Game nickname automatic generation method based on AI model and terminal
Through the AI model-based method, keyword extraction and combination of player behavior records is used to generate personalized game nicknames, which solves the problem of insufficient player satisfaction in the existing technology, and realizes automatic generation and personalized customization of game nicknames.
Patent Information
- Application Number
- CN202311106412.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-30
- Publication Date
- 2025-03-04
AI Technical Summary
The existing game nickname automation generation methods cannot be customized for players, resulting in insufficient player satisfaction.
Using an AI model-based method, keyword extraction and combination of players' behavior records during the game process, multiple game nicknames are randomly generated, and duplicate nicknames are eliminated, and finally pushed to players for selection.
It realizes automatic generation and personalized customization of game nicknames, improving player satisfaction.
Smart Images
Figure CN119548833A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of game design, and in particular to a method and a terminal for automatically generating game nicknames based on an AI model. Background Art
[0002] Game nicknames are very diverse and depend on the game itself, but when players create game characters, they often face the problem of naming, such as duplicate game names, being dissatisfied with the names they choose, etc.
[0003] Some players want a perfect nickname, while others look for a nickname to show off their strengths. Automatic nickname generation is designed to provide gamers with cool nicknames and improve the gaming experience. This design not only solves this problem for players, but also adds some fun to the game with interesting names. Currently, the automatic naming on the market mainly uses an existing name library to read the name library for random generation, which cannot be customized for players, resulting in insufficient player satisfaction. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a method and terminal for automatically generating game nicknames based on an AI model, which can automatically generate personalized game nicknames for players and improve player satisfaction.
[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:
[0006] A method for automatically generating game nicknames based on an AI model, comprising the steps of:
[0007] S1. Based on the player's behavior records during the game, keywords are extracted from the behavior records, and then keywords are combined through AI to randomly generate multiple game nicknames;
[0008] S2, comparing the names already existing in the database with each of the randomly generated game nicknames, and eliminating duplicate game nicknames;
[0009] S3. Push the remaining game nicknames in sequence to the player for selection.
[0010] In order to solve the above technical problems, another technical solution adopted by the present invention is:
[0011] A terminal for automatically generating game nicknames based on an AI model comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When executing the computer program, the processor implements the steps in the method for automatically generating game nicknames based on an AI model as described above.
[0012] The beneficial effect of the present invention is that the present invention provides a method and terminal for automatically generating game nicknames based on an AI model, which extracts keywords from the game behavior records of players, then uses AI to combine keywords to randomly generate multiple game nicknames that meet the preferences of players, and then removes the same game nicknames in the database, and then recommends the generated game nicknames to the players for selection in turn, thereby realizing automatic generation of game nicknames and personalized generation of game nicknames based on the preferences of players to meet the needs of players and improve player satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 This is a main flow chart of a method for automatically generating game nicknames based on an AI model according to an embodiment of the present invention;
[0014] Figure 2 A specific flow chart of a method for automatically generating game nicknames based on an AI model according to an embodiment of the present invention;
[0015] Figure 3 A schematic diagram of the structure of a terminal for automatically generating game nicknames based on an AI model.
[0016] Description of labels:
[0017] 1. A terminal for automatically generating game nicknames based on an AI model; 2. Memory; 3. Processor. DETAILED DESCRIPTION
[0018] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.
[0019] Please refer to Figure 1 and Figure 2 , a method for automatically generating game nicknames based on an AI model, comprising the steps of:
[0020] S1. Based on the player's behavior records during the game, keywords are extracted from the behavior records, and then keywords are combined through AI to randomly generate multiple game nicknames;
[0021] S2, comparing the names already existing in the database with each of the randomly generated game nicknames, and eliminating duplicate game nicknames;
[0022] S3. Push the remaining game nicknames in sequence to the player for selection.
[0023] From the above description, it can be seen that the beneficial effect of the present invention is that: by extracting keywords from the player's game behavior records, and then using AI to combine keywords to randomly generate multiple game nicknames that meet the player's preferences, and then after eliminating the same game nicknames in the database, the generated game nicknames are recommended to the player for selection in turn, while realizing the automatic generation of game nicknames, and at the same time, the game nicknames can be personalized based on the player's preferences to meet the needs of the player and improve the player's satisfaction.
[0024] Furthermore, the behavior record includes:
[0025] The game scenes frequently visited by the player in the games the player has played in the past, the player's main online time, the game function modules that the player is good at, the animals and plants that the player often comes into contact with, and the player's registration information, which includes the player's constellation, zodiac sign and hometown.
[0026] From the above description, it can be seen that the behavior records are obtained from some behavioral habits of players in historical games. By extracting keywords from these behavior records, the game nicknames automatically generated by AI are personalized based on the game habits of different players, reducing the probability that players are dissatisfied with the generated game nicknames.
[0027] Furthermore, the behavior record also includes game data homophonic puns:
[0028] The game data homophonic puns are obtained by obtaining homophones or near-homophones of names given by players to game equipment, monsters, NPCs, scenes and maps in games that the players have played in the past.
[0029] From the above description, we can see that players sometimes name the equipment, monsters, NPCs, scenes and maps in the game by themselves. In order to increase the diversity of game nickname generation, the behavior records can also be the homophonic puns of these names, and the keywords of the homophonic puns can be extracted as the basis for the subsequent AI automatic generation of game nicknames.
[0030] Furthermore, before the keyword combination is performed by AI in step S1, the method further includes:
[0031] The extracted keywords are subjected to behavioral expansion, specifically:
[0032] The keywords are labeled, and behavior expansion is performed using synonym replacement, grammar rule replacement combination, text AI generation, word vector similarity and word sense disambiguation.
[0033] From the above description, it can be seen that the behavior expansion of keywords can further improve the diversity of subsequent game nickname generation and increase the choices of players.
[0034] Furthermore, the keyword combination is performed by AI in step S1, specifically:
[0035] Based on the world view and mission scenarios of the new game, each keyword is weighted and scored, and a plurality of game nicknames are obtained by combining them according to the scores.
[0036] From the above description, it can be seen that the game nickname is generated by combining the weights of the keywords, thereby ensuring that the generated game nickname can better meet the preferences of the players.
[0037] Furthermore, before step S1, the following steps are also included:
[0038] S0. Obtaining the game registration information of the player, and analyzing the player's preferred nickname type in combination with a pre-issued questionnaire, wherein the game registration information includes the player's gender, the player's age, and the game character selected by the player.
[0039] From the above description, it can be seen that in order to make the subsequently generated game nicknames more in line with the player's preferences, the player's initial preferences can be obtained by obtaining the player's game registration information and conducting a questionnaire survey to analyze the player's favorite nickname types.
[0040] Furthermore, the step S0 is specifically as follows:
[0041] S01. Obtaining game registration information of players through questionnaires or database retrieval, classifying player samples according to the game registration information, obtaining various types of players of different genders, different age groups and different game roles, and obtaining questionnaire survey results of various types of players, wherein the questionnaire survey results include favorite game types, hobbies and interests in games, and game time;
[0042] S02. Conduct characteristic behavior analysis on the questionnaire survey results of various types of players;
[0043] S03. Conduct preliminary reason analysis on the questionnaire survey results of various players;
[0044] S04. Conduct credibility analysis on the questionnaire survey results of various types of players;
[0045] S05. Combining the characteristic behavior analysis, the preceding cause analysis and the credibility analysis, obtain the favorite nickname types of various players.
[0046] Furthermore, the characteristic behavior analysis is specifically as follows:
[0047] Analyze the distribution of the interests and hobbies of various types of players to obtain the most important interests and hobbies of various types of players;
[0048] The preceding cause analysis is specifically as follows:
[0049] A scale chart is formed according to the game time of each type of player, and each time and its corresponding game item are recorded in multiple dimensions;
[0050] The credibility analysis is specifically as follows:
[0051] The credibility of the questionnaire is obtained by combining the repetition rate and abnormal answer rate of each type of players in the questionnaire.
[0052] From the above description, it can be seen that players are classified according to their game registration information, and then the game types, interests and hobbies in the game, and game time filled in by the players in the questionnaire are analyzed to analyze the characteristic behaviors, preconditions and credibility of the questionnaire, so as to accurately determine the preferred nickname types of each type of players.
[0053] Furthermore, the step S3 is specifically as follows:
[0054] The desired nickname type is matched according to the player's type, and the game nicknames that meet the desired nickname type are screened from the game nicknames that have been duplicated and pushed to the player for selection.
[0055] From the above description, it can be seen that the game nicknames after the duplicates are eliminated are screened to select game nicknames that meet the players' favorite nickname types and then provide them for the players to choose in turn, further ensuring that the players choose the most satisfactory game nickname.
[0056] Please refer to Figure 3 , a terminal for automatically generating game nicknames based on an AI model, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the method for automatically generating game nicknames based on an AI model as described above when executing the computer program.
[0057] From the above description, it can be seen that the beneficial effects of the present invention are: based on the same technical concept, in conjunction with the above-mentioned method of making an entity perform robot actions, a terminal for automatically generating game nicknames based on an AI model is provided, which extracts keywords from the player's game behavior records, and then uses AI to combine keywords to randomly generate multiple game nicknames that meet the player's preferences. After eliminating the same game nicknames in the database, the generated game nicknames are recommended to the player for selection in turn, thereby realizing the automatic generation of game nicknames and, at the same time, generating personalized game nicknames based on the player's preferences to meet the player's needs and improve player satisfaction.
[0058] The present invention provides an AI model-based automatic game nickname generation method and terminal, which are applied to the scenario where a player needs to create a new character name when opening a new game or re-creating a game account. The method automatically generates a game nickname that meets the player's preferences for the player to choose, thereby improving the player experience. The method is described below in conjunction with a specific embodiment.
[0059] Please refer to Figure 1 , Embodiment 1 of the present invention is:
[0060] A method for automatically generating game nicknames based on an AI model, such as Figure 1 As shown, the steps include:
[0061] S1. Based on the player's behavior records during the game, keywords are extracted from the behavior records. The behavior records include:
[0062] The game scenes that players often visit in the games they have played in the past, the main online time of the players, the game function modules that the players are good at, the animals and plants that the players often come into contact with, and the registration information of the players, which includes the player’s constellation, Chinese zodiac sign and hometown.
[0063] That is, in this embodiment, the behavior records are obtained from some behavioral habits of the players in historical games. By extracting keywords from these behavior records, the game nicknames subsequently automatically generated by AI are personalized based on the game habits of different players, reducing the probability that players are dissatisfied with the generated game nicknames.
[0064] At the same time, the behavior records also include game data homophonic puns, which are obtained by obtaining the homophones or near-phonetic characters used by players in naming game equipment, monsters, NPCs, scenes, and maps in games that players have played in the past.
[0065] That is, in this embodiment, in the historical games that players have played, they sometimes name the equipment, monsters, NPCs, scenes and maps in the game, and these names are sometimes input as homophones, similarities or abbreviations. These names are expanded into homophones as keywords, which can effectively improve the diversity of subsequent game nickname generation. In addition, in this embodiment, the homophones can also come from the popular homophones of the game on the Internet, which are obtained based on the homophones or near-phonetic data in the pinyin input method.
[0066] After keyword extraction, in this embodiment, the extracted keywords are further expanded in behavior, specifically:
[0067] Keywords are marked and behavior expansion is performed using synonym replacement, grammatical rule replacement combination, text AI generation, word vector similarity and word sense disambiguation to further improve the diversity of subsequent game nickname generation and increase player choices.
[0068] Then AI is used to combine keywords and randomly generate multiple game nicknames, specifically:
[0069] Based on the world view and mission scenario of the new game, each keyword is weighted and scored, and multiple game nicknames are obtained by combining them according to the scores. That is, the game nicknames are generated by combining the weights of each keyword, so as to ensure that the generated game nicknames can better meet the preferences of the players. For example, in this embodiment, taking Magic Domain Mobile Game 2 as an example, under the world view of Magic Domain Mobile Game 2, the first act of the main task "Dark Swamp, Wild Hunting" is a mission scenario that players particularly like, and the name will be affected by such factors, and then recommend names such as: "The Chosen One of the Bloodline of the God King", "The Nemesis of Spider Queen Ada", "The Seeker of the Heart of the Universe Fragments", "The Elf Eleanor's Partner", etc.
[0070] After generating multiple game nicknames, proceed to the following steps:
[0071] S2. Compare the names already in the database with each randomly generated game name to eliminate duplicate game names.
[0072] S3. Push the remaining game titles to the players for selection.
[0073] That is, in this embodiment, keywords are extracted from the player's game behavior records, and then AI is used to combine keywords to randomly generate multiple game nicknames that meet the player's preferences. After the same game nicknames in the database are eliminated, the generated game nicknames are recommended to the player for selection in turn. While the game nicknames are automatically generated, the game nicknames can be personalized based on the player's preferences to meet the player's needs and improve player satisfaction.
[0074] Please refer to Figure 2 , Embodiment 2 of the present invention is:
[0075] A method for automatically generating a game nickname based on an AI model, based on the above-mentioned embodiment 1, in this embodiment, as Figure 2 As shown, before step S1, it also includes:
[0076] S0. Obtain the game registration information of the player, and analyze the player's favorite nickname type in combination with a questionnaire distributed in advance. The game registration information includes the player's gender, the player's age, and the game character selected by the player.
[0077] That is, in this embodiment, in order to make the subsequently generated game nicknames more in line with the player's preferences, the player's initial preferences can be obtained by obtaining the player's game registration information and conducting a questionnaire survey to analyze the player's favorite nickname type. The specific method is:
[0078] S01. Obtaining the game registration information of players through questionnaires or database retrieval, classifying the player samples according to the game registration information, obtaining various types of players of different genders, different age groups and different game roles, and obtaining questionnaire survey results of various types of players, the questionnaire survey results including favorite game types, interests and hobbies in games and game time.
[0079] S02. Conduct characteristic behavior analysis on the questionnaire survey results of various types of players, that is, analyze the distribution of interests and hobbies of various types of players, and obtain the main interests and hobbies of various types of players. For example, players like to PK with others, like to kill monsters alone, like to fight high-level BOSS for excitement, like to team up with others to go to dungeons, like to chat with the opposite sex, etc.
[0080] S03. Conduct a preliminary analysis of the causes of the questionnaire survey results for each type of player, that is, form a scale chart based on the game time of each type of player, and divide it into multiple dimensions to record each time and its corresponding game items, such as: when a player kills monsters alone, does he do it before or after lunch or before going to bed at night? Does he recharge the game before and after? Does he communicate with other players before and after, etc.
[0081] S04. Conduct credibility analysis on the questionnaire survey results of various types of players, that is, comprehensively analyze the answer repetition rate and abnormal answer rate of various types of players in the questionnaire to obtain the credibility of the questionnaire.
[0082] S05. Combining characteristic behavior analysis, precondition analysis and credibility analysis, obtain the favorite nickname types of various players.
[0083] That is, players are classified according to their game registration information, and then the game types, interests and hobbies in the game, and game time filled out by the players in the questionnaire are analyzed to analyze the characteristic behaviors, preconditions and credibility of the questionnaire, so as to accurately determine the preferred nickname types of each type of players.
[0084] In this embodiment, the preferred nickname type is introduced, and step S3 is specifically as follows:
[0085] The corresponding desired nickname type is matched according to the player's type, and game nicknames that meet the desired nickname type are filtered out from the game nicknames that have been duplicated, and are pushed to the player for selection.
[0086] That is, the game nicknames after duplicates are eliminated are screened to select game nicknames that meet the players' favorite nickname types and then provide them for the players to choose in turn, further ensuring that the players choose the most satisfactory game nickname.
[0087] In this embodiment, the game nicknames can be displayed in front of the player in sequence. When the player is satisfied with the first one, the nickname is confirmed. If the player is not satisfied, the next nickname is displayed until the player selects a satisfactory one. Multiple nicknames can also be displayed in front of the player, and the player can choose by himself. If there is no nickname that the player is satisfied with on the current page, the next page is entered. If the player is not satisfied with all the nicknames, the process returns to step S1 and the keyword combination is performed through AI to randomly generate a new batch of multiple game nicknames.
[0088] Please refer to Figure 3 , Embodiment 3 of the present invention is:
[0089] A terminal 1 for automatically generating game nicknames based on an AI model comprises a memory 2, a processor 3, and a computer program stored in the memory 2 and executable on the processor 3. When executing the computer program, the processor 3 implements the steps of a method for automatically generating game nicknames based on an AI model in the above-mentioned embodiment 1 or embodiment 2.
[0090] In summary, the present invention provides an AI-based model-based automatic game nickname generation method and terminal, which extracts keywords from the player's game behavior records, then uses AI to combine keywords to randomly generate multiple game nicknames that meet the player's preferences, and then removes the same game nicknames in the database. The generated game nicknames are recommended to the player for selection in turn, which not only realizes the automatic generation of game nicknames, but also can generate personalized game nicknames based on the player's preferences to meet the player's needs and improve player satisfaction.
[0091] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for automatically generating game nicknames based on an AI model, characterized in that: Includes steps: S1. Based on the player's behavior records during the game, keywords are extracted from the behavior records, and then keywords are combined through AI to randomly generate multiple game nicknames; S2, comparing the names already existing in the database with each of the randomly generated game nicknames, and eliminating duplicate game nicknames; S3. Push the remaining game nicknames in sequence to the player for selection.
2. The method for automatically generating game nicknames based on an AI model according to claim 1, characterized in that: The behavior records include: The game scenes frequently visited by the player in the games the player has played in the past, the player's main online time, the game function modules that the player is good at, the animals and plants that the player often comes into contact with, and the player's registration information, which includes the player's constellation, zodiac sign and hometown.
3. The method for automatically generating game nicknames based on an AI model according to claim 2, characterized in that: The behavior record also includes game data puns: The game data homophonic puns are obtained by obtaining homophones or near-homophones of names given by players to game equipment, monsters, NPCs, scenes and maps in games that the players have played in the past.
4. The method for automatically generating game nicknames based on an AI model according to claim 1, characterized in that: Before the keyword combination is performed by AI in step S1, the method further includes: The extracted keywords are subjected to behavioral expansion, specifically: The keywords are labeled, and behavior expansion is performed using synonym replacement, grammar rule replacement combination, text AI generation, word vector similarity and word sense disambiguation.
5. The method for automatically generating game nicknames based on an AI model according to claim 1, characterized in that: In step S1, keyword combination is performed by AI, specifically: Based on the world view and mission scenarios of the new game, each keyword is weighted and scored, and a plurality of game nicknames are obtained by combining them according to the scores.
6. The method for automatically generating game nicknames based on an AI model according to claim 1, characterized in that: Before step S1, the following steps are also included: S0. Obtaining the game registration information of the player, and analyzing the player's preferred nickname type in combination with a pre-issued questionnaire, wherein the game registration information includes the player's gender, the player's age, and the game character selected by the player.
7. The method for automatically generating game nicknames based on an AI model according to claim 6, characterized in that: The step S0 is specifically as follows: S01. Obtaining game registration information of players through questionnaires or database retrieval, classifying player samples according to the game registration information, obtaining various types of players of different genders, different age groups and different game roles, and obtaining questionnaire survey results of various types of players, wherein the questionnaire survey results include favorite game types, hobbies and interests in games, and game time; S02. Conduct characteristic behavior analysis on the questionnaire survey results of various types of players; S03. Conduct preliminary reason analysis on the questionnaire survey results of various players; S04. Conduct credibility analysis on the questionnaire survey results of various types of players; S05. Combining the characteristic behavior analysis, the preceding cause analysis and the credibility analysis, obtain the favorite nickname types of various players.
8. The method for automatically generating game nicknames based on an AI model according to claim 7, characterized in that: The characteristic behavior analysis is specifically as follows: Analyze the distribution of the interests and hobbies of various types of players to obtain the most important interests and hobbies of various types of players; The preceding cause analysis is specifically as follows: A scale chart is formed according to the game time of each type of player, and each time and its corresponding game item are recorded in multiple dimensions; The credibility analysis is specifically as follows: The credibility of the questionnaire is obtained by combining the repetition rate and abnormal answer rate of each type of players in the questionnaire.
9. The method for automatically generating game nicknames based on an AI model according to claim 8, characterized in that: The step S3 is specifically as follows: The desired nickname type is matched according to the player's type, and the game nicknames that meet the desired nickname type are screened from the game nicknames that have been duplicated and pushed to the player for selection.
10. A terminal for automatically generating game nicknames based on an AI model, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the method for automatically generating game nicknames based on an AI model as described in any one of claims 1 to 9 when executing the computer program.