Game player party formation method and apparatus, computer device, and storage medium

Abstract

Disclosed in embodiments of the present application are a game player party formation method and apparatus, a computer device, and a storage medium. On the basis of party formation reference information of players, invitation probability gain values of a target game player and candidate game players can be calculated by means of a player matching system, and then on the basis of the invitation probability gain values, a target candidate game player forming a party with the target game player is determined from among the plurality of candidate game players so as to obtain a target party for completing player matching and party formation operation, so that high-activity and low-activity players are matched with low-activity players, and the low-activity players are driven by the high-activity players, thereby improving the game experience of all players. Moreover, the probability of mutual invitation between players after game playing ends can be improved, thereby effectively saving computer computing resources required by player matching, and improving the matching and party formation efficiency of players.

Description

Game player team formation method, device, computer equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application number 202410205534.1, filed on February 23, 2024, entitled “Method, device, computer equipment and storage medium for forming a team of game players”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The embodiments of the present application relate to the field of computer technology, and in particular to a method, apparatus, computer device, and storage medium for forming a team of game players. Background Art

[0004] To satisfy people's pursuit of spiritual life, entertainment games that can be played on terminals have emerged. For example, role-playing games, tactical competitive games, shooting competitive games, and massively multiplayer online role-playing games (MMORPGs) developed based on client- or server-based architectures are available. In these games, players can manipulate virtual characters on the screen to play the game. Based on the player's first-person or third-person perspective, they can perform actions such as walking, running, jumping, picking up items, and fighting in the game scene. This allows players to experience the visual impact of the game as if they are in the real world, greatly enhancing the initiative and realism of the game.

[0005] Currently, matching systems play a crucial role in multiplayer competitive games. The primary goal of a matching system is to organize players into fair and balanced teams, making the gaming experience more engaging and challenging. In related art, player matching is typically performed based on player ratings or game preferences. For example, each player has a player rating that reflects their gaming proficiency. The matching system then groups players based on their player ratings, minimizing the differences in ratings between players within each team. Another example is that the matching system assigns players to appropriate teams based on their gaming preferences and character selections. However, related art fails to fully consider player matching, resulting in clustering of high- and low-activity players. This makes it difficult to properly match high- and low-activity players, requiring significant computing resources for player matching. This leads to inaccurate matching results and inefficient matching. Summary of the Invention

[0006] The embodiments of the present application provide a method, apparatus, computer equipment, and storage medium for forming a team of game players. A player matching system can be used to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player to be teamed with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. This can pair high- and low-activity players with low-activity players, and use high-activity players to drive low-activity players, thereby improving the gaming experience of all players. In addition, it can also increase the probability of players inviting each other after the game is over, effectively saving computer computing resources required for player matching, and improving the efficiency of player matching and teaming.

[0007] The embodiment of the present application provides a method for forming a team of game players, and the method for forming a team of game players includes:

[0008] Determining a target game player from the pool of players to be matched, obtaining player information and first team reference information of the target game player, and screening a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information;

[0009] Determining a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player;

[0010] determining, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players;

[0011] determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players;

[0012] determining an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to teaming up the target game player and the candidate game player with other candidate game players from the plurality of candidate game players;

[0013] Based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from a plurality of candidate game players to obtain a target team.

[0014] Accordingly, an embodiment of the present application further provides a device for forming a team of game players, the device comprising:

[0015] a processing unit configured to determine a target game player from a pool of players to be matched, obtain player information of the target game player and first team reference information, and screen a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information;

[0016] a first determining unit configured to determine a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player;

[0017] a second determining unit configured to determine, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players;

[0018] a third determining unit configured to determine, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players;

[0019] a fourth determining unit configured to determine an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to when the target game player and the candidate game player are teamed up with other candidate game players among the plurality of candidate game players;

[0020] A fifth determining unit is configured to determine, based on the invitation probability gain value, a target candidate game player to be teamed with the target game player from a plurality of candidate game players to obtain a target team.

[0021] Correspondingly, an embodiment of the present application also provides a computer device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of any one of the methods for forming a team of game players are implemented.

[0022] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements the steps of any one of the methods for forming a team of game players.

[0023] The embodiments of the present application provide a method, apparatus, computer device, and storage medium for forming a team of game players. The method comprises the following steps: determining a target game player from a pool of players to be matched, obtaining player information and first team reference information of the target game player, and screening multiple candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; then, based on the first team reference information of the target game player and the second team reference information of each candidate game player, determining a first probability of an invitation occurring between the target game player and each candidate game player; then, based on the first team reference information of the target game player, determining a second probability of an invitation occurring between the target game player and at least some of the multiple candidate game players; and Then, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the multiple candidate game players is determined; then, based on the second probability, and the first probability and the third probability corresponding to each candidate game player, an invitation probability gain value between the target game player and each candidate game player is determined, wherein the invitation probability gain value is used to represent: after the target game player and the candidate game player are teamed up, the invitation rate increases compared to when the target game player and the candidate game player are respectively teamed up with other candidate game players among the multiple candidate game players; finally, based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from the multiple candidate game players to obtain a target team. The embodiment of the present application can use a player matching system to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player who teams up with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. It can make high and low activity players match with low activity players, and use high activity players to drive low activity players, thereby improving the gaming experience of all players; and it can also increase the probability of players inviting each other after the game is over, effectively saving the computer computing resources required for player matching, and improving the efficiency of player matching and teaming. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0025] FIG1 is a schematic diagram of a scenario of a team formation system for game players provided in one embodiment of the present application.

[0026] FIG2 is a flow chart of a method for forming a team of game players provided in one embodiment of the present application.

[0027] FIG3 a is a schematic structural diagram of a player relationship network diagram provided in one embodiment of the present application.

[0028] FIG3 b is a schematic structural diagram of a player relationship network diagram provided in one embodiment of the present application.

[0029] FIG3 c is a schematic structural diagram of a player relationship network diagram provided in one embodiment of the present application.

[0030] FIG4 is a schematic structural diagram of a device for forming a team of game players according to one embodiment of the present application.

[0031] FIG5 is a schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0033] The embodiments of the present application provide a method, apparatus, computer device, and storage medium for forming a team of game players. Specifically, the method for forming a team of game players according to the embodiments of the present application can be executed by a computer device, wherein the computer device can be a terminal. The terminal can be a terminal device such as a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), etc. The terminal can also include a client, which can be a video application client, music application client, game application client, browser client with a game program, or instant messaging client.

[0034] Please refer to Figure 1, which is a scene diagram of the team formation system of game players provided in an embodiment of the present application, including computer equipment. The system may include at least one terminal, at least one server, and a network. The terminal held by the user can be connected to the servers of different games through the network. The terminal is any device with computing hardware that can support and execute the software product corresponding to the game. In addition, the terminal has one or more multi-touch screens for sensing and obtaining the input of the user through touch or sliding operations performed at multiple points on one or more touch-sensitive displays. In addition, when the system includes multiple terminals, multiple servers, and multiple networks, different terminals can be connected to each other through different networks and different servers. The network can be a wireless network or a wired network, such as a wireless network such as a wireless local area network (WLAN), a local area network (LAN), a cellular network, a 2G network, a 3G network, a 4G network, a 5G network, etc. In addition, different terminals can also use their own Bluetooth network or hotspot network to connect to other terminals or to servers, etc.

[0035] The computer device can determine a target game player from a pool of players to be matched, obtain player information and first team reference information of the target game player, and screen out multiple candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; then, based on the first team reference information of the target game player and the second team reference information of each candidate game player, determine a first probability of invitation between the target game player and each candidate game player; then, based on the first team reference information of the target game player, determine a second probability of invitation between the target game player and at least some of the multiple candidate game players; thereafter, based on the The second team reference information is used to determine a third probability of an invitation occurring between the candidate game player and other candidate game players among the multiple candidate game players; then, based on the second probability, and the first probability and the third probability corresponding to each candidate game player, an invitation probability gain value between the target game player and each candidate game player is determined, wherein the invitation probability gain value is used to represent: after the target game player and the candidate game player are teamed up, the invitation rate increases compared to when the target game player and the candidate game player are separately teamed up with other candidate game players among the multiple candidate game players; finally, based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from the multiple candidate game players to obtain a target team.

[0036] It should be noted that the scenario diagram of the game player team system shown in Figure 1 is only an example. The game player team system and scenario described in the embodiment of the present application are for the purpose of more clearly illustrating the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the game player team system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0037] The disclosed embodiments provide a method, apparatus, computer device, and storage medium for forming a team of gamers. This method can be used with a terminal, such as a smartphone, tablet computer, laptop computer, or personal computer. The following describes the method, apparatus, terminal, and storage medium for forming a team of gamers in detail. It should be noted that the order in which the following embodiments are described does not limit the order of preference.

[0038] Please refer to FIG. 2 , which is a flowchart of a method for forming a team of game players provided in an embodiment of the present application. The specific process may include steps 101 to 106 as follows:

[0039] 101. Determine a target game player from a pool of players to be matched, obtain player information and first team reference information of the target game player, and screen out a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information.

[0040] Among them, the first team reference information is the target player vector of the target game player, and the target player vector is determined based on the player portrait information and game data of the target game player; the second team reference information is the candidate player vector of the candidate game player, and the candidate player vector is determined based on the player portrait information and game data of the candidate game player.

[0041] Specifically, the first team reference information may include a first user vector and a second user vector. The first user vector is obtained by inputting the target game player's user profile information and player match data into target model A to obtain embedding 1, also known as the first user vector. The second user vector is obtained by inputting the target game player's user profile information and player match data into target model B to obtain embedding 2, also known as the second user vector. The first user vector and the second user vector are user vectors in different representations.

[0042] In one example, the step of "determining the target game player from the pool of players to be matched" may include:

[0043] Get the current matching time of each player in the player pool to be matched;

[0044] Based on the current matching time of each game player, the game player with the longest current matching time is selected from the pool of players to be matched as the target game player.

[0045] In another embodiment, the step of "determining the target game player from the pool of players to be matched" may include:

[0046] Get the player level and online time of each player in the player pool to be matched;

[0047] Based on the player level and game online time of each game player, the target game player is screened out from the pool of players to be matched.

[0048] In an optional embodiment, the step of "screening a plurality of candidate game players from the pool of players to be matched based on the player information" may include:

[0049] A plurality of candidate game players are screened out from the pool of players to be matched based on the game character preferences of the target game player.

[0050] In another optional embodiment, the step of "screening a plurality of candidate game players from the pool of players to be matched based on the player information" may include:

[0051] Based on the game match score information of the target game player, a plurality of candidate game players are screened out from the pool of players to be matched.

[0052] 102 : Determine a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player.

[0053] In an embodiment of the present application, the target player vector embedding1 of the target game player target and the candidate player vector embedding1 of each candidate game player candidate_1, candidate_2, ...candidate_n can be respectively and sequentially subjected to dot product and input into the fully connected network for operation, so as to obtain the probability of an invitation occurring between the target game player target and each candidate game player candidate_n. Specifically, the probability of an invitation occurring between the target player and each player in the candidates is calculated as follows: the embedding1 of the target player and the embedding1 of candidate_i are input into the "whether an invitation behavior occurs" module of the target model A. It is specifically calculated by the following formula: Tmp1=Dot(embedding1(target),embedding1(candidate_i)) score1_i=sigmoid(a*tmp1+b)

[0054] Among them, dot represents the dot product, a and b are the parameters of the target model A, which are automatically generated when the target model A is trained.

[0055] In one embodiment, the step of “determining a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player” may include:

[0056] Performing dot product processing based on the target player vector of the target game player and the candidate player vectors of each candidate game player to obtain multiple target dot products;

[0057] The plurality of scalar products are processed through a preset fully connected network to obtain a first probability of an invitation occurring between the target game player and each candidate game player.

[0058] 103 : Determine a second probability of invitation between the target game player and at least some of the candidate game players based on the first team-forming reference information of the target game player.

[0059] In one embodiment, the step of “determining, based on the first team-forming reference information of the target game player, a second probability of invitation between the target game player and at least some of the multiple candidate game players” may include:

[0060] The target player vector of the target game player is processed through a preset fully connected network to determine a second probability of invitation between the target game player and at least some of the candidate game players.

[0061] Specifically, the probability of the target player inviting other players is calculated as follows: input the target player's embedding2 into the "whether an invitation behavior occurs" model of the target model B. The specific calculation formula is as follows: Tmp1 = Σ(xi*wi),xi∈embedding2(target) Score2_0 = sigmoid(a*tmp1+b)

[0062] Among them, Wi, a, and b are parameters of the target model B, which are automatically generated when the target model B is trained.

[0063] 104 : Determine, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players.

[0064] In a specific embodiment, the step of “determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players” may include:

[0065] The candidate player vector of each candidate game player is processed separately through a preset fully connected network to obtain a third probability of invitation between the candidate game player and other candidate game players among the multiple candidate game players.

[0066] Specifically, the third probability of an invitation between a candidate game player and other candidate game players among multiple candidate game players is calculated as follows: embedding2 of each player in candidates is input into the "whether an invitation behavior occurs" model of target model B in sequence. The specific calculation formula is as follows: Tmp1=Σ(xi*wi),xi∈embedding2(candidate_i) Score2_i=sigmoid(a*tmp1+b)

[0067] Among them, Wi, a, and b are parameters of the target model B, which are automatically generated when the target model B is trained.

[0068] Specifically, the second probability corresponding to each candidate player can be obtained based on their embedding2. For example, if the candidate players include player A, player B, and player C, and player A is used as an example, player A's invitation activity can be calculated based on their embedding2. This is a personal attribute of player A and represents the probability of player A inviting other players. Specifically, player B's embedding2 can be processed through a fully connected network to obtain the second probability.

[0069] 105. Determine an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in the invitation rate after the target game player and the candidate game player are teamed up, compared to when the target game player and the candidate game player are teamed up with other candidate game players among multiple candidate game players.

[0070] In one embodiment, the step of “determining the invitation probability gain value between the target game player and each candidate game player based on the second probability and the first probability and third probability corresponding to each candidate game player” may include:

[0071] determining a target reference probability based on the second probability and a third probability corresponding to the candidate game player;

[0072] Obtain a target difference between the first probability corresponding to the candidate game player and the target reference probability, and use the target difference as an invitation probability gain value.

[0073] For example, multiple candidate game players may include a first candidate game player, a second candidate game player, and a third candidate game player. When it is necessary to obtain the invitation probability gain value between the target game player and the first candidate game player, the target reference probability of the target game player and the first candidate game player can be obtained first. Specifically, the second probability corresponding to the target game player and the third probability of the first candidate game player are obtained, and then the target reference probability is determined based on the second probability and the third probability of the first candidate game player.

[0074] Furthermore, the step of “determining a target reference probability based on the second probability and a third probability corresponding to the candidate game player” includes:

[0075] Get the preset weight;

[0076] Performing a summation based on the second probability and the third probability corresponding to the candidate game player to obtain a target sum value;

[0077] A target product of the preset weight and the target sum value is obtained, and the target product is used as the target reference probability.

[0078] For example, multiple candidate game players may include a first candidate game player, a second candidate game player, and a third candidate game player. When it is necessary to obtain the invitation probability gain value between the target game player and the first candidate game player, the target reference probability of the target game player and the first candidate game player can be obtained first. Specifically, the preset weight 0.5 is obtained, and then the target sum value between the second probability corresponding to the target game player and the third probability of the first candidate game player is obtained. Finally, the preset weight is multiplied by the target sum value to obtain the target reference probability.

[0079] In the embodiment of the present application, the invitation probability gain value can be calculated using the following formula, which is specifically as follows: score_k = score1_k - 0.5 × (score2_0 + score2_k), k = 1, 2, ..n

[0080] Among them, score_k is the invitation probability gain value of the target game player (i.e. target player) and the candidate game player (i.e. candidate player), score1_k is the probability of invitation between the target game player and the candidate game player, score2_0 is the probability of invitation after the target game player teams up with other players in the game, and score2_k is the probability of invitation after the candidate game player teams up with other players in the game.

[0081] For example, this application includes a target player (player a) and candidate players, and the candidate players include players b, players c, and players d. Specifically, the formula for calculating the invitation rate growth of players a and b is used as an example, and the following description is given:

[0082] (1) score1_k is score1_1, where score1_1 is the probability of an invitation occurring between player a and player b.

[0083] (2) score2_0 is the probability of invitation after player a teams up with other players in the game. The "other players" here have a prerequisite: players who can match with player a. Players who can play with player a are candidates. Therefore, the other players here refer to all players in the candidates, or players in the candidates except player b (that is, player c and player d). score2_0 can also be understood as player a's invitation activity, which is a personal attribute of player a and represents the probability of player a inviting other players. Specifically, player a's embedding2 can be processed through a fully connected network to obtain the first probability.

[0084] (3) score2_1 is the probability of player B inviting another player after teaming up with them. This is also the probability of player B inviting another player after teaming up with players C or D. score2_1 is player B's invitation activity, a personal attribute of player B, representing the probability of player B inviting another player. Specifically, player B's embedding2 can be processed through a fully connected network to obtain the second probability.

[0085] (4) Give an example to illustrate the specific calculation of score_k = score1_k - 0.5 × (score2_0 + score2_k):

[0086] Assume that the probability of player a and other players inviting each other (score2_0) is 0.3, the probability of player b and other players inviting each other (score2_1) ​​is 0.5, and the probability of player a and player b inviting each other (score1_1) is 0.45.

[0087] So, since player A and other players have an invitation probability of 0.3, dividing it equally among one person is 0.3×0.5=0.15, and player A contributes an invitation rate of 0.15.

[0088] Because the invitation probability of b and other players is 0.5, divided equally among one person is 0.5×0.5=0.25, and player b contributes 0.25% of the invitation rate.

[0089] Therefore, the invitation rate of player a and player b after forming a team with other players is 0.15+0.25=0.4.

[0090] The invitation rate of player a and player b when they team up is 0.45, and the invitation rate of player a and player b when they team up with other players is 0.4. It can be concluded that after player a and player b team up, the invitation rate can be increased by 0.05, that is, the invitation probability gain value is 0.05.

[0091] 106 : Based on the invitation probability gain value, determine a target candidate game player to form a team with the target game player from a plurality of candidate game players to obtain a target team.

[0092] In an embodiment of the present application, the computer device can determine the candidate game player corresponding to the largest invitation probability gain value based on the invitation probability gain values ​​of the target game player and each candidate game player, as the target candidate game player, thereby determining the target candidate game player to team up with the target game player from multiple candidate game players to obtain the target team.

[0093] In the embodiments of the present application, a two-person or three-person team can be generated. For example, this solution can be expanded to a three-person team. The steps for expanding to three people are as follows: Calculate the invitation gain between the target player and each player in the candidates. Select the target candidate player with the highest invitation gain and the target player to form a temporary team, denoted as target2. The embedding1 of the target candidate player and the target player is averaged as the embedding1 of target2, and the embedding2 of the target candidate player and the target player is averaged as the embedding2 of target2. Calculate the invitation gain between target2 and each remaining player in the candidates, and select candidate2 with the highest invitation gain. This forms a three-person team: target, target candidate player, and candidate2.

[0094] In order to further illustrate the method for forming a team of game players provided in an embodiment of the present application, the application of the method for forming a team of game players in a specific implementation scenario will be used as an example for illustration. Please refer to Figures 3a, 3b, and 3c. The specific application scenario is described as follows.

[0095] The present application provides a player teaming system, which includes a model training module, a user vector module, and a real-time matching module. The specific structure and application of each module are as follows:

[0096] (1) The embodiment of the present application provides a model training module, which can specifically input the game player's historical matching log, historical battle log, and user portrait log to output embedding model A2 and embedding model B2. This module outputs a total of 2 embedding generators.

[0097] First, to collect data on game players, the following data can be obtained from historical matching logs, historical battle logs, and user portrait logs: User portrait information (which may vary depending on the game or application), including but not limited to: gender, age, online time, consumption level, number of chats, number of invitations to team up, etc.; Player battle data (which may vary depending on the game or application), including but not limited to: number of kills, number of kills, number of assists, time spent with teammates, time spent acting alone; Matching data: role_id1 and role_id2 match; for example, if role_id1 and role_id2 are matched together to play a game, a matching data will be generated to record the ids of these two people, i.e.<role_id1,role_id2> Combined with invitation team data, we can determine whether two players invited each other after the game ended. Invitation team data: role_id1 invites role_id2 to team up, or role_id2 invites role_id1 to team up. Invitation team data refers to invitations between the player corresponding to role_id1 and the player corresponding to role_id2 after the game ended (role_id1 invites role_id2, or role_id2 invites role_id1). Accepting invitations is optional, depending on business needs.

[0098] Next, a training dataset is constructed, which will serve as the input for the model module. Here, two training datasets need to be constructed: target model A and target model B. For each matching data entry for target model A, one piece of training data is generated, which can include data 1. This data 1 includes the user profile information corresponding to role_id1, the player match data corresponding to role_id1, the user profile information corresponding to role_id2, the player match data corresponding to role_id2, and whether an invitation occurred between role_id1 and role_id2.

[0099] b) For each matching data generated by target model B, generate 2 training data, which may specifically include data 1: user portrait information corresponding to role_id1, player battle data corresponding to role_id1, and whether an invitation behavior occurs between role_id1 and role_id2; and data 2: user portrait information corresponding to role_id2, player battle data corresponding to role_id2, and whether an invitation behavior occurs between role_id1 and role_id2.

[0100] Next, train the model using the training dataset constructed above to train target models A and B. Target model A is shown in Figure 3b: It takes the user profile information and player match data corresponding to role_id1 as input to generate the embedding for role_id1; it takes the user profile information and player match data corresponding to role_id2 as input to generate the embedding for role_id2; it performs a dot product between the embeddings of role_id1 and role_id2 and then performs a fully connected network calculation to obtain the probability of an invitation occurring between role_id1 and role_id2. Target model B is shown in Figure 3c: it takes the user profile information and player match data corresponding to either role_id1 or role_id1 as input to generate the embedding for role_id1; it performs a fully connected network calculation on the embeddings of either role_id1 or role_id2 to obtain the probability of an invitation occurring between either role_id1 or role_id2 and another player. After training, target model A can estimate the probability of an invitation between two players given information about two players. After training, target model B can estimate the probability of an invitation between one player and another player given information about one player. Embedding model A2, a submodel of target model A, can be used as the output of this module, and embedding model B2, a submodel of target model B, can be used as the output of this module.

[0101] (2) The embodiment of the present application provides a user vector module, which obtains the corresponding user portrait information and player battle data based on the player role_id, and inputs these data into the embedding model A2 and the embedding model B2 respectively to obtain embedding1 and embedding2, and uses embedding1 and embedding2 as the output of this module. Specifically, the output of the embedding model A2 and the embedding model B2 is the player vector, and the target model A contains the embedding model A2 and the probability of invitation calculated based on the player vector, that is, the embedding model A2 is the intermediate result of the target model A. The embedding model is a tool whose function is to calculate the user vector based on the role_id.

[0102] (3) The embodiment of the present application also provides a real-time matching module, which can first obtain a user vector set. When the user clicks the match button, the real-time matching module obtains the user role_id, inputs the role_id into the user vector module, and obtains embedding1 and embedding2.<role_id,embedding1,embedding2> Then, the obtained player triple is added to the player pool.<role_id,embedding1,embedding2> Put it into the player pool and record the waiting time wait_ts of each player in the player pool. The player pool is recorded as List[<role_id,embedding1,embedding2,wait_ts> ].

[0103] Next, we select the player with the longest waiting time from the player pool as the target player, denoted as target. From the player pool, we select candidate players (e.g., players with similar scores to the target, or players with different professions) according to the following rules, denoted as candidates, list[candidate_1,candidate_2,...candidate_n]. Finally, we calculate the user vector of each target and the user vector of each candidate, and select the best player from the candidate pool to form a team with the target, denoted as team.

[0104] Specifically, first calculate the probability of an invitation between the target player and each player in the candidate list, denoted as [score1_1, score1_2, ... score1_n]. Specifically, perform a dot product between target's embedding1 and the embedding1 of candidate_1, candidate_2, ... candidate_n, respectively, and then input these into a fully connected network to obtain the invitation probability. Next, calculate the probability of an invitation between the target player and other players, denoted as score2_0. Specifically, process target's embedding2 through the fully connected network. Next, calculate the probability of an invitation between each player in the candidate list, denoted as [score2_1, score2_2, ... score2_n]. Specifically, process each player's embedding2 in the candidate list separately through the fully connected network. Finally, calculate the gain value of an invitation between the target player and each player in the candidate list. Specifically, use the following formula to calculate score_k=score1_k-0.5×(score2_0+score2_k), k=1,2,..n. The meaning of this formula, score1_k: represents the probability of invitation when two players are matched together, 0.5×(score2_0+score2_k): represents the probability of invitation when these two players are matched with other players. Score_k: represents how much the invitation rate will increase by directly matching these two players together compared to matching them with other players. Finally, select the candidate and target with the largest invitation gain to form a team. Specifically, select the optimal k to maximize the score_k value. Then<targetr,candidate_k> Then form a team and return.

[0105] It should be noted that the model mentioned in the embodiment of the present application is an "Embedding model", that is, an embedding model, which refers to a model that maps multidimensional, multimodal data to a low-dimensional space. They can capture the intrinsic connections between different input data (for example, the embedding model of this solution can capture the probability of invitations between different players). The embedding model is not limited to a specific model, as long as it can achieve this function. The input of the embedding model of this solution is: data obtained from game-related logs (historical matching logs, historical battle logs, user portrait logs) that can represent player characteristics, including discrete features (such as gender, age group), continuous features (such as age, online time), and sequence features (such as the win-loss sequence composed of the wins and losses of the last few games).

[0106] In summary, the game player teaming method provided in the embodiment of the present application can determine the target game player from the pool of players to be matched, obtain the player information and first teaming reference information of the target game player, and screen out multiple candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second teaming reference information; then, based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player, determine the first probability of invitation between the target game player and each candidate game player; then, based on the first teaming reference information of the target game player, determine the second probability of invitation between the target game player and at least some of the multiple candidate game players; thereafter, based on The second team reference information of each candidate game player is used to determine a third probability of an invitation occurring between the candidate game player and other candidate game players among the multiple candidate game players; then, based on the second probability, and the first probability and the third probability corresponding to each candidate game player, an invitation probability gain value between the target game player and each candidate game player is determined, wherein the invitation probability gain value is used to represent: after the target game player and the candidate game player are teamed up, the invitation rate increases compared to when the target game player and the candidate game player are separately teamed up with other candidate game players among the multiple candidate game players; finally, based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from the multiple candidate game players to obtain a target team. The embodiment of the present application can use a player matching system to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player who teams up with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. It can make high and low activity players match with low activity players, and use high activity players to drive low activity players, thereby improving the gaming experience of all players; and it can also increase the probability of players inviting each other after the game is over, effectively saving the computer computing resources required for player matching, and improving the efficiency of player matching and teaming.

[0107] In order to better implement the above method, the embodiment of the present application can also provide a game player team-forming device, which can be specifically integrated into a computer device, for example, a computer device such as a terminal.

[0108] Please refer to FIG4 , which is a schematic diagram of the structure of a device for forming a team of game players provided in an embodiment of the present application. The device includes:

[0109] The processing unit 201 is configured to determine a target game player from a pool of players to be matched, obtain player information of the target game player and first team reference information, and screen a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information;

[0110] A first determining unit 202 is configured to determine a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player;

[0111] The second determining unit 203 is configured to determine a second probability of invitation between the target game player and at least some of the candidate game players based on the first team-forming reference information of the target game player;

[0112] The third determining unit 204 is configured to determine, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players;

[0113] The fourth determining unit 205 is configured to determine an invitation probability gain value between the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to when the target game player and the candidate game player are teamed up with other candidate game players from the plurality of candidate game players;

[0114] The fifth determining unit 206 is configured to determine a target candidate game player to form a team with the target game player from a plurality of candidate game players based on the invitation probability gain value, to obtain a target team.

[0115] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0116] determining a target reference probability based on the second probability and a third probability corresponding to the candidate game player;

[0117] Obtain a target difference between the first probability corresponding to the candidate game player and the target reference probability, and use the target difference as an invitation probability gain value.

[0118] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0119] Get the preset weight;

[0120] Performing a summation based on the second probability and the third probability corresponding to the candidate game player to obtain a target sum value;

[0121] A target product of the preset weight and the target sum value is obtained, and the target product is used as the target reference probability.

[0122] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0123] The first team reference information is the target player vector of the target game player, and the target player vector is determined based on the player portrait information and game data of the target game player; the second team reference information is the candidate player vector of the candidate game player, and the candidate player vector is determined based on the player portrait information and game data of the candidate game player.

[0124] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0125] Performing dot product processing based on the target player vector of the target game player and the candidate player vectors of each candidate game player to obtain multiple target dot products;

[0126] The plurality of scalar products are processed through a preset fully connected network to obtain a first probability of an invitation occurring between the target game player and each candidate game player.

[0127] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0128] The target player vector of the target game player is processed through a preset fully connected network to determine a second probability of invitation between the target game player and at least some of the candidate game players.

[0129] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0130] The candidate player vector of each candidate game player is processed separately through a preset fully connected network to obtain a third probability of invitation between the candidate game player and other candidate game players among the multiple candidate game players.

[0131] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0132] Get the current matching time of each player in the player pool to be matched;

[0133] Based on the current matching time of each game player, the game player with the longest current matching time is selected from the pool of players to be matched as the target game player.

[0134] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0135] Get the player level and online time of each player in the player pool to be matched;

[0136] Based on the player level and game online time of each game player, the target game player is screened out from the pool of players to be matched.

[0137] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0138] A plurality of candidate game players are screened out from the pool of players to be matched based on the game character preferences of the target game player.

[0139] In some embodiments, the team-forming device of the game player includes a processing subunit configured to execute:

[0140] Based on the game match score information of the target game player, a plurality of candidate game players are screened out from the pool of players to be matched.

[0141] The embodiment of the present application discloses a device for forming a team of game players, which determines a target game player from a pool of players to be matched through a processing unit 201, obtains player information and first team reference information of the target game player, and screens out a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; a first determining unit 202 determines a first probability of an invitation occurring between the target game player and each candidate game player based on the first team reference information of the target game player and the second team reference information of each candidate game player; a second determining unit 203 determines a second probability of an invitation occurring between the target game player and at least some of the plurality of candidate game players based on the first team reference information of the target game player; a third determining unit 204 determines a second probability of an invitation occurring between the target game player and at least some of the plurality of candidate game players; 04 Based on the second team reference information of each candidate game player, determine the third probability of invitation between the candidate game player and other candidate game players among the multiple candidate game players; the fourth determination unit 205 determines the invitation probability gain value of the target game player and each candidate game player based on the second probability and the first probability and third probability corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: after the target game player and the candidate game player are teamed up, the invitation rate increases compared to when the target game player and the candidate game player are teamed up with other candidate game players among the multiple candidate game players respectively; the fifth determination unit 206 determines the target candidate game player to be teamed up with the target game player from the multiple candidate game players based on the invitation probability gain value to obtain the target team. The embodiment of the present application can use a player matching system to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player who teams up with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. It can make high and low activity players match with low activity players, and use high activity players to drive low activity players, thereby improving the gaming experience of all players; and it can also increase the probability of players inviting each other after the game is over, effectively saving the computer computing resources required for player matching, and improving the efficiency of player matching and teaming.

[0142] Accordingly, an embodiment of the present application also provides a computer device, which may be a terminal or a server, and the terminal may be a terminal device such as a smart phone, a tablet computer, a laptop computer, a touch screen, a game console, a personal computer (PC, Personal Computer), a personal digital assistant (Personal Digital Assistant, PDA). As shown in Figure 5, Figure 5 is a structural diagram of a computer device provided in an embodiment of the present application. The computer device 300 includes a processor 301 having one or more processing cores, a memory 302 having one or more computer-readable storage media, and a computer program stored in the memory 302 and operable on the processor. The processor 301 is electrically connected to the memory 302. Those skilled in the art will appreciate that the computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or arrange components differently.

[0143] The processor 301 is the control center of the computer device 300. It uses various interfaces and lines to connect the various parts of the entire computer device 300. By running or loading software programs and / or modules stored in the memory 302 and calling data stored in the memory 302, it executes various functions of the computer device 300 and processes data, thereby monitoring the computer device 300 as a whole.

[0144] In the embodiment of the present application, the processor 301 in the computer device 300 loads instructions corresponding to one or more application processes into the memory 302 according to the following steps, and the processor 301 runs the application stored in the memory 302 to implement various functions:

[0145] Determining a target game player from the pool of players to be matched, obtaining player information and first team reference information of the target game player, and screening a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information;

[0146] Determining a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player;

[0147] determining, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players;

[0148] determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players;

[0149] determining an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to teaming up the target game player and the candidate game player with other candidate game players from the plurality of candidate game players;

[0150] Based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from a plurality of candidate game players to obtain a target team.

[0151] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0152] Optionally, as shown in FIG5 , the computer device 300 further includes: a touch screen display 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the touch screen display 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power supply 307, respectively. Those skilled in the art will appreciate that the computer device structure shown in FIG5 does not limit the computer device, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0153] The touch display screen 303 can be used for displaying a graphical user interface and receiving an operation instruction generated by the user acting on the graphical user interface. The touch display screen 303 may include a display panel and a touch panel. Among them, the display panel may be used for displaying information input by the user or information provided to the user and various graphical user interfaces of a computer device, and these graphical user interfaces may be composed of graphics, text, icons, videos and any combination thereof. Optionally, a liquid crystal display (LCD), an organic light emitting diode (OLED) or the like may be used to configure the display panel. The touch panel may be used to collect a touch operation performed by the user on or near it (such as an operation performed by a user using any suitable object or accessory such as a finger, a stylus or the like on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 301, and can receive the command sent by the processor 301 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 301 to determine the type of touch event, and then the processor 301 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 303 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 303 can also be used as part of the input unit 306 to realize the input function.

[0154] In the embodiment of the present application, the processor 301 executes the application to generate a graphical interface on the touch screen 303. The touch screen 303 is used to present the graphical interface and receive operation instructions generated by the user acting on the graphical interface.

[0155] The RF circuit 304 may be used to transmit and receive RF signals, thereby establishing wireless communication with a network device or other computer device through wireless communication, and transmitting and receiving signals between the network device or other computer device.

[0156] Audio circuit 305 can be used to provide an audio interface between the user and the computer device through a speaker and microphone. Audio circuit 305 can convert received audio data into electrical signals and transmit them to the speaker, which then converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuit 305 and converted into audio data. The audio data is then output to processor 301 for processing, then transmitted via RF circuit 304 to, for example, another computer device, or to memory 302 for further processing. Audio circuit 305 may also include an earphone jack to allow communication between external headphones and the computer device.

[0157] The input unit 306 may be configured to receive input digital, character information, or user feature information (such as fingerprint, iris, or facial information), and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0158] Power supply 307 is used to supply power to various components of computer device 300. Optionally, power supply 307 can be logically connected to processor 301 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. Power supply 307 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0159] Although not shown in FIG. 5 , the computer device 300 may further include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0160] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0161] As can be seen from the above, the computer device provided by this embodiment determines a target game player from a pool of players to be matched, obtains player information and first team reference information of the target game player, and screens out multiple candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; then, based on the first team reference information of the target game player and the second team reference information of each candidate game player, determines a first probability of invitation between the target game player and each candidate game player; then, based on the first team reference information of the target game player, determines a second probability of invitation between the target game player and at least some of the multiple candidate game players; thereafter, based on the first team reference information of each candidate game player, determines a second probability of invitation between the target game player and at least some of the multiple candidate game players; The method further comprises: determining a third probability of an invitation occurring between the candidate game player and other candidate game players among the multiple candidate game players based on the second team formation reference information of the candidate game player; then, determining an invitation probability gain value between the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in the invitation rate after the target game player and the candidate game player are teamed up compared to teaming up the target game player and the candidate game player with other candidate game players among the multiple candidate game players respectively; finally, determining a target candidate game player to team up with the target game player from the multiple candidate game players based on the invitation probability gain value, and obtaining a target team. The embodiment of the present application can use a player matching system to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player who teams up with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. It can make high and low activity players match with low activity players, and drive low activity players through high activity players, thereby improving the gaming experience of all players; and it can also increase the probability of players inviting each other after the game is over, effectively saving computer computing resources required for player matching, improving the accuracy of player matching and teaming results, and improving the efficiency of player matching and teaming.

[0162] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0163] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of computer programs, which can be loaded by a processor to execute the steps of any of the game player team formation methods provided in the embodiments of the present application. For example, the computer program can execute the following steps:

[0164] Determining a target game player from the pool of players to be matched, obtaining player information and first team reference information of the target game player, and screening a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information;

[0165] Determining a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player;

[0166] determining, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players;

[0167] determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players;

[0168] determining an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to teaming up the target game player and the candidate game player with other candidate game players from the plurality of candidate game players;

[0169] Based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from a plurality of candidate game players to obtain a target team.

[0170] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0171] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0172] Due to the computer program stored in the storage medium, the steps of any one of the game player team formation methods provided in the embodiments of the present application can be executed, by determining a target game player from a pool of players to be matched, obtaining player information and first team formation reference information of the target game player, and screening multiple candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team formation reference information; then, based on the first team formation reference information of the target game player and the second team formation reference information of each candidate game player, determining a first probability of an invitation occurring between the target game player and each candidate game player; then, based on the first team formation reference information of the target game player, determining a probability of an invitation occurring between the target game player and at least some of the multiple candidate game players. Then, based on the second teaming reference information of each candidate game player, determine the third probability of invitation between the candidate game player and other candidate game players among the multiple candidate game players; then, based on the second probability, and the first probability and the third probability corresponding to each candidate game player, determine the invitation probability gain value of the target game player and each candidate game player, wherein the invitation probability gain value is used to represent: after the target game player and the candidate game player are teamed up, the invitation rate increases compared to when the target game player and the candidate game player are respectively teamed up with other candidate game players among the multiple candidate game players; finally, based on the invitation probability gain value, determine the target candidate game player who teams up with the target game player from the multiple candidate game players to obtain the target team. The embodiment of the present application can use a player matching system to calculate the invitation probability gain value of the target game player and each candidate game player based on the team reference information of each player, and then determine the target candidate game player who teams up with the target game player from multiple candidate game players based on the invitation probability gain value, generate a target team, and complete the player matching and teaming operation. It can make high and low activity players match with low activity players, and use high activity players to drive low activity players, thereby improving the gaming experience of all players; and it can also increase the probability of players inviting each other after the game is over, effectively saving the computer computing resources required for player matching, and improving the efficiency of player matching and teaming.

[0173] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0174] The above is a detailed introduction to a method, device, computer equipment and storage medium for forming a team of game players provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the technical solutions and core ideas of the present application. Ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for forming a team of game players, comprising: Determining a target game player from the pool of players to be matched, obtaining player information and first team reference information of the target game player, and screening a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; Determining a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player; determining, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players; determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players; determining an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to teaming up the target game player and the candidate game player with other candidate game players from the plurality of candidate game players; Based on the invitation probability gain value, a target candidate game player who teams up with the target game player is determined from a plurality of candidate game players to obtain a target team.

2. The method for forming a team of game players according to claim 1, wherein: The determining, based on the second probability and the first probability and the third probability corresponding to each candidate game player, the invitation probability gain value of the target game player and each candidate game player includes: determining a target reference probability based on the second probability and a third probability corresponding to the candidate game player; A target difference between the first probability and the target reference probability is obtained, and the target difference is used as an invitation probability gain value.

3. The method for forming a team of game players according to claim 2, wherein: The determining of a target reference probability based on the second probability and a third probability corresponding to the candidate game player includes: Get the preset weight; Performing a summation based on the second probability and the third probability corresponding to the candidate game player to obtain a target sum value; A target product of the preset weight and the target sum value is obtained, and the target product is used as the target reference probability.

4. The method for forming a team of game players according to claim 1, wherein: The first team reference information is the target player vector of the target game player, and the target player vector is determined based on the player portrait information and game data of the target game player; the second team reference information is the candidate player vector of the candidate game player, and the candidate player vector is determined based on the player portrait information and game data of the candidate game player.

5. The method for forming a team of game players according to claim 4, wherein: The determining, based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player, a first probability of an invitation occurring between the target game player and each candidate game player includes: Performing dot product processing based on the target player vector of the target game player and the candidate player vectors of each candidate game player to obtain multiple target dot products; The plurality of scalar products are processed through a preset fully connected network to obtain a first probability of an invitation occurring between the target game player and each candidate game player.

6. The method for forming a team of game players according to claim 4, wherein: The determining, based on the first teaming reference information of the target game player, a second probability of invitation between the target game player and at least some of the candidate game players includes: The target player vector of the target game player is processed through a preset fully connected network to determine a second probability of invitation between the target game player and at least some of the candidate game players.

7. The method for forming a team of game players according to claim 4, wherein: The determining, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players includes: The candidate player vector of each candidate game player is processed separately through a preset fully connected network to obtain a third probability of invitation between the candidate game player and other candidate game players among the multiple candidate game players.

8. The method for forming a team of game players according to claim 1, wherein: Determining the target game player from the pool of players to be matched includes: Get the current matching time of each player in the player pool to be matched; Based on the current matching time of each game player, the game player with the longest current matching time is selected from the pool of players to be matched as the target game player.

9. The method for forming a team of game players according to claim 1, wherein: Identify target game players from the pool of players to be matched, including: Get the player level and online time of each player in the player pool to be matched; Based on the player level and online game time of each game player, the target game player is screened out from the pool of players to be matched.

10. The method for forming a team of game players according to claim 1, wherein: The step of screening a plurality of candidate game players from the pool of players to be matched based on the player information includes: A plurality of candidate game players are screened out from the pool of players to be matched based on the game character preference of the target game player.

11. The method for forming a team of game players according to claim 1, wherein: The step of screening a plurality of candidate game players from the pool of players to be matched based on the player information includes: Based on the game match score information of the target game player, a plurality of candidate game players are screened out from the pool of players to be matched.

12. A device for forming a team of game players, comprising: a processing unit configured to determine a target game player from a pool of players to be matched, obtain player information of the target game player and first team reference information, and screen a plurality of candidate game players from the pool of players to be matched based on the player information, wherein each candidate game player is associated with corresponding second team reference information; a first determining unit configured to determine a first probability of an invitation occurring between the target game player and each candidate game player based on the first teaming reference information of the target game player and the second teaming reference information of each candidate game player; a second determining unit configured to determine, based on the first team-forming reference information of the target game player, a second probability of invitation occurring between the target game player and at least some of the candidate game players; a third determining unit configured to determine, based on the second teaming reference information of each candidate game player, a third probability of an invitation occurring between the candidate game player and other candidate game players among the plurality of candidate game players; a fourth determining unit configured to determine an invitation probability gain value for the target game player and each candidate game player based on the second probability and the first and third probabilities corresponding to each candidate game player, wherein the invitation probability gain value is used to represent: an increase in invitation rate after the target game player and the candidate game player are teamed up compared to when the target game player and the candidate game player are teamed up with other candidate game players among the plurality of candidate game players; A fifth determining unit is configured to determine, based on the invitation probability gain value, a target candidate game player to be teamed with the target game player from a plurality of candidate game players to obtain a target team.

13. A computer device comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the method for forming a team of game players according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for forming a team of game players according to any one of claims 1 to 11.

Images