Game nickname recommendation method and device, electronic equipment and storage medium

Abstract

The application provides a game nickname recommendation method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining a target game nickname and attribute information corresponding to the target game nickname; determining a target partition database corresponding to the target game nickname from a nickname feature database according to the attribute information; wherein the nickname feature database comprises a plurality of partition databases divided according to game nickname types, and each partition database comprises a feature vector corresponding to a plurality of alternative game nicknames; determining a target feature vector corresponding to the target game nickname from the target partition database, and determining a target alternative game nickname to be recommended based on the target feature vector; and recommending the target alternative game nickname. Therefore, the user can be accurately recommended an alternative game nickname meeting the expectation, and the efficiency of game nickname recommendation is further improved by partitioning the database storing the feature vectors corresponding to the alternative game nicknames.

Description

Technical Field

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

[0002] This section is intended to provide background or context for the embodiments of this application as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0003] When users experience a new game, they typically need to set a nickname, which acts as an identity ID for user identification. To differentiate between different players, game operators usually restrict the uniqueness of nicknames within the same server. Therefore, setting a desirable nickname is often a very difficult process. Currently, relevant technical solutions mainly involve two methods: user-defined nicknames and randomly recommended nicknames. However, both methods require users to go through a lot of trials to select a suitable nickname, which is not only inefficient but also detracts from the user experience. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, device, electronic device and storage medium for recommending game nicknames.

[0005] To achieve the above objectives, this application provides a method for recommending game nicknames, including:

[0006] Obtain the target game nickname and the attribute information corresponding to the target game nickname:

[0007] Based on the attribute information, a target partition database corresponding to the target game nickname is determined from the nickname feature database; wherein, the nickname feature database includes multiple partition databases divided according to game nickname type, and each partition database includes feature vectors corresponding to multiple candidate game nicknames;

[0008] The target feature vector corresponding to the target game nickname is determined from the target partition database, and the target candidate game nicknames to be recommended are determined based on the target feature vector.

[0009] Recommended alternative game nicknames for the target.

[0010] Based on the same inventive concept, an exemplary embodiment of this application also provides a game nickname recommendation device, including:

[0011] The acquisition module retrieves the target game nickname and the attribute information corresponding to the target game nickname:

[0012] The first determining module determines the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information; wherein, the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames;

[0013] The second determining module determines the target feature vector corresponding to the target game nickname from the target partition database, and determines the target candidate game nicknames to be recommended based on the target feature vector;

[0014] The recommendation module recommends candidate game nicknames for the target.

[0015] Based on the same inventive concept, an exemplary embodiment of this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the program to implement the game nickname recommendation method as described above.

[0016] Based on the same inventive concept, an exemplary embodiment of this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the game nickname recommendation method as described above.

[0017] As can be seen from the above, the game nickname recommendation method, device, electronic device, and storage medium provided in this application obtain a target game nickname and the attribute information corresponding to the target game nickname: Based on the attribute information corresponding to the target game nickname, a target partition database corresponding to the target game nickname is determined from a nickname feature database; wherein, the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames; a target feature vector corresponding to the target game nickname is determined from the target partition database, and a target candidate game nickname to be recommended is determined based on the target feature vector; the target candidate game nickname is recommended, thereby accurately recommending candidate game nicknames that meet the user's expectations. Furthermore, by partitioning the database storing the feature vectors corresponding to the candidate game nicknames, the efficiency of game nickname recommendation is further improved. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating one application scenario of an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating a method for recommending game nicknames according to an embodiment of this application.

[0021] Figure 3 This is a schematic diagram illustrating the process of constructing a game nickname database according to an embodiment of this application;

[0022] Figure 4 This is a flowchart illustrating another method for recommending game nicknames according to an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the structure of a game nickname recommendation device according to an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the structure of a specific electronic device according to an embodiment of this application. Detailed Implementation

[0025] The principles and spirit of this application will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement this application, and are not intended to limit the scope of this application in any way. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0026] According to embodiments of this application, a method, system, electronic device, and storage medium for recommending game nicknames are proposed.

[0027] In this article, it is important to understand that any number of elements in the accompanying figures is for illustrative purposes and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0028] The principles and spirit of this application will be explained in detail below with reference to several representative embodiments. Invention Overview

[0030] Currently, relevant technical solutions mainly use two methods to set game nicknames for users: user-defined nicknames and randomly recommended nicknames. However, both methods require users to go through a lot of trials to select a suitable nickname, which is not only inefficient but also detracts from the user experience.

[0031] To address the aforementioned issues, this application provides a method for recommending game nicknames, specifically including:

[0032] The process involves: obtaining the target game nickname and its corresponding attribute information; determining the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information; wherein the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames; determining the target feature vector corresponding to the target game nickname from the target partition database, and determining the target candidate game nicknames to be recommended based on the target feature vectors; recommending the target candidate game nicknames, thereby accurately recommending candidate game nicknames that meet the user's expectations based on the target game nickname. Furthermore, by partitioning the database storing the feature vectors corresponding to the candidate game nicknames, the efficiency of game nickname recommendation is further improved.

[0033] After introducing the basic principles of this application, the various non-limiting embodiments of this application will be described in detail below.

[0034] Application Scenarios Overview

[0035] In specific application scenarios, the game nickname recommendation method of this application can be applied to various platforms or systems involving game nickname recommendation. As an example, this application scenario includes at least one server and at least one terminal. (Reference) Figure 1 This diagram illustrates an application scenario of a game nickname recommendation method provided by an exemplary embodiment of this disclosure. The application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, server 102, and data storage system 103 can all be connected via wired or wireless communication networks. Terminal devices include, but are not limited to, desktop computers, mobile phones, mobile computers, tablets, media players, smart wearable devices, personal digital assistants (PDAs), or other electronic devices capable of performing the aforementioned functions. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server and the terminal can communicate via a network to transmit data. The network can be a wired network or a wireless network; this application does not specifically limit its use.

[0036] The server can be a server that provides various services. Specifically, the server can be used to provide background services for applications running on the terminal. Optionally, in some implementations, the game nickname recommendation method provided in this application embodiment can be executed by the terminal device. Optionally, in some implementations, the game nickname recommendation method provided in this application embodiment can be executed by the server. The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software programs or software modules (e.g., software programs or software modules used to provide distributed services), or it can be implemented as a single software program or software module. This application embodiment does not specifically limit this.

[0037] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can be any network, including but not limited to local area networks (LANs), metropolitan area networks (MANs), wide area networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including Hypertext Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPsec) can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0038] The data storage system stores a large amount of data. Optionally, the data storage system can partition the data according to different uses and data types. The data sources include, but are not limited to, existing databases, data crawled from the Internet, or data uploaded by users when using client applications.

[0039] The following describes a method for recommending game nicknames according to an exemplary embodiment of this application, using specific application scenarios. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0040] Exemplary methods

[0041] refer to Figure 2 This application provides a method for recommending game nicknames. The execution entity of this game nickname recommendation method may be, but is not limited to, a server or a terminal device. The method includes the following steps:

[0042] S101, Obtain the target game nickname and the attribute information corresponding to the target game nickname.

[0043] In practice, the target game nickname can be a custom nickname entered by the user, and the corresponding attribute information can be relevant attribute parameters of the game nickname that the user wishes to set. This attribute information can be used to better recommend game nicknames to the user. Optionally, the attribute information can be obtained through user input or based on information provided by the user; there is no limitation on this.

[0044] In some embodiments, in order to provide users with more accurate game nickname recommendation services, the target game nickname and the attribute information corresponding to the target game nickname can be obtained after the user inputs that the target game nickname is unavailable.

[0045] In some embodiments, the attribute information includes style information and gender information of the target game nickname. Optionally, the attribute information may also include other information corresponding to the target game nickname, and there is no limitation thereto.

[0046] S102, based on the attribute information, determine the target partition database corresponding to the target game nickname from the nickname feature database; wherein, the nickname feature database includes multiple partition databases divided according to the game nickname type, and each partition database includes feature vectors corresponding to multiple candidate game nicknames.

[0047] In practice, after obtaining the target game nickname and attribute information, to reduce the data range for recommended game nicknames, a target partition database corresponding to the target game nickname is determined from the nickname feature database based on the attribute information. It should be noted that the nickname feature database includes multiple partition databases divided according to game nickname types; that is, the nickname feature data includes multiple partition databases, each corresponding to a game nickname type. Optionally, game nickname types can be divided using different attribute information. It should also be noted that the various partition databases within the nickname feature database store the feature vectors of the game nicknames, not the game nicknames themselves. This eliminates the need to re-obtain the feature vectors corresponding to the game nickname each time a match is made with a target game nickname, further improving the efficiency of game nickname recommendation.

[0048] In some embodiments, before determining the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information, the method further includes:

[0049] Multiple candidate game nicknames are obtained, and the nickname classification model obtained through training is used to classify the multiple candidate game nicknames to obtain the type of each candidate game nickname;

[0050] The multiple candidate game nicknames are encoded to obtain a feature vector corresponding to each candidate game nickname;

[0051] The feature vectors corresponding to the candidate game nicknames of the same type are saved to the same partition database.

[0052] In practice, multiple unlabeled candidate game nicknames are first obtained. Then, a trained nickname classification model is used to classify these nicknames, resulting in a category for each nickname, thus generating multiple candidate game nicknames with category labels. Optionally, the training process for the nickname classification model can refer to the training process in related technologies, and is not limited thereto. In some embodiments, a fine-tuning method is used, loading the game nicknames with category labels into a pre-trained model. During backpropagation, the weights and biases of the algorithm model are continuously adjusted to adapt the model to a custom game nickname dataset, resulting in a nickname classification model. When encoding multiple candidate game nicknames, embedding technology can be used. Embedding is a technique that converts discrete symbols (such as words, tags, etc.) into continuous vectors. Encoding using embedding technology helps the model better understand the relationships between words, improving the model's accuracy and generalization ability. Optionally, BERT can be used as a vector encoder for embedding encoding to encode candidate game nicknames with category identifiers into fixed-length feature vectors. In some embodiments, the open-source bert-as-service can be used to provide vector encoding services, and the BERT-base Chinese model can be used as the base BERT model, resulting in a 768-dimensional feature vector after encoding. After obtaining the feature vector corresponding to each candidate game nickname, the feature vectors corresponding to candidate game nicknames of the same type are saved to the same partitioned database.

[0053] S103, determine the target feature vector corresponding to the target game nickname from the target partition database, and determine the target candidate game nicknames to be recommended based on the target feature vector.

[0054] In practice, after determining the target partition database, the target feature vector corresponding to the target game nickname is first determined from the target partition database, and then the target candidate game nicknames to be recommended are determined based on the target feature vector.

[0055] S104, Recommend the target alternative game nicknames.

[0056] In practice, after identifying the target candidate game nicknames, these target candidate game nicknames will be recommended. It should be noted that there can be one or more target candidate game nicknames; there is no limitation on this.

[0057] In some embodiments, determining the target feature vector corresponding to the target game nickname from the target partition database specifically includes:

[0058] The target game nickname is encoded to obtain the feature vector of the target game nickname;

[0059] The target feature vector is determined based on the feature vector of the target game nickname and the feature vector corresponding to each candidate game nickname in the target partition database.

[0060] In specific implementation, when determining the target feature vector corresponding to the target game nickname, the target game nickname can be encoded first to obtain its feature vector. Optionally, the encoding process for the target game nickname can be similar to that for the candidate game nicknames, which will not be elaborated further. After obtaining the feature vector of the target game nickname, the target feature vector can be determined by comparing its distance to the feature vectors corresponding to each candidate game nickname in the target partition database. Optionally, the distances between the feature vectors corresponding to each candidate game nickname and the feature vector of the target game nickname can be sorted first, and then the feature vectors corresponding to the candidate game nicknames whose distances fall within a preset range can be determined as the target feature vectors.

[0061] In some embodiments, the target feature vector is determined based on the feature vector of the target game nickname and the feature vector corresponding to each candidate game nickname in the target partition database, specifically including:

[0062] Obtain all feature vectors from the target partition database, and cluster all feature vectors to obtain multiple sets of feature vectors.

[0063] Determine the cluster center for each set of feature vectors;

[0064] Based on the cluster centers of each set of feature vectors, a target set of feature vectors that matches the feature vector of the target game nickname is determined from the multiple sets of feature vectors.

[0065] The target feature vector is determined based on the distance between each feature vector in the target group feature vector set and the feature vector of the target game nickname.

[0066] In practical implementation, considering that even a single partition contains a massive amount of data, directly traversing every feature vector in the partition database to determine the target feature vector is not only inefficient but also wastes computational resources. To further improve the efficiency of determining the target feature vector, all feature vectors in the same partition database can be clustered to obtain multiple sets of feature vectors. Then, the cluster center of each set of feature vectors is determined, and the target set of feature vectors matching the target game nickname is determined based on the distance between the cluster center of each set of feature vectors and the feature vector of the target game nickname. Optionally, the specific clustering method can refer to relevant clustering methods and is not limited thereto; for example, the K-means clustering algorithm can be used. After determining the target set of feature vectors, the target feature vector can be determined simply by the distance between each feature vector in the target set and the feature vector of the target game nickname. Optionally, feature vectors whose distance to the feature vector of the target game nickname is within a preset range can be directly determined as target feature vectors. It should be noted that the target group feature vector set can be multiple sets or a single set, without any limitation.

[0067] In some embodiments, determining a target set of feature vectors that matches the feature vector of the target game nickname from the multiple sets of feature vectors based on the cluster centers of each set of feature vectors specifically includes:

[0068] Determine the cluster center of each feature vector set and the target distance between the feature vector of the target game nickname:

[0069] Sort all the target distances in ascending order of distance, and determine the target distances that fall within the preset ranking range;

[0070] The target group feature vector set is determined from the multiple sets of feature vector sets based on the target distance that falls within the preset ranking range.

[0071] In practice, considering that a larger proportion of the identified target group feature vector set to all feature vector sets results in a higher recall rate, but a lower efficiency in determining the target feature vectors, a strategy is adopted to balance recall and efficiency. First, the cluster centers of multiple feature vector sets are sorted according to their target distances to the target game nickname, from largest to smallest. Then, target distances within a preset ranking range are selected, and one or more feature vector sets corresponding to these target distances are defined as the target group feature vector set. It should be noted that the preset ranking range can be set as needed and is not limited; for example, it can be set to the top three.

[0072] In some embodiments, the step of determining the preset ranking range includes:

[0073] Obtain the total number of all feature vectors in the target partition database;

[0074] The preset ranking range is determined based on the total number.

[0075] In practice, when determining the preset ranking range, it can be based on the total number of feature vectors in the target partitioning database. Generally, the larger the total number, the smaller the corresponding preset ranking range. Optionally, in some embodiments, the preset ranking range can also be determined by the total number of multiple feature vector sets and the total number of feature vectors in the target partitioning database. Optionally, the ratio of the total number to the total number of sets can be calculated, and the larger the ratio, the smaller the corresponding preset ranking range.

[0076] In some embodiments, before recommending the target candidate game nicknames, the method further includes:

[0077] Retrieve the dataset of game nicknames that are already in use;

[0078] The Bloom filter is used to determine whether the target candidate game nicknames overlap with game nicknames in the already occupied game nicknames dataset;

[0079] In response to the overlap between the target candidate game nickname and the game nickname in the already occupied game nickname dataset, the overlapping target candidate game nickname is deleted.

[0080] In practical implementation, to avoid recommending game nicknames that may be duplicated by other users, a Bloom filter can be used to check for duplicate target game nicknames and delete those that are duplicated. Using a Bloom filter method can complete the deduplication of game nicknames with a small memory footprint and in a short time. Although there is a certain false positive rate, it is limited to misclassifying elements that do not exist in the set as if they do. Elements judged not to exist in the set are indeed not in the set, thus satisfying the requirement of deduplication of game nicknames and ensuring the uniqueness of the returned game nicknames. This effectively solves the problem of low efficiency in deduplicating massive amounts of game nickname data. Optionally, when obtaining the dataset of occupied game nicknames, occupied (used) game nicknames can be obtained by collecting user logs. User logs can be collected in real time or periodically as needed; there is no limitation on this.

[0081] In some embodiments, determining the target candidate game nicknames to be recommended based on the target feature vector specifically includes:

[0082] Obtain the target nickname ID corresponding to the target feature vector in the target partition database: wherein, each partition database also includes the nickname ID corresponding to each candidate game nickname;

[0083] The target candidate game nickname is determined from the candidate nickname database based on the target nickname ID; wherein the candidate nickname database includes multiple candidate game nicknames and a nickname ID corresponding to each candidate game nickname.

[0084] In practical implementation, to more accurately determine the target candidate game nicknames, this embodiment stores the candidate game nicknames and their corresponding feature vectors in different databases. Simultaneously, it matches the candidate game nicknames with their corresponding feature vectors using a set nickname ID. (Reference) Figure 3 After collecting unlabeled game nicknames, they are first stored in a basic game nickname dataset. Then, a trained classification model is used to classify these unlabeled nicknames, resulting in a game nickname dataset with category identifiers. By inserting an ID (nickname ID) into each nickname in this dataset, game nicknames with both IDs and category identifiers are obtained and saved to the game nickname database. An encoder encodes each nickname in the dataset to obtain a feature vector. A corresponding ID is then inserted into each feature vector, and the feature vectors with inserted IDs are stored in the corresponding partition of the feature vector database according to their category identifiers. This allows the data in the feature vector database and the game nickname database to be linked through IDs.

[0085] refer to Figure 4This is a flowchart illustrating another method for recommending game nicknames according to an embodiment of this application. When creating a game nickname, a user can customize the target game nickname and set attribute information, such as gender and style. Then, the input target game nickname is encoded by an encoder, converting it into a feature vector of size 1*768. Based on the gender, style, and other attribute information, a target partition database is determined. Vector similarity is searched in the target partition database of the feature vector database to find the IDs corresponding to the top k most similar target feature vectors. The corresponding target candidate game nicknames are then found in the game nickname database, resulting in a target candidate game nickname dataset. Next, a nickname Bloom filter is used to remove duplicate target candidate game nicknames from the dataset. Finally, the deduplicated target candidate game nicknames that are unique, specify gender and style, and semantically similar to the user's custom nickname are recommended to the player. When a player's desired nickname is already registered or contains special characters or sensitive words, this game nickname recommendation method can help obtain a game nickname that highly matches their desired nickname.

[0086] This application provides a method for recommending game nicknames, which involves obtaining a target game nickname and its corresponding attribute information: determining a target partition database corresponding to the target game nickname from a nickname feature database based on the attribute information; wherein the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames; determining the target feature vector corresponding to the target game nickname from the target partition database, and determining the target candidate game nicknames to be recommended based on the target feature vectors; recommending the target candidate game nicknames, thereby accurately recommending candidate game nicknames that meet the user's expectations. Furthermore, by partitioning the database storing the feature vectors corresponding to the candidate game nicknames, the efficiency of game nickname recommendation is further improved.

[0087] Exemplary device

[0088] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a game nickname recommendation device.

[0089] refer to Figure 5 The game nickname recommendation device includes:

[0090] Module 201 acquires the target game nickname and the attribute information corresponding to the target game nickname:

[0091] The first determining module 202 determines the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information; wherein, the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames;

[0092] The second determining module 203 determines the target feature vector corresponding to the target game nickname from the target partition database, and determines the target candidate game nicknames to be recommended based on the target feature vector;

[0093] Recommendation module 204 recommends the target candidate game nicknames.

[0094] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0095] The system described in the above embodiments is used to implement the corresponding game nickname recommendation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0096] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the game nickname recommendation method described in any of the above embodiments.

[0097] Figure 6 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0098] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0099] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0100] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0101] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0102] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0103] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0104] The electronic devices described above are used to implement the corresponding game nickname recommendation method in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0105] Exemplary program product

[0106] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the game nickname recommendation method as described in any of the above embodiments.

[0107] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0108] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the game nickname recommendation method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0109] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a computer program product, which includes a computer program. In some embodiments, the computer program is executed by one or more processors to cause the processors to perform the game nickname recommendation method described in the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0110] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0111] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0112] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0113] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A method for recommending game nicknames, characterized in that, include: Obtain the target game nickname and the attribute information corresponding to the target game nickname: Based on the attribute information, a target partition database corresponding to the target game nickname is determined from the nickname feature database; wherein, the nickname feature database includes multiple partition databases divided according to game nickname type, and each partition database includes feature vectors corresponding to multiple candidate game nicknames; The target game nickname is encoded to obtain a feature vector of the target game nickname; based on the feature vector of the target game nickname and the feature vector corresponding to each candidate game nickname in the target partition database, a target feature vector corresponding to the target game nickname is determined; and based on the target feature vector, a target candidate game nickname to be recommended is determined. Recommended alternative game nicknames for the target.

2. The method according to claim 1, characterized in that, Based on the feature vector of the target game nickname and the feature vector corresponding to each candidate game nickname in the target partition database, the target feature vector is determined, specifically including: Obtain all feature vectors from the target partition database, and cluster all feature vectors to obtain multiple sets of feature vectors. Determine the cluster center for each set of feature vectors; Based on the cluster centers of each set of feature vectors, a target set of feature vectors that matches the feature vector of the target game nickname is determined from the multiple sets of feature vectors. The target feature vector is determined based on the distance between each feature vector in the target group feature vector set and the feature vector of the target game nickname.

3. The method according to claim 2, characterized in that, Based on the cluster centers of each set of feature vectors, a target set of feature vectors matching the feature vector of the target game nickname is determined from the multiple sets of feature vectors. Specifically, this includes: Determine the cluster center of each feature vector set and the target distance between the feature vector of the target game nickname: Sort all the target distances in ascending order of distance, and determine the target distances that fall within the preset ranking range; The target group feature vector set is determined from the multiple sets of feature vector sets based on the target distance that falls within the preset ranking range.

4. The method according to claim 3, characterized in that, The step of determining the preset ranking range includes: Obtain the total number of all feature vectors in the target partition database; The preset ranking range is determined based on the total number.

5. The method according to claim 1, characterized in that, Before recommending the target candidate game nicknames, the method further includes: Retrieve the dataset of game nicknames that are already in use; The Bloom filter is used to determine whether the target candidate game nicknames overlap with game nicknames in the already occupied game nicknames dataset; In response to the overlap between the target candidate game nickname and the game nickname in the already occupied game nickname dataset, the overlapping target candidate game nickname is deleted.

6. The method according to claim 1, characterized in that, Based on the target feature vector, the target candidate game nicknames to be recommended are determined, specifically including: Obtain the target nickname ID corresponding to the target feature vector in the target partition database: wherein, each partition database also includes the nickname ID corresponding to each candidate game nickname; The target candidate game nickname is determined from the candidate nickname database based on the target nickname ID; wherein the candidate nickname database includes multiple candidate game nicknames and a nickname ID corresponding to each candidate game nickname.

7. The method according to claim 1, characterized in that, Before determining the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information, the method further includes: Multiple candidate game nicknames are obtained, and the nickname classification model obtained through training is used to classify the multiple candidate game nicknames to obtain the type of each candidate game nickname; The multiple candidate game nicknames are encoded to obtain a feature vector corresponding to each candidate game nickname; The feature vectors corresponding to the candidate game nicknames of the same type are saved to the same partition database.

8. The method according to claim 1, characterized in that, The attribute information includes the style information and gender information of the target game nickname.

9. A device for recommending game nicknames, characterized in that, include: The acquisition module retrieves the target game nickname and the attribute information corresponding to the target game nickname: The first determining module determines the target partition database corresponding to the target game nickname from the nickname feature database based on the attribute information; wherein, the nickname feature database includes multiple partition databases divided according to game nickname types, and each partition database includes feature vectors corresponding to multiple candidate game nicknames; The second determining module encodes the target game nickname to obtain a feature vector of the target game nickname; based on the feature vector of the target game nickname and the feature vector corresponding to each candidate game nickname in the target partition database, it determines the target feature vector corresponding to the target game nickname; and based on the target feature vector, it determines the target candidate game nicknames to be recommended. The recommendation module recommends candidate game nicknames for the target.

10. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the method according to any one of claims 1 to 8.

Images