation execution information of the specified interactive operation can be obtained, and the adjustment progress of the state evaluation value can be determined based on preset operation evaluation value corresponding information and the operation execution information of the specified interactive operation. Further, target display information for the state evaluation value can be determined based on the adjustment progress, and the user's state evaluation value can be displayed based on the target display information. Further, when the displayed state evaluation value reaches a preset threshold, a first incentive acquisition prompt is displayed, and a first incentive resource can be acquired based on the first incentive prompt.

[0103] Optionally, the interactive prompt information includes a second incentive acquisition prompt information; determining the interactive prompt information to be displayed to the user based on the intervention level, and displaying the corresponding interactive prompt information to the user, including: when the intervention level is the second intervention level, determining that the interactive prompt information to be displayed to the user is the second incentive acquisition prompt information, and displaying the second incentive acquisition prompt information to the user.

[0104] The second incentive acquisition prompt can be understood as a prompt that directly guides the user to acquire the second incentive resource. The second incentive acquisition prompt is used to acquire the second incentive resource. The second incentive acquisition prompt can be any form of information, optionally including at least one of the following: hyperlinks, emails, and pop-up messages. The second incentive resource can be directly acquired by inputting a trigger action in response to the second incentive acquisition prompt. The second incentive resource can be an incentive resource with low resource value and / or a high acquisition probability. The resource value of the second incentive resource is less than the resource value of the first incentive resource. For example, the first incentive resource can be a limited-edition appearance, rare items, etc.; the second incentive resource can be a small amount of game currency, common training materials, and ordinary items, etc.

[0105] It should be noted that users at the second intervention level are considered to have lower retention rates compared to those at the first intervention level. For these users at risk of churn, a quick, lightweight positive feedback approach is used to avoid complex task processes that increase user stress, aiming to prevent user churn with low-cost resources.

[0106] In one implementation, when the user's intervention level is the second intervention level, the interactive prompt to be displayed to the user can be determined to be a second incentive acquisition prompt, which may be sent to the user via email. Furthermore, upon receiving the second incentive acquisition prompt, the user can trigger an operation by inputting a resource acquisition hyperlink corresponding to the second incentive resource contained in the prompt. Further, in response to this trigger operation, the second incentive resource is provided to the user.

[0107] Optionally, the interactive prompts include interactive recommendation information; the interactive prompts to be displayed to the user are determined according to the intervention level, and the corresponding interactive prompts are displayed to the user, including: when the intervention level is the third intervention level, the interactive recommendation information to be displayed to the user is determined according to the user's game interaction behavior information, and the interactive recommendation information is displayed to the user.

[0108] Interactive recommendation information can refer to a specific subtype of interactive prompts, and can be customized recommendation content centered on user social relationships and behaviors. Interactive recommendation information can include game interaction behaviors performed by a first user who has not established a connection with the current user and / or game interaction behaviors performed by a second user who has established a connection with the current user. The first user can refer to other players who have not established any in-game social connections with the current user. The second user can refer to other players who have established in-game social connections with the current user (such as friends, guild members, teammates, mentors / apprentices, etc.). The performed game interaction behaviors can refer to the specific recordable game operations completed by the first or second user in the target game.

[0109] In one implementation, when the user's intervention level is the third level, the user's game interaction information can be acquired, analyzed, and their game interaction preferences identified through classification and labeling. Further, based on these preferences, game interaction behaviors performed by a first user who has not yet established contact with the user, and game interaction behaviors performed by a second user who has already established contact, are matched and filtered from the game user pool. Further, the filtered behavioral information can be integrated into structured text to form customized interactive recommendation information to be displayed to the user. Further, the generated interactive recommendation information can be displayed to the user.

[0110] The technical solution of this invention determines the intervention level for a user based on the user's status assessment value and retention probability, determines the interactive prompts to be displayed to the user based on the intervention level, and displays the corresponding interactive prompts to the user. This achieves accurate classification based on the user's status assessment value and retention probability in two dimensions. By matching appropriate interactive prompts, it reduces the core negative user experience and strengthens retention guidance, thereby improving the fit of the user interaction experience and providing precise support for effective game retention.

[0111] Figure 4 This is a flowchart of an information processing method provided according to an embodiment of the present invention. To facilitate a better understanding of the information processing method provided by the embodiments of the present invention, the following is combined with… Figure 4 An example is provided. Figure 4 As shown, the information processing method includes the following steps:

[0112] First, obtain the resource acquisition information and game interaction behavior information of the user in the target game within the first historical time period. Further, a non-European value quantification model can be used to calculate the resource acquisition information to obtain the non-European value corresponding to the user; and a game stickiness model can be used to process the game interaction behavior information to obtain the game stickiness corresponding to the user.

[0113] Furthermore, a two-dimensional nested decision matrix can be used to analyze the non-European value and game stickiness. The two-dimensional nested decision matrix is ​​shown in Table 1 below:

[0114] Table 1 Two-dimensional nested decision matrix

[0115]

[0116] Furthermore, if the "unlucky score" is greater than 0.5 and the game stickiness is greater than 0.5, the user's intervention level can be determined as S-level care; if the "unlucky score" is greater than 0.5 and the game stickiness is not greater than 0.5, the user's intervention level can be determined as A-level care; if the "unlucky score" is not greater than 0.5 and the game stickiness is greater than 0.5, the user's intervention level can be determined as B-level care; if the "unlucky score" is not greater than 0.5 and the game stickiness is not greater than 0.5, the user's intervention level can be determined as C-level care. Further, for S-level care users, the triggered game interaction function could be triggering the "Chicken and Donkey from the Sky" gameplay and displaying an incentive progress prompt; for A-level care users, the triggered game interaction function could be triggering "Instant Low-Value Rewards," directly giving the user a low-value but useful reward via email or a simple pop-up; for B-level and C-level care users, the triggered game interaction function could be maintaining a normal gaming experience.

[0117] The core principle of this invention lies in constructing two quantitative models: "Unlucky Player Value" and "Game Stickiness," forming a two-dimensional player profile system. First, the Unlucky Player Value model transforms the abstract concept of "bad luck" into concrete numerical values, comprehensively considering the difference between historical investment and return. Second, the Game Stickiness model assesses the depth of a player's connection with the game world, determining their long-term retention potential and value. Finally, the system nests these two indicators for analysis and decision-making, classifying players into different intervention levels (e.g., S, A, B, C levels) and dynamically triggering the most suitable care strategy for each level (e.g., providing only "high stickiness & high unlucky player value" S-level players with a progress bar-based expectation management "unexpectedly appearing" advanced care). This achieves precise and efficient allocation of care resources, transforming negative emotions into in-game driving forces that promote activity, thereby improving player retention.

[0118] Figure 5 This is a schematic diagram of the structure of an information processing device provided in an embodiment of the present invention. Figure 5 As shown, the device includes: an information acquisition module 410, a status evaluation value determination module 420, a retention probability determination module 430, and an intervention level determination module 440. The information acquisition module 410 is used to acquire game data corresponding to a user in a target game within a first historical time period. The game data includes resource acquisition information and game interaction behavior information. The resource acquisition information includes the user's resource acquisition behavior in the target game and / or received resource feedback results. The game interaction behavior information includes the user's specified game behavior information in the target game. The status evaluation value determination module 420 is used to determine the user's status evaluation value based on the resource acquisition information. The status evaluation value characterizes the unfavorable state of the user's resource acquisition behavior. The retention probability determination module 430 is used to determine the user's retention probability in the target game based on the game interaction behavior information. The intervention level determination module 440 is used to determine the intervention level for the user based on the status evaluation value and the retention probability, and trigger the corresponding game interaction function for the user based on the intervention level.

[0119] The technical solution of this invention acquires game data corresponding to a user in a target game within a first historical time period. This game data includes resource acquisition information and game interaction behavior information, providing core data support for subsequent matching of differentiated incentive processing strategies. Furthermore, by determining the user's corresponding state evaluation value based on resource acquisition information, it achieves precise quantification of the user's unfavorable state in resource acquisition behavior within the target game. Further, by determining the user's retention probability in the target game based on game interaction behavior information, it achieves precise quantification of the user's retention intention within the target game. Furthermore, by determining the intervention level for the user based on the state evaluation value and retention probability, and triggering corresponding game interaction functions for the user based on the intervention level, it achieves precise targeted incentives based on the user's unfavorable state in resource acquisition behavior and retention intention. Through the matching of differentiated game interaction functions, it not only specifically reduces the player's negative experience but also effectively reduces the risk of churn, while simultaneously improving the utilization efficiency of game incentive resources and player retention rate. The technical solution of this invention solves the problems existing in related technologies, such as a single judgment dimension, lack of substantial value in rewards and no targeted care, which makes it impossible to accurately respond to the core needs of players and achieve effective retention. It realizes the accurate quantification of the user's status evaluation value and retention intention based on the dual-dimensional information of the user's resource acquisition behavior and game interaction behavior. Through the targeted triggering of differentiated game interaction functions, it accurately responds to the user's substantial needs, which not only improves the user's game experience and retention rate, but also optimizes the allocation efficiency of game incentive resources.

[0120] Optionally, the resource acquisition information includes the number of resource acquisition failures, the resource consumption corresponding to the resource acquisition behavior, the acquisition probability deviation value, and the remaining threshold for the minimum trigger. The status evaluation value determination module 420 includes a weight determination unit and a first status evaluation value determination unit. The weight determination unit is used to determine a first weight corresponding to the number of resource acquisition failures, a second weight corresponding to the resource consumption, a third weight corresponding to the acquisition probability deviation value, and a fourth weight corresponding to the remaining threshold for the minimum trigger. The first status evaluation value determination unit is used to calculate the number of resource acquisition failures, the first weight, the resource consumption, the second weight, the acquisition probability deviation value, the third weight, the remaining threshold for the minimum trigger, and the fourth weight through a weighted summation operation to obtain a status evaluation value corresponding to the user.

[0121] Optionally, the state evaluation value determination module 420 includes: a state evaluation value first determination unit. The state evaluation value first determination unit is used to provide the resource acquisition information to the state evaluation value determination model to obtain an output state evaluation value corresponding to the user.

[0122] Optionally, the retention probability determination module 430 includes a feature determination unit and a retention probability determination unit. The feature determination unit is used to determine at least one game interaction feature corresponding to the user based on the game interaction behavior information; the retention probability determination unit is used to provide at least one of the game interaction features to a retention probability prediction model to obtain the output retention probability of the user for the target game.

[0123] Optionally, the device further includes: a sample information acquisition module, a training sample construction module, a predicted retention probability determination module, a model parameter adjustment module, and a model determination module. The sample information acquisition module is used to acquire sample game interaction behavior information corresponding to sample users in the target game within a second historical time period, and the actual retention probability of the sample users within the predicted time period. The training sample construction module is used to determine at least one sample game interaction feature corresponding to the sample user based on the sample game interaction behavior information, and construct training samples based on the at least one sample game interaction feature and the actual retention probability. The predicted retention probability determination module is used to input at least one sample game interaction feature from the training samples into a pre-constructed machine learning model to obtain the output predicted retention probability. The model parameter adjustment module is used to determine a loss value based on the predicted retention probability and the actual retention probability, and adjust the model parameters of the machine learning model based on the loss value. The model determination module is used to determine the trained machine learning model as the retention probability prediction model when a preset training termination condition is met.

[0124] Optionally, the intervention level determination module 440 includes an intervention level determination unit. The object level determination unit is configured to: determine the intervention level for the user as a first intervention level when the state evaluation value is greater than a first preset threshold and the retention probability is greater than a second preset threshold; determine the intervention level for the user as a second intervention level when the state evaluation value is greater than the first preset threshold and the retention probability is not greater than the second preset threshold; determine the intervention level for the user as a third intervention level when the state evaluation value is not greater than the first preset threshold and the retention probability is greater than the second preset threshold; and determine the intervention level for the user as a fourth intervention level when the state evaluation value is not greater than the first preset threshold and the retention probability is not greater than the second preset threshold.

[0125] Optionally, the game interaction function includes displaying interactive prompt information; the intervention level determination module 440 includes: an interactive prompt information determination unit. The interactive prompt information determination unit is used to determine the interactive prompt information to be displayed to the user based on the intervention level, and to display the corresponding interactive prompt information to the user.

[0126] Optionally, the interactive prompt information includes status assessment value interactive information; the interactive prompt information determining unit includes a status assessment value interactive information display subunit. The status assessment value interactive information display subunit is used to determine, when the intervention level is a first intervention level, that the interactive prompt information to be displayed to the user is status assessment value interactive information, and to display the status assessment value interactive information to the user; wherein the status assessment value interactive information is at least used to indicate a specified interactive operation to be performed to increase the user's status assessment value.

[0127] Optionally, the device further includes: a status evaluation value display module and an incentive acquisition prompt information display module. The status evaluation value display module is configured to, after displaying the status evaluation value interactive information to the user, respond to the completion of the specified interactive operation, determine the adjustment progress of the status evaluation value based on the operation execution information of the specified interactive operation, and determine the target display information of the status evaluation value based on the adjustment progress, so as to display the user's status evaluation value based on the target display information; the incentive acquisition prompt information display module is configured to, when the displayed status evaluation value reaches a preset threshold, display first incentive acquisition prompt information; wherein the first incentive acquisition prompt information is used to acquire a first incentive resource.

[0128] Optionally, the interactive prompt information includes second incentive acquisition prompt information; the interactive prompt information determining unit includes an incentive acquisition prompt information display subunit. The incentive acquisition prompt information display subunit is used to determine, when the intervention level is the second intervention level, that the interactive prompt information to be displayed to the user is the second incentive acquisition prompt information, and to display the second incentive acquisition prompt information to the user, wherein the second incentive acquisition prompt information is used to acquire a second incentive resource; the resource value of the second incentive resource is less than the resource value of the first incentive resource.

[0129] Optionally, the interactive prompt information includes interactive recommendation information; the interactive prompt information determining unit includes an interactive recommendation information display subunit. The interactive recommendation information display subunit is used, when the intervention level is the third intervention level, to determine the interactive recommendation information to be displayed to the user based on the user's game interaction behavior information, and to display the interactive recommendation information to the user, wherein the interactive recommendation information includes game interaction behaviors performed by a first user who has not established contact with the user and / or game interaction behaviors performed by a second user who has established contact with the user.

[0130] The information processing apparatus provided in the embodiments of the present invention can execute the information processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0131] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, 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 (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0132] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0133] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as information processing methods.

[0135] In some embodiments, the information processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the information processing method by any other suitable means (e.g., by means of firmware).

[0136] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0137] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0138] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0139] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. 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).

[0140] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations 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., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), target blockchain networks, and the Internet.

[0141] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0142] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0143] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0144] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An information processing method, characterized in that, include: Acquire game data corresponding to a user in a target game within a first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information; the resource acquisition information includes the resource acquisition behavior participated in by the user in the target game and / or the resource feedback result information received; the game interaction behavior information includes the specified game behavior information performed by the user in the target game; Based on the resource acquisition information, a status evaluation value is determined for the user; wherein the status evaluation value characterizes the unfavorable state of the user's resource acquisition behavior; and, Based on the game interaction behavior information, determine the user's retention probability of the target game; Based on the status assessment value and the retention probability, the intervention level for the user is determined, and the corresponding game interaction function for the user is triggered according to the intervention level.

2. The information processing method according to claim 1, characterized in that, The resource acquisition information includes the number of failed resource acquisitions, the resource consumption corresponding to the resource acquisition behavior, the acquisition probability deviation value, and the remaining threshold for the minimum trigger; determining the user's status evaluation value based on the resource acquisition information includes: Determine a first weight corresponding to the number of resource acquisition failures, a second weight corresponding to the resource consumption, a third weight corresponding to the acquisition probability deviation value, and a fourth weight corresponding to the remaining threshold of the guaranteed trigger. The system calculates the number of failed resource acquisitions, the first weight, the resource consumption, the second weight, the acquisition probability deviation, the third weight, the remaining threshold for the minimum trigger, and the fourth weight using a weighted summation operation to obtain a status evaluation value corresponding to the user.

3. The information processing method according to claim 1, characterized in that, The step of determining the status assessment value corresponding to the user based on the resource acquisition information includes: The resource acquisition information is provided to the status evaluation value determination model to obtain the output status evaluation value corresponding to the user.

4. The information processing method according to claim 1, characterized in that, Determining the user's retention probability for the target game based on the game interaction behavior information includes: Based on the game interaction behavior information, at least one game interaction feature corresponding to the user is determined; At least one of the game interaction features is provided to the retention probability prediction model to obtain the output retention probability of the user for the target game.

5. The information processing method according to claim 1, characterized in that, Determining the intervention level for the user based on the status assessment value and the retention probability includes: If the status assessment value is greater than a first preset threshold and the retention probability is greater than a second preset threshold, the intervention level for the user is determined to be the first intervention level. If the status assessment value is greater than the first preset threshold and the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be the second intervention level. If the status assessment value is not greater than the first preset threshold and the retention probability is greater than the second preset threshold, the intervention level for the user is determined to be the third intervention level. If the status assessment value is not greater than the first preset threshold and the retention probability is not greater than the second preset threshold, the intervention level for the user is determined to be the fourth intervention level.

6. The information processing method according to claim 1, characterized in that, The game's interactive features include displaying interactive prompts; The step of triggering the corresponding game interaction function for the user based on the intervention level includes: Based on the intervention level, determine the interactive prompt information to be displayed to the user, and then display the corresponding interactive prompt information to the user.

7. The information processing method according to claim 6, characterized in that, The interactive prompt information includes status assessment value interactive information; the step of determining the interactive prompt information to be displayed to the user based on the intervention level, and displaying the corresponding interactive prompt information to the user, includes: When the intervention level is the first intervention level, the interactive prompt information to be shown to the user is determined to be the status evaluation value interactive information, and the status evaluation value interactive information is shown to the user; wherein, the status evaluation value interactive information is at least used to indicate the specified interactive operation to be performed to increase the user's status evaluation value.

8. The information processing method according to claim 7, characterized in that, After displaying the status assessment value interactive information to the user, the method further includes: In response to the completion of the specified interactive operation, the adjustment progress of the status evaluation value is determined according to the operation execution information of the specified interactive operation, and the target display information of the status evaluation value is determined according to the adjustment progress, so as to display the user's status evaluation value based on the target display information; When the displayed state evaluation value reaches a preset threshold, a first incentive acquisition prompt message is displayed; wherein, the first incentive acquisition prompt message is used to acquire a first incentive resource.

9. The information processing method according to claim 6, characterized in that, The interactive prompt information includes a second incentive acquisition prompt information; The step of determining the interactive prompt information to be displayed to the user based on the intervention level, and displaying the corresponding interactive prompt information to the user, includes: When the intervention level is the second intervention level, the interactive prompt information to be shown to the user is determined to be the second incentive acquisition prompt information, and the second incentive acquisition prompt information is shown to the user, wherein the second incentive acquisition prompt information is used to acquire the second incentive resource; the resource value of the second incentive resource is less than the resource value of the first incentive resource.

10. The information processing method according to claim 6, characterized in that, The interactive prompt information includes interactive recommendation information; the step of determining the interactive prompt information to be displayed to the user based on the intervention level, and displaying the corresponding interactive prompt information to the user, includes: When the intervention level is the third intervention level, interactive recommendation information to be shown to the user is determined based on the user's game interaction behavior information, and the interactive recommendation information is shown to the user. The interactive recommendation information includes game interaction behaviors performed by a first user who has not established contact with the user and / or game interaction behaviors performed by a second user who has established contact with the user.

11. An information processing device, characterized in that, include: An information acquisition module is used to acquire game data corresponding to a user in a target game within a first historical time period; wherein, the game data includes resource acquisition information and game interaction behavior information; the resource acquisition information includes the resource acquisition behavior participated in by the user in the target game and / or the resource feedback result information received; the game interaction behavior information includes the specified game behavior information performed by the user in the target game; A status assessment value determination module is used to determine a status assessment value corresponding to the user based on the resource acquisition information; wherein, the status assessment value is used to characterize the unfavorable state of the user's resource acquisition behavior; and, The retention probability determination module is used to determine the user's retention probability of the target game based on the game interaction behavior information. The intervention level determination module is used to determine the intervention level for the user based on the status evaluation value and the retention probability, and to trigger the corresponding game interaction function for the user based on the intervention level.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the information processing method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the information processing method according to any one of claims 1-10.

14. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the information processing method according to claims 1-10.

Images