Game nickname recommendation method, device, system, and storage medium

Abstract

The application provides a game nickname recommendation method, device, system and storage medium. A game nickname recommendation request sent by a client is received. The request carries a nickname demand parameter. According to the nickname demand parameter carried in the request, a to-be-recommended game nickname corresponding to the nickname demand parameter is obtained by searching a preset multilingual game nickname database. The multilingual game nickname database stores a plurality of game nickname data sets corresponding to a plurality of language types. Each game nickname in each game nickname data set corresponds to a category label. The to-be-recommended game nickname is returned to the client. According to the nickname recommendation request initiated by the user and containing a plurality of nickname demand parameters, and the multilingual game nickname database pre-constructed and including a plurality of language types and the nicknames labeled with corresponding category labels, accurate game nickname searching and recommendation are performed, the self-defined demand of the user in a plurality of scenarios is met, and the game experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of game technology, and in particular to a method, apparatus, system, and storage medium for recommending game nicknames. Background Technology

[0002] A game nickname is a name a player creates for themselves after registering a game account. It acts as an identity ID, used for in-game social interaction, privacy protection, and identification. From the game's perspective, servers within the same game typically restrict the uniqueness of game nicknames to distinguish different players, thus achieving functions like identity verification and social interaction. From the player's perspective, choosing a favorite game nickname allows them to communicate and cooperate with other players through a virtual identity, fulfilling functions like social interaction and privacy protection. Setting a game nickname is often an essential step before starting a game, and coming up with a suitable nickname is already a difficult process. Coupled with the uniqueness restriction, setting a game nickname can significantly reduce the player's gaming experience. Therefore, game developers usually recommend game nicknames to players to better assist them in their gaming experience.

[0003] However, in game nickname recommendation technologies, game developers typically maintain a massive database of game nicknames on the server side. After a player initiates a nickname recommendation request on the client side, the server automatically returns a random nickname to the player. This approach is merely a simple accumulation of nickname data, hindering further iterative development, limiting the flexibility of functional expansion, failing to meet customization needs in multiple scenarios, and ultimately reducing the player's gaming experience. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, system, and storage medium for recommending game nicknames. Based on a nickname recommendation request initiated by a user that includes multiple nickname requirement parameters, and a pre-built multilingual game nickname database that includes nicknames in multiple languages ​​and labeled with corresponding category tags, the application can accurately retrieve and recommend game nicknames, meet the user's customized needs in various scenarios, facilitate subsequent iterative development, and improve the user's gaming experience.

[0005] In a first aspect, embodiments of this application provide a method for recommending game nicknames. The method is applied to a server and includes: receiving a game nickname recommendation request sent by a client; the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; retrieving from a preset multilingual game nickname database according to the nickname requirement parameters carried in the request to obtain the game nickname to be recommended corresponding to the nickname requirement parameters; wherein, the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and returning the game nickname to be recommended to the client.

[0006] In a preferred embodiment of this application, the method further includes: determining whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, performing a big data search based on the game nickname to be recommended, and determining the content used to characterize the source of the game nickname to be recommended based on the search results; and returning the game nickname to be recommended to the client, including: returning the content along with the game nickname to be recommended to the client.

[0007] In a preferred embodiment of this application, the construction process of the multilingual game nickname database is as follows: each language type is taken as the current language type, and a basic game nickname dataset corresponding to the current language type is constructed; each game nickname in the basic game nickname dataset is input into a preset nickname category recognition model for prediction to obtain the category label corresponding to each game nickname; a game nickname dataset corresponding to the current language type is constructed based on the game nicknames labeled with category labels.

[0008] In a preferred embodiment of this application, the step of constructing the basic game nickname dataset corresponding to the current language type includes: obtaining the language text corresponding to the current language type; performing entity recognition on the language text to obtain entity recognition results; wherein, the entity recognition results include: entity content and entity category; extracting entity content representing the name from the entity recognition results; and constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content.

[0009] In a preferred embodiment of this application, before the step of constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content, the method further includes: performing a preset filtering operation on the extracted entity content.

[0010] In a preferred embodiment of this application, the training process of the above-mentioned nickname category recognition model is as follows: obtain the model training sample set corresponding to the current language type; the samples in the model training sample set include game nicknames labeled with category tags; apply the samples in the model training sample set to train the preset BERT model to obtain the nickname category recognition model.

[0011] In a preferred embodiment of this application, the method further includes: obtaining currently used game nicknames; filtering out used game nicknames in the multilingual game nickname database to determine the number of unused game nicknames in the multilingual game nickname database; determining whether the number of unused game nicknames is less than a threshold; and if so, updating the multilingual game nickname database based on the game nicknames with pre-labeled category tags.

[0012] Secondly, this application also provides a method for recommending game nicknames. The method is applied to a client and includes: sending a game nickname recommendation request to a server, so that the server retrieves a game nickname to be recommended from a preset multilingual game nickname database based on the nickname requirement parameters carried in the request; wherein the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and receiving the game nickname to be recommended returned by the server.

[0013] In a preferred embodiment of this application, the client provides a nickname creation interface; before the step of sending a game nickname recommendation request to the server, the method further includes: responding to the user's parameter selection operation in the nickname creation interface, and generating a game nickname recommendation request based on the nickname requirement parameters corresponding to the parameter selection operation.

[0014] Thirdly, this application also provides a game nickname recommendation device, which is applied to a server. The device includes: a request receiving module, used to receive a game nickname recommendation request sent by a client; the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; a nickname retrieval module, used to retrieve from a preset multilingual game nickname database according to the nickname requirement parameters carried in the request, and obtain the game nickname to be recommended corresponding to the nickname requirement parameters; wherein, the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and a nickname recommendation module, used to return the game nickname to be recommended to the client.

[0015] Fourthly, this application also provides a game nickname recommendation device. The device is applied to a client and includes: a request sending module, used to send a game nickname recommendation request to a server, so that the server can retrieve the game nickname to be recommended from a preset multilingual game nickname database according to the nickname requirement parameters carried in the request; wherein, the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and a nickname receiving module, used to receive the game nickname to be recommended returned by the server.

[0016] Fifthly, embodiments of this application also provide a game nickname recommendation system, the system comprising a server and a client, the server being communicatively connected to the client; the server being configured to perform the method described in the first aspect; and the client being configured to perform the method described in the second aspect.

[0017] In a sixth aspect, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the methods described in the first and second aspects above.

[0018] This application provides a method, apparatus, system, and storage medium for recommending game nicknames. First, a game nickname recommendation request is received from a client. The request carries nickname requirement parameters, which include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames. Based on the nickname requirement parameters in the request, a search is performed from a pre-set multilingual game nickname database to obtain the game nickname to be recommended corresponding to the nickname requirement parameters. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each game nickname dataset has a corresponding category tag. The category tag includes at least one of the following: gender tag, style tag, language type tag, and domain tag. The game nickname to be recommended is then returned to the client. This application embodiment can accurately retrieve and recommend game nicknames based on user requests initiated through multiple nickname requirement parameters and a pre-built multilingual game nickname database containing nicknames labeled with corresponding category tags for multiple language types. This satisfies users' customized needs in various scenarios, facilitates subsequent iterative development, and improves the user's gaming experience. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for recommending game nicknames as provided in this application embodiment;

[0021] Figure 2 A flowchart illustrating the database construction process in a game nickname recommendation method provided in this application embodiment;

[0022] Figure 3 A schematic diagram illustrating the database construction process in a game nickname recommendation method provided in this application embodiment;

[0023] Figure 4 A flowchart illustrating another method for recommending game nicknames provided in this application embodiment;

[0024] Figure 5 A structural block diagram of a game nickname recommendation device provided in an embodiment of this application;

[0025] Figure 6 A structural block diagram of another game nickname recommendation device provided in an embodiment of this application;

[0026] Figure 7 A structural block diagram of a game nickname recommendation system provided in an embodiment of this application;

[0027] Figure 8 This is a schematic diagram illustrating the working process of a game nickname recommendation system provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] Currently, the recommended game nicknames typically involve game developers maintaining a massive database of nicknames on the server. After a player submits a nickname recommendation request on the client, the server automatically returns a random nickname. The shortcomings of this existing technical solution are:

[0030] 1) The nickname database is too simple to build and mostly covers a single language scenario, which cannot meet the customization needs of multiple scenarios;

[0031] 2) The existing game nickname database does not have any category identifiers and is just a simple collection of nickname data, which hinders further iterative development and limits the flexibility of functional expansion.

[0032] 3) When a player initiates a game nickname recommendation request, only a random nickname result is returned, which is meaningless and usually cannot meet the player's actual needs, resulting in a reduced player's gaming experience.

[0033] Based on this, embodiments of this application provide a method, apparatus, system, and storage medium for recommending game nicknames. It can accurately retrieve and recommend game nicknames based on a nickname recommendation request initiated by a user that includes multiple nickname requirement parameters, and a pre-built multilingual game nickname database that includes nicknames in multiple language types labeled with corresponding category tags. This satisfies the user's customized needs in various scenarios, facilitates subsequent iterative development, and improves the user's gaming experience.

[0034] To facilitate understanding of this embodiment, a method for recommending game nicknames disclosed in this application will first be described in detail.

[0035] Figure 1 A flowchart illustrating a game nickname recommendation method provided in this application embodiment. This method is applied to a server and includes the following steps:

[0036] Step S102: Receive a game nickname recommendation request sent by the client; the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter.

[0037] Compared to existing simple game nickname recommendation requests, the request in this embodiment carries nickname requirement parameters. These parameters are usually customized by the user according to their preferences. Therefore, by searching based on the user's nickname requirement parameters, game nicknames that better meet the user's needs can be determined. These nickname requirement parameters typically include gender parameters, such as male, female, or neutral; style parameters, such as modern, classical, common, or natural; language parameters, such as Chinese, English, or Russian; and domain parameters, such as poetry, classical literature, etc.

[0038] Step S104: Based on the nickname requirement parameters carried in the request, retrieve the game nicknames to be recommended from the preset multilingual game nickname database; wherein, the multilingual game nickname database stores game nickname datasets corresponding to multiple language types; each game nickname in each game nickname dataset has a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label.

[0039] The aforementioned multilingual game nickname database was obtained by using a category recognition model to classify basic game nickname datasets in multiple language types. In other words, each game nickname in the multilingual game nickname database has a corresponding category label, which corresponds to the aforementioned nickname requirement parameters. Therefore, by matching the parameters with the labels, suitable game nicknames can be found and recommended to users.

[0040] Step S106: Return the game nickname to be recommended to the client.

[0041] The aforementioned nickname requirement parameters may also include a nickname quantity parameter, and the server can return nicknames to the client that match the number of nicknames in the nickname quantity parameter.

[0042] This application provides a method for recommending game nicknames. First, a game nickname recommendation request is received from a client. The request carries nickname requirement parameters, which include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames. Based on the nickname requirement parameters in the request, a search is performed from a pre-set multilingual game nickname database to obtain the game nickname to be recommended corresponding to the nickname requirement parameters. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each game nickname dataset has a corresponding category tag. The category tag includes at least one of the following: gender tag, style tag, language type tag, and domain tag. The game nickname to be recommended is then returned to the client. This application embodiment can accurately retrieve and recommend game nicknames based on user requests initiated through multiple nickname requirement parameters and a pre-built multilingual game nickname database containing nicknames labeled with corresponding category tags for multiple language types. This satisfies users' customized needs in various scenarios, facilitates subsequent iterative development, and improves the user's gaming experience.

[0043] This application also provides a method for recommending game nicknames, which is implemented based on the previous embodiment. This embodiment focuses on describing the construction process of a multilingual game nickname database and the specific nickname recommendation process.

[0044] See Figure 2 As shown, the construction process of the above multilingual game nickname database is as follows:

[0045] First, NER or word segmentation operations are performed on the pre-collected multilingual text dataset to extract initial nicknames. Then, special characters in non-linguistic text are cleaned, and special nicknames (such as interjections, meaningless names, and sensitive names) are filtered to construct a multilingual basic game nickname dataset. Next, a pre-trained BERT model is loaded using a fine-tuning method. Some nicknames with category labels (such as gender and style) are loaded into the model as training data, and backpropagation training is performed on the network to continuously optimize the network weight parameters, thereby learning a model suitable for the current data classification task. Finally, the game nicknames in the basic game nickname dataset are classified to obtain category labels, thus constructing a game nickname dataset with category identification.

[0046] The specific implementation process is as follows:

[0047] For each language type designated as the current language type, perform the following steps, see [link to relevant documentation]. Figure 3 As shown:

[0048] Step S302: Construct the basic game nickname dataset corresponding to the current language type.

[0049] In a specific embodiment, the basic game nickname dataset is constructed through the following steps (this embodiment uses the generation process of an English-type game nickname dataset as an example):

[0050] (1) Obtain the language text corresponding to the current language type; the language text can be a sentence extracted from an article. For example, by splitting the text set “The King James of the Bible, Chapter 1 - Genesis” into sentences, the following extracted text content can be obtained;

[0051] "And Esau was forty years old when he took to wife Judith the daughter of Beeri the Hittite, and Bashemath the daughter of Elon the Hittite."

[0052] (2) Perform entity recognition on the language text to obtain entity recognition results; wherein, entity recognition results include: entity content and entity category.

[0053] In practice, the above-mentioned language text can be input into the corpus model in HanLP, and the "NER" task can be selected to perform entity recognition on the language text. The recognized content is as follows:

[0054]

[0055]

[0056] The first item in the list is the content being identified, the second item is the category of the identified content, and the third and fourth items are the starting positions of the identified content in the text.

[0057] (3) Extract the entity content representing the person's name from the entity recognition results.

[0058] The content corresponding to the "PERSON" category is the name of a person. Therefore, the dataset after extracting the names from this text content is: ["Esau","Judith","Beeri","Bashemath","Elon"].

[0059] After completing the overall name extraction, some names may be incorrect. Here, you can also perform preset filtering operations on the extracted entity content:

[0060] ●Special characters that are not linguistic or textual, such as "@", "-", " / ", etc.;

[0061] ● Names with a lowercase first letter;

[0062] ●Special nicknames, such as interjections, meaningless names, sensitive names, etc.

[0063] (4) Construct a basic game nickname dataset corresponding to the current language type based on the extracted entity content. After filtering, the English nickname dataset in the multilingual basic game nickname dataset can be constructed, as shown below:

[0064]

[0065]

[0066] Step S304: Input each game nickname in the basic game nickname dataset into the preset nickname category recognition model for prediction, and obtain the category label corresponding to each game nickname;

[0067] Here we will first introduce the training process of the preset nickname category recognition model:

[0068] (1) Obtain the model training sample set corresponding to the current language type; the samples in the model training sample set include game nicknames labeled with category tags.

[0069] In practice, some nicknames with category tags (such as gender and style) undergo data preprocessing, that is, different categories are converted into corresponding tag sequences. Taking English nicknames as an example, the gender category is set to 3 types: male, female, and neutral, and the style category is set to the following 12 types:

[0070]

[0071] Each style has two opposing categories, and at most one can be selected. For example, the style within the category ["modern", "classic"] can be "modern", "classic", or None. Any combination of the 12 styles can be selected. Taking the English game nickname "Aaliyah" as an example, its category tags are:

[0072]

[0073] The converted category labels are:

[0074]

[0075] The corresponding relationships are as follows: 0 represents a neutral gender or a neutral style (i.e., not particularly inclined towards a certain style), 1 represents a male gender or the first style, and 2 represents a female gender or the second style.

[0076] (2) The sample in the model training sample set is used to train the preset BERT model to obtain the nickname category recognition model.

[0077] The pre-trained BERT model is loaded using a fine-tune method. Pre-processed nicknames are loaded into the model as training data. The error between the predicted value and the expected value is calculated through forward propagation. Then, the gradient of the loss is calculated on the network weights through backpropagation. This gradient is fed back to the optimization method (such as gradient descent). The optimization is used to update the network weight parameters to minimize the loss function, thereby learning a model suitable for the current data classification task, namely the nickname category recognition model.

[0078] Then, the optimized nickname category recognition model is used to classify the game nicknames in the basic game nickname dataset to obtain the category labels corresponding to the nicknames. Then, based on the category correspondence, the nicknames are converted back into the original categories to construct a game nickname dataset with category labels.

[0079] Step S306: Construct a game nickname dataset corresponding to the current language type based on game nicknames labeled with category tags.

[0080] The completed game nickname dataset is shown below (using "Judith" from the above English nickname dataset as an example):

[0081]

[0082]

[0083] The process of returning the game nickname to be recommended to the client also includes: determining whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, performing a big data search based on the game nickname to be recommended, and determining the content used to represent the source of the game nickname to be recommended based on the search results; and returning the content along with the game nickname to be recommended to the client to improve the user's gaming experience.

[0084] The above method also includes maintenance operations for the multilingual game nickname database, the specific steps of which are as follows:

[0085] (1) Get the currently used game nickname; the game company has a user information database, which contains information about the user's game nickname. Through this database server, you can find out the game nickname that has been used in a certain game on the current game server.

[0086] (2) Filter out used game nicknames from the multilingual game nickname database to determine the number of unused game nicknames in the database. The number of unused game nicknames can be determined by removing already used game nicknames from the multilingual game nickname database.

[0087] (3) Determine whether the number of unused game nicknames is less than the threshold;

[0088] (4) If so, update the multilingual game nickname database based on the game nicknames with the pre-labeled category tags.

[0089] The game nickname recommendation method provided in this application embodiment uses techniques such as NER or word segmentation to perform nickname annotation, cleaning, and stop word filtering on a pre-collected multilingual (including Chinese, English, Japanese, Korean, etc.) text dataset, constructing a multilingual basic game nickname dataset. Then, based on data modeling, each game nickname is labeled with a category tag, such as gender (e.g., male, female, neutral) and style (e.g., "modern," "youthful," "informal," "common," "natural," "wholesome," etc., in English). For some fields (e.g., poetry, classic literature), this application embodiment also classifies nicknames accordingly, thereby associating game nicknames with categories such as gender, style, field, and language, establishing a game nickname dataset with category tags. For certain special fields, this application embodiment relies on big data search to provide a source retrieval function for game nicknames, further enhancing the player's gaming experience. The game interface for creating nicknames allows players to customize their game nicknames by setting options such as gender, style, domain, and number of nicknames. The entire game nickname database is connected to the game and provided as a service via HTTP API, thus decoupling the game nickname naming service from game version iterations.

[0090] Based on the above method embodiments, this application also provides a method for recommending game nicknames. This method is applied to a client-side application. (See attached image.) Figure 4 As shown, the method includes:

[0091] Step S402: A game nickname recommendation request is sent to the server, so that the server can retrieve the recommended game nicknames corresponding to the nickname requirement parameters from a preset multilingual game nickname database based on the nickname requirement parameters carried in the request. The request carries nickname requirement parameters, which include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each dataset has a corresponding category label. The category label includes at least one of the following: gender label, style label, language type label, and domain label.

[0092] Step S404: Receive the game nickname to be recommended from the server.

[0093] In a preferred embodiment of this application, the client provides a nickname creation interface; before the step of sending a game nickname recommendation request to the server, the method further includes: responding to the user's parameter selection operation in the nickname creation interface, and generating a game nickname recommendation request based on the nickname requirement parameters corresponding to the parameter selection operation.

[0094] This embodiment relies on a game nickname database with category tags. The game interface for creating nicknames allows users to set options such as gender, style, domain, and number of nicknames. Based on the player's selections, a specified number of suitable game nicknames are recommended for the player to choose from. For game nicknames from certain domains, the specific source of the currently selected nickname will be displayed.

[0095] For example, if a player sets their nickname (using an English nickname as an example) with the parameters: {"gender":"female","style":"classic","number":5}, the naming server will ultimately return data to the game client in a format similar to the following:

[0096]

[0097]

[0098] Of the five game nicknames returned, only "Judith" belongs to the "Classic Literature" category. The other nicknames have no category tags. Therefore, when returning the nickname "Judith", the corresponding classic literature source will also be returned.

[0099] Based on the above server-side method embodiments, this application also provides a game nickname recommendation device, which is applied to a server. See [link to relevant documentation]. Figure 5As shown, the device includes: a request receiving module 52, used to receive a game nickname recommendation request sent by a client; the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; a nickname retrieval module 54, used to retrieve the game nickname to be recommended from a preset multilingual game nickname database according to the nickname requirement parameters carried in the request; wherein, the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and a nickname recommendation module 56, used to return the game nickname to be recommended to the client.

[0100] In a preferred embodiment of this application, the nickname recommendation module 56 is used to determine whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, a big data search is performed based on the game nickname to be recommended, and the content used to represent the source of the game nickname to be recommended is determined according to the search results; the content is returned to the client along with the game nickname to be recommended.

[0101] In a preferred embodiment of this application, the above-mentioned apparatus further includes: a database construction module, configured to perform the following multilingual game nickname database construction process: taking each language type as the current language type, constructing a basic game nickname dataset corresponding to the current language type; inputting each game nickname in the basic game nickname dataset into a preset nickname category recognition model for prediction, obtaining a category label corresponding to each game nickname; and constructing a game nickname dataset corresponding to the current language type based on the game nicknames labeled with category labels.

[0102] In a preferred embodiment of this application, the database construction module is used to obtain the language text corresponding to the current language type; perform entity recognition on the language text to obtain entity recognition results; wherein, the entity recognition results include: entity content and entity category; extract entity content representing the name of the person from the entity recognition results; and construct a basic game nickname dataset corresponding to the current language type based on the extracted entity content.

[0103] In a preferred embodiment of this application, the database construction module is used to perform a preset filtering operation on the extracted entity content.

[0104] In a preferred embodiment of this application, the database construction module is used to perform the following training process for the nickname category recognition model: obtaining the model training sample set corresponding to the current language type; the samples in the model training sample set include game nicknames labeled with category tags; and using the samples in the model training sample set to train a preset BERT model to obtain the nickname category recognition model.

[0105] In a preferred embodiment of this application, the database construction module is configured to: obtain currently used game nicknames; filter out used game nicknames in the multilingual game nickname database to determine the number of unused game nicknames in the multilingual game nickname database; determine whether the number of unused game nicknames is less than a threshold; and if so, update the multilingual game nickname database based on the game nicknames with pre-labeled category tags.

[0106] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts of the device embodiment not mentioned can be referred to the corresponding content in the aforementioned method embodiment.

[0107] Based on the above client-side method embodiments, this application also provides a game nickname recommendation device, which is applied to the client. See [link to relevant documentation]. Figure 6 As shown, the device includes: a request sending module 62, used to send a game nickname recommendation request to a server, so that the server can retrieve the game nickname to be recommended from a preset multilingual game nickname database according to the nickname requirement parameters carried in the request; wherein, the request carries nickname requirement parameters; the nickname requirement parameters include at least one of the following: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; the multilingual game nickname database stores multiple game nickname datasets corresponding to different language types; each game nickname in each game nickname dataset corresponds to a category label; the category label includes at least one of the following: gender label, style label, language type label, and domain label; and a nickname receiving module 64, used to receive the game nickname to be recommended returned by the server.

[0108] In a preferred embodiment of this application, the client provides a nickname creation interface; the apparatus further includes: a request generation module, configured to respond to the user's parameter selection operation in the nickname creation interface before sending a game nickname recommendation request to the server, and generate a game nickname recommendation request based on the nickname requirement parameters corresponding to the parameter selection operation.

[0109] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts of the device embodiment not mentioned can be referred to the corresponding content in the aforementioned method embodiment.

[0110] This application also provides a game nickname recommendation system, such as... Figure 7 As shown, the system includes a server 72 and a client 74, which are communicatively connected; the server 72 is used to execute the server-side method as described above; the client is used to execute the client-side method as described above.

[0111] See Figure 8 As shown, the overall game nickname recommendation process on both the client and server sides includes:

[0112] 1) Users create game nicknames and set category options;

[0113] 2) The game client encapsulates the current user's custom requirements such as gender, style, domain, and number of nicknames into request parameters;

[0114] 3) The HTTP API service passes the request parameters to the name generator server, which then uses a combination of multiple category tags to retrieve the specified game nickname for the client. For nicknames related to poetry, classic literature, etc., it simultaneously retrieves matching document content from a massive library of poetry and classic literature and returns it to the client as well.

[0115] 4) Regarding nickname data updates, a threshold alarm service is set up. When the number of unused game nicknames is less than the threshold, new nicknames that have been categorized are added to the game nickname database.

[0116] This application embodiment, through the construction of a multilingual basic game nickname dataset, can meet the game nickname recommendation needs in different scenarios. Furthermore, it categorizes game nicknames by gender, style, and domain, constructing a game nickname dataset with category labels to meet users' custom nickname settings. The server can respond to users' custom game nickname requests initiated in the game client, returning game nicknames of the corresponding category from the game nickname database and sending them to the game client. For nicknames in fields such as poetry, classic literature, etc., it simultaneously retrieves matching document content from a massive poetry and classic literature database and returns it to the game client, improving the player's gaming experience. The game nickname naming service is completely decoupled from game version iterations, effectively increasing service development efficiency, reducing later maintenance costs, and achieving cost reduction and efficiency improvement in game development.

[0117] This application also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are invoked and executed by a processor, they cause the processor to implement the following server-side method steps:

[0118] The system receives a game nickname recommendation request from the client. The request carries nickname requirement parameters, which include at least one of the following: gender, style, language, domain, or number of nicknames. Based on the nickname requirement parameters in the request, the system retrieves the corresponding game nicknames from a pre-defined multilingual game nickname database. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each dataset has a corresponding category label, which includes at least one of the following: gender, style, language, or domain. The system then returns the recommended game nicknames to the client.

[0119] In a preferred embodiment of this application, the method further includes: determining whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, performing a big data search based on the game nickname to be recommended, and determining the content used to characterize the source of the game nickname to be recommended based on the search results; returning the game nickname to be recommended to the client includes: returning the content to the client together with the game nickname to be recommended.

[0120] In a preferred embodiment of this application, the construction process of the multilingual game nickname database is as follows: for each language type as the current language type, the following steps are performed: construct a basic game nickname dataset corresponding to the current language type; input each game nickname in the basic game nickname dataset into a preset nickname category recognition model for prediction to obtain the category label corresponding to each game nickname; construct a game nickname dataset corresponding to the current language type based on the game nicknames labeled with category labels.

[0121] In a preferred embodiment of this application, the step of constructing the basic game nickname dataset corresponding to the current language type includes: obtaining the language text corresponding to the current language type; performing entity recognition on the language text to obtain entity recognition results; wherein, the entity recognition results include: entity content and entity category; extracting entity content representing the name from the entity recognition results; and constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content.

[0122] In a preferred embodiment of this application, before the step of constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content, the method further includes: performing a preset filtering operation on the extracted entity content.

[0123] In a preferred embodiment of this application, the training process of the above-mentioned nickname category recognition model is as follows: obtain the model training sample set corresponding to the current language type; the samples in the model training sample set include game nicknames labeled with category tags; apply the samples in the model training sample set to train the preset BERT model to obtain the nickname category recognition model.

[0124] In a preferred embodiment of this application, the method further includes: obtaining currently used game nicknames; filtering out used game nicknames in the multilingual game nickname database to determine the number of unused game nicknames in the multilingual game nickname database; determining whether the number of unused game nicknames is less than a threshold; and if so, updating the multilingual game nickname database based on the game nicknames with pre-labeled category tags.

[0125] The following client-side method steps can also be executed:

[0126] A game nickname recommendation request is sent to the server, so that the server can retrieve the recommended game nicknames corresponding to the nickname requirement parameters carried in the request from a pre-set multilingual game nickname database. The request carries nickname requirement parameters, which include at least one of the following: gender, style, language type, domain, or number of nicknames. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each dataset has a corresponding category label, which includes at least one of the following: gender, style, language type, or domain. The server then returns the recommended game nicknames.

[0127] In a preferred embodiment of this application, the client provides a nickname creation interface; before the step of sending a game nickname recommendation request to the server, the method further includes: responding to the user's parameter selection operation in the nickname creation interface, and generating a game nickname recommendation request based on the nickname requirement parameters corresponding to the parameter selection operation.

[0128] The computer program products of the methods, apparatus and systems provided in the embodiments of this application include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0129] Unless otherwise specifically stated, the relative steps, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application.

[0130] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0132] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the technical scope disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for recommending game nicknames, characterized in that, The method is applied to a server, and the method includes: Receive a game nickname recommendation request sent by the client; the request carries nickname requirement parameters; the nickname requirement parameters include: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; Based on the nickname requirement parameters carried in the request, a search is performed from a preset multilingual game nickname database to obtain the game nicknames to be recommended corresponding to the nickname requirement parameters. The multilingual game nickname database stores game nickname datasets corresponding to multiple language types. Each game nickname in each of the game nickname datasets corresponds to a category label. The category labels include: gender label, style label, language type label, and domain label. The construction process of the multilingual game nickname database is as follows: each language type is taken as the current language type, and a basic game nickname dataset corresponding to the current language type is constructed; each... Each game nickname is input into a preset nickname category recognition model for prediction, resulting in a category label for each nickname. A game nickname dataset corresponding to the current language type is constructed based on the game nicknames labeled with category labels. The steps for constructing the basic game nickname dataset corresponding to the current language type include: obtaining the language text corresponding to the current language type; performing entity recognition on the language text to obtain entity recognition results; wherein the entity recognition results include: entity content and entity category; extracting entity content representing the person's name from the entity recognition results; and constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content. Determine whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; If so, perform a big data search based on the game nickname to be recommended, and determine the content used to represent the source of the game nickname to be recommended based on the search results; The content, along with the game nickname to be recommended, will be returned to the client.

2. The method according to claim 1, characterized in that, Before the step of constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content, the following steps are also included: Perform preset filtering operations on the extracted entity content.

3. The method according to claim 1, characterized in that, The training process of the nickname category recognition model is as follows: Obtain the model training sample set corresponding to the current language type; the samples in the model training sample set include game nicknames labeled with category tags; The preset BERT model is trained using samples from the model training sample set to obtain the nickname category recognition model.

4. The method according to claim 1, characterized in that, The method further includes: Get the currently used game nickname; Filter out the used game nicknames from the multilingual game nickname database to determine the number of unused game nicknames in the multilingual game nickname database; Determine whether the number of unused game nicknames is less than a threshold; if so, update the multilingual game nickname database based on the game nicknames with pre-labeled category tags.

5. A method for recommending game nicknames, characterized in that, The method is applied to a client, and the method includes: A game nickname recommendation request is sent to the server, so that the server can retrieve the recommended game nicknames corresponding to the nickname requirement parameters from a preset multilingual game nickname database based on the nickname requirement parameters carried in the request. The request carries nickname requirement parameters, which include: gender, style, language type, domain, and number of nicknames. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each dataset has a corresponding category label, which includes: gender, style, language type, and domain labels. The construction process of the multilingual game nickname database is as follows: each language type is used as the current language type. The process of constructing a basic game nickname dataset corresponding to the current language type includes: inputting each game nickname in the basic game nickname dataset into a preset nickname category recognition model for prediction to obtain a category label corresponding to each game nickname; constructing a game nickname dataset corresponding to the current language type based on the game nicknames labeled with category labels; and constructing a basic game nickname dataset corresponding to the current language type based on the extracted entity content. Determine whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; If so, perform a big data search based on the game nickname to be recommended, and determine the content used to represent the source of the game nickname to be recommended based on the search results; Receive the content returned by the server and the game nickname to be recommended.

6. The method according to claim 5, characterized in that, The client provides a nickname creation interface; Before sending a game nickname recommendation request to the server, the process also includes: In response to the user's parameter selection operation in the nickname creation interface, a game nickname recommendation request is generated based on the nickname requirement parameters corresponding to the parameter selection operation.

7. A device for recommending game nicknames, characterized in that, The device is used in a server, and the device includes: The request receiving module is used to receive game nickname recommendation requests sent by the client; the request carries nickname requirement parameters; the nickname requirement parameters include: gender parameter, style parameter, language type parameter, domain parameter, and number of nicknames parameter; The nickname retrieval module is used to retrieve game nicknames corresponding to the nickname requirement parameters carried in the request from a preset multilingual game nickname database. The multilingual game nickname database stores game nickname datasets corresponding to multiple language types. Each game nickname in each of the game nickname datasets corresponds to a category label. The category labels include: gender label, style label, language type label, and domain label. The construction process of the multilingual game nickname database is as follows: Each language type is taken as the current language type, and a basic game nickname dataset corresponding to the current language type is constructed; the basic game nickname dataset... Each game nickname in the dataset is input into a preset nickname category recognition model for prediction, resulting in a category label for each nickname. A game nickname dataset corresponding to the current language type is constructed based on the game nicknames labeled with category labels. The steps for constructing the basic game nickname dataset corresponding to the current language type include: obtaining the language text corresponding to the current language type; performing entity recognition on the language text to obtain entity recognition results; wherein the entity recognition results include: entity content and entity category; extracting entity content representing the person's name from the entity recognition results; and constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content. The nickname recommendation module is used to determine whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, it performs a big data search based on the game nickname to be recommended, and determines the content used to represent the source of the game nickname to be recommended based on the search results; and returns the content and the game nickname to be recommended together to the client.

8. A device for recommending game nicknames, characterized in that, The device is used on a client side, and the device includes: A request sending module is used to send a game nickname recommendation request to the server, so that the server can retrieve the recommended game nicknames corresponding to the nickname requirement parameters from a preset multilingual game nickname database based on the nickname requirement parameters carried in the request. The request carries nickname requirement parameters, which include: gender parameters, style parameters, language type parameters, domain parameters, and number of nicknames. The multilingual game nickname database stores multiple game nickname datasets corresponding to different language types. Each game nickname in each dataset corresponds to a category label, which includes: gender label, style label, language type label, and domain label. The construction process of the multilingual game nickname database is as follows: each language type is used as the current... The process involves several steps: First, constructing a basic game nickname dataset corresponding to the current language type. Second, inputting each game nickname from the basic game nickname dataset into a preset nickname category recognition model for prediction, obtaining a category label for each game nickname. Third, constructing a game nickname dataset corresponding to the current language type based on the game nicknames labeled with category labels. The steps for constructing the basic game nickname dataset corresponding to the current language type include: acquiring language text corresponding to the current language type; performing entity recognition on the language text to obtain entity recognition results; wherein the entity recognition results include: entity content and entity category; extracting entity content representing the person's name from the entity recognition results; and constructing the basic game nickname dataset corresponding to the current language type based on the extracted entity content. The nickname receiving module is used to determine whether the category tag corresponding to the game nickname to be recommended includes a preset domain tag; if so, it performs a big data search based on the game nickname to be recommended, and determines the content used to represent the source of the game nickname to be recommended based on the search results; and receives the content returned by the server along with the game nickname to be recommended.

9. A game nickname recommendation system, characterized in that, The system includes a server and a client, the server being communicatively connected to the client; the server is used to perform the method as described in any one of claims 1-4; the client is used to perform the method as described in any one of claims 5-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method described in any one of claims 1 to 4.

Images