Data processing method and device, equipment, medium and product

Abstract

Embodiments of the invention provide a data processing method and apparatus, a device, a medium and a product. The method comprises the steps of obtaining a first winning parameter of a target object in a game match scene; determining a matching object state set of the target object from the plurality of object state sets according to the state information of the target object; each object state set is associated with a game state feature, the game state feature comprises game state information and a game winning parameter, and the game state feature associated with each object state set is determined based on the game state feature of each object in the corresponding object state set; and determining a match matching strategy of the target object based on the first winning parameter and a second winning parameter associated with the matching object state set. According to the embodiment of the invention, the match matching strategy in the game match scene can be flexibly adjusted.

Description

Technical Field

[0001] This application relates to the field of computer technology, particularly to the field of artificial intelligence technology, and specifically to a data processing method, apparatus, device, medium, and product. Background Art

[0002] With the development of computer technology, virtual games have become an entertainment method for more and more people. Enabling people to participate in game matches through virtual games is one of the important gameplay of virtual games. For example, the objects in a racing game can control virtual characters to participate in a racing competition. Currently, opponents or teammates can be assigned to the objects in a virtual game to participate in the same game together, but the assignment method is relatively rigid and not flexible enough. Summary of the Invention

[0003] Embodiments of this application provide a data processing method, apparatus, device, medium, and product, which can flexibly adjust the matching strategy in the game match scenario.

[0004] On the one hand, embodiments of this application provide a data processing method, which includes:

[0005] Obtain the first victory parameter of the first object in the game match scenario;

[0006] According to the status information of the first object, determine the matching object status set of the first object from multiple object status sets; each object status set is associated with a game status feature, and the game status feature includes game status information and a game victory parameter. The game status feature associated with each object status set is determined based on the game status features of each object in the corresponding object status set;

[0007] Based on the first victory parameter and the second victory parameter associated with the matching object status set, determine the game matching strategy of the first object.

[0008] Correspondingly, embodiments of this application provide a game processing apparatus, which includes:

[0009] An obtaining unit, configured to obtain the first victory parameter of the target object in the game match scenario;

[0010] A processing unit, configured to determine the matching object status set of the target object from multiple object status sets according to the status information of the target object; each object status set is associated with a game status feature, and the game status feature includes game status information and a game victory parameter. The game status feature associated with each object status set is determined based on the game status features of each object in the corresponding object status set;

[0011] The processing unit is further used to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set.

[0012] In one implementation, the game matching strategy includes a matching parameter adjustment strategy; when the processing unit is used to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically used to perform the following steps:

[0013] If the first victory parameter is greater than the second victory parameter, the current matching parameter of the target object is adjusted upward, and the game match scenario of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter;

[0014] If the first victory parameter is less than the second victory parameter, the current matching parameter of the target object is adjusted downward, and the game match scenario of the target object is processed according to one or both of the matching parameter after the adjustment and the current matching parameter;

[0015] If the first victory parameter is equal to the second victory parameter, the game match scene of the target object is processed according to the current matching parameter of the target object.

[0016] In one implementation, the game matching strategy includes an agent parameter adjustment strategy; when the processing unit is used to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically used to perform the following steps:

[0017] If the first victory parameter is greater than the second victory parameter, the game scene of the target object is processed according to the first agent parameter;

[0018] If the first victory parameter is equal to the second victory parameter, the game scene of the target object is processed according to the second agent parameter;

[0019] If the first victory parameter is less than the second victory parameter, the game scene of the target object is processed according to the third agent parameter;

[0020] Among them, the first agent parameter, the second agent parameter and the third agent parameter all include one or two of the number of agents and the ability parameters of the agents, and the first agent parameter, the second agent parameter and the third agent parameter are different.

[0021] In one implementation, when the processing unit is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is specifically used to perform the following steps:

[0022] Obtain the first status information of the target object. The status parameters in the first status information include the first historical game status parameters and the real-time game status parameters of the target object in the target time period, and the target time period is determined based on the current system time;

[0023] Determine the matching object status set of the target object from multiple object status sets according to the first status information. The status parameters in the game status information associated with the matching object status set are the same as those in the first status information.

[0024] In one implementation, when the processing unit is used to determine the matching object status set of the target object from multiple object status sets according to the status information of the target object, it is also used to perform the following steps:

[0025] If the matching object status set of the target object cannot be determined from multiple object status sets according to the first status information, obtain the second status information of the target object. The status parameters in the second status information include the first historical game status parameters of the target object in the target time period;

[0026] Determine the matching object status set of the target object from multiple object status sets according to the second status information. The status parameters in the game status information associated with the matching object status set are the same as those in the second status information.

[0027] In one implementation, when the processing unit is used to determine the matching object status set of the target object from multiple object status sets according to the status information of the target object, it is used to perform the following steps:

[0028] Obtain the third status information of the target object. The status parameters in the third status information include the second historical game status parameters and the real-time game status parameters of the target object in the target time period, and the target time period is determined based on the current system time;

[0029] Determine the matching object status set of the target object from multiple object status sets according to the third status information. The status parameters in the game status information associated with the matching object status set are the same as those in the third status information.

[0030] In one implementation, the processing unit is also used to perform the following steps:

[0031] Obtain the third status information of the target object. The status parameters in the third status information include the second historical game status parameters and the real-time game status parameters of the target object in the target time period;

[0032] Determine the auxiliary object status set of the target object from multiple object status sets according to the third status information. The status parameters in the game status information associated with the auxiliary object status set are the same as those in the third status information;

[0033] Get the game victory parameters associated with the auxiliary object state set and the game victory parameters associated with the matching object state set;

[0034] According to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, a second victory parameter associated with the matching object state set is determined.

[0035] In one implementation, the processing unit is further configured to perform the following steps:

[0036] Determine N objects participating in the game scene in a historical game cycle, where the historical game cycle is divided into one or more statistical time periods, and N is a positive integer;

[0037] Determine the game status characteristics of each object in each statistical time period;

[0038] According to the game state characteristics of each object in each statistical time period, clustering processing is performed on N objects to obtain multiple initial state sets, each initial state set includes one or more objects with the same game state characteristics;

[0039] According to the object retention parameter of each initial state set, multiple initial state sets are screened to obtain multiple object state sets.

[0040] In one implementation, the object i is any one of the N objects, the statistical time period j is any one of the one or more statistical time periods, and both i and j are positive integers; when the processing unit is used to determine the game state information of the object i in the statistical time period j, it is specifically used to perform one or more of the following steps:

[0041] Determine the first historical game state parameter and the real-time game state parameter of the object i in the statistical time period j as the game state information of the object i in the statistical time period j;

[0042] Determine the second historical game state parameter and the real-time game state parameter of the object i in the statistical time period j as the game state information of the object i in the statistical time period j;

[0043] The first historical game state parameter of the object i in the statistical time period j is determined as the game state information of the object i in the statistical time period j.

[0044] In one implementation, before obtaining the first victory parameter of the target object in the game scene, the processing unit is further configured to perform the following steps:

[0045] Determine the number of times a matchmaking strategy is determined for a target object in a target time period, where the target time period is determined based on the current system time;

[0046] If the determined number of times is greater than the first number threshold, determine a system matching strategy for the target object, and process the game session scenario of the target object according to the system matching strategy;

[0047] If the determined number of times is less than or equal to the first number threshold, trigger the step of obtaining the first victory parameter of the target object in the game session scenario.

[0048] In one implementation, before triggering the step of obtaining the first victory parameter of the target object in the game session scenario, the processing unit is further configured to perform the following steps:

[0049] Determine whether the number of game sessions of the target object in the target time period is equal to the second number threshold;

[0050] If the number of game sessions is equal to the second number threshold, determine a default matching strategy for the target object, and process the game session scenario of the target object according to the default matching strategy;

[0051] If the number of game sessions is not equal to the second number threshold, trigger the step of obtaining the first victory parameter of the target object in the game session scenario.

[0052] Correspondingly, an embodiment of the present application provides a computer device, which includes:

[0053] A processor, adapted to implement a computer program;

[0054] A computer-readable storage medium storing a computer program, the computer program being adapted to be loaded and executed by the processor to perform the above data processing method.

[0055] Correspondingly, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when read and executed by the processor of the computer device, causes the computer device to perform the above data processing method.

[0056] Correspondingly, an embodiment of the present application provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, causing the computer device to perform the above data processing method.

[0057] In the embodiments of the present application, multiple object state sets are constructed. Each object state set is associated with game state characteristics (including game state information and game victory parameters), and the game state characteristics associated with each object state set are determined based on the game state characteristics of each object in the corresponding object state set. For the game scenario of a target object, the matching object state set of the target object can be determined from multiple object state sets according to the state information of the target object; wherein, the matching object state set is the object state set in which the associated game state information in the multiple object state sets matches the state information of the target object (matching if they are the same, not matching if they are different). According to the second victory parameter associated with the matching object state set and the first victory parameter of the target object, the game matching strategy of the target object is determined. It can be seen that the embodiments of the present application can customize the game matching strategy for the game scenario of the target object, so that the flexible adjustment of the game matching strategy in the game scenario can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1 It is a schematic structural diagram of a network architecture provided by an embodiment of the present application;

[0060] Figure 2 It is a schematic diagram of an interaction scenario provided by an embodiment of the present application;

[0061] Figure 3 It is a schematic flowchart of a data processing method provided by an embodiment of the present application;

[0062] Figure 4 It is a schematic flowchart of a state set generation method provided by an embodiment of the present application;

[0063] Figure 5 It is a schematic flowchart of a game matching strategy determination method provided by an embodiment of the present application;

[0064] Figure 6 It is a schematic flowchart of another game matching strategy determination method provided by an embodiment of the present application;

[0065] Figure 7 It is a schematic system framework diagram of a data processing method proposed by the present application;

[0066] Figure 8It is a schematic diagram of an optimal growth path determination service provided by an embodiment of the present application;

[0067] Figure 9 It is a schematic diagram of a player growth path dynamic adjustment service provided by an embodiment of the present application;

[0068] Figure 10 It is a schematic diagram of the optimal player growth paths corresponding to different groups provided by an embodiment of the present application;

[0069] Figure 11 It is a schematic diagram of the structure of a data processing device provided by an embodiment of the present application;

[0070] Figure 12 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0071] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0072] To more clearly understand the technical solutions provided by the embodiments of the present application, the key terms involved in the embodiments of the present application will be introduced here:

[0073] (1) Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, and to perceive the environment, acquire knowledge, and use knowledge to obtain the best results in theory, method, technology, and application systems. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence.

[0074] Artificial intelligence technology is an interdisciplinary subject, involving a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, and other technologies. The software technologies of artificial intelligence mainly include several major directions such as audio processing technology, computer vision technology, natural language processing technology, machine learning / deep learning, autonomous driving, and intelligent transportation.

[0075] Enabling computers to listen, see, speak, and sense is the future development direction of human-computer interaction. Among them, Machine Learning (ML) is the core of artificial intelligence and the fundamental way to endow computers with intelligence, and its applications cover all fields of artificial intelligence. Machine learning is an interdisciplinary subject that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve their own performance. Machine learning and deep learning usually include technologies such as reinforcement learning, artificial neural networks, belief networks, transfer learning, inductive learning, and learning from demonstration.

[0076] The data processing method provided in the embodiments of this application relates to the machine learning technology of artificial intelligence, specifically to Reinforcement Learning (RL), also known as reward learning, evaluation learning, or enhancement learning, which is one of the paradigms and methodologies of machine learning. Reinforcement learning does not require any pre-given data, but obtains learning information and updates model parameters by receiving rewards (feedback) from the environment for actions. In one implementation, an AI model for controlling the behavior of an agent can be obtained based on reinforcement learning.

[0077] (2) The embodiments of this application relate to virtual games (which can be simply referred to as games). Virtual games refer to games that rely on computer devices (such as personal computers, smart terminals, or wearable devices, etc.) and are controlled by computer programs to run. Virtual games can include single-player games and online games. ① Online games, also known as Internet games, generally refer to individual multi-player online games that use the Internet as the communication medium, use game servers and player terminals as game processing devices, and use game clients running on player terminals as information interaction windows, aiming to achieve entertainment, leisure, communication, and virtual achievements; the game client refers to a program that provides local game services for players participating in online games corresponding to the game server; the game server refers to a service device that provides data calculation, verification, storage, and forwarding functions for the game client. ② Single-player games refer to electronic games that can run independently using a single computer or other game platforms and do not require a game server to run properly.

[0078] For online games, the embodiments of the present application do not limit the game types of online games. For example, when classifying online games according to the game operation mode, online games can be divided into: mobile games, client games, web games, and cloud games, etc. ① Mobile games can be simply referred to as mobile games, which are games running on smart phones; to operate a mobile game on a smart phone, it is necessary to download and install the installation package of the mobile game on the smart phone. ② Client games can be simply referred to as PC games, which are games running on smart computers; to operate a client game, it is necessary to download and install the installation package of the game in a smart computer (such as a personal computer). ③ Web games can be called web (World Wide Web) games, or web games (which can be simply referred to as browser games), which are online games that can be operated after opening the game web page based on a browser. ④ Cloud games can also be called gaming on demand, which is an online game technology based on cloud computing technology; in the operation mode of cloud games, cloud games do not run on the terminal devices (such as smart phones, personal computers, or wearable devices, etc.) held by game users (or called players), but run on cloud servers, and the cloud server renders the game scene into a video and audio stream, and the cloud server transmits the rendered video and audio stream to the terminal device through the network, so that the terminal device can directly play the video and audio stream. Based on the above description, it can be seen that cloud games have the following advantages: the requirements for the computing and processing capabilities of the terminal devices held by game users are not high, and the development of cloud games does not need to consider the hardware adaptability, etc., which makes cloud games gradually achieve large-scale development.

[0079] For another example, classifying online games according to gameplay, online games can be divided into: role-playing games (RPG), shooting games, and action games (ACT), etc. ① Role-playing games are games in which game users play one or several virtual characters in the game and have a complete storyline; in multiplayer online role-playing games, game users can improve the gaming abilities (or called abilities, competitive levels) of virtual characters by completing game tasks set by the game or purchasing virtual items sold, etc., so as to achieve better interaction with virtual characters controlled by other game users in the network virtual space. ② Shooting games include first-person shooting games (FPS), third-person shooting games (TPS), or multiplayer online battle arena games (MOBA), etc. First-person shooting games refer to shooting games in which game users can play from a first-person perspective, and the picture of the virtual scene in the game is observed from a first-person perspective. Third-person shooting games refer to shooting games in which game users play from a third-person perspective, and the picture of the virtual scene in the game is observed from a third-person perspective. Multiplayer online battle arena games refer to competitive games in which multiple game users can form the same game group or game camp online to compete. ③ Action games are games in which game users control virtual characters and use various methods to eliminate enemies or ensure passing the levels; action games often do not deliberately pursue storylines, and the design purpose is for ordinary game users, with the purpose of pure entertainment and leisure, belonging to popular games. The game users here can refer to any user who plays virtual games using computer devices (such as personal computers, smart terminals, or wearable devices, etc.).

[0080] Among them, the above-mentioned virtual characters can be virtual images used to represent game users and controlled through the operations of game users in the game client. This virtual image is the image of various virtual humans and virtual objects that can interact in the virtual game, or movable objects in the virtual game; among them, the movable objects can be virtual characters, virtual animals, virtual plants, and anime characters, etc. For example, the movable objects are virtual characters and virtual animals, etc. displayed in any virtual scene provided by the virtual game. In the virtual game, game skills can be released by manipulating virtual characters to perform corresponding behavioral operations; such as controlling virtual characters to jump, run, or lie prone, etc. behavioral operations.

[0081] An agent refers to a virtual character driven by artificial intelligence (AI) in a virtual scenario (such as a simulation environment of the real world, a semi-simulated and semi-fictional virtual environment, or a purely fictional virtual environment; the virtual scenario can be any one of a two-dimensional virtual scenario, a 2.5D virtual scenario, or a three-dimensional virtual scenario). That is to say, the agent is not controlled by the game user and can, in a specific game environment, communicate and cooperate or fight with the virtual character controlled by the game user or other agents, etc., according to its perception of the game environment, in accordance with existing instructions or through autonomous learning. In an exemplary scenario, the agent configured for the game match scene of the target object can participate in the game match with the target object. For example, the agent and the target object are in an adversarial relationship (i.e., agent opponent), or the agent and the target object are in a cooperative relationship (i.e., agent teammate). It should be noted that if any player is in an adversarial relationship with the target object, they are called opponent players, and if any player is in a cooperative relationship with the target object, they are called teammate players.

[0082] In the embodiments of this application, an object refers to a game user who plays a virtual game, and a target object refers to any game user who plays a virtual game. Among them, a game user can be uniquely identified by a game account (such as an account registered in the game client). In other words, a game account identifies a game user (i.e., an object).

[0083] (3) The ranked match is one of the important gameplay of the virtual game. By accumulating experience in the ordinary matching mode and reaching a certain level, a ranked match can be played to prove one's strength. For example, the ranked match divides the player's level (i.e., ranked level) into: Bronze Tier, Silver Tier, Gold Tier, Platinum Tier, Diamond Tier, Starlight Tier, and King Tier. The higher the ranked level, the stronger the strength. Since the abilities of each player are different, the ranked match will evaluate the player's ability according to the player's tier score (a matching parameter) (for example, the tier score of the Bronze Tier is 0 to 100, the tier score of the Silver Tier is 101 to 200, and so on), and match players with similar abilities (i.e., similar tier scores) into the same game match. When the player completes the game, the tier score will be adjusted according to the player's performance.

[0084] It can be seen that the existing game matching strategies mainly consider matching parameters, without considering the abilities of players and the gaming experience, which is likely to increase the probability of players abandoning the game, thereby reducing the object retention parameter of the game (used to reflect the user stickiness of the game). For example, if a player stays at a certain rank for too long due to ability issues or keeps losing in game matches, it will dampen the player's enthusiasm for participating in game matches, leading to an increased probability of the player abandoning the game. Another example is that some players prefer to play against highly skilled opponents (i.e., matches with higher difficulty), while some players prefer easier matches (i.e., matches with lower difficulty). If the gaming experience of a player does not match their needs, the probability of the player quitting the game will increase. Based on this, the embodiments of this application propose a data processing method that can flexibly adjust the game matching strategy in the game match scenario and improve the object retention parameter of the game.

[0085] The following introduces the network architecture applicable to the data processing method proposed in this application. Please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a network architecture provided by the embodiments of this application. As Figure 1 shown, the network architecture may include a server 100 and a terminal cluster. The terminal cluster may include multiple terminal devices, and the embodiments of this application do not limit the number of terminal devices included in the terminal cluster. Among them, as Figure 1 shown, the terminal cluster may specifically include: terminal devices 200a, 200b, 200c,..., 200n. Among them, there may be communication connections between the terminal clusters. For example, there is a communication connection between terminal device 200a and terminal device 200b, and there is a communication connection between terminal device 200a and terminal device 200c. At the same time, any terminal device in the terminal cluster may have a communication connection with the server 100. For example, there is a communication connection between terminal device 200a and the server 100, so that each terminal device in the terminal cluster can perform data interaction with the server 100 through this communication connection. Among them, the above communication connection does not limit the connection method, and it can be directly or indirectly connected through a wired communication method, or directly or indirectly connected through a wireless communication method, or through other methods, and this application does not make any restrictions here.

[0086] Among them, the above-mentioned server 100 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud databases, cloud services, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Any terminal device in the above terminal cluster can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a palm computer, a mobile internet device (MID), a wearable device (such as a smart watch, a smart bracelet, etc.), a smart computer, a smart vehicle, a game controller, a remote control, an arcade device, etc., which are smart terminals that can run game clients.

[0087] As Figure 1 shown, each terminal device in the terminal cluster can be installed with an application client. When the application client runs on each terminal device, it can perform data interaction with the above-mentioned Figure 1 shown server 100. Among them, the application client can be a game application, a live broadcast application, a short video application, a video application, a music application, a shopping application, a novel application, a payment application, a browser, etc., which have functions of displaying data information such as text, images, audio, and video. Among them, the application client can be an independent client or an embedded sub-client integrated in a certain client (such as a game client, etc.), which is not limited here. Among them, the server 100 can be a collection of multiple servers such as a background server and a data processing server corresponding to the application client. Therefore, each terminal device can perform data transmission with the server 100 through the installed application client. Taking the application client as a game client as an example, the game client can be a program that provides local game services for players participating in virtual games. Each player can control the corresponding virtual character to participate in the game session through the game client. When the game session ends, the game client can collect the session information of the corresponding game session (such as the session result (win or lose) of the game session, the start time and end time of the game session, etc.), and send the collected session information to the server 100.

[0088] Next, taking any terminal device (such as terminal device 200a) and the server 100 jointly executing the data processing method provided in the embodiment of the present application as an example, the process of the data processing method will be briefly introduced.

[0089] The terminal device 200a (which can be installed with a game client) can respond to a session service request operation initiated by a target object (that is, the object using the terminal device 200a) (such as a trigger operation on the session start control and session matching control in the game client), and send a game session service request to the server 100.

[0090] After the server 100 receives the game session service request sent by the terminal device 200a, it obtains the first victory parameter of the target object. The first victory parameter is the game victory parameter (or the number of game victories) of the target object in the target time period. The target time period is determined based on the current system time. For example, if the current system time is 2:00 on a certain day, the target time period can be 0:00 - 2:00 on the same day. Obtain the status information of the target object, and according to the status information of the target object, determine the matching object status set of the target object from multiple object status sets; among them, the matching object status set is the object status set in which the associated game status information in the multiple object status sets matches (matches if they are the same, does not match if they are different) the status information of the target object. Each object status set has an object retention parameter, and the object retention parameter is used to reflect the stickiness of each object in the corresponding object status set to the game; among them, the greater the stickiness of an object to the game, the more willing the object is to spend time on the game, and the smaller the stickiness of an object to the game, the less willing the object is to spend time on the game. The matching object status set of the target object usually has a relatively high object retention parameter (such as greater than the preset parameter threshold), so the stickiness of each object in the matching object status set to the game is also relatively large. Exemplarily, when the status information of the target object matches the game status information associated with the matching object status set, the closer the first victory parameter of the target object is to the second victory parameter associated with the matching object status set, the closer the stickiness of the target object to the game is to the stickiness of each object in the matching object status set, and then the retention probability of the target object (used to reflect the willingness to participate in the next game session; the greater the retention probability, the greater the willingness to participate in the next game session, and the smaller the retention probability, the smaller the willingness to participate in the next game session) is relatively large. Therefore, based on the second victory parameter associated with the matching object status set and the first victory parameter of the target object, the difficulty tendency of the game session scenario configured for the target object can be analyzed, and the game session matching strategy for the target object can be determined according to this difficulty. The game session matching strategy includes one or both of a matching parameter adjustment strategy and an agent parameter adjustment strategy. Specifically, if the first victory parameter is less than the second victory parameter, the difficulty of the game session scenario of the target object can be reduced to increase the probability of the target object winning; for example, assign an opponent player with weaker ability (such as a player with a matching parameter less than the current matching parameter of the target object) to the target object, assign a teammate player with stronger ability (such as a player with a matching parameter greater than the current matching parameter of the target object) to the target object, assign an agent teammate with stronger ability (such as an agent with an ability parameter greater than the set ability parameter) to the target object, assign an agent opponent with weaker ability (such as an agent with an ability parameter less than the set ability parameter) to the target object, etc.If the first victory parameter is greater than the second victory parameter, the difficulty of the target object's game match scenario can be increased to reduce the target object's probability of winning; for example, assigning a teammate player with weaker ability to the target object (such as a player whose matching parameter is less than the target object's current matching parameter), assigning a rival player with stronger ability to the target object (such as a player whose matching parameter is greater than the target object's current matching parameter), assigning a smart agent opponent with stronger ability to the target object (such as a smart agent with ability parameter greater than the set ability parameter), assigning a smart agent teammate with weaker ability to the target object (such as a smart agent with ability parameter less than the set ability parameter), etc. If the first victory parameter is equal to the second victory parameter, the difficulty of the target object's game match scenario may not be intervened; for example, assigning a rival player and a teammate player whose matching parameter is close to the target object's current matching parameter to the target object, and assigning a smart agent opponent and a smart agent teammate whose ability parameter is equal to the set ability parameter to the target object.

[0091] Among them, the server 100 needs to construct the above-mentioned multiple object state sets and associate game state features (including game state information and game victory parameters) for each object state set. The game state features associated with each object state set are determined based on the game state features of each object in the corresponding object state set; illustratively, the game state features of each object in each object state set can be the same (i.e., objects with the same game state features are aggregated into the same object state set). Among them, the game state information can be used to reflect one or more of the first historical game state parameters (such as the number of days participating in game games in a certain game season) of the corresponding object in a certain time period, the second historical game state parameters (such as the winning rate of the previous day, whether to participate in game games), and the real-time game state parameters (such as the initial level of the day, the number of games). The game victory parameter can be used to reflect the number of game wins of the corresponding object in a certain time period.

[0092] For further understanding, please refer to Figure 2 , Figure 2 is a schematic diagram of an interactive scenario provided by an embodiment of the present application. Figure 2 The terminal device 200a shown in the figure has a racing game installed (such as Figure 2 The racing game shown in the figure is a racing game: after the first player crosses the line and reaches the end of the track, the remaining players must cross the line and reach the end of the track within a certain period of time, otherwise the result is incomplete). User A can initiate a game match service request to the server 100 through the terminal device 200a; for example, Figure 2 As shown, user A can click on the game matching control (i.e. Figure 2Initiate a trigger operation through the "start matching" shown, thereby triggering the terminal device 200a to send a game session service request to the server 100. The terminal device 200a can display a matching progress interface (for prompting user A that a game session matching is in progress). The server 100 determines user A as the target object in response to the game session service request, determines the game session matching strategy for user A based on the data processing method provided in this application, matches an opponent for user A (which may include one or both of an opponent player and an agent opponent), and sends the game session matching result (including the opponent player and / or agent opponent participating in the same game session as user A) to the terminal device 200a. The terminal device 200a displays a matching success interface (for prompting user A that the game session matching is successful), and then displays the game session matching result in the game session start interface (which is the start interface of the game session scene).

[0093] It can be seen that in the embodiments of this application, by means of the first victory parameter of the target object and the second victory parameter associated with the matching object state set, it can be analyzed what difficulty level of game session the target object participates in and the retention probability will be greater. In this way, the game session matching strategy of the target object can be customized individually, realizing flexible adjustment of the game session matching strategy in the game session scene, and at the same time being able to improve the retention probability of the target object, thereby improving the object retention parameter of the game.

[0094] It can be understood that Figure 1 it only exemplarily represents the possible network architecture of the technical solution of this application and does not limit the specific architecture of the technical solution of this application, that is, the technical solution of this application can also provide other forms of network architecture.

[0095] It should be noted that when the embodiments of this application are applied to specific products or technologies, such as obtaining game session information, the first historical game session state parameter, the second historical game session state parameter, and the real-time game session state parameter, etc., the permission or consent of the corresponding object needs to be obtained, and the relevant data collection, use, and processing processes need to comply with the relevant laws, regulations, and standards of the region, conform to the principles of legality, legitimacy, and necessity, and do not involve obtaining data types prohibited or restricted by laws and regulations. In some optional embodiments, the relevant data involved in the embodiments of this application is obtained after the separate authorization of the corresponding object. In addition, when obtaining the separate authorization of the corresponding object, the purpose of the relevant data involved is indicated to the corresponding object.

[0096] The following describes the specific embodiments related to the data processing method with reference to the accompanying drawings. Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a data processing method provided by the embodiments of this application. This data processing method can be performed by Figure 1The server 100 shown executes. Among them, the data processing method mainly includes but is not limited to the following steps S301 to S303:

[0097] S301. Obtain the first victory parameter of the target object in the game session scene.

[0098] A game session refers to a competition carried out to complete a certain game goal. For different games, the above game goals are also different. For example, the game goal can be to pass a certain level, push down the enemy's base camp, pass the finish line of the track as soon as possible, etc. The embodiments of the present application do not limit this. Taking a racing game as an example, the game goal of the game session is to control the virtual character to pass the track terminal line in the first place.

[0099] In a game session, the number of virtual characters can be one or multiple. When the number of virtual characters is one, it is usually a single-player game, and the virtual character refers to the virtual character corresponding to the current game client. When the number of virtual characters is multiple, it can be a single-player game, and the current game client corresponds to multiple different virtual characters, and the player can replace the virtual character they substitute and control during the game session; it can also be a multi-player game, and multiple virtual characters correspond to multiple different game clients, and each player of each game client substitutes and controls one or more virtual characters, and the virtual characters substituted and controlled by different players can belong to the same camp or different camps. During the game session, the virtual character can move in the game scene, such as walking, running, jumping, etc., and can change different postures.

[0100] In one embodiment, any object can send a game session service request to the server (for requesting to enter the game session scene, that is, requesting to start a game session), and the server can, in response to the game session service request, determine the any object as the target object and obtain the first victory parameter of the target object. The first victory parameter refers to the victory parameter of the target object in the target time period. The game victory parameter refers to the number of game sessions with a victory result (that is, the number of game victories). The target time period needs to be determined based on the current system time. Specifically, the target time period needs to be determined based on the current system time and the duration of the unit time period (which can be set manually). For example, in the embodiments of the present application, the duration of the unit time period is set to 24 hours, and the current system time is 16:00 on a certain day, then the target time period is from 0:00 to 16:00 on the same day; another example is that the duration of the unit time period set in the present application is 12 hours, and the current system time is 16:00 on a certain day, then the target time period is from 12:00 to 16:00 on the same day. The embodiments of the present application take the duration of the unit time period as 24 hours as an example.

[0101] S302. Determine a matching object state set of the target object from multiple object state sets according to the state information of the target object; each object state set is associated with a game state feature, the game state feature includes game state information and game victory parameters, and the game state feature associated with each object state set is determined based on the game state features of each object in the corresponding object state set.

[0102] See also Figure 4 , Figure 4 is a flow chart of a state set generation method provided in an embodiment of the present application, wherein the state set generation method is used to generate multiple object state sets; Figure 4 As shown, the state set generation method includes the following steps S11-S14:

[0103] S11. Determine N objects participating in a game scene in a historical game cycle, where the historical game cycle is divided into one or more statistical time periods, and N is a positive integer.

[0104] The duration of a game cycle can be set manually. For example, if a game season is every three months (such as the player's ranking points are reset every three months in the qualifying competition), the duration of a game cycle can be set to three months. The historical game cycle includes one or more game cycles before the current game cycle, such as game season S1 and game season S2 before the current game season S3. In an embodiment of the present application, the historical game cycle is divided into one or more statistical time periods based on the length of the unit time period, and the length of a statistical time period is equal to the length of the unit time period (such as 24 hours); for example, the historical game cycle includes January 1 to January 30, then each day from January 1 to January 30 is a statistical time period.

[0105] In one embodiment, N objects participating in the game scene in the historical game cycle may be obtained, where N is an integer greater than 1.

[0106] S12. Determine the game status characteristics of each object in each statistical time period.

[0107] The object i is any one of the N objects, the statistical time period j is any one of the one or more statistical time periods, and i and j are both positive integers. In one embodiment, determining the game state characteristics of the object i in the statistical time period j includes: determining the game victory parameters (i.e., the number of game wins) of the object i in the statistical time period j, and determining the game state information of the object i in the statistical time period j, and determining the game victory parameters and the game state information of the object i in the statistical time period j as the game state characteristics of the object i in the statistical time period j.

[0108] Optionally, determine the game status information of object i in statistical time period j, including: obtaining the first historical game status parameter and the real-time game status parameter of object i in statistical time period j. Determine the first historical game status parameter and the real-time game status parameter of object i in statistical time period j as the game status information of object i in statistical time period j. For ease of description, in the embodiments of this application, the game status feature composed of the game victory parameter and the game status information including the first historical game status parameter and the real-time game status parameter is referred to as the first status feature.

[0109] Among them, the first historical game status parameter is a parameter used to describe the long-term game status of the corresponding object. For example, the number of days that object i participates in the game scenario within the historical game cycle (such as the number of ranked days participating in the ranked match). The real-time game status parameter is a parameter used to describe the real-time game status of the corresponding object. For example, the initial level of object i in statistical time period j (such as the initial ranked level) and the number of game matches (that is, the number of times participating in the game match).

[0110] Optionally, determine the game status information of object i in statistical time period j, including: obtaining the second historical game status parameter and the real-time game status parameter of object i in statistical time period j. Determine the second historical game status parameter and the real-time game status parameter of object i in statistical time period j as the game status information of object i in statistical time period j. For ease of description, in the embodiments of this application, the game status feature composed of the game victory parameter and the game status information including the second historical game status parameter and the real-time game status parameter is referred to as the second status feature.

[0111] Among them, the second historical game status parameter is a parameter used to describe the short-term game status of the corresponding object. For example, the win rate of object i in statistical time period j - 1 (the previous statistical time period of statistical time period j, such as if statistical time period j is January 2nd, statistical time period j - 1 is January 1st) and the indication parameter used to indicate whether object i participates in the game match (such as the ranked match) in statistical time period j - 1 (for example, the indication parameter is 1 indicating participating in the game match, and the indication parameter is 0 indicating not participating in the game match).

[0112] Optionally, determine the game status information of object i in statistical time period j, including: obtaining the first historical game status parameter of object i in statistical time period j, and determining the first historical game status parameter of object i in statistical time period j as the game status information of object i in statistical time period j. For ease of description, in the embodiments of this application, the game status feature composed of the game victory parameter and the game status information including the first historical game status parameter is referred to as the third status feature.

[0113] S13. Cluster the N objects according to the game status characteristics of each object in each statistical time period to obtain multiple initial state sets, where each initial state set includes one or more objects with the same game status characteristics.

[0114] In one embodiment, obtain the game status characteristics of each object in each statistical time period, aggregate one or more objects with the same game status characteristics among the N objects into the same initial state set to obtain multiple initial state sets. Determine the game status characteristics associated with the corresponding initial state set based on the game status characteristics of the objects aggregated into the same initial state set.

[0115] For example, assume that the game status characteristics of each object obtained in each statistical time period include: the game status characteristic 1 of object 1 in statistical time period 1 (such as January 1st), the game status characteristic 2 of object 1 in statistical time period 2 (such as January 2nd), the game status characteristic 3 of object 2 in statistical time period 2, and the game status characteristic 4 of object 3 in statistical time period 2. The game status characteristic 1 and the game status characteristic 3 are the same, and the game status characteristic 2 and the game status characteristic 4 are the same. Then the determined initial state sets include: initial state set 1 {object 1, object 2}, and the game status characteristic associated with initial state set 1 is the game status characteristic 1 (of course, the game status characteristic 1 and the game status characteristic 3 are the same, and it is the same to associate the game status characteristic 3); initial state set 2 {object 1, object 3}, and the game status characteristic associated with initial state set 2 is the game status characteristic 2 (of course, the game status characteristic 2 and the game status characteristic 4 are the same, and it is the same to associate the game status characteristic 4).

[0116] S14. Screen the multiple initial state sets according to the object retention parameters of each initial state set to obtain multiple object state sets.

[0117] In one embodiment, if any object included in any initial state set is clustered based on the game status characteristic of the object in statistical time period j, the object retention parameter of the any state set needs to be determined based on the retention indication information of the object in reference time period k (used to indicate whether the corresponding object participates in the game scenario in the corresponding reference time period, where if the retention indication information is 1, it participates in the game scenario, and if the retention indication information is 0, it does not participate in the game scenario). The reference time period k needs to be determined based on the statistical time period j, specifically referring to a certain time period after the statistical time period j; k is a positive integer. That is to say, the object retention parameter of each initial state set is determined based on the retention indication information of each object in the corresponding initial state set in the corresponding reference time period, and specifically, it can be obtained by calculating the average value of the retention indication information of each object in the corresponding initial state set in the corresponding reference time period.

[0118] For example, the in-game status features of each object obtained in each statistical time period include: the in-game status feature 1 of object 1 in statistical time period 1 (such as January 1st), the in-game status feature 2 of object 1 in statistical time period 2 (such as January 2nd), the in-game status feature 3 of object 2 in statistical time period 2, and the in-game status feature 4 of object 3 in statistical time period 2. If the in-game status feature 1, the in-game status feature 2, the in-game status feature 3, and the in-game status feature 4 are the same, the determined initial status set includes: initial status set 1 {object 1, object 2, object 3}, and the in-game status feature associated with initial status set 1 is the in-game status feature 1. For initial status set 1, since the retention indication information of object 1 in reference time period 1 (a certain time period after statistical time period 1, such as January 2nd) is 1, the retention indication information of object 1 in reference time period 2 (a certain time period after statistical time period 2, such as January 3rd) is 1, the retention indication information of object 2 in reference time period 2 is 1, and the retention indication information of object 3 in reference time period 2 is 0, the object retention parameter of initial status set 1 is 0.75 = (1 + 1 + 1 + 0) ÷ 4.

[0119] It should be noted that if reference time period k is the Mth day after statistical time period j, the object retention parameter of each initial status set is used to reflect the M-day retention rate of each object in the corresponding initial status set (when in the in-game status feature associated with the corresponding initial status set) (for example, if reference time period k is the 1st day after statistical time period j, it is the next-day retention rate; if reference time period k is the 3rd day after statistical time period j, it is the three-day retention rate, and so on). In other words, the object retention parameter of each initial status set is used to reflect the stickiness of each object in the corresponding initial status set to the game (when in the in-game status feature associated with the corresponding initial status set). For example, the in-game status features associated with initial status set 1 {object 1, object 2} include: in-game status information 1, in-game victory parameter 1; the in-game status features associated with initial status set 2 {object 1, object 2} include: in-game status information 2, in-game victory parameter 2; the object retention parameter of initial status set 1 is 0.8, and the object retention parameter of initial status set 2 is 0.3. This indicates that the stickiness of object 1 and object 2 to the game when in the in-game status indicated by in-game status information 1 and the in-game victory parameter is in-game victory parameter 1 is greater than the stickiness of object 1 and object 2 to the game when in the in-game status indicated by in-game status information 2 and the in-game victory parameter is in-game victory parameter 2.

[0120] In one embodiment, multiple initial state sets are screened according to the object retention parameters of each initial state set to obtain multiple object state sets. Specifically, if the game state information associated with the first initial state set is different from the game state information associated with other initial state sets (and greater than a preset parameter threshold), the first initial state set is determined as the object state set; if the game state information associated with the first initial state set is the same as the game state information associated with one or more second initial state sets, the initial state set corresponding to the maximum object retention parameter (and greater than the preset parameter threshold) among the first initial state set and the one or more second initial state sets is determined as the object state set. Herein, the first initial state set and the second initial state set are any of the multiple initial state sets, and the other initial state sets are the initial state sets other than the first initial state set among the multiple initial state sets.

[0121] For example, the game state characteristics associated with the initial state set 1 are: [game state information 1, game win parameter 1], the game state characteristics associated with the initial state set 2 are: [game state information 2, game win parameter 2], and the game state characteristics associated with the initial state set 3 are: [game state information 3, game win parameter 3]. The game state information 1 is different from both the game state information 2 and the game state information 3, and the object retention parameter of the initial state set 1 is greater than the preset parameter threshold, then the initial state set 1 is determined as the object initial state set. The game state information 2 and the game state information 3 are the same, then obtain the object retention parameter 1 of the initial state set 2 and the object retention parameter 2 of the initial state set 3, determine the maximum object retention parameter among the object retention parameter 1 and the object retention parameter 2, if the maximum object retention parameter is greater than the preset parameter threshold, then the initial state set corresponding to the maximum object retention parameter is determined as the object state set.

[0122] It can be seen that when the game state information associated with multiple initial state sets is the same but the associated game win parameters are different, the multiple initial state sets can be de-duplicated to retain the initial state set corresponding to the maximum object retention parameter among the multiple initial state sets as the object state set. In this way, when the state information of the target object is the same as the game state information associated with any object state set among the multiple object state sets, the closer the game win parameter of the target object in the current unit time period is to the game win parameter associated with any object state set, the closer the stickiness of the target object to the game is to the stickiness of each object to the game in any object state set, and thus the retention probability of the target object is relatively high.

[0123] Among them, the status information of the target object includes at least one of the following: ① The first status information of the target object, and the status parameters in the first status information include the first historical game status parameters and the real-time game status parameters of the target object in the target time period. Among them, the first historical game status parameter is a parameter used to describe the long-term game status of the corresponding object, such as the number of days the target object participates in the game scenario within the historical game cycle (such as the number of ranking days in the ranked match). The real-time game status parameter is a parameter used to describe the real-time game status of the corresponding object, such as the initial level (such as the initial ranking level) and the number of game matches of the target object in the target time period. ② The second status information of the target object, and the status parameters in the second status information include the first historical game status parameters of the target object in the target time period. ③ The third status information of the target object, and the status parameters in the third status information include the second historical game status parameters and the real-time game status parameters of the target object in the target time period. Among them, the second historical game status parameter is a parameter used to describe the short-term game status of the corresponding object, such as the winning rate of the target object in the previous unit time period (the previous day) of the current unit time period (such as the current day) and the indication parameter used to indicate whether the target object i participates in the game match (such as the ranked match) in the previous unit time period of the current unit time period.

[0124] In one embodiment, determining a matching object state set of a target object from multiple object state sets according to the status information of the target object includes: obtaining first status information of the target object, and determining the matching object state set of the target object from multiple object state sets according to the first status information. The status parameters in the game status information associated with the matching object state set are the same as the status parameters in the first status information (i.e., both the first historical game status parameters and the real-time game status parameters are the same). If the matching object state set of the target object cannot be determined from multiple object state sets according to the first status information, then obtain second status information of the target object, and determine the matching object state set of the target object from multiple object state sets according to the second status information. The status parameters in the game status information associated with the matching object state set are the same as the status parameters in the second status information (i.e., the first historical game status parameters are the same). Optionally, determine the game victory parameter associated with the matching object state set as the second victory parameter associated with the matching object state set. Optionally, obtain third status information of the target object. Determine an auxiliary object state set of the target object from multiple object state sets according to the third status information. The status parameters in the game status information associated with the auxiliary object state set are the same as the status parameters in the third status information (i.e., both the second historical game status parameters and the real-time game status parameters are the same). Obtain the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set. Determine the second victory parameter associated with the matching object state set according to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set; for example, perform a mean calculation on the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set to obtain the second victory parameter associated with the matching object state set.

[0125] In another embodiment, determining a matching object state set of a target object from multiple object state sets according to the state information of the target object includes: obtaining third state information of the target object, and determining a matching object state set of the target object from multiple object state sets according to the third state information. The state parameters in the game state information associated with the matching object state set are the same as the state parameters in the third state information (that is, both the second historical game state parameters and the real-time game state parameters are the same). If a matching object state set of the target object cannot be determined from multiple object state sets according to the third state information, then obtain second state information of the target object, and determine a matching object state set of the target object from multiple object state sets according to the second state information. The state parameters in the game state information associated with the matching object state set are the same as the state parameters in the second state information (that is, the first historical game state parameters are the same). Optionally, determine the game victory parameter associated with the matching object state set as the second victory parameter associated with the matching object state set. Optionally, obtain first state information of the target object, and determine an auxiliary object state set of the target object from multiple object state sets according to the first state information. The state parameters in the game state information associated with the auxiliary object state set are the same as the state parameters in the first state information (that is, both the first historical game state parameters and the real-time game state parameters are the same). Obtain the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set. Determine the second victory parameter associated with the matching object state set according to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set; for example, perform a mean calculation on the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set to obtain the second victory parameter associated with the matching object state set.

[0126] It should be noted that the first state information can reflect the long-term game state of the target object, so that the second victory parameter associated with the matching object state set determined based on the first state information indicates the game matching strategy of the target object from the perspective of enhancing the long-term stickiness of the target object to the game. Correspondingly, the third state information can reflect the short-term game state of the target object, so that the second victory parameter associated with the matching object state set determined based on the third state information indicates the game matching strategy of the target object from the perspective of enhancing the short-term stickiness of the target object to the game. In addition, the second state information includes fewer state parameters (less comprehensive information) compared to the first state information and the third state information. Therefore, in the embodiments of the present application, the matching object state set determined based on the second state information is used as an alternative when the matching object state set cannot be determined based on the first state information and cannot be determined based on the third state information.

[0127] S303: Determine a game matching strategy for the target object based on the first victory parameter and a second victory parameter associated with the matching object state set.

[0128] Optionally, the game matching strategy includes one or both of a matching parameter adjustment strategy and an agent parameter adjustment strategy.

[0129] In one embodiment, the game matching strategy includes a matching parameter adjustment strategy (a strategy for adjusting matching parameters); determining the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set includes:

[0130] (1) If the first victory parameter is greater than the second victory parameter, the current matching parameter of the target object is adjusted upward, and the game match scenario of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter.

[0131] Among them, the matching parameter is a parameter used to represent the competitive level of the object; illustratively, the larger the matching parameter, the higher the competitive level, and the smaller the matching parameter, the lower the competitive level.

[0132] Specifically, when the first victory parameter is greater than the second victory parameter, the difficulty of the target object's game match scenario needs to be increased (to reduce the target object's probability of winning). At this time, the target object's game match scenario is processed according to one or both of the adjusted matching parameters and the current matching parameters, including one or more of the following steps: assigning an opponent player whose corresponding matching parameter is similar to the adjusted matching parameter (such as the difference between the matching parameters is less than a preset matching threshold) to the target object's game match scenario; assigning a teammate player whose corresponding matching parameter is less than the current matching parameter to the target object's game match scenario.

[0133] The current matching parameter of the target object is adjusted upward, including one or more of the following steps: adding the current matching parameter of the target object to the first preset matching parameter; setting the current matching parameter of the target object to the second preset matching parameter, the second preset matching parameter being greater than the current matching parameter. The first preset matching parameter and the second preset matching parameter can be set manually or by AI.

[0134] (2) If the first victory parameter is less than the second victory parameter, the current matching parameter of the target object is adjusted downward, and the game scene of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter.

[0135] Specifically, when the first victory parameter is less than the second victory parameter, it is necessary to reduce the difficulty of the game scene of the target object (to increase the probability of the target object winning). At this time, the game scene of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter after the downward adjustment process, including one or more of the following steps: allocating an opponent player with a matching parameter corresponding to the adjusted matching parameter similar to the adjusted matching parameter (for example, the difference between the matching parameters is less than the preset matching threshold) for the game scene of the target object; allocating a teammate player with a matching parameter greater than the current matching parameter for the game scene of the target object.

[0136] Among them, the process of downwardly adjusting the current matching parameter of the target object includes one or more of the following steps: subtracting the third preset matching parameter from the current matching parameter of the target object; setting the current matching parameter of the target object to the fourth preset matching parameter, and the fourth preset matching parameter is less than the current matching parameter. The third preset matching parameter and the fourth preset matching parameter can be set manually or by AI.

[0137] (3) If the first victory parameter is equal to the second victory parameter, the game scene of the target object is processed according to the current matching parameter of the target object. Specifically, an opponent player and a teammate player with matching parameters corresponding to the current matching parameter similar to the current matching parameter (for example, the difference between the matching parameters is less than the preset matching threshold) are allocated for the game scene of the target object.

[0138] It should be noted that the matching parameter of the opponent player or the teammate player can be determined based on their current matching parameter, or can be obtained after being adjusted by their matching parameter adjustment strategy.

[0139] It can be seen that the embodiment of the present application can customize the matching parameter adjustment strategy of the target object, thereby increasing the retention probability of the target object.

[0140] In one embodiment, the game matching strategy includes an agent parameter adjustment strategy (a strategy for adjusting agent parameters); based on the first victory parameter and the second victory parameter associated with the matching object state set, determining the game matching strategy of the target object includes:

[0141] (1) If the first victory parameter is greater than the second victory parameter, the difficulty of the game scene of the target object is increased (to reduce the probability of the target object winning). At this time, the game scene of the target object can be processed according to the first agent parameter.

[0142] (2) If the first victory parameter is equal to the second victory parameter, the difficulty of the game scenario of the target object is not intervened. At this time, the game scenario of the target object is processed according to the second agent parameter. (3) If the first victory parameter is less than the second victory parameter, the difficulty of the game scenario of the target object is reduced (to increase the probability of the target object winning). At this time, the game scenario of the target object can be processed according to the third agent parameter.

[0143] Among them, the first agent parameter, the second agent parameter, and the third agent parameter all include one or both of the number of agents (including one or both of the agent opponent and the agent teammate) and the ability parameter of the agent (used to reflect the strength of the corresponding agent, the larger the ability parameter, the stronger the strength, and the smaller the ability parameter, the weaker the strength), and the first agent parameter, the second agent parameter, and the third agent parameter are different.

[0144] Optionally, the first agent parameter includes one or more of the first number of agent opponents, the second number of agent teammates, the first ability parameter of the agent opponent, and the second ability parameter of the agent teammate. The second agent parameter includes one or more of the third number of agent opponents, the fourth number of agent teammates, the third ability parameter of the agent opponent, and the fourth ability parameter of the agent teammate. The third agent parameter includes one or more of the fifth number of agent opponents, the sixth number of agent teammates, the fifth ability parameter of the agent opponent, and the sixth ability parameter of the agent teammate. Among them, the first number is greater than the third number, and the third number is greater than the fifth number. The first ability parameter is greater than the third ability parameter, and the third ability parameter is greater than the fifth ability parameter. The second number is less than the fourth number, and the fourth number is less than the sixth number. The second ability parameter is less than the fourth ability parameter, and the fourth ability parameter is less than the sixth ability parameter. It should be noted that the second agent parameter can refer to the parameter set by default by the system when not intervening in the difficulty of the game scenario of the target object.

[0145] For example, in a racing game, if the first victory parameter is greater than the second victory parameter, 5 intelligent agent opponents can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 5; if the first victory parameter is equal to the second victory parameter, 3 intelligent agent opponents can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 3; if the first victory parameter is less than the second victory parameter, 1 intelligent agent opponent can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 1. In a single-player level game, if the first victory parameter is greater than the second victory parameter, 1 intelligent agent opponent can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 5; if the first victory parameter is equal to the second victory parameter, 1 intelligent agent opponent can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 3; if the first victory parameter is less than the second victory parameter, 1 intelligent agent opponent can be assigned to the target object, and the ability parameter of the intelligent agent opponent is 1.

[0146] In one embodiment, before obtaining the first victory parameter of the target object in the game match scene (i.e., before executing S301), the number of times of determining the match strategy for the target object in the target time period can also be judged. If the determined number of times is greater than the first number threshold (which can be set manually, such as 15), the game object scene of the target object is not intervened, the system match strategy is determined for the target object, and the game match scene of the target object is processed according to the system match strategy. The system match strategy refers to the match strategy set by default by the system, and this system match strategy includes a match parameter system match strategy (such as processing the game match scene of the target object according to the current match parameter of the target object above) and an intelligent agent parameter system match strategy (such as processing the game match scene of the target object according to the second intelligent agent parameter above). If the determined number of times is less than or equal to the first number threshold, the step of obtaining the first victory parameter of the target object in the game match scene is triggered to be executed.

[0147] In one implementation manner, before triggering the execution of the step of obtaining the first victory parameter of the target object in the game match scene, it can be judged whether the number of matches of the target object in the target time period is equal to the second number threshold (which is 1). If the number of matches is equal to the second number threshold, the default match strategy is determined for the target object, and the game match scene of the target object is processed according to the default match strategy. The default match strategy includes one or both of a first-game match parameter match strategy and a first-game intelligent agent parameter match strategy. The default match strategy can be used to increase the probability of the target object winning in the first game match in the target time period, and this application does not limit this. If the number of matches is not equal to the second number threshold, the step of obtaining the first victory parameter of the target object in the game match scene is triggered to be executed.

[0148] As shown above, please refer to Figure 5 , Figure 5It is a schematic flowchart of a method for determining a game matching strategy provided by an embodiment of the present application; this method for determining a game matching strategy is used to process the game match scene of a target object starting from matching parameters; as Figure 5 shown, this method includes the following steps S21 - S29:

[0149] S21. Detect whether the number of intervention times on the current day (i.e., the number of times of determining a game matching strategy for the target object in the target time period) is greater than the first number threshold. If so, enter S22; if not, enter S23. This first number threshold can be determined by statistics on the number of game matches of a large number of game objects. For example, within a day, if the number of game objects with more than 15 game matches is less than a certain value, then 15 can be considered as the first number threshold.

[0150] S22. Process the game match scene of the target object according to the matching parameter system matching strategy. The matching parameter system matching strategy can refer to a matching strategy for processing the game match scene of the target object based on the current matching parameters of the target object.

[0151] S23. Detect whether the current number of game matches of the target object (i.e., the number of game matches of the target object in the target time period) is equal to the second number threshold (which is 1). If so, enter S24; if not, enter S25 or S26.

[0152] S24. Process the game match scene of the target object based on the first - game - match parameter matching strategy. The first - game - match parameter matching strategy can be used to increase the probability of winning the first game match, such as assigning an opponent player with a weaker competitive level to the target object.

[0153] S25. If a matching object state set is determined based on the first state information of the target object, obtain the game win parameters associated with the matching object state set. Specifically, multiple object state sets can be determined, and the matching object state set whose associated game state information matches the first state information of the target object is obtained, and the game win parameters associated with the matching object state set are obtained.

[0154] S26. If a matching object state set is not determined based on the first state information of the target object, then determine a matching object state set based on the second state information of the target object, and obtain the game win parameters associated with the matching object state set. Specifically, multiple object state sets can be determined, and the matching object state set whose associated game state information matches the second state information of the target object is obtained, and the game win parameters associated with the matching object state set are obtained.

[0155] S27. Determine an auxiliary object state set based on the third state information of the target object, and obtain the game win parameters associated with the auxiliary object state set.

[0156] S28. Based on the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, determine the second victory parameter associated with the matching object state set, and determine the matching parameter adjustment strategy of the target object based on the second victory parameter associated with the matching object state set. The matching parameter adjustment strategy of the target object is used to adjust the current matching parameter of the target object. If the first victory parameter of the target object is less than the second victory parameter, the current matching parameter of the target object is subtracted by 50; when the first victory parameter of the target object is equal to the second victory parameter, the current matching parameter of the target object is not changed; when the first victory parameter of the target object is greater than the second victory parameter, the current matching parameter of the target object is added by 50.

[0157] S29. Processing the game scene of the target object based on the matching parameter adjustment strategy of the target object.

[0158] Accordingly, see Figure 6 , Figure 6 is a flow chart of another method for determining a matchmaking strategy provided by an embodiment of the present application; the method for determining a matchmaking strategy is used to process a game matchmaking scenario of a target object based on agent parameters; Figure 6 As shown, the method includes the following steps S31-S39:

[0159] S31, detect whether the number of interventions on the day (i.e., the number of times the matchmaking strategy is determined for the target object in the target time period) is greater than the first number threshold, if so, proceed to S32, if not, proceed to S33. The first number threshold can be determined based on the number of games for a large number of game objects, for example, if the number of game objects with more than 15 games in a day is less than a certain value, 15 can be considered as the first number threshold.

[0160] S32, processing the game scene of the target object according to the agent parameter system matching strategy. The agent parameter system matching strategy may refer to a matching strategy for processing the game scene of the target object according to the second agent parameter.

[0161] S33, check whether the current number of games played by the target object (i.e., the number of games played by the target object in the target time period) is equal to the second number threshold (1), if so, proceed to S34, if not, proceed to S35 or S36.

[0162] S34, processing the game scene of the target object based on the first-game agent parameter matching strategy. The first-game agent parameter matching strategy can be used to increase the probability of winning the first game, such as assigning an agent opponent with lower ability parameters to the target object.

[0163] S35: If a matching object state set is determined based on the first state information of the target object, then a game victory parameter associated with the matching object state set is obtained. Specifically, a matching object state set whose game state information associated with multiple object state sets matches the first state information of the target object is determined, and the game victory parameter associated with the matching object state set is obtained.

[0164] S36: If the matching object state set is not determined based on the first state information of the target object, a matching object state set is determined based on the second state information of the target object, and a game victory parameter associated with the matching object state set is obtained. Specifically, a matching object state set whose game state information associated with multiple object state sets matches the second state information of the target object is determined, and the game victory parameter associated with the matching object state set is obtained.

[0165] S37. Determine an auxiliary object state set based on the third state information of the target object, and obtain a game victory parameter associated with the auxiliary object state set.

[0166] S38. Based on the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, determine the second victory parameter associated with the matching object state set, and determine the agent parameter adjustment strategy of the target object based on the second victory parameter associated with the matching object state set. If the first victory parameter of the target object is less than the second victory parameter, 5 agent teammates are assigned to the game game scene of the target object; when the first victory parameter of the target object is equal to the second victory parameter, 2 agent teammates are assigned to the game game scene of the target object; when the first victory parameter of the target object is greater than the second victory parameter, 0 agent teammates are assigned to the game game scene of the target object.

[0167] S39. Process the game scenario of the target object based on the agent parameter adjustment strategy of the target object.

[0168] It can be seen that the embodiments of the present application will further consider the players' needs for game experience on the basis of similar players' abilities, that is, through the game status of the target object (including long-term game status, short-term game status and real-time game status), analyze what difficulty level the target object will be more willing to participate in the next game under this game state, thereby adjusting the matching parameters and agent parameters to obtain the game matching strategy of the target object. In this way, the game matching method of the game game scene can be flexibly adjusted, and through the optimization of the game matching strategy, the player's experience indicators in the game (such as the number of games, retention probability, active days during the observation period and even asset consumption) can be greatly improved, which is conducive to increasing the user stickiness of the game and improving the player's game experience.

[0169] In summary, see Figure 7 ,Figure 7 This is a schematic diagram of the system framework of a data processing method proposed in this application. As Figure 7 shown, this method includes: offline training and online intervention.

[0170] Offline training: Obtain the historical game data of players, and use the obtained historical game data of players to provide an optimal growth path formulation service. As Figure 8 (This is a schematic diagram of an optimal growth path formulation service provided by an embodiment of this application) shown, the historical game data of players may include whether they participated in game matches in the past 5 days (such as whether they participated in ranked matches), the win rate in the past 5 days, the players who participated in game match scenarios in the past 60 days, the most recent level (such as the rank level), and the number of days of played games (such as the number of ranked days). Among them, summary data 1 can be obtained from the historical game data of players (for example, taking whether they participated in game matches in the past 5 days, the win rate in the past 5 days, the players who participated in game match scenarios in the past 60 days, and the most recent level as the first state features, and this summary data 1 includes the first state features associated with multiple initial sets clustered based on the first state features) and summary data 2 (for example, taking the number of days of played games, the players who participated in game match scenarios in the past 60 days, and the most recent level as the second state features, and this summary data 2 includes the second state features associated with multiple initial sets clustered based on the second state features). Then, write summary data 1 into data table 1, and write summary data 2 into data table 2. Then convert data table 1 into the redis format to obtain redis data 1; convert data table 2 into the redis format to obtain redis data 2. In this way, the data in redis data 1 can be exported into data that can be read by the machine (in milliseconds), and the data in redis data 2 can be exported into data that can be read by the machine (in milliseconds). Among them, redis (Remote Dictionary Server), that is, the remote dictionary service, is an open-source key-value database written in ANSI C language (a programming language), supporting the network, and can be based on memory or persistent, log-based, and provides APIs (Application Programming Interfaces) in multiple languages.

[0171] Online intervention: When a player starts a match, provide a player growth path dynamic adjustment service through the optimal growth path formulation service. This player growth path dynamic adjustment service may include a matching parameter adjustment service (implemented based on a matching parameter adjustment strategy) and an agent parameter adjustment service (implemented based on an agent parameter adjustment strategy). As Figure 9 (This is a schematic diagram of a player growth path dynamic adjustment service provided by an embodiment of this application) shown, Figure 9The redis data in (including redis data 1, redis data 2, ... redis data 5) includes at least one of the following parameters: preset matching parameters (such as the first preset matching parameters, the second preset matching parameters, the third preset matching parameters, and the fourth preset matching parameters mentioned above), preset agent parameters (such as the first agent parameters, the second agent parameters, and the third agent parameters mentioned above), which can be based on the player's status information (such as Figure 9 The game scenario of the player is processed by deriving the preset matching parameters and / or preset agent parameters from the corresponding redis data, which includes status information of past winning rates, status information without distinguishing the number of game days, status information distinguishing the number of game days, status information including the current number of game times (the first game), and status information including the current number of interventions (15 times).

[0172] Optionally, the data of recent seasons can be summarized to train the actor model in reinforcement learning, and the player's ranking speed can be scored through the critic model in reinforcement learning (for example, if the player's level is increased by 5 levels after participating in 5 games, the ranking speed is 1 level per game). The score is used as feedback to adjust the model parameters of the actor model so that the actor model can learn the optimal player growth path for different groups. For example, Figure 10 A schematic diagram of the optimal player growth path for different groups (obtained through reinforcement learning). In this way, the player's ranking speed should be determined based on the group to which the player belongs (e.g., if the state information matches the game state information associated with a certain object state set, then the player belongs to the group indicated by the corresponding object state set), thereby customizing the game matching strategy for the target object's game scene.

[0173] It can be seen that the embodiments of the present application can be based on the player experience optimization strategy of historical game data and reinforcement learning, and the offline difficulty optimizer (that is, the optimal player growth path corresponding to different groups obtained through reinforcement learning). Through this difficulty optimizer, the optimal growth path formulation service can be provided to the players, thereby adjusting the matching parameters and intelligent agent parameters in a targeted manner, and realizing flexible adjustment of the game matching strategy in the game game scenario.

[0174] The following provides a device of an embodiment of the present application. Next, in combination with the data processing method provided in the above-mentioned embodiment of the present application, the relevant device of the embodiment of the present application is introduced accordingly.

[0175] See also Figure 11 , Figure 11 Schematic diagram of a data processing device provided in an embodiment of the present application. Figure 11As shown, the data processing device 1100 can be applied to the server mentioned in the foregoing embodiments. Specifically, the data processing device 1100 can be a computer program (including program code) running in the server. For example, the data processing device 1100 is an application software; the data processing device 1100 can be used to execute the corresponding steps in the data processing method provided in the embodiments of the present application. Specifically, when implemented, the data processing device 1100 can specifically include:

[0176] An acquisition unit 1101, configured to acquire a first victory parameter of a target object in a game match scene;

[0177] A processing unit 1102, configured to determine a matching object state set of the target object from multiple object state sets according to the state information of the target object; each object state set is associated with a game state feature, and the game state feature includes game state information and a game victory parameter. The game state feature associated with each object state set is determined based on the game state features of each object in the corresponding object state set;

[0178] The processing unit 1102 is further configured to determine a game match strategy for the target object based on the first victory parameter and the second victory parameter associated with the matching object state set. The game match strategy includes one or both of a matching parameter adjustment strategy and an agent parameter adjustment strategy.

[0179] In an implementation manner, the game match strategy includes a matching parameter adjustment strategy; when the processing unit 1102 is configured to determine the game match strategy for the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically configured to perform the following steps:

[0180] If the first victory parameter is greater than the second victory parameter, the current matching parameter of the target object is adjusted upward, and the game match scene of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter;

[0181] If the first victory parameter is less than the second victory parameter, the current matching parameter of the target object is adjusted downward, and the game match scene of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter;

[0182] If the first victory parameter is equal to the second victory parameter, the game match scene of the target object is processed according to the current matching parameter of the target object.

[0183] In an implementation manner, the game match strategy includes an agent parameter adjustment strategy; when the processing unit 1102 is configured to determine the game match strategy for the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically configured to perform the following steps:

[0184] If the first victory parameter is greater than the second victory parameter, the game play scene of the target object is processed according to the first agent parameter;

[0185] If the first victory parameter is equal to the second victory parameter, the game play scene of the target object is processed according to the second agent parameter;

[0186] If the first victory parameter is less than the second victory parameter, the game play scene of the target object is processed according to the third agent parameter;

[0187] Wherein, the first agent parameter, the second agent parameter, and the third agent parameter each include one or two of the number of agents and the ability parameter of the agent, and the first agent parameter, the second agent parameter, and the third agent parameter are different.

[0188] In one implementation, when the processing unit 1102 is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is specifically used to perform the following steps:

[0189] Obtain the first state information of the target object. The state parameters in the first state information include the first historical game state parameter and the real-time game state parameter of the target object in the target time period, and the target time period is determined based on the current system time;

[0190] Determine the matching object state set of the target object from multiple object state sets according to the first state information. The state parameters in the game state information associated with the matching object state set are the same as the state parameters in the first state information.

[0191] In one implementation, when the processing unit 1102 is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is further used to perform the following steps:

[0192] If the matching object state set of the target object is not determined from multiple object state sets according to the first state information, obtain the second state information of the target object. The state parameters in the second state information include the first historical game state parameter of the target object in the target time period;

[0193] Determine the matching object state set of the target object from multiple object state sets according to the second state information. The state parameters in the game state information associated with the matching object state set are the same as the state parameters in the second state information.

[0194] In one implementation, when the processing unit 1102 is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is used to perform the following steps:

[0195] Acquire third state information of the target object, where the state parameters in the third state information include a second historical game state parameter and a real-time game state parameter of the target object in a target time period, where the target time period is determined based on the current system time;

[0196] A matching object state set of the target object is determined from a plurality of object state sets according to the third state information, and state parameters in the game state information associated with the matching object state set are the same as the state parameters in the third state information.

[0197] In one implementation, the processing unit 1102 is further configured to perform the following steps:

[0198] Acquire third state information of the target object, where the state parameters in the third state information include a second historical game state parameter and a real-time game state parameter of the target object in a target time period;

[0199] Determine an auxiliary object state set of the target object from a plurality of object state sets according to the third state information, wherein the state parameters in the game state information associated with the auxiliary object state set are the same as the state parameters in the third state information;

[0200] Get the game victory parameters associated with the auxiliary object state set and the game victory parameters associated with the matching object state set;

[0201] According to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, a second victory parameter associated with the matching object state set is determined.

[0202] In one implementation, the processing unit 1102 is further configured to perform the following steps:

[0203] Determine N objects participating in the game scene in a historical game cycle, where the historical game cycle is divided into one or more statistical time periods, and N is a positive integer;

[0204] Determine the game status characteristics of each object in each statistical time period;

[0205] According to the game state characteristics of each object in each statistical time period, clustering processing is performed on N objects to obtain multiple initial state sets, each initial state set includes one or more objects with the same game state characteristics;

[0206] According to the object retention parameter of each initial state set, multiple initial state sets are screened to obtain multiple object state sets.

[0207] In one implementation, object i is any one of N objects, and statistical time period j is any one of one or more statistical time periods. Both i and j are positive integers. When the processing unit 1102 is used to determine the game state information of object i in statistical time period j, it is specifically used to execute one or more of the following steps:

[0208] Determine the first historical game state parameter and the real-time game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j;

[0209] Determine the second historical game state parameter and the real-time game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j;

[0210] Determine the first historical game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j.

[0211] In one implementation, before obtaining the first victory parameter of the target object in the game scene, the processing unit 1102 is further used to execute the following steps:

[0212] Judge the number of times of determining the game matching strategy for the target object in the target time period, where the target time period is determined based on the current system time;

[0213] If the determined number of times is greater than the first number threshold, determine the system matching strategy for the target object, and process the game scene of the target object according to the system matching strategy;

[0214] If the determined number of times is less than or equal to the first number threshold, trigger the step of obtaining the first victory parameter of the target object in the game scene.

[0215] In one implementation, before triggering the step of obtaining the first victory parameter of the target object in the game scene, the processing unit 1102 is further used to execute the following steps:

[0216] Judge whether the number of game times of the target object in the target time period is equal to the second number threshold;

[0217] If the number of game times is equal to the second number threshold, determine the default matching strategy for the target object, and process the game scene of the target object according to the default matching strategy;

[0218] If the number of game times is not equal to the second number threshold, trigger the step of obtaining the first victory parameter of the target object in the game scene.

[0219] In the embodiments of the present application, multiple object state sets are constructed. Each object state set is associated with game state characteristics (including game state information and game victory parameters), and the game state characteristics associated with each object state set are determined based on the game state characteristics of each object in the corresponding object state set. For the game scenario of a target object, the matching object state set of the target object can be determined from multiple object state sets according to the state information of the target object; wherein, the matching object state set is the object state set in which the associated game state information in the multiple object state sets matches the state information of the target object (matching if they are the same, not matching if they are different). According to the second victory parameter associated with the matching object state set and the first victory parameter of the target object, the game matching strategy of the target object is determined. It can be seen that the embodiments of the present application can customize the game matching strategy for the game scenario of the target object, so that the flexible adjustment of the game matching strategy in the game scenario can be realized.

[0220] Please refer to Figure 12 , Figure 12 FIG. is a schematic structural diagram of a computer device provided by an embodiment of the present application. The computer device 1200 is used to execute the steps performed by the server in the foregoing method embodiments. The computer device 1200 includes: one or more processors 1201; one or more input devices 1202, one or more output devices 1203, and a memory 1204. The above-mentioned processors 1201, input devices 1202, output devices 1203, and memory 1204 are connected through a bus 1205. Among them, the memory 1204 is used to store computer programs, and the computer programs include program instructions. In a feasible embodiment, the processor 1201 is used to call the program instructions stored in the memory 1204 to perform the following operations:

[0221] Obtain the first victory parameter of the target object in the game scenario;

[0222] According to the state information of the target object, determine the matching object state set of the target object from multiple object state sets; each object state set is associated with game state characteristics, and the game state characteristics include game state information and game victory parameters. The game state characteristics associated with each object state set are determined based on the game state characteristics of each object in the corresponding object state set;

[0223] Based on the first victory parameter and the second victory parameter associated with the matching object state set, determine the game matching strategy of the target object. The game matching strategy includes one or both of a matching parameter adjustment strategy and an agent parameter adjustment strategy.

[0224] In one implementation, the game matching strategy includes a matching parameter adjustment strategy; when the processor 1201 is used to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically used to perform the following steps:

[0225] If the first victory parameter is greater than the second victory parameter, the current matching parameter of the target object is adjusted upward, and the game match scenario of the target object is processed according to one or both of the adjusted matching parameter and the current matching parameter;

[0226] If the first victory parameter is less than the second victory parameter, the current matching parameter of the target object is adjusted downward, and the game match scenario of the target object is processed according to one or both of the matching parameter after the adjustment and the current matching parameter;

[0227] If the first victory parameter is equal to the second victory parameter, the game match scene of the target object is processed according to the current matching parameter of the target object.

[0228] In one implementation, the game matching strategy includes an agent parameter adjustment strategy; when the processor 1201 is used to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set, it is specifically used to perform the following steps:

[0229] If the first victory parameter is greater than the second victory parameter, the game scene of the target object is processed according to the first agent parameter;

[0230] If the first victory parameter is equal to the second victory parameter, the game scene of the target object is processed according to the second agent parameter;

[0231] If the first victory parameter is less than the second victory parameter, the game scene of the target object is processed according to the third agent parameter;

[0232] Among them, the first agent parameter, the second agent parameter and the third agent parameter all include one or two of the number of agents and the ability parameters of the agents, and the first agent parameter, the second agent parameter and the third agent parameter are different.

[0233] In one implementation, the processor 1201 is configured to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, specifically to perform the following steps:

[0234] Acquire first state information of the target object, where the state parameters in the first state information include first historical game state parameters and real-time game state parameters of the target object in a target time period, where the target time period is determined based on the current system time;

[0235] Determine the matching object state set of the target object from multiple object state sets according to the first state information, and the state parameters in the game state information associated with the matching object state set are the same as the state parameters in the first state information.

[0236] In one implementation, when the processor 1201 is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is further used to perform the following steps:

[0237] If the matching object state set of the target object is not determined from multiple object state sets according to the first state information, obtain the second state information of the target object, and the state parameters in the second state information include the first historical game state parameters of the target object in the target time period;

[0238] Determine the matching object state set of the target object from multiple object state sets according to the second state information, and the state parameters in the game state information associated with the matching object state set are the same as the state parameters in the second state information.

[0239] In one implementation, when the processor 1201 is used to determine the matching object state set of the target object from multiple object state sets according to the state information of the target object, it is used to perform the following steps:

[0240] Obtain the third state information of the target object, and the state parameters in the third state information include the second historical game state parameters and the real-time game state parameters of the target object in the target time period, and the target time period is determined based on the current system time;

[0241] Determine the matching object state set of the target object from multiple object state sets according to the third state information, and the state parameters in the game state information associated with the matching object state set are the same as the state parameters in the third state information.

[0242] In one implementation, the processor 1201 is further used to perform the following steps:

[0243] Obtain the third state information of the target object, and the state parameters in the third state information include the second historical game state parameters and the real-time game state parameters of the target object in the target time period;

[0244] Determine the auxiliary object state set of the target object from multiple object state sets according to the third state information, and the state parameters in the game state information associated with the auxiliary object state set are the same as the state parameters in the third state information;

[0245] Obtain the game victory parameters associated with the auxiliary object state set and the game victory parameters associated with the matching object state set;

[0246] According to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, a second victory parameter associated with the matching object state set is determined.

[0247] In one implementation, the processor 1201 is further configured to execute the following steps:

[0248] Determine N objects participating in the game scene in a historical game cycle, where the historical game cycle is divided into one or more statistical time periods, and N is a positive integer;

[0249] Determine the game status characteristics of each object in each statistical time period;

[0250] According to the game state characteristics of each object in each statistical time period, clustering processing is performed on N objects to obtain multiple initial state sets, each initial state set includes one or more objects with the same game state characteristics;

[0251] According to the object retention parameter of each initial state set, multiple initial state sets are screened to obtain multiple object state sets.

[0252] In one implementation, the object i is any one of the N objects, the statistical time period j is any one of the one or more statistical time periods, and both i and j are positive integers; when the processor 1201 is used to determine the game state information of the object i in the statistical time period j, it is specifically used to perform one or more of the following steps:

[0253] Determine the first historical game state parameter and the real-time game state parameter of the object i in the statistical time period j as the game state information of the object i in the statistical time period j;

[0254] Determine the second historical game state parameter and the real-time game state parameter of the object i in the statistical time period j as the game state information of the object i in the statistical time period j;

[0255] The first historical game state parameter of the object i in the statistical time period j is determined as the game state information of the object i in the statistical time period j.

[0256] In one implementation, before obtaining the first victory parameter of the target object in the game scene, the processor 1201 is further configured to perform the following steps:

[0257] Determine the number of times a matchmaking strategy is determined for a target object in a target time period, where the target time period is determined based on the current system time;

[0258] If the determined number of times is greater than the first number threshold, a system matching strategy is determined for the target object, and the game match scenario of the target object is processed according to the system matching strategy;

[0259] If the determined number of times is less than or equal to the first number threshold, trigger the step of obtaining the first victory parameter of the target object in the game session scenario.

[0260] In one implementation, before triggering the step of obtaining the first victory parameter of the target object in the game session scenario, the processor 1201 is further configured to perform the following steps:

[0261] Determine whether the number of times of the target object in the target time period is equal to the second number threshold;

[0262] If the number of times of the game session is equal to the second number threshold, determine the default matching strategy for the target object, and process the game session scenario of the target object according to the default matching strategy;

[0263] If the number of times of the game session is not equal to the second number threshold, trigger the step of obtaining the first victory parameter of the target object in the game session scenario.

[0264] Based on the same inventive concept, the principle of problem-solving and the beneficial effects of the computer device provided in the embodiments of the present application are similar to the principle of problem-solving and the beneficial effects of the data processing method in the method embodiments of the present application. For details, reference can be made to the principle and beneficial effects of the method implementation. For the sake of brevity, it will not be elaborated here.

[0265] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0266] In addition, it should be noted here that: The embodiments of the present application also provide a computer storage medium, and the computer 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 methods in the corresponding embodiments described above. Therefore, it will not be elaborated here. For the technical details not disclosed in the embodiments of the computer storage medium involved in the present application, please refer to the description of the method embodiments of the present application. As an example, the program instructions can be deployed on one computer device, or executed on multiple computer devices located at one place, or executed on multiple computer devices distributed at multiple places and interconnected through a communication network.

[0267] According to one aspect of the present application, embodiments of the present application further provide a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device can execute the methods in the corresponding embodiments described above. Therefore, details will not be repeated here.

[0268] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0269] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data processing device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive (SSD)).

[0270] The foregoing disclosure is only for the preferred embodiments of the present application, and of course, it 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 still fall within the scope covered by the present application.

Claims

1. A data processing method, characterized in that, Including: Obtain the first victory parameter of the target object in the game battle scene; According to the status information of the target object, determine the matching object status set of the target object from multiple object status sets; each object status set is associated with a battle status feature, and the battle status feature includes battle status information and a battle victory parameter. The battle status feature associated with each object status set is determined based on the battle status features of each object in the corresponding object status set; Based on the first victory parameter and the second victory parameter associated with the matching object status set, determine the battle matching strategy of the target object.

2. The method according to claim 1, characterized in that The battle matching strategy includes a matching parameter adjustment strategy; based on the first victory parameter and the second victory parameter associated with the matching object status set, determining the battle matching strategy of the target object includes: If the first victory parameter is greater than the second victory parameter, perform an upward adjustment on the current matching parameter of the target object, and process the game battle scene of the target object according to one or both of the matching parameter after the upward adjustment and the current matching parameter; If the first victory parameter is less than the second victory parameter, perform a downward adjustment on the current matching parameter of the target object, and process the game battle scene of the target object according to one or both of the matching parameter after the downward adjustment and the current matching parameter; If the first victory parameter is equal to the second victory parameter, process the game battle scene of the target object according to the current matching parameter of the target object.

3. The method according to claim 1, characterized in that The battle matching strategy includes an agent parameter adjustment strategy; based on the first victory parameter and the second victory parameter associated with the matching object status set, determining the battle matching strategy of the target object includes: If the first victory parameter is greater than the second victory parameter, process the game battle scene of the target object according to the first agent parameter; If the first victory parameter is equal to the second victory parameter, process the game battle scene of the target object according to the second agent parameter; If the first victory parameter is less than the second victory parameter, process the game battle scene of the target object according to the third agent parameter; Wherein, the first agent parameter, the second agent parameter, and the third agent parameter each include one or both of the number of agents and the ability parameter of the agent, and the first agent parameter, the second agent parameter, and the third agent parameter are different.

4. The method according to claim 1, wherein The determining the matching object status set of the target object from multiple object status sets according to the status information of the target object includes: Obtain the first status information of the target object, and the status parameters in the first status information include the first historical battle status parameter and the real-time battle status parameter of the target object in the target time period, and the target time period is determined based on the current system time; A matching object state set of the target object is determined from a plurality of object state sets according to the first state information, and state parameters in the game state information associated with the matching object state set are the same as the state parameters in the first state information.

5. The method according to claim 4, wherein The determining, according to the state information of the target object, a matching object state set of the target object from a plurality of object state sets further comprises: If a matching object state set of the target object is not determined from a plurality of object state sets according to the first state information, obtaining second state information of the target object, where state parameters in the second state information include first historical game state parameters of the target object in a target time period; A matching object state set of the target object is determined from the plurality of object state sets according to the second state information, and state parameters in the game state information associated with the matching object state set are the same as state parameters in the second state information.

6. The method according to claim 4 or 5, characterized in that The method further comprises: Acquire third state information of the target object, where state parameters in the third state information include a second historical game state parameter and a real-time game state parameter of the target object in a target time period; Determine an auxiliary object state set of the target object from the plurality of object state sets according to the third state information, wherein state parameters in the game state information associated with the auxiliary object state set are the same as state parameters in the third state information; Obtaining the game victory parameters associated with the auxiliary object state set and the game victory parameters associated with the matching object state set; According to the game victory parameter associated with the auxiliary object state set and the game victory parameter associated with the matching object state set, a second victory parameter associated with the matching object state set is determined.

7. The method according to claim 1, wherein The step of determining a matching object state set of the target object from a plurality of object state sets according to the state information of the target object includes: Acquire third state information of the target object, where state parameters in the third state information include a second historical game state parameter and a real-time game state parameter of the target object in a target time period, where the target time period is determined based on the current system time; A matching object state set of the target object is determined from a plurality of object state sets according to the third state information, and state parameters in the game state information associated with the matching object state set are the same as state parameters in the third state information.

8. The method according to claim 1, characterized in that, The method further comprises: Determine N objects participating in a game scene in a historical game cycle, where the historical game cycle is divided into one or more statistical time periods, and N is a positive integer; Determine the game status characteristics of each object in each statistical time period; Clustering the N objects according to the game state characteristics of each object in each statistical time period to obtain a plurality of initial state sets, each initial state set including one or more objects with the same game state characteristics; The multiple initial state sets are screened according to the object retention parameter of each initial state set to obtain the multiple object state sets.

9. The method according to claim 8, wherein Object i is any one of the N objects, and statistical time period j is any one of the one or more statistical time periods. Both i and j are positive integers. Determining the game state information of object i in statistical time period j includes one or more of the following steps: Determine the first historical game state parameter and the real-time game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j; Determine the second historical game state parameter and the real-time game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j; Determine the first historical game state parameter of object i in statistical time period j as the game state information of object i in statistical time period j.

10. The method according to claim 1, characterized in that, Before obtaining the first victory parameter of the target object in the game scenario, the method further includes: Judging the number of times of determining the game matching strategy for the target object in the target time period, where the target time period is determined based on the current system time; If the determined number of times is greater than the first number threshold, determine the system matching strategy for the target object, and process the game scenario of the target object according to the system matching strategy; If the determined number of times is less than or equal to the first number threshold, trigger the step of obtaining the first victory parameter of the target object in the game scenario.

11. The method according to claim 10, characterized in that, Before triggering the step of obtaining the first victory parameter of the target object in the game scenario, the method further includes: Judging whether the number of games of the target object in the target time period is equal to the second number threshold; If the number of games is equal to the second number threshold, determine the default matching strategy for the target object, and process the game scenario of the target object according to the default matching strategy; If the number of games is not equal to the second number threshold, trigger the step of obtaining the first victory parameter of the target object in the game scenario.

12. A game processing device, characterized in that, Includes: An acquisition unit for acquiring the first victory parameter of the target object in the game scenario; A processing unit for determining the matching object state set of the target object from multiple object state sets according to the state information of the target object; each object state set is associated with a game state feature, and the game state feature includes game state information and a game victory parameter. The game state feature associated with each object state set is determined based on the game state features of each object in the corresponding object state set; The processing unit is further configured to determine the game matching strategy of the target object based on the first victory parameter and the second victory parameter associated with the matching object state set.

13. A computer device, characterized in that, The computer device includes: A processor adapted to implement a computer program; A computer-readable storage medium storing a computer program, the computer program being adapted to be loaded and executed by the processor to perform the data processing method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is adapted to be loaded and executed by a processor to perform the data processing method according to any one of claims 1-11.

15. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the data processing method according to any one of claims 1-11.

Images