A method, device, electronic device and storage medium for recommending player nicknames

Abstract

The present application provides a method, apparatus, electronic device, and storage medium for recommending player nicknames. In response to a nickname setting request of a target player, at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs are obtained; according to the number of target historical nicknames under each nickname style, the recommended probability of each nickname style being recommended is determined; according to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, multiple nicknames to be recommended are screened from the preset nickname dataset; at least one target nickname among the multiple nicknames to be recommended is displayed to the target player. In this way, by analyzing the historical nicknames of the target player, the recommended probability of each nickname style is determined, and nicknames are recommended to the target player in a targeted manner according to the recommended probabilities of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

Description

Technical Field

[0001] The present application relates to the field of game technologies, and in particular, to a method, device, electronic device, and storage medium for recommending player nicknames. Background Art

[0002] When game players download a game or experience a new game, they usually need to customize and enter a nickname for the selected character during the registration phase, or during the game process, players can use the obtained items to change their nicknames. Whether it is the registration phase or the player name change phase, players need to choose a suitable nickname for their game characters.

[0003] At present, generally, there are two ways for players to define the nicknames of their characters. One is that players themselves enter the desired nicknames, and the other is that the game system recommends a series of nicknames to players, and players choose the nicknames of their characters according to their preferences. For the way of system-recommended nicknames, the system will randomly recommend different nicknames according to the requirements of the game and present them to players, which will result in players needing to go through multiple rounds of selection to obtain the nicknames they like, and the recommendation accuracy is relatively low. Summary of the Invention

[0004] In view of this, the purpose of the present application is to provide a method, device, electronic device, and storage medium for recommending player nicknames, which can analyze the historical nicknames of the target player, determine the preferences of the target player for different nickname styles, and then determine the recommendation probability of each nickname style, so as to recommend nicknames to the target player in a targeted manner according to the recommendation probabilities of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending player nicknames, and the recommendation method includes:

[0006] In response to a nickname setting request of a target player, obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs;

[0007] According to the number of target historical nicknames included in each nickname style, determine the nickname proportion of each nickname style in the target historical nicknames, and according to the nickname proportion of each nickname style, determine the recommendation probability that each nickname style is recommended for the target player;

[0008] According to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, screen multiple nicknames to be recommended from the preset nickname dataset;

[0009] Determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player, so as to recommend the target nickname for the target player to use.

[0010] In a possible implementation manner, the screening of multiple nicknames to be recommended from the preset nickname dataset according to the recommendation probability of each alternative nickname belonging to the nickname style in the preset nickname dataset and the semantic similarity between each alternative nickname and the corresponding target historical nickname includes:

[0011] For each nickname style, screen out a target number of alternative recommended nicknames under this nickname style according to the semantic similarity between each alternative nickname under this nickname style and the target historical nickname under this nickname style; wherein, the target number is determined based on the recommendation probability of this nickname style, and the higher the recommendation probability, the larger the corresponding target number;

[0012] Determine the at least one alternative recommended nickname under each screened nickname style as the nickname to be recommended.

[0013] In a possible implementation manner, the screening of multiple nicknames to be recommended from the preset nickname dataset according to the recommendation probability of each alternative nickname belonging to the nickname style in the preset nickname dataset and the semantic similarity between each alternative nickname and the corresponding target historical nickname includes:

[0014] Determine the nickname styles with recommendation probabilities greater than the preset recommendation probability among the multiple nickname styles as the target nickname styles;

[0015] For each target nickname style, screen out a target number of alternative recommended nicknames under this target nickname style according to the semantic similarity between each alternative nickname under this target nickname style and the target historical nickname under this target nickname style; wherein, the target number is determined based on the recommendation probability of this nickname style, and the higher the recommendation probability, the larger the corresponding target number;

[0016] Determine the alternative recommended nicknames under each screened target nickname style as the nicknames to be recommended.

[0017] In a possible implementation manner, before obtaining at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs, the recommendation method further includes:

[0018] In response to the nickname setting request of the target player, based on the identity identification information of the target player, obtain at least one historical nickname used by the target player and the nickname style to which each historical nickname belongs;

[0019] Filter out historical nicknames that match the target game style of the target game the target player is operating on and the target player's nickname setting preferences for the target game style from the at least one historical nickname, to obtain at least one target historical nickname.

[0020] In a possible implementation, the preset nickname dataset is at least one nickname that meets the nickname setting conditions screened from a preset nickname database according to the nickname setting conditions of the target game the target player is operating on, and the preset nickname dataset is composed of these nicknames;

[0021] The nickname setting conditions include at least one of the following:

[0022] The number of characters in the nickname is less than the preset number of characters, the nickname does not include sensitive words, and the nickname does not contain special characters.

[0023] In a possible implementation, the preset nickname database is a database updated based on an initial nickname database containing multiple initial designed nicknames. The preset nickname database is determined through the following steps:

[0024] Obtain multiple initial designed nicknames and the nickname style to which each initial designed nickname belongs;

[0025] For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname;

[0026] Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined to obtain multiple combined nicknames;

[0027] Update the initial nickname database according to the determined combined nicknames of the nickname style to obtain the preset nickname database; wherein, the nickname style to which the combined nickname belongs is determined by classification based on a pre-trained nickname classification label model, and each combined nickname belongs to at least one nickname style.

[0028] In a possible implementation, after responding to the nickname setting request of the target player, the recommendation method further includes:

[0029] If the target historical nickname used by the target player cannot be obtained, filter out at least one nickname to be recommended from the preset nickname dataset according to the target game style of the target game the target player is operating on and the nickname setting conditions of the target game;

[0030] Show at least one nickname to be recommended to the target player so that the target player can select a target nickname for use.

[0031] In a possible implementation, the recommendation method further includes:

[0032] In response to the display of the nickname to be recommended meeting the display end condition, end the display of the nickname to be recommended;

[0033] The display of the nickname to be recommended meeting the display end condition includes at least one of the following:

[0034] The target player selects any one of the nicknames to be recommended, and all the multiple nicknames to be recommended are displayed.

[0035] In a possible implementation, the recommendation method further includes:

[0036] Delete the target nickname selected by the target player from the preset nickname dataset and update the preset nickname database.

[0037] In a possible implementation, the nickname style is used to characterize the name semantic category and / or the affiliated domain category of the nickname.

[0038] In a second aspect, an embodiment of the present application further provides a recommendation device for player nicknames, and the recommendation device includes:

[0039] A nickname acquisition module, configured to, in response to a nickname setting request of a target player, acquire at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs;

[0040] A probability determination module, configured to determine the nickname proportion of each nickname style in the target historical nicknames according to the number of target historical nicknames included in each nickname style, and determine the recommended probability of each nickname style being recommended for the target player according to the nickname proportion of each nickname style;

[0041] A nickname screening module, configured to screen multiple nicknames to be recommended from the preset nickname dataset according to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs and the semantic similarity between each alternative nickname and the corresponding target historical nickname;

[0042] A nickname display module, configured to determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player to recommend the target nickname for the target player to use.

[0043] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the method for recommending a player nickname as described in any one of the first aspects.

[0044] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the method for recommending a player nickname as described in any one of the first aspects.

[0045] A method, device, electronic device, and storage medium for recommending a player nickname provided by an embodiment of the present application. In response to a nickname setting request of a target player, at least one target historical nickname used by the target player is obtained, and the nickname style to which each target historical nickname belongs is determined; according to the number of target historical nicknames included in each nickname style, the proportion of each nickname style in the target historical nicknames is determined, and then the recommendation probability of each nickname style for the target player is determined; according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the target historical nickname, a plurality of nicknames to be recommended are determined; at least one target nickname is determined from the plurality of nicknames to be recommended and displayed to the target player, so as to recommend the target nickname for the target player to use. In the embodiment of the present application, by analyzing the historical nicknames of the target player, the preference of the target player for different nickname styles is determined, and then the recommendation probability of each nickname style is determined, so as to recommend nicknames to the target player in a targeted manner according to the recommendation probability of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

[0046] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. Description of the Drawings

[0047] To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a flowchart of a method for recommending a player nickname provided by an embodiment of the present application;

[0049] Figure 2Flowchart of another method for recommending player nicknames provided by the embodiments of the present application;

[0050] Figure 3 One of the structural schematic diagrams of a device for recommending player nicknames provided by the embodiments of the present application;

[0051] Figure 4 Another structural schematic diagram of a device for recommending player nicknames provided by the embodiments of the present application;

[0052] Figure 5 Another structural schematic diagram of a device for recommending player nicknames provided by the embodiments of the present application;

[0053] Figure 6 Structural schematic diagram of an electronic device provided by the embodiments of the present application. Detailed implementation manners

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Usually, the components of the embodiments of the present application described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative efforts belongs to the scope of protection of the present application.

[0055] First, the applicable application scenarios of the present application are introduced. The present application can be applied to the game technology field. When starting a game, a player needs to register a nickname for their character to distinguish their character from those of other players; at the same time, as the game progresses, the player can also consume certain items in the game to change the nickname of their character.

[0056] It has been found through research that at the present stage, generally, there are two ways to enable players to define the nicknames of their characters. One is that the player enters the desired nickname by themselves, and the other is that the game system recommends a series of nicknames to the player, and the player selects the nickname of their character according to their own preferences. For the way of system-recommended nicknames, the system will randomly recommend different nicknames according to the requirements of the game and present them to the player, which will cause the player to need to go through multiple rounds of selection to obtain the nickname they like, and the recommendation accuracy is relatively low.

[0057] Based on this, the embodiments of the present application provide a method for recommending player nicknames, so as to recommend nicknames to target players in a targeted manner and improve the accuracy of recommending nicknames to players.

[0058] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for recommending player nicknames provided by the embodiments of the present application. As Figure 1 shown in

[0059] S101. In response to a nickname setting request of a target player, obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs.

[0060] S102. According to the number of target historical nicknames included in each nickname style, determine the nickname proportion of each nickname style in the target historical nicknames, and according to the nickname proportion of each nickname style, determine the recommended probability of each nickname style being recommended for the target player.

[0061] S103. According to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, screen multiple nicknames to be recommended from the preset nickname dataset.

[0062] S104. Determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player, so as to recommend the target nickname for the target player to use.

[0063] The method for recommending player nicknames provided by the embodiments of the present application can analyze the historical nicknames of the target player, determine the preferences of the target player for different nickname styles, and then determine the recommended probability of each nickname style, so as to recommend nicknames to the target player in a targeted manner according to the recommended probability of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

[0064] The following is an explanation of the exemplary steps of the embodiments of the present application:

[0065] S101. In response to a nickname setting request of a target player, obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs.

[0066] In the embodiments of the present application, in response to the nickname setting request of the target player during the game setting process, according to the identity identification information of the target player, obtain at least one target historical nickname that the target player has used, and at the same time determine the nickname style to which each target historical nickname belongs.

[0067] Among them, the nickname of the target player is the name given by the target player to his or her character in the game. It can generally be modified according to the target player's preferences, and will also be subject to relevant conditions of the game, such as word limit, special characters, sensitive words, duplicate names, etc.

[0068] In one possible implementation, the nickname style is used to characterize the name semantic category and / or the field category of the nickname. For example, according to the name semantic category, it can be divided into categories such as two-dimensional, ancient style, funny, cute, etc.; according to the field category, it can be divided into categories such as basketball, football, martial arts, military, etc.

[0069] In one possible implementation, the target player's nickname setting request may be a setting request when the player names his or her character in the game when registering at the beginning of a new game, or it may be a setting request when the target player obtains a name-changing item that can be used to change the nickname during the game process and uses the name-changing item to change his or her character in the game.

[0070] In a possible implementation, obtaining the target historical nickname that the target player has used is obtained through the target player's identity information (mobile phone number, email address, etc.) from games that the target player has played.

[0071] Furthermore, after obtaining at least one target historical nickname that the target player has used, it is necessary to determine the nickname style to which each target historical nickname belongs. In an embodiment of the present application, the nickname style to which each target historical nickname belongs can be determined by a pre-trained nickname classification label model.

[0072] In one possible implementation, the pre-trained nickname classification label model is a multi-label model. After classification and determination by the nickname classification label model, each target historical nickname may belong to one nickname style or multiple nickname styles. That is, the nickname style of each target historical nickname determined by the nickname classification label model is not necessarily unique, and may belong to multiple different nickname styles, which helps to improve the accuracy of style determination of each target historical nickname.

[0073] S102. Determine the nickname ratio of each nickname style in the target historical nicknames based on the number of target historical nicknames included in each nickname style, and determine the recommendation probability of each nickname style being recommended to the target player based on the nickname ratio of each nickname style.

[0074] In an embodiment of the present application, after determining the nickname style to which each target historical nickname belongs, for each nickname style, the number of target historical nicknames included in the nickname style is determined, and combined with the total number of target historical nicknames that the target player has ever used, the nickname ratio of the nickname style in the target historical nicknames is determined, and the determined nickname ratio is determined as the recommendation probability of the nickname style for the target player.

[0075] For example, the target player has used 5 target historical nicknames. After classification by the pre-trained nickname classification label model, it is determined that among the 5 target historical nicknames, 1 nickname style belongs to the two-dimensional style, 2 nickname styles belong to the aesthetic style and the ancient style, 1 nickname style belongs to the ancient style, and 1 nickname style belongs to the cute style. Then for the target player, the recommendation probability of the two-dimensional style is 1 / 5, the recommendation probability of the aesthetic style is 2 / 5, the recommendation probability of the ancient style is 3 / 5, and the recommendation probability of the cute style is 1 / 5.

[0076] S103 , screening multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname.

[0077] In an embodiment of the present application, based on the determined recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname data set, and the semantic similarity between each candidate nickname and the corresponding target historical nickname, a plurality of nicknames to be recommended that match the target player's selection style are screened from the preset nickname data set.

[0078] In a possible implementation, the preset nickname data set is composed of at least one nickname that meets the nickname setting condition and is screened from a preset nickname database based on the nickname setting condition of the target game being played by the target player, and the preset nickname data set is formed;

[0079] The nickname setting condition includes at least one of the following:

[0080] The nickname contains fewer than the preset number of characters, does not contain sensitive words, and does not contain special characters.

[0081] Specifically, when setting a nickname, it is necessary to comply with the target game's nickname setting requirements, such as the length of the nickname (which can be limited by the number of characters contained in the nickname); the nickname cannot contain sensitive words. In an embodiment of the present application, the definition of sensitive words can be words divided according to the game setting standards, or some words specified according to relevant setting conditions; some games also stipulate that special characters (such as some currency symbols, etc.) cannot be included in the nickname; it is also possible to pre-screen nicknames in the preset nickname database that have too high a duplication with nicknames already existing in the target game during setting to avoid the occurrence of duplicate names in the game.

[0082] In one possible implementation, the preset nickname data set is a subset of a preset nickname database that includes all alternative nicknames that can be recommended. Since the nickname setting conditions may be different for different target games, in order to reduce the amount of data processing, before performing the nickname recommendation step, the nickname setting conditions in the game currently being operated by the target player can be used to filter out alternative nicknames that meet the nickname setting conditions of this game from the nickname database to form a preset nickname data set, and the subsequent nickname recommendation process is performed based on the preset nickname data set.

[0083] In an embodiment of the present application, for the setting of a preset nickname database, in order to ensure that the nickname data covers a larger number of nicknames, it can be considered to include as many nicknames as possible in the setting of the preset nickname database, that is, the preset nickname database is a database updated (expanded) based on the initial nickname database containing multiple initial design nicknames, and a larger number of nicknames can be included in the preset nickname database.

[0084] Specifically, the preset nickname database is determined by the following steps:

[0085] a1: Get multiple initial design nicknames and the nickname style to which each initial design nickname belongs.

[0086] In the embodiment of the present application, multiple initially designed nicknames are obtained. These initially designed nicknames can be nicknames designed by the designer based on the game type or game requirements, or they can be historical nicknames obtained from different players. Similarly, the nickname style to which each initial nickname belongs is also determined by classification using a pre-trained nickname classification label model.

[0087] In a possible implementation, nicknames of various styles may be predefined, and nickname datasets with styles may be labeled and constructed, and a multi-label model may be trained through supervised learning.

[0088] Specifically:

[0089] Step 1: Preset multiple styles for the nickname, such as second dimension, ancient style, funny, cute, military, xianxia, aesthetic, etc. Through one-hot encoding, map the style into a one-dimensional vector. For example, the style of "the bright starry sky" is aesthetic, which can be converted into [0,0,0,0,0,0,1], that is, the position corresponding to the style is 1, and the rest are 0. At the same time, it is also allowed that a nickname has multiple styles. For example, the styles of "Half City Mist and Rain, A Tribute to the Clear City" are ancient style and aesthetic, which can be converted into [0,1,0,0,0,0,1].

[0090] Step 2: Convert each nickname in the dataset into a word vector through discrete representation, distributed representation, etc., and convert it into an N*M matrix representation.

[0091] Step 3: Use a multi-layer neural network to train the dataset converted into vectors to obtain a multi-label model for nickname styles.

[0092] a2: For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname.

[0093] In the embodiment of the present application, for each obtained initial designed nickname, according to the part of speech of each word that makes up the initial designed nickname, split the initial designed nickname into multiple words to be combined.

[0094] Specifically, for each initial designed nickname, it can be split into combined words of adjective + noun, verb + noun. For example, if the initial designed nickname is "Cool Guy's 8x Scope", then for this initial designed nickname, it can be split into two words to be combined, namely "Cool Guy" and "8x Scope".

[0095] a3: Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined to obtain multiple combined nicknames.

[0096] In the embodiment of the present application, after splitting each initial designed nickname into multiple words to be combined, shuffle the multiple words to be combined and recombine them according to the part of speech to determine multiple combined nicknames, and it is necessary to remove the nicknames that are the same as the initial designed nickname among the multiple combined nicknames to avoid duplicate nicknames in the preset nickname database.

[0097] a4: Update the initial nickname database according to each combined nickname whose style is determined to obtain the preset nickname database.

[0098] In an embodiment of the present application, after determining a plurality of combined nicknames, at least one nickname style to which each combined nickname belongs is determined according to a pre-trained nickname classification label model, and the combined nicknames are stored in an initial nickname database according to different nickname styles, so as to expand the initial nickname database to obtain a preset nickname database with an updated number of nicknames.

[0099] In a possible implementation manner, the number of nicknames that can be recommended under each nickname style can be determined according to the recommendation probabilities of each nickname style, and then a plurality of nicknames to be recommended are screened out from the preset nickname dataset.

[0100] Specifically, the step of "screening a plurality of nicknames to be recommended from the preset nickname dataset according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs and the semantic similarity between each alternative nickname and the corresponding target historical nickname" includes:

[0101] b1: For each nickname style, according to the semantic similarity between each alternative nickname under this nickname style and the target historical nickname under this nickname style, screen out the target number of alternative recommended nicknames under this nickname style.

[0102] In an embodiment of the present application, for each nickname style, calculate the semantic similarity between each alternative nickname under this nickname style and the target historical nickname under this nickname style, and after calculating the semantic similarity between each alternative nickname and the target historical nickname under this nickname style, sort the plurality of alternative nicknames in descending order of the semantic similarity with the target historical nickname, and determine the alternative nicknames ranked before the target number position as the alternative recommended nicknames under this nickname style.

[0103] Among them, the target number is determined based on the recommendation probability of this nickname style, and the higher the recommendation probability, the larger the corresponding target number.

[0104] Specifically, the total number of nicknames to be recommended can be preset in advance, and the target number of alternative recommended nicknames under each nickname style to be determined is calculated according to the recommendation probabilities of each nickname style.

[0105] For example, in a round of calculation, 5 nicknames to be recommended are required, and for the nickname style of the ancient style, the recommendation probability is 3 / 5. Then, for the ancient style, 3 alternative recommended nicknames need to be determined.

[0106] b2: Determine the at least one alternative recommended nickname under each nickname style screened out as the nickname to be recommended.

[0107] In the embodiments of the present application, at least one alternative recommended nickname under each nickname style selected is determined as the nickname to be recommended for the target player.

[0108] In another possible implementation manner, in order to reduce the amount of data processing, it is also possible to directly first screen out the target nickname styles with relatively high recommendation probabilities from the nickname styles corresponding to the target historical nicknames used by the target player, and then determine the nickname to be recommended based on the semantic similarity between the alternative nickname and the target historical nickname for the target nickname style.

[0109] Specifically, the step of "screening multiple nicknames to be recommended from the preset nickname dataset according to the recommendation probability of each nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname" further includes:

[0110] c1: Determine the nickname styles with recommendation probabilities greater than the preset recommendation probability among the multiple nickname styles as the target nickname styles.

[0111] In the embodiments of the present application, the nickname styles with corresponding recommendation probabilities greater than the preset recommendation probability among the multiple nickname styles are determined as the target nickname styles that can be further recommended for calculation.

[0112] Specifically, the preset recommendation probability can be determined according to the recommendation requirements, or can be determined according to the recommendation effect when recommending according to the historical recommendation probability.

[0113] In a possible implementation manner, in order to reduce the amount of data processing in the nickname recommendation process, it is possible to select and screen the nickname styles according to the preset recommendation probability. And in order to ensure the comprehensiveness of the nickname screening, it is also possible not to screen the recommended styles and directly perform the step of calculating the semantic similarity between the alternative nickname and the target historical nickname.

[0114] c2: For each target nickname style, screen out the target number of alternative recommended nicknames under the target nickname style according to the semantic similarity between each alternative nickname under the target nickname style and the target historical nickname under the target nickname style; where the target number is determined based on the recommendation probability of the nickname style, and the higher the recommendation probability, the larger the corresponding target number.

[0115] In the embodiments of the present application, after determining multiple target nickname styles, for each target nickname style, after calculating the semantic similarity between each alternative nickname and the target historical nickname under the target nickname style, sort the multiple alternative nicknames in descending order of the semantic similarity with the target historical nickname, and determine the alternative nicknames before the target number position as the alternative recommended nicknames under the target nickname style.

[0116] The number of targets corresponding to each target nickname style is also determined based on the recommendation probability of each target nickname style. The specific determination method is the same as the method for determining the number of targets corresponding to each nickname style, and will not be repeated here.

[0117] In the above method, it is also possible to no longer consider multiple nickname style categories, and no longer determine the number of recommendations for each nickname style by the recommendation probabilities of different target nickname styles. The candidate recommended nicknames can be directly screened according to the preset semantic similarity threshold.

[0118] For each target nickname style, the semantic similarity between each alternative nickname under the target nickname style and the target historical nickname under the nickname style is calculated. After calculating the semantic similarity between each alternative nickname and the target historical nickname under the nickname style, the alternative nicknames whose semantic similarity is greater than the preset semantic similarity threshold are directly determined as nicknames to be recommended.

[0119] Among them, the preset semantic similarity threshold can be set according to the semantic similarity between the recommended alternative nicknames and the historical nicknames used by the player before during the historical nickname recommendation process. For example, it can be the average value of the semantic similarity between the recommended alternative nicknames and the historical nicknames used by the player before during multiple recommendation processes; it can also be set according to the recommendation requirements of the game nickname. The specific setting process is not specifically limited in the embodiments of this application.

[0120] c3: Determine the candidate recommended nicknames under each target nickname style that have been screened out as nicknames to be recommended.

[0121] In the embodiment of the present application, at least one candidate recommended nickname under each target nickname style is screened out to determine a nickname to be recommended for the target player.

[0122] S104: Determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player, so as to recommend the target nickname to the target player.

[0123] In an embodiment of the present application, at least one target nickname is determined from the multiple nicknames to be recommended and displayed to the target player. During the display process, the target nickname selected by the target player is determined based on the selection operation of the target player.

[0124] In one possible implementation, the target player may trigger the display of the nicknames to be recommended by a click operation. During the display process of the nicknames to be recommended, the target player may trigger it once, and then randomly select a nickname from the nicknames to be recommended and display it to the target player; the target player may also trigger it once, and then the nicknames to be recommended may be displayed to the target player in order according to the recommendation probability of each nickname style; or all the nicknames to be recommended may be displayed to the target player based on the triggering operation of the target player.

[0125] In a possible implementation, after the target player selects the target nickname, it is necessary to perform a deduplication operation on the preset nickname database.

[0126] Specifically, the recommendation method further includes:

[0127] d1: deleting the target nickname selected by the target player from the preset nickname data set, and updating the preset nickname database.

[0128] In an embodiment of the present application, after the target player selects a target nickname, the target nickname selected by the player needs to be deleted from the preset nickname database. When recommending nicknames to other players in the future, the nickname selected by the target player will no longer exist in the preset nickname database. This can effectively prevent the occurrence of duplicate nicknames between different players.

[0129] In a possible implementation, in order to reduce the amount of data processing, the target historical nicknames of the target player may be screened in advance based on the target game the target player is currently playing and the target player's preferences.

[0130] Specifically, before the step of "obtaining at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs", the recommendation method further includes:

[0131] e1: In response to a nickname setting request from a target player, obtaining at least one historical nickname used by the target player and the nickname style to which each historical nickname belongs based on the identity identification information of the target player.

[0132] In an embodiment of the present application, when a nickname setting request of a target player is received, at least one historical nickname that the target player has used is obtained based on the identity information of the target player, and the nickname style of each historical nickname is determined.

[0133] e2: According to the target game style of the target game that the target player is operating and the target player's nickname setting preference for the target game style, screen out historical nicknames that meet the target game style and the target player's nickname setting preference for the target game style from the at least one historical nickname, so as to obtain at least one target historical nickname.

[0134] In the embodiment of the present application, the target game style of the target game that the target player is operating is determined, and at the same time, when determining the target player's nickname setting preference for the target game style during historical nickname selection, screen out historical nicknames that meet the target game style and the target player's preference for the target game style from at least one historical nickname used by the player, so as to obtain at least one target historical nickname.

[0135] Specifically, for the target player, when screening nicknames, the player may prefer different styles of nicknames in different games for different game styles. For example, in some ancient style plot games, the player may prefer ancient style nicknames, etc. When obtaining the target player's historical nicknames, through the screening of game styles, while reducing the amount of data processing, it is also possible to more accurately screen out the nicknames to be recommended that the target player may choose.

[0136] In a possible implementation manner, the target player may be a newly registered user and there is no used target historical nickname. At this time, the nicknames to be recommended for the target player can be screened according to the setting conditions of the target game that the target player is operating.

[0137] Specifically, please refer to Figure 2 , Figure 2 which is a flowchart of another method for recommending player nicknames provided by the embodiment of the present application. As shown in Figure 2 , after the step "responding to the nickname setting request of the target player", the recommendation method further includes:

[0138] S201. If the target historical nickname used by the target player cannot be obtained, screen out at least one nickname to be recommended from the preset nickname dataset according to the target game style of the target game that the target player is operating and the nickname setting conditions of the target game.

[0139] In the embodiment of the present application, if the target historical nickname used by the target player cannot be obtained, at this time, at least one nickname to be recommended can be screened from the preset nickname dataset according to the target game style of the target game that the target player is operating and the nickname setting conditions of the target game.

[0140] Specifically, the nickname setting conditions of the target game include at least one of the following: the number of characters in the nickname is less than a preset number of characters, the nickname does not include sensitive words, and the nickname does not include special characters.

[0141] S202: Display the determined at least one nickname to be recommended to the target player, so that the target player can select a target nickname to use.

[0142] In the embodiment of the present application, similarly, after determining a plurality of nicknames to be recommended that can be recommended to the target player, the plurality of nicknames to be recommended are displayed to the target player, so that the target player can select a target nickname that can be used.

[0143] In a possible implementation, after displaying multiple nicknames to be recommended to target players, it is also necessary to determine the timing for ending the display of the nicknames to be recommended based on usage conditions.

[0144] Specifically, the recommendation method further includes:

[0145] f1: In response to the display of the nickname to be recommended meeting the display end condition, end the display of the nickname to be recommended.

[0146] The recommended nickname display meeting the display end conditions includes at least one of the following:

[0147] The target player selects any nickname to be recommended, and all of the multiple nicknames to be recommended are displayed.

[0148] In one possible implementation, the display of nicknames is a cyclic display process. If the first batch of recommended nicknames is not selected by the target player, after the recommendation of the first batch of recommended nicknames is completed, the above-mentioned nickname screening step is performed again to select the second batch of recommended nicknames to be displayed to the target player for selection, until the target player selects the target nickname he likes, thus completing the entire nickname recommendation process for the target player.

[0149] A method for recommending player nicknames provided by an embodiment of the present application, in response to a nickname setting request of a target player, obtains at least one target historical nickname that the target player has used before, and determines the nickname style to which each target historical nickname belongs; determines the proportion of each nickname style in the target historical nicknames according to the number of target historical nicknames included in each nickname style, and further determines the recommendation probability of each nickname style for the target player; determines a plurality of nicknames to be recommended according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the target historical nickname; determines at least one target nickname from the plurality of nicknames to be recommended and displays it to the target player, so as to recommend the use of the target nickname to the target player. In the embodiment of the present application, by analyzing the historical nicknames of the target player, the preference of the target player for different nickname styles is determined, and then the recommendation probability of each nickname style is determined, so as to recommend nicknames to the target player in a targeted manner according to the recommendation probability of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

[0150] Based on the same inventive concept, an embodiment of the present application also provides a player nickname recommendation device corresponding to the player nickname recommendation method. Since the principle of solving problems by the device in the embodiment of the present application is similar to the above-mentioned player nickname recommendation method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0151] Please refer to Figures 3 to 5 , Figure 3 which is one of the structural schematic diagrams of a player nickname recommendation device provided by an embodiment of the present application, Figure 4 which is another structural schematic diagram of a player nickname recommendation device provided by an embodiment of the present application, Figure 5 which is the third structural schematic diagram of a player nickname recommendation device provided by an embodiment of the present application. As Figure 3 shown in, the recommendation device 300 includes:

[0152] A nickname acquisition module 310, configured to obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs in response to a nickname setting request of the target player;

[0153] A probability determination module 320, configured to determine the nickname proportion of each nickname style in the target historical nicknames according to the number of target historical nicknames included in each nickname style, and determine the recommendation probability of each nickname style being recommended for the target player according to the nickname proportion of each nickname style;

[0154] The nickname screening module 330 is configured to screen multiple nicknames to be recommended from a preset nickname dataset according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname;

[0155] The nickname display module 340 is configured to determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player, so as to recommend the target player to use the target nickname.

[0156] In a possible implementation manner, as Figure 4 shown, the recommendation device 300 further includes a nickname selection module 350, and the nickname selection module 350 is configured to:

[0157] In response to a nickname setting request of a target player, based on the identity identification information of the target player, obtain at least one historical nickname used by the target player and the nickname style to which each historical nickname belongs;

[0158] According to the target game style of the target game that the target player is operating and the target player's nickname setting preference for the target game style, screen out the historical nicknames that meet the target game style and the target player's nickname setting preference for the target game style from the at least one historical nickname, so as to obtain at least one target historical nickname.

[0159] In a possible implementation manner, as Figure 4 shown, the recommendation device 300 further includes a database determination module 360, and the database determination module 360 is configured to:

[0160] Obtain multiple initial designed nicknames and the nickname style to which each initial designed nickname belongs;

[0161] For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname;

[0162] Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined, so as to obtain multiple combined nicknames;

[0163] Update the initial nickname database according to each combined nickname whose nickname style is determined, so as to obtain the preset nickname database; wherein, the nickname style to which the combined nickname belongs is determined by classification based on a pre-trained nickname classification label model, and each combined nickname belongs to at least one nickname style.

[0164] In a possible implementation manner, as Figure 4As shown, the recommendation device 300 further includes a nickname end display module 370, and the nickname end display module 370 is used to:

[0165] In response to the display of the nickname to be recommended meeting the display end condition, ending the display of the nickname to be recommended;

[0166] The recommended nickname display must meet at least one of the following conditions to end the display:

[0167] The target player selects any nickname to be recommended, and all of the multiple nicknames to be recommended are displayed.

[0168] In one possible implementation, Figure 4 As shown, the recommendation device 300 further includes a nickname deletion module 380, which is used to:

[0169] The target nickname selected by the target player is deleted from the preset nickname data set, and the preset nickname database is updated.

[0170] In one possible implementation, Figure 5 As shown, the recommendation device 300 further includes a nickname setting module 390, which is used to:

[0171] In response to a nickname setting request from a target player, obtaining at least one historical nickname used by the target player and a nickname style to which each historical nickname belongs based on the identity identification information of the target player;

[0172] According to the target game style of the target game being operated by the target player and the target player's nickname setting preference for the target game style, historical nicknames that match the target game style and the target player's nickname setting preference for the target game style are filtered out from the at least one historical nickname to obtain at least one target historical nickname.

[0173] In one possible implementation, when the nickname screening module 330 is used to screen multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname, the nickname screening module 330 is used to:

[0174] For each nickname style, based on the semantic similarity between each candidate nickname under that nickname style and the target historical nickname under that nickname style, a target number of candidate recommended nicknames under that nickname style are screened out; wherein the target number is determined based on the recommendation probability of the nickname style, and a higher recommendation probability corresponds to a larger target number;

[0175] At least one candidate recommended nickname under each screened nickname style is determined as the nickname to be recommended.

[0176] In one possible implementation, when the nickname screening module 330 is used to screen multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname, the nickname screening module 330 is used to:

[0177] Determine a nickname style with a recommendation probability greater than a preset recommendation probability among the multiple nickname styles as a target nickname style;

[0178] For each target nickname style, based on the semantic similarity between each candidate nickname under the target nickname style and the target historical nickname under the target nickname style, a target number of candidate recommended nicknames under the target nickname style are screened out; wherein the target number is determined based on the recommendation probability of the nickname style, and a higher recommendation probability corresponds to a larger target number;

[0179] The candidate recommended nicknames under each target nickname style that has been screened out are determined as nicknames to be recommended.

[0180] In a possible implementation, the preset nickname data set is composed of at least one nickname that meets the nickname setting condition and is screened from a preset nickname database based on the nickname setting condition of the target game being played by the target player, and the preset nickname data set is formed;

[0181] The nickname setting condition includes at least one of the following:

[0182] The nickname contains fewer than the preset number of characters, does not contain sensitive words, and does not contain special characters.

[0183] In a possible implementation, the nickname style is used to characterize the name semantic category and / or the domain category to which the nickname belongs.

[0184] A recommended device for player nicknames provided by an embodiment of the present application, in response to a nickname setting request of a target player, obtains at least one target historical nickname that the target player has used before, and determines the nickname style to which each target historical nickname belongs; according to the number of target historical nicknames included in each nickname style, determines the proportion of each nickname style in the target historical nicknames, and further determines the recommendation probability of each nickname style for the target player; according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the target historical nickname, determines a plurality of nicknames to be recommended; determines at least one target nickname from the plurality of nicknames to be recommended and displays it to the target player, so as to recommend the use of the target nickname to the target player. In the embodiment of the present application, by analyzing the historical nicknames of the target player, the preference of the target player for different nickname styles is determined, and then the recommendation probability of each nickname style is determined, so as to recommend nicknames to the target player in a targeted manner according to the recommendation probability of different nickname styles, which helps to improve the accuracy of recommending nicknames to players.

[0185] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 6 shown in, the electronic device 600 includes: a processor 610, a storage medium 620, and a bus 630. The storage medium 620 stores machine-readable instructions executable by the processor 610. When the electronic device runs a recommended method for a player nickname as in the embodiment, the processor 610 communicates with the storage medium 620 through the bus 630, and the processor 610 executes the machine-readable instructions, the preamble part of the method item of the processor 610, to perform the following steps:

[0186] In response to a nickname setting request of a target player, obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs;

[0187] According to the number of target historical nicknames included in each nickname style, determine the nickname proportion of each nickname style in the target historical nicknames, and according to the nickname proportion of each nickname style, determine the recommendation probability that each nickname style is recommended for the target player;

[0188] According to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, screen a plurality of nicknames to be recommended from the preset nickname dataset;

[0189] Determine at least one target nickname from the plurality of nicknames to be recommended and display it to the target player, so as to recommend the use of the target nickname to the target player.

[0190] In a feasible implementation, when the processor 610 is used to screen multiple nicknames to be recommended from a preset nickname dataset according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, the processor 610 is used to:

[0191] For each nickname style, screen out a target number of alternative recommended nicknames under the nickname style according to the semantic similarity between each alternative nickname under the nickname style and the target historical nickname under the nickname style; wherein, the target number is determined based on the recommendation probability of the nickname style, and the higher the recommendation probability, the larger the corresponding target number;

[0192] Determine at least one alternative recommended nickname under each screened nickname style as the nickname to be recommended.

[0193] In a feasible implementation, when the processor 610 is used to screen multiple nicknames to be recommended from a preset nickname dataset according to the recommendation probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, the processor 610 is further used to:

[0194] Determine the nickname styles with a recommendation probability greater than the preset recommendation probability among the multiple nickname styles as the target nickname styles;

[0195] For each target nickname style, screen out a target number of alternative recommended nicknames under the target nickname style according to the semantic similarity between each alternative nickname under the target nickname style and the target historical nickname under the target nickname style; wherein, the target number is determined based on the recommendation probability of the nickname style, and the higher the recommendation probability, the larger the corresponding target number;

[0196] Determine the alternative recommended nicknames under each screened target nickname style as the nickname to be recommended.

[0197] In a feasible implementation, the processor 610 is further used to:

[0198] In response to the nickname setting request of the target player, based on the identity identification information of the target player, obtain at least one historical nickname used by the target player and the nickname style to which each historical nickname belongs;

[0199] According to the target game style of the target game that the target player is operating and the target player's nickname setting preference for the target game style, screen out the historical nicknames that meet the target game style and the target player's nickname setting preference for the target game style from the at least one historical nickname to obtain at least one target historical nickname.

[0200] In a feasible implementation, the preset nickname dataset is at least one nickname that meets the nickname setting conditions, screened from a preset nickname database according to the nickname setting conditions of the target game that the target player is operating, and constitutes the preset nickname dataset;

[0201] The nickname setting conditions include at least one of the following:

[0202] The number of characters in the nickname is less than the preset number of characters, the nickname does not include sensitive words, and the nickname does not contain special characters.

[0203] In a feasible implementation, the preset nickname database is a database updated based on an initial nickname database containing multiple initial designed nicknames. The processor 610 determines the preset nickname database through the following steps:

[0204] Obtain multiple initial designed nicknames and the nickname styles to which each initial designed nickname belongs;

[0205] For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname;

[0206] Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined to obtain multiple combined nicknames;

[0207] Update the initial nickname database according to the determined combined nicknames of the nickname styles to obtain the preset nickname database; wherein, the nickname style to which the combined nickname belongs is determined by classification based on a pre-trained nickname classification label model, and each combined nickname belongs to at least one nickname style.

[0208] In a feasible implementation, the processor 610 is further configured to:

[0209] If the target historical nickname used by the target player cannot be obtained, screen at least one nickname to be recommended from the preset nickname dataset according to the target game style of the target game that the target player is operating and the nickname setting conditions of the target game;

[0210] Display the determined at least one nickname to be recommended to the target player so that the target player can select the target nickname to use.

[0211] In a feasible implementation, the processor 610 is further configured to:

[0212] Respond to the display of the nickname to be recommended meeting the display end condition and end the display of the nickname to be recommended;

[0213] The recommended nickname display must meet at least one of the following conditions to end the display:

[0214] The target player selects any nickname to be recommended, and all of the multiple nicknames to be recommended are displayed.

[0215] In one feasible embodiment, the processor 610 is further configured to:

[0216] The target nickname selected by the target player is deleted from the preset nickname data set, and the preset nickname database is updated.

[0217] In a feasible embodiment, the nickname style is used to characterize the semantic category and / or the field category of the nickname.

[0218] Through the above method, by analyzing the historical nicknames of the target player, the target player's preference for different nickname styles is determined, and then the recommendation probability of each nickname style is determined, so that nicknames can be recommended to the target player in a targeted manner based on the recommendation probability of different nickname styles, which helps to improve the accuracy of recommending nicknames to players; at the same time, when screening the player's historical nicknames, you can first screen out historical nicknames that are more in line with the player's preferences based on the game style of the target game the player is playing and the player's preference for nickname settings for this game style, which can further reduce the amount of data processing and improve the efficiency of nickname recommendations.

[0219] An embodiment of the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium. The computer program is executed when a processor is run, and the processor performs the following steps:

[0220] In response to a nickname setting request from a target player, obtaining at least one target historical nickname used by the target player and a nickname style to which each target historical nickname belongs;

[0221] Determining the nickname ratio of each nickname style in the target historical nicknames based on the number of target historical nicknames included in each nickname style, and determining the recommendation probability of each nickname style being recommended to the target player based on the nickname ratio of each nickname style;

[0222] Filtering multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style of each candidate nickname in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname;

[0223] At least one target nickname is determined from the multiple nicknames to be recommended and displayed to the target player, so as to recommend the target nickname to the target player.

[0224] In a feasible embodiment, the method of screening multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname includes:

[0225] For each nickname style, based on the semantic similarity between each candidate nickname under that nickname style and the target historical nickname under that nickname style, a target number of candidate recommended nicknames under that nickname style are screened out; wherein the target number is determined based on the recommendation probability of the nickname style, and a higher recommendation probability corresponds to a larger target number;

[0226] At least one candidate recommended nickname under each screened nickname style is determined as the nickname to be recommended.

[0227] In a feasible embodiment, the method of screening multiple nicknames to be recommended from the preset nickname dataset based on the recommendation probability of the nickname style to which each candidate nickname belongs in the preset nickname dataset and the semantic similarity between each candidate nickname and the corresponding target historical nickname includes:

[0228] Determine a nickname style with a recommendation probability greater than a preset recommendation probability among the multiple nickname styles as a target nickname style;

[0229] For each target nickname style, based on the semantic similarity between each candidate nickname under the target nickname style and the target historical nickname under the target nickname style, a target number of candidate recommended nicknames under the target nickname style are screened out; wherein the target number is determined based on the recommendation probability of the nickname style, and a higher recommendation probability corresponds to a larger target number;

[0230] The candidate recommended nicknames under each target nickname style that has been screened out are determined as nicknames to be recommended.

[0231] In a feasible embodiment, before obtaining at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs, the recommendation method further includes:

[0232] In response to a nickname setting request from a target player, obtaining at least one historical nickname used by the target player and a nickname style to which each historical nickname belongs based on the identity identification information of the target player;

[0233] According to the target game style of the target game being operated by the target player and the target player's nickname setting preference for the target game style, historical nicknames that match the target game style and the target player's nickname setting preference for the target game style are filtered out from the at least one historical nickname to obtain at least one target historical nickname.

[0234] In a feasible implementation, the preset nickname dataset is at least one nickname that meets the nickname setting conditions, screened from a preset nickname database according to the nickname setting conditions of the target game that the target player is operating, and constitutes the preset nickname dataset;

[0235] The nickname setting conditions include at least one of the following:

[0236] The number of characters in the nickname is less than the preset number of characters, the nickname does not include sensitive words, and the nickname does not contain special characters.

[0237] In a feasible implementation, the preset nickname database is a database updated based on an initial nickname database containing multiple initial designed nicknames. The preset nickname database is determined through the following steps:

[0238] Obtain multiple initial designed nicknames and the nickname styles to which each initial designed nickname belongs;

[0239] For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname;

[0240] Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined to obtain multiple combined nicknames;

[0241] Update the initial nickname database according to the determined combined nicknames of each nickname style to obtain the preset nickname database; wherein, the nickname style to which the combined nickname belongs is determined by classification based on a pre-trained nickname classification label model, and each combined nickname belongs to at least one nickname style.

[0242] In a feasible implementation, after responding to the nickname setting request of the target player, the recommendation method further includes:

[0243] If the target historical nickname used by the target player cannot be obtained, at least one nickname to be recommended is screened from the preset nickname dataset according to the target game style of the target game that the target player is operating and the nickname setting conditions of the target game;

[0244] Display the determined at least one nickname to be recommended to the target player so that the target player can select the target nickname to use.

[0245] In a feasible implementation, the recommendation method further includes:

[0246] Respond to the display of the nickname to be recommended meeting the display end condition, and end the display of the nickname to be recommended;

[0247] The display of the to-be-recommended nicknames meets the display end condition including at least one of the following:

[0248] The target player selects any one of the to-be-recommended nicknames, and all the to-be-recommended nicknames are displayed.

[0249] In a feasible implementation, the recommendation method further includes:

[0250] Delete the target nickname selected and used by the target player from the preset nickname dataset, and update the preset nickname database.

[0251] In a feasible implementation, the nickname style is used to characterize the name semantic category and / or the affiliated domain category of the nickname.

[0252] In the above manner, by analyzing the historical nicknames of the target player, the preference of the target player for different nickname styles is determined, and then the recommendation probability of each nickname style is determined. According to the recommendation probabilities of different nickname styles, nicknames are recommended to the target player in a targeted manner, which helps to improve the accuracy of nickname recommendation to players. At the same time, when screening the historical nicknames of players, the historical nicknames that are more in line with the player's preference can be screened out first according to the game style of the target game that the player is playing and the player's preference for the nickname setting of this game style. This can further reduce the amount of data processing and improve the nickname recommendation efficiency.

[0253] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0254] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the couplings or direct couplings or communication connections shown or discussed with each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0255] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0256] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0257] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0258] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. These modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for recommending player nicknames, characterized in that, The recommended method includes: In response to a nickname setting request of a target player, obtaining at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs; According to the number of target historical nicknames included in each nickname style, determining the nickname proportion of each nickname style in the target historical nicknames, and according to the nickname proportion of each nickname style, determining the recommended probability of each nickname style being recommended for the target player; According to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname, screening multiple nicknames to be recommended from the preset nickname dataset; the nickname to be recommended is the target number of alternative nicknames determined according to the semantic similarity between the alternative nickname and the target historical nickname in each nickname style or the target nickname style with a recommended probability greater than the preset recommended probability in the nickname style; the target number is determined by the recommended probability of the nickname style; the target historical nickname is a historical nickname that conforms to the target game style of the target game that the target player is operating and the target player's nickname setting preference for the target game style; Determining at least one target nickname from the multiple nicknames to be recommended and presenting it to the target player to recommend the target player to use the target nickname.

2. The recommendation method according to claim 1, wherein The screening of multiple nicknames to be recommended from the preset nickname dataset according to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname includes: For each nickname style, screening out the target number of alternative recommended nicknames in the nickname style according to the semantic similarity between each alternative nickname in the nickname style and the target historical nickname in the nickname style; wherein, the target number is determined based on the recommended probability of the nickname style, and the higher the recommended probability, the larger the corresponding target number; Determining the at least one alternative recommended nickname in each screened nickname style as the nickname to be recommended.

3. The recommended method according to claim 1, characterized in that The screening of multiple nicknames to be recommended from the preset nickname dataset according to the recommended probability of the nickname style to which each alternative nickname in the preset nickname dataset belongs, and the semantic similarity between each alternative nickname and the corresponding target historical nickname includes: Determining the nickname styles with a recommended probability greater than the preset recommended probability among the multiple nickname styles as the target nickname styles; For each target nickname style, screening out the target number of alternative recommended nicknames in the target nickname style according to the semantic similarity between each alternative nickname in the target nickname style and the target historical nickname in the target nickname style; wherein, the target number is determined based on the recommended probability of the nickname style, and the higher the recommended probability, the larger the corresponding target number; Determining the alternative recommended nicknames in each screened target nickname style as the nickname to be recommended.

4. The recommendation method according to claim 1, wherein Before obtaining at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs, the recommended method further includes: In response to a nickname setting request of a target player, based on the identity identification information of the target player, obtain at least one historical nickname used by the target player and the nickname style to which each historical nickname belongs; According to the target game style of the target game that the target player is operating and the target player's nickname setting preference for the target game style, screen out historical nicknames that meet the target game style and the target player's nickname setting preference for the target game style from the at least one historical nickname, and obtain at least one target historical nickname.

5. The recommendation method according to claim 1, wherein The preset nickname data set is at least one nickname that meets the nickname setting conditions screened from a preset nickname database according to the nickname setting conditions of the target game that the target player is operating, and forms the preset nickname data set; The nickname setting conditions include at least one of the following: The number of characters included in the nickname is less than the preset number of characters, the nickname does not include sensitive words, and the nickname does not contain special characters.

6. The recommendation method according to claim 5, wherein The preset nickname database is a database updated based on an initial nickname database containing multiple initial designed nicknames. The preset nickname database is determined through the following steps: Obtain multiple initial designed nicknames and the nickname style to which each initial designed nickname belongs; For each initial designed nickname, split the initial designed nickname into multiple words to be combined according to the part of speech of each word that makes up the initial designed nickname; Recombine the determined multiple words to be combined according to the semantics and part of speech of each word to be combined to obtain multiple combined nicknames; Update the initial nickname database according to each combined nickname whose nickname style is determined to obtain the preset nickname database; wherein, the nickname style to which the combined nickname belongs is determined by classification based on a pre-trained nickname classification label model, and each combined nickname belongs to at least one nickname style.

7. The recommended method according to claim 1, wherein The recommendation method further includes: In response to the display of the nickname to be recommended satisfying the display end condition, end the display of the nickname to be recommended; The display of the nickname to be recommended satisfying the display end condition includes at least one of the following: The target player selects any nickname to be recommended, and all the nicknames to be recommended are displayed.

8. The recommendation method according to claim 6, wherein The recommendation method further includes: Delete the target nickname selected and used by the target player from the preset nickname data set, and update the preset nickname database.

9. The recommendation method according to claim 1, characterized in that The nickname style is used to characterize the name semantic category and / or the domain category to which the nickname belongs.

10. A recommended device for player nicknames, characterized in that, The recommendation device includes: A nickname acquisition module, configured to, in response to a nickname setting request of a target player, obtain at least one target historical nickname used by the target player and the nickname style to which each target historical nickname belongs; A probability determination module, configured to determine the nickname proportion of each nickname style in the target historical nickname according to the number of target historical nicknames included in each nickname style, and determine the recommended probability of each nickname style being recommended for the target player according to the nickname proportion of each nickname style; A nickname screening module, configured to screen multiple nicknames to be recommended from a preset nickname dataset according to the recommendation probability of each alternative nickname belonging to a nickname style in the preset nickname dataset and the semantic similarity between each alternative nickname and the corresponding target historical nickname; the nickname to be recommended is the target number of alternative nicknames determined according to the semantic similarity between the alternative nicknames in each nickname style or the target nickname style with a recommendation probability greater than a preset recommendation probability and the target historical nickname; the target number is determined by the recommendation probability of the nickname style; the target historical nickname is a historical nickname that conforms to the target game style of the target game that the target player is operating and the nickname setting preference of the target player for the target game style. A nickname display module, configured to determine at least one target nickname from the multiple nicknames to be recommended and display it to the target player, so as to recommend the target nickname for the target player to use.

11. An electronic device, characterized in that, Including: A processor, a storage medium and a bus, the storage medium stores machine-readable instructions executable by the processor, when the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the method for recommending a player nickname according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, it performs the steps of the method for recommending a player nickname according to any one of claims 1 to 9.

Images