Information processing method and related equipment

Abstract

The embodiment of the invention provides an information processing method and related equipment, and the method comprises the steps: displaying a sharing interface which comprises a sharing option and to-be-shared information; in response to a triggering operation of the sharing option, obtaining feature data of each game object in a plurality of game objects; based on the feature data of each game object, response indication information of each game object to the to-be-shared information is determined, and the response indication information comprises a response probability used for representing that the game object responds to the to-be-shared information; and determining a target game object from the plurality of game objects according to the response probability that each game object responds to the to-be-shared information, and sharing the to-be-shared information to the target game object. According to the embodiment of the invention, the shared objects can be screened in a targeted manner, so that more effective information sharing is realized.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an information processing method and related equipment. Background Art

[0002] With the development of Internet technology, game objects can now share information with other game objects. For example, a game object can share a game activity with other game objects so that other game objects can quickly participate in the game interaction through sharing, achieving object reflux. However, existing sharing methods mainly rely on game objects manually selecting game objects (such as friends) to share with. However, the friends shared with may not respond to the information shared by the game object, which makes sharing ineffective. How to better share information has become a hot research issue. Summary of the Invention

[0003] The embodiments of the present application provide an information processing method and related equipment, which can perform targeted screening of shared objects, thereby achieving more effective information sharing.

[0004] In one aspect, an embodiment of the present application provides an information processing method, the method comprising:

[0005] Display the sharing interface, which includes sharing options and information to be shared;

[0006] In response to a triggering operation of the sharing option, obtaining feature data of each of the plurality of game objects;

[0007] Determining response indication information of each game object to the information to be shared based on the characteristic data of each game object, the response indication information including a response probability indicating that the game object responds to the information to be shared;

[0008] According to the response probability of each game object responding to the information to be shared, a target game object is determined from multiple game objects, and the information to be shared is shared to the target game object.

[0009] In one aspect, an embodiment of the present application provides an information processing device, comprising:

[0010] A display unit, configured to display a sharing interface including sharing options and information to be shared;

[0011] a processing unit, configured to obtain feature data of each of the plurality of game objects in response to a triggering operation of a sharing option;

[0012] The processing unit is further configured to determine, based on the characteristic data of each game object, response indication information of each game object to the information to be shared, wherein the response indication information includes a response probability indicating that the game object responds to the information to be shared;

[0013] The processing unit is further configured to determine a target game object from a plurality of game objects based on a response probability of each game object responding to the information to be shared, and share the information to be shared with the target game object.

[0014] The processing unit is specifically used for:

[0015] Get the activity parameter of each game object, which is used to indicate the activity level of the game object in the game;

[0016] Determine the sharing response value of each game object based on the response probability and activity parameters of each game object in responding to the shared information;

[0017] According to the sharing response value of each game object, a game object is selected from multiple game objects as a target game object.

[0018] The processing unit is specifically used for:

[0019] Select the game object with the largest shared response value as the target game object; or,

[0020] Sort multiple game objects in descending order of their sharing response values, and select the first M game objects from the sorted multiple game objects as target game objects, where M is a positive integer.

[0021] The processing unit is specifically used for:

[0022] Sort multiple game objects in descending order of their sharing response values, and select the first N game objects from the sorted game objects; N is a positive integer;

[0023] Output N game objects;

[0024] In response to a selection operation on N game objects, the game object indicated by the selection operation is used as a target game object.

[0025] The response probability of each game object to respond to the shared information is determined based on a sharing prediction model, which includes K regression trees, where K is an integer greater than 1; and a processing unit, specifically configured to:

[0026] For any game object among the multiple game objects, input feature data of any game object into each regression tree, perform response prediction of any game object to the shared information, and obtain a response prediction value of any game object to the shared information output by each regression tree;

[0027] Determine the response probability of any game object responding to the information to be shared based on the predicted response value of any game object to the information to be shared output by each regression tree;

[0028] Response indication information of any game object to the information to be shared is generated according to the response probability of any game object responding to the information to be shared.

[0029] The processing unit is specifically used for:

[0030] Obtaining initial feature data of each of the multiple game objects;

[0031] Perform feature construction on the initial feature data of each game object to obtain feature data of each game object;

[0032] Among them, feature construction includes one or more of the following: constructing missing values ​​for the initial feature data of each game object; discretizing the initial feature data of each game object; and normalizing the initial feature data of each game object.

[0033] The processing unit is specifically used for:

[0034] Determine maximum initial feature data and minimum initial feature data from the initial feature data of the plurality of game objects;

[0035] determining a second data difference between the maximum initial feature data and the minimum initial feature data;

[0036] The feature data of each game object is determined according to the first data difference value and the second data difference value between the initial feature data of each game object and the minimum initial feature data.

[0037] In one aspect, an embodiment of the present application provides a computer device, comprising:

[0038] a processor suitable for executing a computer program;

[0039] Computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the above information processing method is implemented.

[0040] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is loaded by a processor and executes the above-mentioned information processing method.

[0041] On the one hand, an embodiment of the present application provides a computer program product, which includes a computer program or computer instructions, and when the computer program or computer instructions are executed by a processor, the above-mentioned information processing method is implemented.

[0042] In an embodiment of the present application, a sharing interface is displayed, which includes a sharing option and information to be shared; in response to a triggering operation of the sharing option, characteristic data of each game object in a plurality of game objects is obtained; based on the characteristic data of each game object, response indication information of each game object to the information to be shared is determined, and the response indication information includes a response probability for indicating that the game object responds to the information to be shared; based on the response probability of each game object responding to the information to be shared, a target game object is determined from the plurality of game objects, and the information to be shared is shared to the target game object. It can be seen that the screening of the shared objects (i.e., the target game objects) can be completed in a targeted manner according to the response probability, thereby achieving more effective sharing; in addition, the response probability represents the probability (i.e., possibility) that the shared objects can respond to the information to be shared, which can ensure to a certain extent that the shared objects can respond to the information to be shared, and can also achieve effective sharing of information. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 An architectural diagram of an information processing system provided in an embodiment of the present application;

[0045] Figure 2 A flowchart of an information processing method provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of a sharing interface provided in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of the entire life cycle of a game object in a game provided in an embodiment of the present application;

[0048] Figure 5 A flowchart of an information processing method provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of selecting a game object to share provided in an embodiment of the present application;

[0050] Figure 7 A structural diagram of a sharing prediction model provided in an embodiment of the present application;

[0051] Figure 8 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0052] Figure 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] The implementation of this application provides an information processing solution, which includes three parts: ① Feature construction: When a certain game object (hereinafter referred to as a sharing object) wants to share game-related information (such as game-related activities and gameplay), the sharing option in the sharing interface can be triggered. In response to the triggering operation of the sharing option, the computer device can obtain the feature data of each game object in multiple game objects (the feature data here can include, for example, behavioral characteristics, attribute information, etc. in the game). ② Response indication information determination: Based on the feature data of each game object, the response indication information of each game object to the shared information is determined. The response indication information includes a response probability for indicating that the game object responds to the shared information. Specifically, the embodiment of this application can predict the response probability of the game object to respond to the shared information based on the feature data of each game object through artificial intelligence (AI). ③ Sharing game object fission: According to the response probability of the game object to respond to the shared information, the target game object is determined from multiple game objects. For example, the game object corresponding to the maximum response probability is used as the target game object, and the information to be shared is shared to the target game object.

[0055] In some optional implementations, an activity parameter may be introduced, which is used to indicate the activity level of a game object in the game. The higher the activity level, the more likely the game object is to respond to shared information. The embodiment of the present application may determine a target game object from multiple game objects based on the probability of the game object responding to shared information and the activity parameter. This may increase the likelihood of the target game object responding to shared information, thereby increasing the effectiveness of sharing.

[0056] In summary, through the information processing scheme provided by the embodiment of the present application, the response probability of the game object to the information to be shared can be predicted based on the characteristic data of the game object. In this way, the screening of the shared object (i.e., the object of the shared information, such as the target game object) can be completed in a targeted manner based on the response probability, thereby achieving more effective sharing and reducing information interference with the shared object to a certain extent. In addition, the response probability is used to represent the probability (i.e., possibility) that the shared object can respond to the information to be shared. In this way, it can ensure to a certain extent that the shared object can respond to the information to be shared, and can also achieve effective sharing of information, thereby improving the effectiveness of information sharing. If the information to be shared is a game activity, sharing the information to be shared with the game object through the response probability can allow the game object to also participate in the game activity, thereby improving the effectiveness of information sharing and successfully achieving the purpose of game object reflux. In addition, it can avoid sharing the game object multiple times, which causes information interference to the game object.

[0057] Next, the technical terms involved in the embodiments of this application are explained.

[0058] (1) AI:

[0059] AI is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI also involves studying the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0060] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, pre-trained models, operating / interaction systems, and mechatronics. Pre-trained models, also known as large models or basic models, can be fine-tuned and widely applied to downstream tasks across various AI disciplines. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0061] Machine learning (ML) is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning. Ensemble models are a development of deep learning, integrating these techniques.

[0062] (2) Integrated model

[0063] Model ensemble is a technique that combines multiple independently trained learners to improve overall performance. This approach leverages the different strengths and learning characteristics of multiple learners in the hope of achieving better generalization, robustness, and performance after integration.

[0064] Among them, the integrated model can be, for example, a boosting model. The boosting model adopts a multi-decision tree integration strategy to fit the residual (residual refers to the difference between the predicted result and the actual result) to reduce the bias and variance of the model. Specifically, for the data set input to the boosting, the latter decision tree learns the residual of the previous decision tree, and adds the prediction results of the decision tree to obtain the final prediction result. Among them, the decision tree is a kind of learner. The decision tree is a tree structure. Each node of the decision tree represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. Among them, the decision tree can include but is not limited to a regression tree.

[0065] In an embodiment of the present application, the integrated model may be a boosting model that integrates multiple regression trees. By utilizing the classification and regression capabilities of the multiple regression trees, the prediction of the game object's response to the shared information is achieved. In this embodiment of the present application, each node in the regression tree represents a feature in the feature data, each branch represents the predicted response of the game object to the shared information, and each leaf node represents the predicted response value of the game object in response to the shared information.

[0066] (3) Information to be shared

[0067] The information to be shared refers to information that needs to be shared with the game object. The information to be shared can be associated with the game, such as activities related to the game, game play, etc. For example, the information to be shared is an activity to find missing objects in the game. The so-called missing objects in the game refer to objects that are not active in the game within a period of time (such as a week, a month, etc.). Among them, indicators for measuring whether the game object is active can be, for example, the number of logins, online time, etc.; for example, if the number of logins of a game object in the game is less than the number threshold, the game object is considered to be inactive in the game. Conversely, if the number of logins of a game object in the game is greater than or equal to the number threshold, the game object is considered to be active in the game. In addition, the information to be shared can also be activities related to other applications (such as social communication applications), etc. The embodiments of the present application do not impose any restrictions on the information to be shared.

[0068] Next, the information processing system provided in the embodiments of the present application will be described.

[0069] See Figure 1 , is an architectural diagram of an information processing system provided in an embodiment of the present application. Figure 1As shown, the information processing system may include terminal device 101, terminal device 102... and more terminal devices, and this application does not limit the number of terminal devices. The information processing system also includes a server 103. Of course, the number of servers can also be multiple, and this application still does not limit this. Terminal device 101 and terminal device 102 can be devices used by game objects, and game applications, social applications, etc. can be run on the terminal devices. Terminal device 101 and terminal device 102 can be used to display a sharing interface, and the sharing interface includes sharing options and information to be shared, wherein terminal device 101 and terminal device 102 can be smart phones, tablet computers, laptops, desktop computers, smart cars, smart wearable devices, etc. Server 103 can be used to store feature data of game objects, and the feature data here can include, for example, attribute information (such as game level, age, etc.), behavioral characteristics (such as time of logging into the game, number of activity participations, game login duration, etc.). The server 103 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Any terminal device in the information processing system may be directly or indirectly connected to the server 103 via wired or wireless communication, and any two terminal devices may exchange information via the server 103.

[0070] In one embodiment, combined Figure 1 The terminal device and the server shown illustrate the information processing flow between the terminal device and the server, which includes the following steps:

[0071] ① When game object 1 wants to share information, game object 1 can trigger (e.g., single-click, double-click, etc.) a sharing option in the sharing interface displayed by terminal device 101. In response to the triggering operation of the sharing option, terminal device 101 obtains feature data of each of the multiple game objects from server 103. The game objects here can be objects in the same game.

[0072] ② The terminal device 101 can determine the response indication information of each game object based on the characteristic data of each game object. The response indication information includes a response probability indicating that the game object responds to the information to be shared.

[0073] ③ The terminal device 101 determines the target game object from multiple game objects based on the response probability of the game object responding to the shared information. Assuming that the game object with the highest response probability is game object 2, game object 2 is determined as the target game object.

[0074] ④ The terminal device 101 can share the information to be shared with the terminal device 102 used by the target game object through the server 103, that is, share the information to be shared with the terminal device 102 used by the game object 2.

[0075] ⑤ The terminal device 102 receives the information to be shared and displays it, and the game object 2 can respond to the information to be shared. For example, the information to be shared is an activity to find a missing object in the game, then the game object 2 can re-enter the game through the information to be shared and participate in the missing object activity.

[0076] To sum up, through the above-mentioned interaction process between the terminal device and the server, the game object can trigger the sharing option when sharing information, and the terminal device can respond to the sharing option. The response probability of the game object to respond to the shared information is determined based on the characteristic data of the game object. According to the response probability, the screening of the shared objects can be completed in a targeted manner to achieve more effective sharing, and to a certain extent, the information interference to the shared objects can be reduced; in addition, the response probability is used to indicate the probability (i.e., possibility) that the shared object can respond to the shared information, which can ensure to a certain extent that the shared object can respond to the shared information, and can also achieve effective sharing of information, thereby improving the effectiveness of information sharing.

[0077] It should be noted that the above-described information processing interaction process is for illustrative purposes only and does not limit the specific execution process of the terminal device and the server. Optionally, obtaining characteristic data of each game object and determining response indication information for each game object based on the characteristic data of each game object, and determining a target game object from multiple game objects based on the response probability of each game object responding to the shared information can be performed by the server; or, determining the response indication information for each game object based on the characteristic data of each game object can be performed by the server, and determining the target game object can be performed by the terminal device.

[0078] It can be understood that the system architecture diagram described in the embodiment of the present application is intended to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0079] In addition, it should be noted that in this application, the relevant data involved in the information processing process, for example, attribute information of a game object, behavioral data, activity participation data, etc. When the above embodiments of this application are applied to specific products or technologies, the permission or consent of the object must be obtained, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and comply with the principles of legality, legitimacy and necessity, and does not involve the acquisition of data types prohibited or restricted by laws and regulations. In some optional embodiments, the relevant data involved in the embodiments of this application are obtained after the object has been separately authorized. In addition, when obtaining the separate authorization of the object, the purpose of the relevant data involved is indicated to the object.

[0080] Next, the information processing method provided in the embodiments of the present application is described.

[0081] See Figure 2 , is a flow chart of an information processing method provided in an embodiment of the present application. The information processing method can be executed by a computer device, which can be a terminal device or server in the above-mentioned information processing system. The information processing method can include the following steps S201-S204:

[0082] S201: Display a sharing interface, which includes sharing options and information to be shared.

[0083] The sharing options and information to be shared can be fixedly displayed at any position in the sharing interface, such as the top, bottom, middle, etc., and the present embodiment does not impose any limitation on this. Figure 3 As shown in FIG, a schematic diagram of a sharing interface provided by an embodiment of the present application. Figure 3 In the example, the sharing option is displayed at position 31 in the sharing interface 301; the information to be shared is displayed at position 32 in the sharing interface 301. In addition, the sharing option can also be displayed in a floating manner on the sharing interface. The embodiment of the present application does not impose any limitation on the display method of the sharing option and the information to be shared.

[0084] The information to be shared can be related to the game, such as game activities, game play, etc. For example, for a game object in a certain game, the entire life cycle of the game object in the game is as follows: Figure 4As shown, the entire life cycle of a game object in the game includes the new user acquisition stage (i.e., just joined the game), the active stage (i.e., active in the game for a period of time), the retention stage (i.e., still active after a period of time), the silent stage (i.e., occasionally participating in the game for a period of time), and the churn stage (i.e., no longer participating in the game for a period of time, that is, the activity value is less than the activity threshold for a period of time). Then, the information to be shared can be an activity for finding game churn objects. Of course, the information to be shared can also be other information related to other social applications, and the embodiments of this application do not impose any restrictions on this.

[0085] S202: In response to a triggering operation of a sharing option, obtain feature data of each of a plurality of game objects.

[0086] Among them, triggering operations may include but are not limited to: single-click operation, double-click operation, sliding operation, etc.; characteristic data may include but are not limited to: attribute information, behavior data, activity participation data, etc.; among them, attribute information may include but is not limited to: object attributes (such as object name, object location), login terminal, game registration time, login system (such as Android system, Apple system), etc. Active behavior may include but is not limited to: the number of weekly game login days in the past L weeks (such as L can be 2, 4, etc.), the growth rate of weekly login days compared to the previous month, the weekly game online time in the past L weeks, the growth rate of weekly online time compared to the previous month, the number of weekly game logins in the past L weeks (for example, if Game A and Game B are logged in in a certain week, the number of game logins in that week is 2), the growth rate of weekly game logins compared to the previous month, the increase in the average daily login days on weekends compared to the average daily login days on weekdays in the past L weeks, the proportion of login time in each time period (such as morning, noon, after get off work, early morning, etc.) in the past L weeks, and the change in combat power value in the game in the past L weeks. Activity participation data includes but is not limited to: the cumulative number of login days for participating in a certain activity (for example, if the game object has participated in game activity 1 for 5 days, then the cumulative number of login days for participating in game interaction 1 is 5), active period (for example, if the game object is active from 10:00 to 12:00, then the active period is 2 hours), click operations on the activity module, the number of resources collected at each level of the activity, the number of coupons collected at each level, the number of tasks completed, etc.

[0087] In this embodiment, multiple game objects can be determined for candidate games to participate in the game, which can increase the probability of subsequent game objects responding to the shared information. The method of determining multiple game objects can include the following methods:

[0088] Method 1: randomly select multiple candidate game objects from the candidate game objects participating in the game as game objects.

[0089] Method 2: To achieve the return of lost game objects, multiple game objects can be determined by obtaining the activity of candidate game objects within a target time period, and then determining candidate game objects with activity levels less than an activity threshold from the candidate game objects, and then determining the candidate game objects with activity levels less than the activity threshold as game objects. The activity threshold can be set as needed, and activity levels can include, but are not limited to, the number of times the candidate game object logs into the game within the target time period, the number of times the candidate game object participates in game-related activities, and the length of time the game is online (e.g., the length of time the game is online for a specific game or for multiple games). If activity levels include game online time, for example, if a candidate game object has been online for 10 hours within the target time period, then the activity level of the candidate game object is 10.

[0090] Method three: The method for determining multiple game objects can be: according to the identifier of the sharing object that initiates sharing, obtain candidate game objects (such as friends) that have a social relationship with the sharing object, and determine the obtained candidate game objects that have a social relationship with the sharing object as game objects.

[0091] Method 4: When the game objects determined based on the candidate game objects that have a social relationship with the sharing object are insufficient, other candidate game objects can be obtained as game objects. Specifically, if the number of game objects determined by the obtained candidate game objects that have a social relationship with the sharing object is less than the quantity threshold, then based on the quantity threshold and the quantity difference between the number of objects, the game objects are determined from the candidate game objects that do not have a social relationship with the sharing object. The candidate game objects that do not have a social relationship with the sharing object may be objects that play games together, objects that have watched the shared object play games, objects that have liked the shared object, etc., and the embodiments of the present application do not impose any restrictions on this. Among them, determining the game object from the candidate game objects that do not have a social relationship with the sharing object may include: randomly selecting a candidate game object from the candidate game objects that do not have a social relationship with the sharing object as the game object, or determining a candidate game object that may return as the game object from the candidate game objects that do not have a social relationship with the sharing object. The candidate game object that may return here may, for example, refer to a candidate game object corresponding to an activity level less than the activity threshold; or it may refer to an object that has logged into the game in the recent period of time.

[0092] S203: Determine response indication information of each game object to the information to be shared based on the characteristic data of each game object, where the response indication information includes a response probability indicating that the game object responds to the information to be shared.

[0093] Among them, the response indication information may also include the response time of the game object, the attribute information of the game object, etc. The embodiment of the present application does not impose any limitation on the response indication information.

[0094] In an embodiment of the present application, a sharing prediction model can be pre-trained based on training samples, and a computing device can call the sharing prediction model to predict the response of each game object to the shared information based on the feature data of each game object, and obtain the response probability of each game object to the shared information.

[0095] In one implementation, a correspondence between characteristic data and response probabilities is established. Based on the characteristic data of each game object, the response probability of each game object responding to the information to be shared is determined from the correspondence between the characteristic data and the response probability. For example, if the characteristic data includes online login time, a response probability of 0.3 is associated with an online login time of 1-10 hours; a response probability of 0.4 is associated with an online login time of 11-20 hours; and a response probability of 0.6 is associated with an online login time of 21-30 hours. If the characteristic data of a game object includes an online login time of 28 hours, the response probability of the game object responding to the information to be shared can be determined to be 0.6.

[0096] S204 : Determine a target game object from the plurality of game objects based on the response probability of each game object responding to the information to be shared, and share the information to be shared with the target game object.

[0097] In one implementation, the game object corresponding to the highest response probability may be determined as the target game object. In another implementation, multiple game objects may be sorted in descending order of response probability, and M game objects may be selected from the sorted multiple game objects as target game objects.

[0098] Among them, sharing the information to be shared to the target game object can be: obtaining the attribute information of the target game object, and based on the attribute information, sharing the information to be shared to the target game object. After the sharing is successful, a prompt message can be output, and the prompt message is used to indicate that the information to be shared has been shared to the target game object.

[0099] In an embodiment of the present application, a sharing interface is displayed, which includes a sharing option and information to be shared; in response to a triggering operation of the sharing option, characteristic data of each game object in a plurality of game objects is obtained; based on the characteristic data of each game object, response indication information of each game object to the information to be shared is determined, and the response indication information includes a response probability for indicating that the game object responds to the information to be shared; based on the response probability of each game object responding to the information to be shared, a target game object is determined from the plurality of game objects, and the information to be shared is shared to the target game object. It can be seen that the screening of the objects to be shared can be completed in a targeted manner according to the response probability, more effective sharing can be achieved, and information interference to the objects to be shared can also be reduced; in addition, the response probability is used to indicate the probability (i.e., possibility) that the object to be shared can respond to the information to be shared, which can ensure to a certain extent that the object to be shared can respond to the information to be shared, and can also achieve effective sharing of information, thereby improving the effectiveness of information sharing.

[0100] See Figure 5 , is a flow chart of another information processing method provided in an embodiment of the present application. The information processing method can be executed by a computer device, which can be a terminal device or a server. The information processing method includes the following steps S501-S506:

[0101] S501: Display a sharing interface, which includes sharing options and information to be shared;

[0102] S502: In response to a triggering operation of a sharing option, obtain feature data of each of a plurality of game objects.

[0103] In one implementation, since the acquired feature data of the game objects may be missing, in order to better predict the response probability of each game object to the information to be shared, the embodiment of the present application may perform feature construction on the initial feature data of each game object. Step S502 may include: acquiring initial feature data of each game object from a plurality of game objects; performing feature construction on the initial feature data of each game object to obtain feature data of each game object; wherein the feature construction includes one or more of the following:

[0104] ① When obtaining the initial feature data of each game object, there may be missing data. Therefore, in the embodiment of the present application, considering data integrity, the initial feature data of each game object can be constructed with missing values. Specifically, if a missing game object is determined to have missing initial feature data, the missing initial feature data can be filled to obtain the feature data of the missing game object. In one implementation, the feature data of the missing game object can be constructed based on the initial feature data of other game objects, such as calculating the average value of the initial feature data of other game objects and determining the feature data of the missing game object based on the average value. For example, there are three game objects, namely object 1, object 2 and object 3. Among them, the login duration included in the initial feature data of object 1 is missing. Then the average value of the login duration included in the initial feature data of object 2 and the login duration included in the initial feature data of object 3 can be determined, and the average value can be used as the login duration of object 1, that is, the feature data of object 1 is generated based on the average value. The missing value construction can ensure data integrity to a certain extent, which is more conducive to the subsequent determination of the response probability of the game object to the shared information.

[0105] In addition, in some optional implementations, if the feature data of the game object is rich and sufficient, the game object that is missing the initial feature data can also be deleted.

[0106] ② Discretize the initial feature data of each game object. By discretizing the initial feature data of each game object, the nonlinearity of the subsequent shared prediction model can be increased and the generalization ability of the model can be improved. In one implementation, multiple feature data intervals are pre-divided, and then the feature data interval in which the initial feature data of each game object is located is determined, and the feature data of each game object is determined based on the feature data interval in which the initial feature data of each game object is located. Specifically, each feature data interval corresponds to a discrete value, and the feature data of each game object can be determined based on the discrete value corresponding to the feature data interval in which the initial feature data of each game object is located. Alternatively, the feature data interval in which the initial feature data of each game object is located is hashed, and the calculated hash is used as the feature data of each game object. It should be understood that the initial feature data in the same data interval can mean the same to a certain extent.

[0107] For example, if the initial feature data includes age or game level, it can be discretized by dividing the feature data into intervals. Taking the age range of 1 to 80 as an example, 1-80 can be divided into 10 feature data intervals, that is, the age is divided into (1, 10), (11, 20), (21, 30), (31, 40), (41, 50), ... (71, 80) in sequence; wherein the feature data interval (1, 10) corresponds to a discrete value of 1, the feature data interval (11, 20) corresponds to a discrete value of 2; the feature data interval (21, 30) corresponds to a discrete value of 3, and so on, the feature data interval (71, 80) corresponds to a discrete value of 8; if the initial feature data of a game object includes age 25, then age 25 is discretized, that is, the feature data interval in which age 25 is located is determined to be (21, 30), and then age 25 is discretized into 3, and the final feature data of the game object includes age 3.

[0108] ③ Performing feature construction on the initial feature data of each game object to obtain the feature data of each game object may include: normalizing the initial feature data of each game object. The normalization process can accelerate the speed of model gradient descent and rapid solution. In one implementation, the normalization process includes: determining the maximum initial feature data and the minimum initial feature data from the initial feature data of multiple game objects, and determining a first data difference between the maximum initial feature data and the minimum initial feature data; then calculating a second data difference between the initial feature data of each game object and the minimum initial feature data, and determining the feature data of each game object based on the second data difference between the initial feature data of each game object and the minimum initial feature data and the first data difference.

[0109] The above normalized calculation formula can be expressed as follows: ′ =(zz min ) / (z max -z min ), where z ′ represents the normalized feature data of the game object, z represents the initial feature data of the game object, and z min Represents the minimum initial feature data, z max Indicates the maximum initial feature data.

[0110] For example, the three game objects are object 1, object 2 and object 3; the initial feature data of object 1 includes that the game online time is 5 hours, the initial feature data of object 2 includes that the game online time is 2 hours; the initial feature data of object 3 includes that the game online time is 4 hours; from the initial feature data of these three game objects, the maximum initial feature data is determined to be 5, and the minimum initial feature data is 2. The initial feature data of object 1 is normalized, that is, the feature data of object 1 is: (5-2) / (5-2)=1; the initial feature data of object 2 is normalized, that is, the feature data of object 2 is: (2-2) / (5-2)=0; the initial feature data of object 3 is normalized, that is, the feature data of object 3 is: (4-2) / (5-2)=0.67.

[0111] S503: Determine response indication information of each game object to the information to be shared based on the characteristic data of each game object, where the response indication information includes a response probability indicating that the game object responds to the information to be shared.

[0112] In one implementation, the response probability of the game object responding to the information to be shared may be determined based on a sharing prediction model. The sharing prediction model may be an integrated model, for example, a boosting model. The sharing prediction model may more accurately predict the response probability of the game object responding to the information to be shared. In this embodiment of the present application, the sharing prediction model may include K regression trees, where K is an integer greater than 1. The specific implementation of step S503 includes:

[0113] Step 1: For any of the multiple game objects, input the feature data of the game object into each regression tree, perform a prediction on the response of the game object to shared information, and obtain the predicted response value of the game object to shared information output by each regression tree. For example, there are two game objects, namely Object 1 and Object 2; the feature data of Object 1 is input into each regression tree, and the response prediction of Object 1 to shared information is obtained, and the predicted response value of Object 1 to shared information is obtained. Similarly, the feature data of Object 1 is input into each regression tree, and the response prediction of Object 2 to shared information is obtained, and the predicted response value of Object 2 to shared information is obtained, which is output by each regression tree.

[0114] Step 2: Based on the predicted response value of any game object to the information to be shared output by each regression tree, determine the response probability of any game object responding to the information to be shared. In one implementation, the predicted response values ​​of any game object to the information to be shared output by each regression tree can be summed to obtain the response probability of any game object responding to the information to be shared. For example, in the above example, the predicted response values ​​of object 1 to the information to be shared output by each regression tree are summed to obtain the response probability of object 1 responding to the information to be shared, and the predicted response values ​​of object 2 to the information to be shared output by each regression tree are summed to obtain the response probability of object 2 responding to the information to be shared.

[0115] Step 3: Generate response indication information for each game object based on the probability of each game object responding to the information to be shared. In one implementation, the probability of each game object responding to the information to be shared can be used as the response indication information for each game object. In another implementation, attribute information of each game object can be obtained, and the response indication information for each game object can be generated based on the attribute information and the probability of each game object responding to the information to be shared.

[0116] S504: Obtain an activity parameter of each game object, where the activity parameter is used to indicate the activity level of the game object in the game.

[0117] Among them, the activity parameters may include but are not limited to: number of days logged into the game, number of times logged into the game, online time, etc. The larger the activity parameter of the game object, the more active the game object is in the game.

[0118] S505: Determine a sharing response value for each game object based on the response probability of each game object responding to the information to be shared and the activity parameter.

[0119] Step S505 includes the following implementations:

[0120] (1) Taking into account the different levels of activity of game objects in the game, the response probability can be inflated by the activity parameter. Specifically, the response probability of each game object to the information to be shared and the activity parameter can be multiplied to obtain the sharing response value of each game object; or, the activity parameter of each game object can be logarithmically operated, and the operation result of each game object can be multiplied by the response probability of responding to the information to be shared to obtain the sharing response value of each game object. The calculation formula of the sharing response value is as follows: Sharing response value = P*log(activity parameter). Among them, P represents the response probability of the game object to respond to the information to be shared; log() represents the logarithmic operation.

[0121] (2) The response probability and activity parameter of each game object in responding to the information to be shared are weighted and summed to obtain the sharing response value of each game object. For example, the response probability has a weight of 0.7, and the activity parameter has a weight of 0.3; multiple game objects include object 1 and object 2, and the response probability of object 1 in responding to the information to be shared is 0.8, and the activity parameter is 5; the sharing response value of object 1 is: 0.7*0.8+0.3*5=2.06; the response probability of object 2 in responding to the information to be shared is 0.7, and the activity parameter is 7; the sharing response value of object 1 is: 0.7*0.7+0.3*7=2.59.

[0122] (3) The response probability and activity parameters of each game object in responding to the shared information are summed to obtain the sharing response value of each game object.

[0123] S506: Based on the sharing response value of each game object, a game object is selected from the multiple game objects as the target game object, and the information to be shared is shared with the target game object. The sharing response value indicates the likelihood that the game object will respond to the information to be shared. A larger sharing response value indicates a greater probability that the game object will respond to the information to be shared, thereby improving the effectiveness of sharing and the success rate of sharing.

[0124] According to the sharing response value of each game object, the game object may be selected as the target game object from multiple game objects in the following specific ways, but not limited to:

[0125] (1) Select the game object with the largest sharing response value as the target game object. The maximum sharing response value = max(P*log(active parameter)). By selecting the game object with the largest sharing response value, the likelihood of responding to the shared information can be increased, thereby improving the effectiveness of sharing.

[0126] (2) Sort multiple game objects in descending order of their sharing response values, and select the first M game objects from the sorted multiple game objects as target game objects, where M is a positive integer.

[0127] (3) The game object corresponding to the sharing response value greater than the response threshold is used as the target game object, wherein the response threshold can be set according to needs, and the embodiment of the present application does not impose any limitation on this.

[0128] (4) Selecting a game object as a target game object from a plurality of game objects according to the sharing response value of each game object may specifically include: sorting the plurality of game objects in descending order of the sharing response value of each game object, and selecting the first N game objects from the sorted plurality of game objects; N is a positive integer; outputting N game objects; and in response to a selection operation for the N game objects, using the game object indicated by the selection operation as the target game object. The N game objects may be output in a sharing interface, or the N game objects may be output in another interface independent of the sharing interface. For example, see Figure 6 , is a schematic diagram of selecting a game object to share provided in an embodiment of the present application. Figure 6 In the example, three game objects (i.e., game object A, game object B, and game object C) are displayed in another interface 601 independent of the sharing interface. The sharing object can select a game object from the three game objects to share. For example, if the sharing object selects game object C from the three game objects, in response to the selection operation on game object C, game object C is determined as the target game object. By displaying game objects with higher sharing response values ​​for selection by the sharing object, the effectiveness of the shared information is improved while also increasing the participation of the sharing object and enhancing the object experience.

[0129] In an embodiment of the present application, a sharing interface is displayed, the sharing interface including a sharing option and information to be shared; in response to a triggering operation of the sharing option, characteristic data of each game object among a plurality of game objects is obtained; based on the characteristic data of each game object, response indication information of each game object to the information to be shared is determined, the response indication information including a response probability for indicating the game object's response to the information to be shared; an activity parameter of each game object is obtained, the activity parameter being used to indicate the level of activity of the game object in the game; a sharing response value of each game object is determined based on the response probability of each game object responding to the information to be shared and the activity parameter; based on the sharing response value of each game object, a game object is selected from the plurality of game objects as a target game object, and the information to be shared is shared with the target game object. It can be seen that according to the response probability and the activity parameter, the selection of the shared objects can be completed in a targeted manner, achieving more effective sharing and reducing information interference to the shared objects; in addition, the shared objects determined based on the activity parameter and the response probability can ensure to a certain extent that the shared objects can respond to the information to be shared, and can also achieve effective sharing of information, thereby improving the effectiveness of information sharing.

[0130] Next, the training process of the sharing prediction model is described. In some optional embodiments, the sharing prediction model can be constructed based on the boosting model, and the structure diagram of the sharing prediction model can be as follows: Figure 7 As shown, in Figure 7 In [1], the shared prediction model includes K regression trees. The training of the shared prediction model includes the following steps:

[0131] S1. Obtain a sample set, which includes sample feature data of each training sample in multiple training samples and a sample label corresponding to each training sample. The sample feature data includes multiple sample features. Let the sample set be represented by D, which includes N training samples, that is, D = {(x1, y1), (x2, y2), ..., (x n ,y n ),(x N ,y N )}, where x represents the feature data of the training sample and y represents the sample label.

[0132] In one implementation, initial feature data of multiple training samples can be obtained, and feature construction can be performed on the initial feature data of each training sample in the multiple training samples to obtain sample feature data of each training sample. The feature construction process can be referred to the description of the relevant parts above and will not be repeated here.

[0133] S2. Determine the residual that needs to be fitted for the Kth time based on the sample response prediction values ​​of the first K-1 regression trees for each training sample and the sample labels corresponding to each training sample. In one implementation, the difference between the sample response prediction values ​​of the first K-1 regression trees for each training sample and the corresponding sample labels can be calculated as the residual that needs to be fitted for the Kth time. In another implementation, step S2 may include: obtaining a target loss function, and performing a gradient descent calculation on the target loss function based on the sample set, the sample response prediction values ​​of the first K-1 regression trees for each training sample, and the sample labels corresponding to each training sample to obtain a gradient descent value, and using the gradient descent value as the residual that needs to be fitted for the Kth time. The target loss function can be expressed as:

[0134] Among them, J represents the target loss function, f k (x) represents the sum of the sample response prediction values ​​of the first K regression trees, that is, the sample response probability corresponding to the training sample, T i (x) represents the i-th regression tree. When i=K, T k (x) represents the Kth regression tree, that is, for a training sample, the sample response prediction values ​​of the training sample in each regression tree can be accumulated by addition operation as the sample response probability of the training sample. In order to facilitate understanding and calculation, the sample response probability of the first K regression trees is expressed as a recursive form: f k (x) = f k-1 (x)+T k (x); fk-1 (x) represents the sum of the response prediction values ​​of the first K-1 regression trees, such as f k (x n ) represents the sample response probability of the nth training sample. L(y n ,f k (x n )) represents the loss between the sample label and the sample response probability corresponding to the nth training sample. It should be understood that through gradient descent, the target loss function can be quickly minimized, achieving a rapid reduction in the target loss function value and improving model training efficiency.

[0135] S3. According to the residual error to be fitted for the Kth time, fitting learning is performed to obtain the Kth regression tree. At this point, the number of regression trees reaches a preset value (such as K), and a shared prediction model consisting of K regression trees is obtained.

[0136] Among them, the K-th decision tree is expressed as:

[0137] It should be understood that the training methods of the K-1th regression tree and the K-2th regression tree can refer to the training method of the K-1th regression tree mentioned above. When fitting and constructing the K-1th regression tree, it is necessary to determine the residuals to be fitted for the K-1th time based on the sample response prediction values ​​of the K-2 regression trees for each training sample and the sample labels corresponding to each training sample. The K-1th regression tree is obtained by fitting and learning based on the residuals to be fitted for the K-1th time. The specific process can be referred to the process of fitting and constructing the K-1th regression tree, which will not be repeated here. For example Figure 7In , taking the construction of two regression trees as an example, the training process of the first regression tree is: analyzing the sample feature data included in the sample set to determine the division point. Specifically, the division point can be determined according to the information entropy, and the division point corresponding to the minimum information entropy is selected to construct regression tree 1, wherein the value of each leaf node of regression tree 1 is the average value of the sample label corresponding to the training sample falling into the leaf node. At this time, the residual to be fitted for the second time can be determined based on the constructed regression tree 1, and regression tree 2 can be obtained by fitting and learning based on the residual to be fitted for the second time; specifically, the target loss function can be gradient descended according to the sample response prediction value of each training sample in regression tree 1 and the sample label corresponding to each training sample to obtain the gradient descent value (i.e., the residual). By analogy, a shared prediction model composed of K regression trees can be finally obtained. In actual application, the parameters involved in the process of sharing the prediction model include: the number of regression trees included in the shared prediction model is: 100 (ie K = 100); the purity corresponding to each regression tree is determined by information entropy, and the maximum tree depth of 100 regression trees (the maximum tree depth represents the distance between the leaf node and the root node. The maximum tree depth is the critical point for stopping the iteration of the decision tree. When the regression tree depth reaches the maximum tree depth, the regression tree will stop splitting, which means that the regression tree is constructed) can be 8; the maximum number of feature bins is 32 (the number of feature bins refers to the number of continuous feature data converted into discrete feature data). Optionally, a validation set can be obtained to verify the shared prediction model through the validation set. For example, the validation set can account for 10% of the training set; in actual practice, the offline training effect is as follows:

[0138]

[0139]

[0140] Among them, AUC represents the area enclosed by the ROC curve and the X-axis, and is a commonly used indicator to measure the performance of regression tree classification. The recall rate refers to the ratio of samples predicted by the regression tree as positive examples to the actual number of positive examples. In addition, by comparing the rule group (i.e., game objects team up to invite friends) and the information processing method provided by the embodiment of the present application, in the game object pull-back activity, the reflux rate of the method provided by the embodiment of the present application is 35% higher than that of the rule group, and the retention rate of game objects shared by the method provided by the embodiment of the present application within 7 days is 26% higher than the retention rate of game objects invited by the rule group.

[0141] Next, the information processing device provided in the embodiments of the present application is described.

[0142] See Figure 8 , Figure 8is a structural diagram of an information processing device provided in an embodiment of the present application. The information processing device may be a computer program (including program code) in a computer device. For example, the information processing device may be an application software in a computer device. The information processing device may be used to execute Figure 2 or Figure 5 Some or all of the steps in the method embodiment shown. Figure 8 , the information processing device includes the following units:

[0143] The display unit 801 is used to display a sharing interface, which includes sharing options and information to be shared;

[0144] The processing unit 802 is configured to obtain feature data of each of the plurality of game objects in response to a triggering operation of the sharing option;

[0145] The processing unit 802 is further configured to determine, based on the characteristic data of each game object, response indication information of each game object to the information to be shared, where the response indication information includes a response probability indicating that the game object responds to the information to be shared;

[0146] The processing unit 802 is further configured to determine a target game object from the plurality of game objects based on a response probability of each game object responding to the information to be shared, and share the information to be shared with the target game object.

[0147] The processing unit 802 is specifically configured to:

[0148] Get the activity parameter of each game object, which is used to indicate the activity level of the game object in the game;

[0149] Determine the sharing response value of each game object based on the response probability and activity parameters of each game object in responding to the shared information;

[0150] According to the sharing response value of each game object, a game object is selected from multiple game objects as a target game object.

[0151] The processing unit 802 is specifically configured to:

[0152] Select the game object with the largest shared response value as the target game object; or,

[0153] Sort multiple game objects in descending order of their sharing response values, and select the first M game objects from the sorted multiple game objects as target game objects, where M is a positive integer.

[0154] The processing unit 802 is specifically configured to:

[0155] Sort multiple game objects in descending order of their sharing response values, and select the first N game objects from the sorted game objects; N is a positive integer;

[0156] Output N game objects;

[0157] In response to a selection operation on N game objects, the game object indicated by the selection operation is used as a target game object.

[0158] The response probability of each game object to respond to the shared information is determined based on a sharing prediction model, which includes K regression trees, where K is an integer greater than 1; and a processing unit, specifically configured to:

[0159] For any game object among the multiple game objects, input feature data of any game object into each regression tree, perform response prediction of any game object to the shared information, and obtain a response prediction value of any game object to the shared information output by each regression tree;

[0160] Determine the response probability of any game object responding to the information to be shared based on the predicted response value of any game object to the information to be shared output by each regression tree;

[0161] Response indication information of any game object to the information to be shared is generated according to the response probability of any game object responding to the information to be shared.

[0162] The processing unit 802 is specifically configured to:

[0163] Obtaining initial feature data of each of the multiple game objects;

[0164] Perform feature construction on the initial feature data of each game object to obtain feature data of each game object;

[0165] Among them, feature construction includes one or more of the following: constructing missing values ​​for the initial feature data of each game object; discretizing the initial feature data of each game object; and normalizing the initial feature data of each game object.

[0166] The processing unit 802 is specifically configured to:

[0167] Determine maximum initial feature data and minimum initial feature data from the initial feature data of the plurality of game objects;

[0168] determining a second data difference between the maximum initial feature data and the minimum initial feature data;

[0169] The feature data of each game object is determined according to the first data difference value and the second data difference value between the initial feature data of each game object and the minimum initial feature data.

[0170] In an embodiment of the present application, a sharing interface is displayed, which includes a sharing option and information to be shared; in response to a triggering operation of the sharing option, characteristic data of each game object among a plurality of game objects is obtained; based on the characteristic data of each game object, response indication information of each game object to the information to be shared is determined, and the response indication information includes a response probability for indicating that the game object responds to the information to be shared; based on the response probability of each game object to respond to the information to be shared, a target game object is determined from the plurality of game objects, and the information to be shared is shared to the target game object. It can be seen that the screening of the objects to be shared can be completed in a targeted manner according to the response probability, thereby achieving more effective sharing; in addition, the response probability represents the probability (i.e., possibility) that the object to be shared can respond to the information to be shared, which can ensure to a certain extent that the object to be shared can respond to the information to be shared, and can also achieve effective sharing of information.

[0171] Next, the computer device provided in the embodiments of the present application is described.

[0172] Furthermore, the present invention also provides a schematic diagram of the structure of a computer device. Figure 9 The computer device may include a processor 901, an input device 902, an output device 903, and a memory 904. The processor 901, input device 902, output device 903, and memory 904 are connected via a bus. The memory 904 is used to store a computer program, which includes program instructions. The processor 901 is used to execute the program instructions stored in the memory 904.

[0173] The processor 901 executes the following operations by running the program instructions in the memory 904:

[0174] Display the sharing interface, which includes sharing options and information to be shared;

[0175] In response to a triggering operation of the sharing option, obtaining feature data of each of the plurality of game objects;

[0176] Determining response indication information of each game object to the information to be shared based on the characteristic data of each game object, the response indication information including a response probability indicating that the game object responds to the information to be shared;

[0177] According to the response probability of each game object responding to the information to be shared, a target game object is determined from multiple game objects, and the information to be shared is shared to the target game object.

[0178] The processor 901 may specifically perform the following operations when determining a target game object from multiple game objects based on the response probability of each game object responding to the information to be shared:

[0179] Get the activity parameter of each game object, which is used to indicate the activity level of the game object in the game;

[0180] Determine the sharing response value of each game object based on the response probability and activity parameters of each game object in responding to the shared information;

[0181] According to the sharing response value of each game object, a game object is selected from multiple game objects as a target game object.

[0182] When the processor 901 selects a game object as a target game object from a plurality of game objects according to the sharing response value of each game object, the processor 901 may specifically perform the following operations:

[0183] Select the game object with the largest shared response value as the target game object; or,

[0184] Sort multiple game objects in descending order of their sharing response values, and select the first M game objects from the sorted multiple game objects as target game objects, where M is a positive integer.

[0185] When the processor 901 selects a game object as a target game object from a plurality of game objects according to the sharing response value of each game object, the processor 901 may specifically perform the following operations:

[0186] Sort multiple game objects in descending order of their sharing response values, and select the first N game objects from the sorted game objects; N is a positive integer;

[0187] Output N game objects;

[0188] In response to a selection operation on N game objects, the game object indicated by the selection operation is used as a target game object.

[0189] The response probability of each game object responding to the shared information is determined based on a sharing prediction model, which includes K regression trees, where K is an integer greater than 1. When the processor 901 determines the response indication information of each game object to the shared information based on the feature data of each game object, it can specifically perform the following operations:

[0190] For any game object among the multiple game objects, input feature data of any game object into each regression tree, perform response prediction of any game object to the shared information, and obtain a response prediction value of any game object to the shared information output by each regression tree;

[0191] Determine the response probability of any game object responding to the information to be shared based on the predicted response value of any game object to the information to be shared output by each regression tree;

[0192] Response indication information of any game object to the information to be shared is generated according to the response probability of any game object responding to the information to be shared.

[0193] When acquiring the object data of each of the multiple game objects, the processor 901 may specifically perform the following operations:

[0194] Obtaining initial feature data of each of the multiple game objects;

[0195] Perform feature construction on the initial feature data of each game object to obtain feature data of each game object;

[0196] Among them, feature construction includes one or more of the following: constructing missing values ​​for the initial feature data of each game object; discretizing the initial feature data of each game object; and normalizing the initial feature data of each game object.

[0197] The feature construction includes normalizing the initial feature data of each game object. When the processor 901 performs feature construction on the initial feature data of each game object to obtain the feature data of each game object, the processor 901 may specifically perform the following operations:

[0198] Determine maximum initial feature data and minimum initial feature data from the initial feature data of the plurality of game objects;

[0199] determining a second data difference between the maximum initial feature data and the minimum initial feature data;

[0200] The feature data of each game object is determined according to the first data difference value and the second data difference value between the initial feature data of each game object and the minimum initial feature data.

[0201] In an embodiment of the present application, a sharing interface is displayed, which includes a sharing option and information to be shared; in response to a triggering operation of the sharing option, characteristic data of each game object among a plurality of game objects is obtained; based on the characteristic data of each game object, response indication information of each game object to the information to be shared is determined, and the response indication information includes a response probability for indicating that the game object responds to the information to be shared; based on the response probability of each game object to respond to the information to be shared, a target game object is determined from the plurality of game objects, and the information to be shared is shared to the target game object. It can be seen that the screening of the objects to be shared can be completed in a targeted manner according to the response probability, thereby achieving more effective sharing; in addition, the response probability represents the probability (i.e., possibility) that the object to be shared can respond to the information to be shared, which can ensure to a certain extent that the object to be shared can respond to the information to be shared, and can also achieve effective sharing of information.

[0202] In the embodiments of the present application, the term "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more units. In addition, each unit can be part of an overall unit that includes the function of the unit.

[0203] In addition, it should be noted that the present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the processor executes the above program instructions, it can execute the above Figure 3 or Figure 5 The method in the corresponding embodiment will therefore not be described in detail here. For technical details not disclosed in the computer-readable storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, the program instructions can be deployed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected by a communication network.

[0204] According to one aspect of the present application, a computer program product is provided, the computer program product comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, so that the computer device can perform the above-mentioned Figure 3 or Figure 5 The method in the corresponding embodiment will therefore not be described in detail here.

[0205] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0206] The above disclosure is only a preferred embodiment of the present application, and certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. An information processing method, characterized in that: The method comprises: Displaying a sharing interface, wherein the sharing interface includes sharing options and information to be shared; In response to a triggering operation of the sharing option, obtaining feature data of each of the plurality of game objects; Determining, based on the characteristic data of each game object, response indication information of each game object to the information to be shared, wherein the response indication information includes a response probability indicating that the game object responds to the information to be shared; According to the response probability of each game object responding to the information to be shared, a target game object is determined from the multiple game objects, and the information to be shared is shared with the target game object.

2. The method according to claim 1, wherein The determining a target game object from the plurality of game objects according to a response probability of each game object responding to the information to be shared includes: Obtaining an activity parameter for each game object, where the activity parameter is used to indicate the activity level of the game object in the game; determining a sharing response value of each game object according to a response probability of each game object responding to the information to be shared and an activity parameter; A game object is selected from the plurality of game objects as the target game object according to the sharing response value of each game object.

3. The method according to claim 2, wherein The selecting a game object from the plurality of game objects as the target game object according to the sharing response value of each game object includes: Select the game object with the largest sharing response value as the target game object; or The multiple game objects are sorted in descending order of the sharing response values ​​of the game objects, and the first M game objects are selected from the sorted multiple game objects as the target game objects, where M is a positive integer.

4. The method according to claim 2, wherein The selecting a game object from the plurality of game objects as the target game object according to the sharing response value of each game object includes: Sorting the plurality of game objects in descending order of the sharing response values ​​of the game objects, and selecting the first N game objects from the sorted plurality of game objects; N is a positive integer; Output N game objects; In response to a selection operation on the N game objects, the game object indicated by the selection operation is used as the target game object.

5. The method according to claim 1, wherein The response probability of each game object responding to the information to be shared is determined based on a sharing prediction model, wherein the sharing prediction model includes K regression trees, where K is an integer greater than 1; and the response indication information of each game object to the information to be shared is determined based on the feature data of each game object, including: For any game object among the multiple game objects, input the feature data of the any game object into each regression tree, perform response prediction of the any game object to the information to be shared, and obtain a response prediction value of the any game object to the information to be shared output by each regression tree; Determining a response probability of any game object responding to the information to be shared based on a predicted response value of any game object to the information to be shared output by each regression tree; Generate response indication information of any game object to the information to be shared according to the response probability of any game object responding to the information to be shared.

6. The method according to claim 1, wherein The obtaining of object data of each of the plurality of game objects comprises: Obtaining initial feature data of each of the multiple game objects; Performing feature construction on the initial feature data of each game object to obtain feature data of each game object; The feature construction includes one or more of the following: constructing missing values ​​for the initial feature data of each game object; discretizing the initial feature data of each game object; and normalizing the initial feature data of each game object.

7. The method according to claim 6, wherein The feature construction includes normalizing the initial feature data of each game object, and the feature construction of the initial feature data of each game object to obtain the feature data of each game object includes: Determining maximum initial feature data and minimum initial feature data from the initial feature data of the plurality of game objects; determining a second data difference between the maximum initial feature data and the minimum initial feature data; The feature data of each game object is determined according to the first data difference between the initial feature data of each game object and the minimum initial feature data and the second data difference.

8. An information processing device, characterized in that include: A display unit, configured to display a sharing interface, wherein the sharing interface includes sharing options and information to be shared; a processing unit, configured to obtain feature data of each of the plurality of game objects in response to a triggering operation of the sharing option; The processing unit is further configured to determine, based on the characteristic data of each game object, response indication information of each game object to the information to be shared, wherein the response indication information includes a response probability indicating that the game object responds to the information to be shared; The processing unit is further configured to determine a target game object from the plurality of game objects based on a response probability of each game object responding to the information to be shared, and share the information to be shared with the target game object.

9. A computer device, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the information processing method according to any one of claims 1 to 7 is executed.

10. A computer-readable storage medium, characterized in that The computer storage medium stores a computer program, and when the computer program is executed by a processor, the information processing method according to any one of claims 1 to 7 is executed.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the information processing method according to any one of claims 1 to 7 is implemented.

Images