Game data processing method and device, readable medium and electronic equipment

Abstract

The present disclosure relates to a game data processing method and device, readable medium and electronic equipment, and relates to electronic information processing technology. The method comprises: obtaining game operation records generated by a game client within a preset time period, extracting a plurality of behavior characteristic values from the game operation records, identifying the type of the game client according to the plurality of behavior characteristic values, when the game client is of a preset type, determining the contribution score of each behavior characteristic value to the preset type according to the plurality of behavior characteristic values, and determining the game configuration for the game client according to the contribution score of each behavior characteristic value. The present disclosure extracts a plurality of behavior characteristic values from game operation records, and determines the type of the game client and the contribution score of each behavior characteristic value, thereby obtaining a game configuration suitable for the game client.

Description

Technical Field

[0001] This disclosure relates to the field of electronic information processing technology, and more specifically, to a game data processing method, apparatus, readable medium, and electronic device. Background Technology

[0002] With the continuous development of electronic information technology, a wide variety of game applications have emerged in the application market. During game operation, various game modes and resources are offered. For example, game applications may provide PVP (Player vs. Player) and PVE (Player vs. Environment) modes, as well as game resources such as equipment, gold coins, and cards. Different game modes and resources can be tailored to different game clients to improve the player's gaming experience. Summary of the Invention

[0003] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] In a first aspect, this disclosure provides a game data processing method, the method comprising:

[0005] Acquire game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records;

[0006] The type of the game client is identified based on multiple behavioral feature values;

[0007] When the game client is of a preset type, a contribution score for each of the behavioral feature values ​​to the preset type is determined based on multiple behavioral feature values.

[0008] Based on the contribution score corresponding to each behavioral feature value, the game configuration for the game client is determined.

[0009] Secondly, this disclosure provides a game data processing apparatus, the apparatus comprising:

[0010] The acquisition module is used to acquire game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records;

[0011] A type determination module is used to identify the type of the game client based on multiple behavioral feature values;

[0012] The processing module is used to determine the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values ​​when the game client is of a preset type.

[0013] The configuration determination module is used to determine the game configuration for the game client based on the contribution score corresponding to each of the behavioral feature values.

[0014] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the method described in the first aspect of this disclosure.

[0015] Fourthly, this disclosure provides an electronic device, comprising:

[0016] A storage device on which computer programs are stored;

[0017] A processing device for executing the computer program in the storage device to implement the steps of the method described in the first aspect of this disclosure.

[0018] Through the above technical solution, this disclosure first obtains game operation records generated by the game client within a preset time period, and extracts multiple behavioral feature values ​​from the game operation records. Then, it identifies the type of the game client based on the multiple behavioral feature values. If the game client is a preset type, it determines the contribution score of each behavioral feature value to the preset type based on the multiple behavioral feature values. Finally, it determines the game configuration for the game client based on the contribution score corresponding to each behavioral feature value. This disclosure extracts multiple behavioral feature values ​​from game operation records and uses these to determine the type of the game client and the contribution score of each behavioral feature value, thereby obtaining a game configuration suitable for the game client.

[0019] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0021] Figure 1 This is a flowchart illustrating a game data processing method according to an exemplary embodiment;

[0022] Figure 2 This is a flowchart illustrating another game data processing method according to an exemplary embodiment;

[0023] Figure 3This is a flowchart illustrating another game data processing method according to an exemplary embodiment;

[0024] Figure 4 This is a flowchart illustrating another game data processing method according to an exemplary embodiment;

[0025] Figure 5 This is a flowchart illustrating another game data processing method according to an exemplary embodiment;

[0026] Figure 6 This is a schematic diagram illustrating a historical contribution scoring sequence according to an exemplary embodiment;

[0027] Figure 7 This is a flowchart illustrating a training recognition model and a processing model according to an exemplary embodiment;

[0028] Figure 8 This is a block diagram illustrating a game data processing apparatus according to an exemplary embodiment;

[0029] Figure 9 This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment;

[0030] Figure 10 This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment;

[0031] Figure 11 This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment;

[0032] Figure 12 A block diagram of an electronic device is shown according to an exemplary embodiment. Detailed Implementation

[0033] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0034] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0035] The term "comprising" and its variations as used herein are open-ended inclusion, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0036] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0037] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0038] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0039] All actions involving the acquisition of signals, information, or data in this disclosure are carried out in accordance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0040] Figure 1 This is a flowchart illustrating a game data processing method according to an exemplary embodiment, such as... Figure 1 As shown, the method includes the following steps:

[0041] Step 101: Obtain game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records.

[0042] For example, game operation records generated by the game client during the use of the game application within a preset time period can be obtained. The preset time period could be, for example, the week preceding the current moment. Game operation records can be extracted from the game application's behavior logs or obtained through embedded tracking within the game application. Game operation records can include multiple game actions performed by the game client while using the game application, along with the timestamp of each action. Game actions can include changes in game resources, such as obtaining item A, using 200 gold coins to draw card C, or obtaining equipment B. Game actions can also include records of game matches, such as completing a PVP match, completing a PVE match, the match result (success or failure), the number of kills in a match, and character health. Game actions can also include logging into the game, logging out, character level, character type, etc., without specific limitations in this disclosure. It should be noted that any information recorded in the game operation records is obtained with the player's authorization, or submitted voluntarily by the player after reading the relevant instructions, or is automatically uploaded by the player when using the game application through the game client.

[0043] Then, behavioral feature values ​​of various behavioral characteristics can be extracted from the game operation records according to preset extraction rules. Behavioral feature values ​​can characterize the game client's use of the game application, and can include resource flow of various game resources (e.g., item flow, equipment flow, card flow, gold coin flow, etc.), participation in various gameplay modes (e.g., number of PVP mode battles, number of PVE mode battles, etc.), total number of kills, success rate, failure rate, total match duration, login duration, login frequency, etc.

[0044] Step 102: Identify the type of game client based on multiple behavioral feature values.

[0045] For example, the type of a game client can be determined based on multiple behavioral feature values. For instance, multiple behavioral feature values ​​can be used as input to a pre-trained recognition model to determine the type of the game client. This can be understood as the recognition model being able to classify game clients. Alternatively, multiple behavioral feature values ​​can be used as input to a classification algorithm to determine the type of the game client based on the algorithm's output. A game client can belong to any of several pre-specified types, such as: active, normal, inactive; PVP, PVE; social, single-player, etc. This disclosure does not specifically limit this.

[0046] Step 103: If the game client is a preset type, determine the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values.

[0047] For example, among multiple pre-specified types, one or more preset types can be determined based on specific needs. For instance, if a game application launches a new PVP mode, the preset type can be set to PVP. Similarly, if a game application launches community features, the preset type can be set to social. Or, if a game application needs to increase activity, the preset type can be set to inactive. If the game client is a preset type, then the contribution score of each behavioral feature value to the preset type can be calculated based on multiple behavioral feature values. Specifically, the matching degree between the game client and the preset type can be determined first based on multiple behavioral feature values.

[0048] Next, based on multiple behavioral feature values ​​and the matching degree between the game client and the preset type, the contribution score of each behavioral feature value to the preset type can be determined. The contribution score can be understood as a SHAP (Shapley Additive Explanations) value, used to characterize the contribution of each behavioral feature value to classifying the game client into the preset type. In other words, the contribution score can explain the degree of influence (or importance) of each behavioral feature value on the preset type, providing an interpretable basis for determining subsequent game configurations.

[0049] Step 104: Determine the game configuration for the game client based on the contribution score corresponding to each behavioral feature value.

[0050] For example, after obtaining the contribution score corresponding to each behavioral feature value, the contribution score of each behavioral feature value can be compared with a preset threshold, and the game configuration applicable to the game client can be determined based on the comparison results. Alternatively, the game configuration can be determined based on the comparison results combined with the behavioral feature value. Another option is to determine the game configuration based on the comparison results combined with the behavioral feature value and its corresponding statistical distribution (e.g., dispersion, mean, variance, standard deviation, etc.). Game configuration can be understood as the game client's control over behavioral feature values ​​when using the game application. This can include adjusting the direction and / or size of one or more behavioral feature values. For example, if the behavioral feature value is the number of PVP mode matches, the game configuration could be to increase the number of PVP mode matches pushed. Or, if the behavioral feature value is the turnover of C-rank cards, the game configuration could be to increase the probability of obtaining C-rank cards. In this way, multiple behavioral feature values ​​are extracted from the game client's operation records, and the type of the game client is determined accordingly, as well as the contribution score of each behavioral feature value. The contribution score can explain the degree of influence of each behavioral feature value on the preset type. Therefore, a game configuration adapted to the game client can be obtained based on the corresponding contribution score, which can effectively improve the player's gaming experience.

[0051] In summary, this disclosure first obtains game operation records generated by the game client within a preset time period and extracts multiple behavioral feature values ​​from these records. Then, it identifies the game client type based on these behavioral feature values. If the game client is a preset type, it determines the contribution score of each behavioral feature value to the preset type based on the multiple behavioral feature values. Finally, it determines the game configuration for the game client based on the contribution score corresponding to each behavioral feature value. This disclosure extracts multiple behavioral feature values ​​from game operation records and uses these to determine the game client type and the contribution score of each behavioral feature value, thereby obtaining a game configuration suitable for the game client.

[0052] Figure 2 This is a flowchart illustrating another game data processing method according to an exemplary embodiment, such as... Figure 2 As shown, step 102 can be:

[0053] Multiple behavioral feature values ​​are input into a pre-trained recognition model to obtain the type of game client output by the recognition model.

[0054] For example, multiple behavioral feature values ​​can be input into a pre-trained recognition model, which outputs the type of the game client. In other words, the recognition model can predict the matching degree between the game client and each of several pre-specified types based on multiple behavioral feature values ​​that characterize the game client's use of the game application. Specifically, the higher the matching degree, the higher the probability that the game client belongs to that type; conversely, the lower the matching degree, the lower the probability that the game client belongs to that type. The recognition model can determine the type with the highest matching degree as the game client type, or it can determine the type with a matching degree that meets preset conditions (e.g., greater than a preset matching degree threshold). The structure of the recognition model can be, for example, an XGBoost tree model, a decision tree model, a random forest model, etc., and this disclosure does not specifically limit its application.

[0055] Accordingly, step 103 can be implemented in the following ways:

[0056] Step 1031: Using a pre-trained processing model, determine the matching probability between the game client and the preset type based on multiple behavioral feature values.

[0057] Step 1032: Determine the contribution score of each behavioral feature value to the preset type based on the matching probability between the game client and the preset type.

[0058] For example, multiple behavioral feature values ​​can be used as input to a pre-trained processing model. The model can determine the matching probability (or matching degree) between the game client and a preset type based on these feature values. Then, based on each behavioral feature value and the matching probability, the model determines the contribution score of each behavioral feature value to the preset type. Alternatively, a subset of behavioral feature values ​​(i.e., the target behavioral feature values ​​mentioned later) can be selected from the multiple behavioral feature values ​​and used as input to the processing model. The model can then determine the matching probability (or matching degree) between the game client and a preset type based on these subset of behavioral feature values. Finally, based on each behavioral feature value in the subset and the matching probability, the model determines the contribution score of each behavioral feature value in the subset of behavioral feature values ​​to the preset type.

[0059] Similarly, the structure of the processing model can be, for example, an XGBoost tree model, a decision tree model, a random forest model, etc., and this disclosure does not specifically limit it. That is to say, the processing model and the recognition model can have the same function. The input of the processing model is all the behavioral feature values, and the input of the recognition model can be all the behavioral feature values ​​or a portion of the behavioral feature values ​​(i.e., the target behavioral feature values ​​mentioned later).

[0060] For example, to determine the contribution score of each behavioral feature value to a preset type, multiple behavioral features values ​​can first be divided into various combinations, and a processing model can be used to determine the matching probability between the game client and the preset type for each input combination. Then, based on the matching probability between the game client and the preset type for each input combination, the contribution score of each behavioral feature value to the preset type can be determined. Taking the contribution score as the SHAP value as an example, the contribution score of each behavioral feature value to the preset type can be determined by the following formula:

[0061]

[0062] Where, φ j Let {x1, ..., xj} represent the contribution score of the j-th behavioral feature value to the preset type. p} represents the set of all behavioral feature values ​​(i.e., a total of p behavioral feature values), {x1,…,x p}\{x j} represents the set of possible behavioral feature values ​​other than the j-th behavioral feature value. S represents the set of {x1,…,x}. p}\{x j A subset of}, f x The processing model, f x (S) represents inputting S into the processing model and processing the model's output, f. x (S∪{x j}) represents S∪{x j Input the model and process its output.

[0063] In one implementation, step 104 can be achieved in the following way:

[0064] For each behavioral feature value, if the contribution score corresponding to the behavioral feature value is greater than or equal to a preset threshold, the game configuration is determined based on the behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size for the behavioral feature value.

[0065] For example, game configuration can be determined by comparing the contribution score corresponding to each behavioral feature value with a preset threshold. If the contribution score corresponding to the behavioral feature value is greater than or equal to the preset threshold, the game configuration can be further determined based on the behavioral feature value. The game configuration can include the direction and / or magnitude of adjustments for the behavioral feature value. If the contribution score corresponding to the behavioral feature value is less than the preset threshold, it can be determined that the behavioral feature value has a small impact on classifying the game client into a preset type, and therefore, the behavioral feature value can be disregarded when determining the game configuration. Furthermore, since contribution scores can be negative, the game configuration can be determined by comparing the absolute value of the contribution score corresponding to each behavioral feature value with a preset threshold. If the absolute value of the contribution score corresponding to the behavioral feature value is greater than or equal to the preset threshold, the game configuration can be further determined based on the behavioral feature value and whether it is positive or negative. If the absolute value of the contribution score corresponding to the behavioral feature value is less than the preset threshold, it can be determined that the behavioral feature value has a small impact on classifying the game client into a preset type, and therefore, the behavioral feature value can be disregarded when determining the game configuration.

[0066] Taking the PVP mode battle ratio as an example, with the PVP mode as the behavioral characteristic and the default type as PVP, the contribution score for the PVP mode battle ratio is 0.3, and the default threshold is 0.1. This indicates that the PVP mode battle ratio has a positive contribution to the default type and is greater than the default threshold. Game configuration can be further determined based on the characteristic value of the PVP mode battle ratio. If the purpose of the game configuration is to promote the PVP type, and the characteristic value of the PVP mode battle ratio is high (e.g., 65%), then the game configuration could be to increase the number of PVP mode battles. As another example, taking the equipment turnover as the behavioral characteristic and the default type as silence, with the equipment turnover having a contribution score of -0.28 and a default threshold of 0.1, this indicates that the equipment turnover has a negative contribution to the default type, and the absolute value is greater than the default threshold. Game configuration can be further determined based on the characteristic value of the equipment turnover. If the purpose of the game configuration is to reduce silence and the characteristic value of the equipment turnover is low (e.g., 5), then the game configuration could be to increase the probability of equipment drops.

[0067] In another implementation, step 104 may include:

[0068] Compare the behavioral feature value with the corresponding feature mean, and determine the adjustment direction based on the comparison result. And / or,

[0069] The adjustment size is determined based on the characteristic value of the behavior and the statistical distribution corresponding to the characteristic value.

[0070] For example, if the contribution score corresponding to a behavioral feature value is greater than or equal to a preset threshold, the behavioral feature value can be compared with the mean value of the corresponding feature, and the adjustment direction can be determined based on the comparison result. For instance, if the game configuration aims to promote a preset type, and the contribution score corresponding to this behavioral feature value is positive, and if the behavioral feature value is greater than or equal to the mean value of the behavioral feature to which it belongs (which can be understood as the behavioral feature value being high), then the adjustment direction can be determined to be increasing (i.e., increasing the behavioral feature value). If the behavioral feature value is less than the mean value of the behavioral feature to which it belongs (which can be understood as the behavioral feature value being low), then the adjustment direction can be determined to be decreasing (i.e., decreasing the behavioral feature value).

[0071] The adjustment level can be determined based on the behavioral characteristic value and its corresponding statistical distribution. Adjustment levels can be categorized into four levels: strong, medium, weak, and none. The statistical distribution corresponding to this behavioral characteristic value can be obtained by collecting and statistically analyzing the behavioral characteristic values ​​of various behaviors of game clients during game application usage. For example, if the game configuration aims to promote a preset type, and the contribution score corresponding to this behavioral characteristic value is positive, the adjustment direction is to increase it. If the characteristic value is located at the head of the statistical distribution of the behavioral characteristic to which it belongs (e.g., top 10%), then further increasing the characteristic value is less meaningful, and the adjustment level can be determined as weak or none. If the characteristic value is located at the tail of the statistical distribution of the behavioral characteristic to which it belongs, then further adjusting the characteristic value is more meaningful, and the adjustment level can be determined as strong.

[0072] Figure 3 This is a flowchart illustrating another game data processing method according to an exemplary embodiment, such as... Figure 3 As shown, the method may further include:

[0073] Step 105: If the game client is a preset type, determine the game configuration based on each behavioral feature value and the statistical distribution corresponding to that behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size of at least one behavioral feature value.

[0074] In one application scenario, if the game client is determined to be of a preset type, the game configuration can be determined directly based on each behavioral characteristic value and its corresponding statistical distribution. For example, if the preset type is PVE, and the number of PVE mode matches for this game client is in the top 5% of the entire server, then it indicates that the player on this game client is a hardcore PVE mode player, and there is no need to adjust the number of PVE mode matches for this game client.

[0075] Figure 4 This is a flowchart illustrating another game data processing method according to an exemplary embodiment, such as... Figure 4 As shown, the method may further include:

[0076] Step 106: Among multiple behavioral feature values, determine the target behavioral feature value that meets the preset conditions.

[0077] Accordingly, step 103 can be:

[0078] Based on multiple target behavior feature values, determine the contribution score of each target behavior feature value to the preset type.

[0079] Step 104 can be:

[0080] The game configuration is determined based on the contribution score corresponding to each target behavior feature value.

[0081] For example, if the game client is of a preset type, then target behavioral feature values ​​can be selected from the multiple behavioral feature values ​​extracted in step 101. Correspondingly, these multiple target behavioral feature values ​​can be used as input to the processing model. The processing model can determine the matching degree between the game client and the preset type based on these multiple target behavioral feature values, and then determine the contribution score of each target behavioral feature value to the preset type based on the target behavioral feature values ​​and the matching probability between the game client and the preset type.

[0082] Finally, the game configuration is determined based on the contribution score corresponding to each target behavior feature value. This can be achieved by comparing the contribution score of each target behavior feature value with a preset threshold, and determining the appropriate game configuration for the game client based on the comparison results. Alternatively, the game configuration can be determined by combining the comparison results with the target behavior feature value itself. Another approach is to determine the game configuration by combining the comparison results with the target behavior feature value and its corresponding statistical distribution.

[0083] The target behavioral feature value is a behavioral feature value that meets preset conditions, and the number of target behavioral feature values ​​is less than or equal to the number of behavioral feature values. In one approach, all behavioral feature values ​​can be used as target behavioral feature values ​​(in this case, the processing model and recognition model can be the same). In another approach, target behavioral feature values ​​can be marked among multiple behavioral feature values ​​according to specific needs. In yet another approach, historical game operation records from multiple game clients prior to the current moment can be used to pre-determine the contribution score of each behavioral feature value based on the historical game operation records as described above. Then, behavioral feature values ​​with contribution scores greater than a preset threshold (or the preset number of behavioral feature values ​​with the highest contribution scores) can be used as target behavioral feature values.

[0084] Figure 5 This is a flowchart illustrating another game data processing method according to an exemplary embodiment, such as... Figure 5 As shown, the method may further include:

[0085] Step 107: Obtain historical game operation records of multiple sample game clients, and extract historical feature value sequences corresponding to each behavioral feature based on the historical game operation records. The historical feature value sequences include historical feature values ​​of multiple sample game clients corresponding to each behavioral feature.

[0086] For example, we can pre-acquire historical game operation records from multiple sample game clients within a historical time period. A historical time period can be understood as the period preceding the current moment, such as the past year. Then, based on the historical game operation records corresponding to each sample game client, we can extract the historical feature value sequence corresponding to each behavioral feature. This historical feature sequence includes the historical feature values ​​of multiple sample game clients for that behavioral feature. The historical feature value sequence of the nth behavioral feature can be represented as {F}. 1,n ,…,F m,n ,…F M,n There are a total of M sample game clients, F m,n F represents the historical feature value of the nth behavioral feature of the mth sample game client. m,n It can include multiple historical feature values ​​of the nth behavioral feature of the mth sample game client within a historical time period.

[0087] Step 108: Based on the historical feature value sequence corresponding to multiple behavioral features, determine the historical contribution score sequence of each behavioral feature to the preset type. The historical contribution score sequence includes the historical contribution scores of multiple sample game clients to the corresponding behavioral feature.

[0088] Step 109: Determine the target behavioral feature based on the historical contribution score sequence of each behavioral feature to the preset type.

[0089] Accordingly, step 106 can be:

[0090] Among multiple behavioral feature values, the behavioral feature value corresponding to the target behavioral feature is taken as the target behavioral feature value.

[0091] For example, based on the historical feature value sequences corresponding to multiple behavioral features, a recognition model can determine the historical contribution score sequence of each behavioral feature to a preset type. In other words, the historical feature value sequences corresponding to multiple behavioral features can be input into the recognition model, which then determines the matching degree between each sample game client and the preset type. Then, multiple sample game clients are identified, and their historical contribution scores to the preset type for each behavioral feature are determined, thus obtaining the historical contribution score sequence of each behavioral feature to the preset type. The historical contribution score of a sample game client to a preset type for a given behavioral feature represents the contribution of that behavioral feature input into the recognition model to classifying the sample game client into the preset type. Therefore, the historical contribution score sequence of a behavioral feature to a preset type represents the contribution of that behavioral feature to the preset type.

[0092] Furthermore, the target behavioral feature can be determined based on the historical contribution scoring sequence of each behavioral feature to a preset type. Finally, the behavioral feature value corresponding to the target behavioral feature can be selected from the multiple behavioral feature values ​​extracted in step 101 as the target behavioral feature value.

[0093] In one implementation, step 109 can be implemented as follows:

[0094] For each behavioral feature, if the dispersion of that behavioral feature to the historical contribution score sequence of the preset type is greater than the preset dispersion threshold, then that behavioral feature is determined as the target behavioral feature.

[0095] For example, the target behavioral feature can be determined based on the dispersion of the historical contribution score sequence of each behavioral feature to a preset type. If the dispersion of the behavioral feature to the historical contribution score sequence of the preset type is greater than a preset dispersion threshold, it means that the increase or decrease of the behavioral feature value will change the degree of influence on the preset type, and thus the behavioral feature can be identified as the target behavioral feature. If the dispersion of the behavioral feature to the historical contribution score sequence of the preset type is less than or equal to the preset dispersion threshold, it means that the increase or decrease of the behavioral feature value has a small degree of influence on the preset type, and thus the behavioral feature is not the target behavioral feature.

[0096] Taking historical contribution scores as an example, SHAP values Figure 6This includes three historical contribution score sequences. The horizontal axis represents the SHAP value, and the vertical axis represents the number of historical contribution scores. Each row represents the historical contribution score sequence corresponding to a certain behavioral feature. The portion with diagonal lines on the horizontal axis indicates that the behavioral feature value is less than the feature mean of that behavioral feature; the portion with horizontal lines on the horizontal axis indicates that the behavioral feature value is greater than or equal to the feature mean of that behavioral feature. Figure 6 It can be seen that the historical contribution score sequences corresponding to behavioral feature 1 and behavioral feature 2 are relatively discrete, and can be identified as target behavioral features. Taking behavioral feature 1 as an example, when the feature value of behavioral feature 1 is greater than or equal to the feature mean of that behavioral feature, the corresponding historical contribution score is located at... Figure 6 The left side (i.e., the negative contribution to the preset type) shows that when the feature value of behavioral feature 1 is less than the feature mean of that behavioral feature, the corresponding historical contribution score is located in... Figure 6 The right-hand side (i.e., the positive contribution to the preset type). In other words, by adjusting the behavioral feature value corresponding to behavioral feature 1, the magnitude and sign of the contribution to the preset type can be changed; therefore, behavioral feature 1 can be identified as the target behavioral feature. For example, taking behavioral feature 3 as an example, when the feature value of behavioral feature 3 is greater than or equal to the feature mean of that behavioral feature, the corresponding historical contribution score is located in... Figure 6 The middle part (i.e., contributing almost nothing to the preset type), when the feature value of behavioral feature 3 is less than the feature mean of that behavioral feature, the corresponding historical contribution score is also in the middle. Figure 6 The middle part. In other words, whether the feature value of behavioral feature 3 is increased or decreased, the contribution to the preset type is not significant. Therefore, behavioral feature 3 is not used as the target behavioral feature.

[0097] Figure 7 This is a flowchart illustrating a training recognition model and a processing model according to an exemplary embodiment, such as... Figure 7 As shown, the recognition model is trained through the following steps:

[0098] Step A: Obtain the training game operation records generated by the training game client within the preset training time period, and extract multiple training feature values ​​based on the training game operation records.

[0099] Step B involves using multiple training feature values ​​as input to the recognition model and the actual type of the game client as output to train the recognition model.

[0100] For example, before training the recognition model, a sample input set can be obtained. This set includes multiple sample inputs, each containing training feature values ​​for various behavioral characteristics corresponding to a training game client. These training feature values ​​are extracted from the training game operation records generated by the client within a preset training time period. The preset training time period can be any period prior to the current time. An observation window and a performance window can be set to determine the preset training time period. For instance, if the observation window is 14 days, the performance window is 7 days, and the preset time period is within 14 days prior to the current moment, then the preset training time period could be within 21 days prior to the current moment. The training game operation records collected within the 7 days prior to the current moment can be used to validate the recognition model, while the training game operation records collected between the 7 and 21 days prior to the current moment can be used to train the recognition model.

[0101] After obtaining the sample input set, the sample output set can be further obtained. The sample output set includes the sample output corresponding to each sample input, and each sample output includes the real type to which the corresponding training game client belongs.

[0102] When training a recognition model, any sample input can be used as the input to the recognition model, and the corresponding sample output can be used as the output to train the model. This ensures that when a sample is input, the model's output matches the corresponding sample output. A loss function can be determined based on the model's output and the sample output. To reduce the loss function, the backpropagation algorithm is used to correct the neuron parameters in the recognition model. These parameters can be, for example, the neuron's weights and biases. This process is repeated until the loss function meets a preset condition, such as its value being less than a preset loss threshold, thus achieving the goal of training the recognition model.

[0103] The processing model is trained through the following steps:

[0104] Step C: Train the processing model based on multiple training feature values ​​and the real type of the training game client.

[0105] For example, any sample input can be used as the input to the processing model, and the corresponding sample output can be used as the output to train the processing model. Alternatively, the sample input set for training the processing model can be determined from the sample input set used to train the recognition model. The sample input set for training the processing model also includes multiple sample inputs, each containing training feature values ​​for various target behavior features corresponding to the training game client. Then, the sample output set used to train the recognition model can be used as the sample output set for training the processing model.

[0106] When training the processing model, the training feature values ​​of various target behavior features corresponding to any training game client can be used as the input to the processing model, and the sample output corresponding to that training game client can be used as the output of the processing model. This process trains the processing model so that its output matches the corresponding sample output. Based on the output of the processing model and the sample output, a loss function can be determined. With the goal of reducing the loss function, the backpropagation algorithm is used to correct the neuron parameters in the processing model. The above steps are repeated until the loss function meets the preset conditions, thus achieving the purpose of training the processing model.

[0107] In summary, this disclosure first obtains game operation records generated by the game client within a preset time period and extracts multiple behavioral feature values ​​from these records. Then, it identifies the game client type based on these behavioral feature values. If the game client is a preset type, it determines the contribution score of each behavioral feature value to the preset type based on the multiple behavioral feature values. Finally, it determines the game configuration for the game client based on the contribution score corresponding to each behavioral feature value. This disclosure extracts multiple behavioral feature values ​​from game operation records and uses these to determine the game client type and the contribution score of each behavioral feature value, thereby obtaining a game configuration suitable for the game client.

[0108] Figure 8 This is a block diagram illustrating a game data processing apparatus according to an exemplary embodiment, such as... Figure 8 As shown, the device 200 includes:

[0109] The acquisition module 201 is used to acquire game operation records generated by the game client within a preset time period, and extract individual behavioral feature values ​​based on the game operation records.

[0110] The type determination module 202 is used to identify the type of the game client based on multiple behavioral feature values.

[0111] The processing module 203 is used to determine the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values ​​if the game client is of a preset type.

[0112] The configuration determination module 204 is used to determine the game configuration for the game client based on the contribution score corresponding to each behavioral feature value.

[0113] Figure 9 This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment, such as... Figure 9 As shown, the type determination module 202 is used for:

[0114] Multiple behavioral feature values ​​are input into a pre-trained recognition model to obtain the type of game client output by the recognition model.

[0115] Processing module 203 may include:

[0116] The first processing submodule 2031 is used to determine the matching probability between the game client and the preset type based on multiple behavioral feature values ​​using a pre-trained processing model.

[0117] The second processing submodule 2032 is used to determine the contribution score of each behavioral feature value to the preset type based on the matching probability between the game client and the preset type.

[0118] In one implementation, the configuration determination module 204 can be used for:

[0119] For each behavioral feature value, if the contribution score corresponding to the behavioral feature value is greater than or equal to a preset threshold, the game configuration is determined based on the behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size for the behavioral feature value.

[0120] In another implementation, the configuration determination module 204 can be used for:

[0121] Compare the behavioral feature value with the corresponding feature mean, and determine the adjustment direction based on the comparison result. And / or,

[0122] The adjustment size is determined based on the characteristic value of the behavior and the statistical distribution corresponding to the characteristic value.

[0123] Configuration determination module 204 can also be used for:

[0124] If the game client is a preset type, the game configuration is determined based on each behavioral feature value and the statistical distribution corresponding to that behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size of at least one behavioral feature value.

[0125] Figure 10 This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment, such as... Figure 10 As shown, the device 200 may further include:

[0126] The filtering module 205 is used to determine the target behavioral feature value that meets the preset conditions from multiple behavioral feature values.

[0127] Accordingly, the processing module 203 can be used to: determine the contribution score of each target behavior feature value to the preset type based on multiple target behavior feature values.

[0128] The configuration determination module 204 can be used to determine the game configuration based on the contribution score corresponding to each target behavior feature value.

[0129] Figure 11This is a block diagram illustrating another game data processing apparatus according to an exemplary embodiment, such as... Figure 11 As shown, the device 200 may further include:

[0130] The pre-acquisition module 206 is used to acquire historical game operation records of multiple sample game clients and extract historical feature value sequences corresponding to each behavioral feature based on the historical game operation records. The historical feature value sequences include historical feature values ​​of multiple sample game clients corresponding to the behavioral feature.

[0131] Preprocessing module 207 is used to determine the historical contribution score sequence of each behavioral feature to a preset type based on the historical feature value sequence corresponding to multiple behavioral features. The historical contribution score sequence includes the historical contribution scores of multiple sample game clients to the corresponding behavioral feature.

[0132] The target feature determination module 208 is used to determine the target behavioral features based on the historical contribution scoring sequence of each behavioral feature for a preset type.

[0133] Accordingly, the filtering module 205 can be used to: select the behavioral feature value corresponding to the target behavioral feature from multiple behavioral feature values ​​as the target behavioral feature value.

[0134] In one implementation, the target feature determination module 208 can be used to:

[0135] For each behavioral feature, if the dispersion of that behavioral feature to the historical contribution score sequence of the preset type is greater than the preset dispersion threshold, then that behavioral feature is determined as the target behavioral feature.

[0136] In another implementation, the recognition model is trained through the following steps:

[0137] Step A: Obtain the training game operation records generated by the training game client within the preset training time period, and extract multiple training feature values ​​based on the training game operation records.

[0138] Step B involves using multiple training feature values ​​as input to the recognition model and the actual type of the game client as output to train the recognition model.

[0139] The processing model is trained through the following steps:

[0140] Step C: Train the processing model based on multiple training feature values ​​and the real type of the training game client.

[0141] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0142] In summary, this disclosure first obtains game operation records generated by the game client within a preset time period and extracts multiple behavioral feature values ​​from these records. Then, it identifies the game client type based on these behavioral feature values. If the game client is a preset type, it determines the contribution score of each behavioral feature value to the preset type based on the multiple behavioral feature values. Finally, it determines the game configuration for the game client based on the contribution score corresponding to each behavioral feature value. This disclosure extracts multiple behavioral feature values ​​from game operation records and uses these to determine the game client type and the contribution score of each behavioral feature value, thereby obtaining a game configuration suitable for the game client.

[0143] The following is for reference. Figure 12 This document illustrates a structural diagram of an electronic device 300 suitable for implementing embodiments of the present disclosure (which can be understood as the main body performing the above embodiments, such as a terminal device or a server). The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 12 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0144] like Figure 12 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0145] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 12An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0146] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure 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 device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of embodiments of this disclosure.

[0147] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0148] In some implementations, terminal devices and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0149] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0150] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records; identify the type of the game client based on the multiple behavioral feature values; when the game client is a preset type, determine a contribution score for each behavioral feature value to the preset type based on the multiple behavioral feature values; and determine the game configuration for the game client based on the contribution score corresponding to each behavioral feature value.

[0151] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0153] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The name of a module does not necessarily limit the module itself; for example, an acquisition module can also be described as a "module for acquiring game operation records".

[0154] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0155] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0156] According to one or more embodiments of this disclosure, Example 1 provides a game data processing method, including: acquiring game operation records generated by a game client within a preset time period, and extracting multiple behavioral feature values ​​based on the game operation records; identifying the type of the game client based on the multiple behavioral feature values; when the game client is a preset type, determining a contribution score for each behavioral feature value to the preset type based on the multiple behavioral feature values; and determining a game configuration for the game client based on the contribution score corresponding to each behavioral feature value.

[0157] According to one or more embodiments of this disclosure, Example 2 provides the method of Example 1, wherein identifying the type of the game client based on a plurality of behavioral feature values ​​includes: inputting the plurality of behavioral feature values ​​into a pre-trained recognition model to obtain the type of the game client output by the recognition model; and determining the contribution score of each behavioral feature value to the preset type based on the plurality of behavioral feature values ​​includes: using a pre-trained processing model to determine the matching probability of the game client with the preset type based on the plurality of behavioral feature values; and determining the contribution score of each behavioral feature value to the preset type based on the matching probability of the game client with the preset type.

[0158] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 1, wherein determining the game configuration for the game client based on the contribution score corresponding to each of the behavioral feature values ​​includes: for each of the behavioral feature values, if the contribution score corresponding to the behavioral feature value is greater than or equal to a preset threshold, determining the game configuration based on the behavioral feature value, wherein the game configuration includes the adjustment direction and / or adjustment size for the behavioral feature value.

[0159] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 3, wherein determining the game configuration based on the behavioral feature value includes: comparing the behavioral feature value with the mean value of the feature corresponding to the behavioral feature value, and determining the adjustment direction based on the comparison result; and / or, determining the adjustment size based on the behavioral feature value and the statistical distribution corresponding to the behavioral feature value.

[0160] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 1, the method further comprising: when the game client is a preset type, determining the game configuration based on each of the behavioral feature values ​​and the statistical distribution corresponding to the behavioral feature value, the game configuration including the adjustment direction and / or adjustment size of at least one of the behavioral feature values.

[0161] According to one or more embodiments of this disclosure, Example 6 provides the method of Example 1, the method further comprising: determining a target behavioral feature value that meets preset conditions among a plurality of behavioral feature values; determining a contribution score of each behavioral feature value to the preset type based on the plurality of behavioral feature values, comprising: determining a contribution score of each target behavioral feature value to the preset type based on the plurality of target behavioral feature values; determining a game configuration for the game client based on the contribution score corresponding to each behavioral feature value, comprising: determining the game configuration based on the contribution score corresponding to each target behavioral feature value.

[0162] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 6, the method further comprising: acquiring historical game operation records of multiple sample game clients, and extracting a historical feature value sequence corresponding to each behavioral feature based on the historical game operation records, the historical feature value sequence including historical feature values ​​of multiple sample game clients corresponding to the behavioral feature; determining a historical contribution score sequence for each behavioral feature to the preset type based on the historical feature value sequences corresponding to the multiple behavioral features, the historical contribution score sequence including historical contribution scores of multiple sample game clients corresponding to the behavioral feature; determining a target behavioral feature based on the historical contribution score sequence for each behavioral feature to the preset type; the step of determining a target behavioral feature value that meets preset conditions among the multiple behavioral feature values ​​includes: taking the behavioral feature value corresponding to the target behavioral feature as the target behavioral feature value among the multiple behavioral feature values.

[0163] According to one or more embodiments of this disclosure, Example 8 provides the method of Example 7, wherein determining a target behavioral feature based on the historical contribution scoring sequence of the preset type for each behavioral feature includes: for each behavioral feature, if the dispersion of the behavioral feature to the historical contribution scoring sequence of the preset type is greater than a preset dispersion threshold, determining the behavioral feature as the target behavioral feature.

[0164] According to one or more embodiments of this disclosure, Example 9 provides the method of Example 2, wherein the recognition model is trained by the following steps: acquiring training game operation records generated by the training game client within a preset training time period, and extracting multiple training feature values ​​based on the training game operation records; using the multiple training feature values ​​as input to the recognition model, and using the real type to which the training game client belongs as output to the recognition model, to train the recognition model; the processing model is trained by the following steps: training the processing model based on the multiple training feature values ​​and the real type to which the training game client belongs.

[0165] According to one or more embodiments of this disclosure, Example 10 provides a game data processing apparatus, comprising: an acquisition module, configured to acquire game operation records generated by a game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records; a type determination module, configured to identify the type of the game client based on the multiple behavioral feature values; a processing module, configured to determine a contribution score of each behavioral feature value to the preset type based on the multiple behavioral feature values ​​when the game client is of a preset type; and a configuration determination module, configured to determine a game configuration for the game client based on the contribution score corresponding to each behavioral feature value.

[0166] According to one or more embodiments of the present disclosure, Example 11 provides a computer-readable medium having a computer program stored thereon that, when executed by a processing device, implements the steps of the methods described in Examples 1 to 9.

[0167] According to one or more embodiments of this disclosure, Example 12 provides an electronic device including: a storage device having a computer program stored thereon; and a processing device for executing the computer program in the storage device to implement the steps of the methods described in Examples 1 to 9.

[0168] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0169] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0170] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A game data processing method, characterized in that, The method includes: Acquire game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records; Multiple behavioral feature values ​​are input into a pre-trained recognition model to obtain the type of the game client output by the recognition model; When the game client is of a preset type, a contribution score for each of the behavioral feature values ​​to the preset type is determined based on multiple behavioral feature values. Based on the contribution score corresponding to each of the aforementioned behavioral feature values, the game configuration for the game client is determined; The step of determining the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values ​​includes: Using a pre-trained processing model, the matching probability between the game client and the preset type is determined based on multiple behavioral feature values; Based on the matching probability between the game client and the preset type, determine the contribution score of each behavioral feature value to the preset type.

2. The method according to claim 1, characterized in that, The step of determining the game configuration for the game client based on the contribution score corresponding to each behavioral feature value includes: For each of the behavioral feature values, if the contribution score corresponding to the behavioral feature value is greater than or equal to a preset threshold, the game configuration is determined based on the behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size for the behavioral feature value.

3. The method according to claim 2, characterized in that, Determining the game configuration based on the behavioral characteristic value includes: Compare the behavioral feature value with the mean feature value corresponding to the behavioral feature value, and determine the adjustment direction based on the comparison result; and / or, The adjustment size is determined based on the behavioral characteristic value and the statistical distribution corresponding to the behavioral characteristic value.

4. The method according to claim 1, characterized in that, The method further includes: When the game client is a preset type, the game configuration is determined based on each behavioral feature value and the statistical distribution corresponding to that behavioral feature value. The game configuration includes the adjustment direction and / or adjustment size of at least one of the behavioral feature values.

5. The method according to claim 1, characterized in that, The method further includes: Among the multiple behavioral feature values, a target behavioral feature value that meets the preset conditions is determined; The step of determining the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values ​​includes: Based on multiple target behavior feature values, determine the contribution score of each target behavior feature value to the preset type; The step of determining the game configuration for the game client based on the contribution score corresponding to each behavioral feature value includes: The game configuration is determined based on the contribution score corresponding to each of the target behavior feature values.

6. The method according to claim 5, characterized in that, The method further includes: The historical game operation records of multiple sample game clients are obtained, and the historical feature value sequence corresponding to each behavioral feature is extracted based on the historical game operation records. The historical feature value sequence includes the historical feature values ​​of multiple sample game clients corresponding to the behavioral feature. Based on the historical feature value sequences corresponding to the various behavioral features, a historical contribution score sequence for each behavioral feature to the preset type is determined, wherein the historical contribution score sequence includes the historical contribution scores of multiple sample game clients for the corresponding behavioral feature; The target behavioral feature is determined based on the historical contribution score sequence of each of the aforementioned behavioral features to the preset type; The step of determining a target behavioral feature value that meets preset conditions from among multiple behavioral feature values ​​includes: Among the multiple behavioral feature values, the behavioral feature value corresponding to the target behavioral feature is taken as the target behavioral feature value.

7. The method according to claim 6, characterized in that, The step of determining the target behavioral feature based on the historical contribution scoring sequence of the preset type for each behavioral feature includes: For each of the aforementioned behavioral features, if the dispersion of that behavioral feature for the historical contribution score sequence of the preset type is greater than a preset dispersion threshold, then that behavioral feature is determined as the target behavioral feature.

8. The method according to claim 1, characterized in that, The recognition model is trained through the following steps: Acquire training game operation records generated by the training game client within a preset training time period, and extract multiple training feature values ​​based on the training game operation records; The recognition model is trained by using multiple training feature values ​​as inputs and the real type of the training game client as output. The processing model is trained through the following steps: The processing model is trained based on multiple training feature values ​​and the actual type of the training game client.

9. A game data processing device, characterized in that, The device includes: The acquisition module is used to acquire game operation records generated by the game client within a preset time period, and extract multiple behavioral feature values ​​based on the game operation records; The type determination module is used to input multiple behavioral feature values ​​into a pre-trained recognition model to obtain the type of the game client output by the recognition model; The processing module is used to determine the contribution score of each behavioral feature value to the preset type based on multiple behavioral feature values ​​when the game client is of a preset type. The configuration determination module is used to determine the game configuration for the game client based on the contribution score corresponding to each of the behavioral feature values. The processing module includes: The first processing submodule is used to determine the matching probability between the game client and the preset type based on multiple behavioral feature values ​​using a pre-trained processing model. The second processing submodule is used to determine the contribution score of each behavioral feature value to the preset type based on the matching probability between the game client and the preset type.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processing device, it implements the steps of the method described in any one of claims 1-8.

11. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-8.

Images