Method, device and equipment for generating response information of game assistant

Abstract

The embodiment of the invention discloses a response information generation method, device and equipment for a game assistant, and the method comprises the steps: obtaining social behavior data, attack behavior data, defense behavior data and player dialogue information in real time, carrying out the semantic analysis of the player dialogue information, and determining basic response information corresponding to a semantic analysis result; performing social range analysis and social content analysis on the social behavior data, obtaining a corresponding first activeness value and a corresponding second activeness value according to an analysis result, and determining an activeness level of the game role according to the first activeness value, the second activeness value and a preset level parameter; the attack behavior data and the defense behavior data are analyzed to obtain the proportion of the attack operation duration and the defense operation duration, response tone data associated with the game style of the player is determined based on the proportion, the basic response information is adjusted according to the activeness level and the response tone data, and game assistant response information is generated. And the flexibility and diversity of response information of the game assistant are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method, device, and apparatus for generating response information of a game assistant. Background Art

[0002] In today's digital entertainment era, the gaming industry is booming, with a constant stream of new games and players' expectations for a more engaging gaming experience. To meet players' diverse gaming needs, game assistants have emerged. These assistants aim to provide players with convenient access to gaming information, assist them in making decisions, and enhance their interaction with the game. For example, they help users understand game settings, strategy guides, and game news, while also offering services like game history query and chat.

[0003] In related technologies, a series of rules and corresponding reply scripts are usually set in advance. When receiving a user's question, the system will extract keywords from the question, then search for matching rules in the rule library based on these keywords, and return corresponding response information. The generation method of this response information is limited to preset fixed lines and simple question-and-answer logic, which lacks flexibility and diversity, and is difficult to meet players' expectations for diversified and personalized interactive experience. Summary of the Invention

[0004] The present invention provides a method, device, and apparatus for generating game assistant response information, which solves the problem of lack of flexibility and diversity in dialogues between game characters and players. The method can generate game assistant response information based on complex game backgrounds and gameplay, thereby increasing the flexibility and diversity of game assistant response information.

[0005] In a first aspect, an embodiment of the present application provides a method for generating response information of a game assistant, comprising:

[0006] Acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to semantic prompt words in the semantic analysis results, wherein the game behavior data includes social behavior data, offensive behavior data, and defensive behavior data;

[0007] Performing social scope analysis and social content analysis on the social behavior data, and obtaining a corresponding first activity value and a second activity value according to the analysis results, and determining an activity level of the game character according to the first activity value, the second activity value, and a preset level parameter;

[0008] The attack behavior data and the defense behavior data are analyzed for operation duration to obtain the ratio of the attack operation duration to the defense operation duration, and the response tone data associated with the player's game style is determined based on the duration ratio. The basic response information is adjusted according to the activity level and the response tone data to generate game assistant response information.

[0009] Optionally, performing social scope parsing and social content parsing on the social behavior data, and obtaining corresponding first activity values and second activity values according to the parsing results, includes:

[0010] Performing social scope analysis on the social behavior data to determine a social frequency and a social method, and generating a first activity value according to the social frequency and the social method;

[0011] The social behavior data is subjected to social content analysis to determine a type of social content, and a second activity value is determined according to the type of social content.

[0012] Optionally, generating a first activity value according to the social frequency and the social manner includes:

[0013] Determining target activity values corresponding to the range of the social frequency and activity weighting parameters corresponding to the social modes;

[0014] A first activity value is calculated according to the target activity value and the activity weighting parameter, the social mode includes one-to-one social interaction and one-to-many social interaction, and the activity weighting parameter corresponding to the one-to-one social interaction is smaller than the activity weighting parameter corresponding to the one-to-many social interaction.

[0015] Optionally, the type of the social content includes a skill interaction type and a non-skill interaction type, and determining the second activity value according to the type of the social content includes:

[0016] When the type of the social content is a skill interaction type, the second activity value is determined to be a first preset value; when the type of the social content is a non-skill interaction type, the second activity value is determined to be a second preset value, and the first preset value is greater than the second preset value.

[0017] Optionally, the basic response information includes basic response content information and basic response tone information, and the adjusting the basic response information according to the activity level and the response tone data includes:

[0018] Determining a response information type corresponding to the activity level, and if the response information type is a basic information type, performing natural language conversion on the basic response content information to obtain natural language response content, and adjusting the basic response tone information according to the response tone data;

[0019] In the case where the response information type is a non-basic information type, the basic response content information is adjusted to obtain personalized response content, and the basic response tone information is adjusted according to the response tone data.

[0020] Optionally, after generating the game assistant response information, the method further includes:

[0021] Acquire game progress data in real time, and perform status analysis on the game progress data to determine the character growth value within a preset time period;

[0022] Comparing the character growth value with a preset growth threshold, and generating a corresponding type of intelligent interaction statement according to the comparison result;

[0023] A speech synthesis operation is performed on the adjustment result of the intelligent interaction statement and the basic response tone information to generate game assistant intelligent interaction information.

[0024] Optionally, before obtaining the game behavior data and player conversation information in real time, the method further includes:

[0025] Get story background information and gameplay information;

[0026] A corpus model is trained based on the story background information and the game play information to generate a prediction model, and the corpus model is used to determine the mapping relationship between semantic prompt words and basic response information.

[0027] In a second aspect, an embodiment of the present application provides a game assistant response information generating device, comprising:

[0028] A data acquisition module is used to acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to the semantic analysis results. The game behavior data includes social behavior data, offensive behavior data, and defensive behavior data;

[0029] A first data analysis module is used to perform social scope analysis and social content analysis on the social behavior data;

[0030] An activity level determination module, configured to generate a first activity value based on the social scope analysis result, generate a second activity value based on the social content analysis result, and determine the activity level of the game character based on the first activity value, the second activity value, and preset level parameters;

[0031] A second data analysis module is used to analyze the attack behavior data and the defense behavior data for operation duration, and obtain a ratio of the attack operation duration to the defense operation duration according to the analysis result;

[0032] A response information generation module is used to compare the duration ratio with a preset duration ratio range, determine the player's gaming style based on the comparison result, and determine the response tone data associated with the player's gaming style, adjust the basic response information based on the activity level and the response tone data, and generate game assistant response information.

[0033] In a third aspect, an embodiment of the present application provides an electronic device comprising: one or more processors; a storage device configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for generating response information of the game assistant described in the first aspect.

[0034] In a fourth aspect, an embodiment of the present application provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the method for generating response information of a game assistant as described in the first aspect.

[0035] The embodiment of the present application acquires game behavior data and player conversation information in real time, performs semantic analysis on the player conversation information, determines basic response information corresponding to the semantic prompt words in the semantic analysis results, and the game behavior data includes social behavior data, attack behavior data, and defense behavior data; performs social scope analysis and social content analysis on the social behavior data, and obtains corresponding first activity value and second activity value based on the analysis results, and determines the activity level of the game character based on the first activity value, the second activity value, and a preset level parameter; analyzes the operation duration of the attack behavior data and the defense behavior data to obtain the duration ratio of the attack operation duration to the defense operation duration, determines the response tone data associated with the player's game style based on the duration ratio, adjusts the basic response information based on the activity level and response tone data, and generates game assistant response information. It can analyze the activity level of game players in complex game backgrounds and gameplay, determine the player's personality or game style based on the player's activity level, and thus generate game assistant response information that meets the user's game style or matches the player's personality, thereby improving the flexibility and diversity of the game assistant response information and enhancing the game player's gaming experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flowchart of a method for generating response information of a game assistant provided in an embodiment of the present application;

[0037] Figure 2 This is a schematic diagram of a corpus model training process provided by the present application;

[0038] Figure 3 This is a process diagram of a method for generating response information of a game assistant provided in an embodiment of the present application;

[0039] Figure 4 This is a flow chart of a method for generating an activity value provided in an embodiment of the present application;

[0040] Figure 5 This is a flowchart of a basic response information adjustment method provided in an embodiment of the present application;

[0041] Figure 6 This is a structural diagram of a device for generating response information of a game assistant provided in an embodiment of the present application;

[0042] Figure 7 It is a structural diagram of a response information generating device of a game assistant provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. It should also be noted that, for ease of description, only parts related to the present application, not all of the contents, are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0044] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0045] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0046] The following, in conjunction with the accompanying drawings, describes in detail the method, device and equipment for generating response information of the game assistant provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0047] The game assistant response information generation method provided in the embodiment of the present application can be applied to the dialogue scenario in the game system, especially for the scenario of answering the question information of the players in the game. Based on the above application scenario, it can be understood that the execution subject of this solution can be a server.

[0048] Figure 1 This is a flowchart of a method for generating response information of a game assistant provided in an embodiment of the present application. Figure 1 Shown, including:

[0049] Step S101: Acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to the semantic prompt words in the semantic analysis results. The game behavior data includes social behavior data, attack behavior data, and defense behavior data.

[0050] Game behavior data refers to quantifiable and recorded information generated during gameplay. This can include action data such as movement, jumping, and attacking, as well as skill usage data, such as skill usage order and cooldown time. Player conversation information refers to content generated by players communicating through chat channels, voice calls, and other means during gameplay, including text chat content, voice call content, emoticons, and shortcut phrases. Semantic cues are keywords or phrases used in natural language processing tasks to guide the model in generating text related to specific semantics or themes. Semantic cues can accurately reflect the main body and key information of the target text. Basic response information is a pre-designed, universal answer pattern used to quickly and standardizedly respond to various questions or requests in specific scenarios. Social behavior data refers to a series of data generated by users through various behaviors in social scenarios that reflect their social activities and social relationships. This can include interaction data and social relationships, such as chat logs, comments, likes, shares, and private messages. Attack behavior data refers to a series of data generated by players or game characters performing attack-related actions during gameplay, including attack type, attack time, and attack frequency. Defensive behavior data refers to the data generated by a series of actions taken by players or game characters during the game to resist enemy attacks, protect themselves or teammates, and guard specific targets. It may include defense type, defense time, and defense frequency.

[0051] In one embodiment, social behavior data, attack behavior data, defense behavior data, and player conversation information are acquired in real time, and semantic analysis is performed on the player conversation information to determine the exact meaning of each word in the text, as well as various semantic relationships between words, such as synonyms, antonyms, or hyponyms, etc. The meaning of each word is matched with the meaning of a preset semantic prompt word, and words with the same meaning as the preset semantic prompt word in the semantic analysis result are determined. Based on the mapping relationship between the preset semantic prompt word and the basic response information, the basic response information corresponding to the semantic prompt word in the semantic analysis result is determined.

[0052] Step S102: performing social scope analysis and social content analysis on the social behavior data, obtaining a corresponding first activity value and a second activity value according to the analysis results, and determining the activity level of the game character according to the first activity value, the second activity value, and a preset level parameter.

[0053] Among them, social scope analysis refers to a comprehensive analysis of the social relationships between characters in the game and other characters, and social content analysis refers to a specific analysis of the various interactive behaviors, communication methods, and their meaning or impact between characters in the game, which may include text chat, voice chat, and symbols or gestures in the game. The first activity value refers to the level of activity of the game character determined based on the social scope of the game character by performing social scope analysis on the social behavior data, and the second activity value refers to the level of activity of the game character determined based on the social content of the game character by performing social content analysis on the social behavior data. The preset level parameter refers to the numerical value of different importance assigned to different activity-related parameters when calculating the player activity in the game. The activity level refers to the quantitative level division used to represent the level of participation and activity of the character in the game platform.

[0054] In one embodiment, social scope analysis is performed on social behavior data to determine the communication scope of a game player with other game players on the game platform, such as the number of players with whom the current game player is communicating. The greater the number of players with whom the current game player is communicating, the wider the game player's social scope, and accordingly, the larger the first activity value. For example, a determination is made as to whether the number of players is greater than or equal to a preset number of interacting players. If so, the first activity value is determined to be a first preset activity value, such as 0.7; if so, the first activity value is determined to be a second preset activity value, such as 0.3. Social content analysis is performed on the social behavior data to determine the content of the game player's communication with other game players on the game platform. The communication is determined to be voice or text. If the communication is voice, the corresponding second activity value is determined to be 0.7; if the communication is text, the corresponding second activity value is determined to be 0.3. A target activity value is calculated based on the first and second activity values and a preset level parameter, and the activity level to which the target activity value belongs is determined. For example, the pre-set mapping relationship between activity values and activity levels is as follows: an activity value of 0.7 corresponds to the first activity level, an activity value of 0.54 corresponds to the second activity level, an activity value of 0.46 corresponds to the third activity level, and an activity value of 0.3 corresponds to the fourth activity level. The preset level parameter corresponding to the first activity value is 60%, and the preset level parameter corresponding to the second activity value is 40%. If the first activity value is 0.7 and the second activity value is 0.7, then the target activity value can be calculated as 0.7*60%+0.7*40%=0.7. Based on the pre-set mapping relationship between activity values and activity levels, the activity level corresponding to the target activity value of 0.7 can be determined as level 1 activity.

[0055] Step S103: Analyze the attack behavior data and the defense behavior data to obtain the ratio of the attack operation duration to the defense operation duration, determine the response tone data associated with the player's game style based on the duration ratio, adjust the basic response information according to the activity level and the response tone data, and generate game assistant response information.

[0056] Response tone data is used to describe and analyze the tone characteristics of the game assistant during communication, and can include intonation, speaking speed, volume, and timbre. Game assistant response information refers to the feedback provided by the game assistant in response to player operations, questions, or commands during interaction with the player. In one embodiment, the attack behavior data is analyzed for duration to determine the total attack duration of the current player in the game. The defense behavior data is analyzed for duration to determine the total defense duration of the current player in the game, and the ratio of the total attack duration to the total defense duration is determined. This duration ratio is then compared within a preset ratio range. If the duration ratio is greater than the preset ratio range, the player's gaming style is determined to be adventurous, and the response tone data associated with the adventurous style is determined to be passionate. If the duration ratio is less than the preset ratio range, the player's gaming style is determined to be defensive, and the response tone data associated with the defensive style is determined to be gentle. If the duration ratio is within the preset ratio range, the player's gaming style is determined to be strategic, and the response tone data associated with the strategic style is determined to be calm. The passionate tone data is used to describe and analyze the passionate emotions, strong feelings, or excitement reflected in the language, and is characterized by large fluctuations in intonation values, high speech speed values, and high volume values. Gentle tone data refers to the relevant data used to describe and analyze the emotions or attitudes such as gentleness, softness, and kindness reflected in the language. The tone data has a small fluctuation range, a moderate speaking speed value, and a small volume value. Calm tone data refers to the relevant data used to describe and analyze the characteristics such as calmness, steadiness, and composure reflected in the language. The tone data has a small fluctuation range, a moderate speaking speed value, and a moderate volume value. After determining the response tone data, the content of the basic response information is adjusted according to the activity level, and the tone, speaking speed, volume and other data in the basic response information are adjusted according to the response tone data to generate game assistant response information that conforms to the current game scenario.

[0057] The embodiment of the present application acquires game behavior data and player conversation information in real time, performs semantic analysis on the player conversation information, determines basic response information corresponding to the semantic prompt words in the semantic analysis results, and the game behavior data includes social behavior data, attack behavior data, and defense behavior data; performs social scope analysis and social content analysis on the social behavior data, and obtains corresponding first activity value and second activity value based on the analysis results, and determines the activity level of the game character based on the first activity value, the second activity value, and a preset level parameter; analyzes the operation duration of the attack behavior data and the defense behavior data to obtain the duration ratio of the attack operation duration to the defense operation duration, determines the response tone data associated with the player's game style based on the duration ratio, adjusts the basic response information based on the activity level and response tone data, and generates game assistant response information. It can analyze the activity level of game players in complex game backgrounds and gameplay, determine the player's personality or game style based on the player's activity level, and thus generate game assistant response information that meets the user's game style or matches the player's personality, thereby improving the flexibility and diversity of the game assistant response information and enhancing the game player's gaming experience.

[0058] Figure 2 This is a schematic diagram of the corpus model training process provided by this application. Figure 2 As shown, before acquiring real-time game behavior data and player conversation information, the process also includes: acquiring story background information and gameplay information; training a corpus model based on this story background information and gameplay information to generate a prediction model. The corpus model is used to determine the mapping relationship between semantic prompts and basic response information. Story background information refers to relevant background information about the game's fictional world, including its history, geography, and culture. It provides a foundation and framework for the game's plot, characters, and quests, helping players better understand the game world and plot. Gameplay information refers to information about how the game proceeds, how players operate, and what they can do in the game. It can include control methods, game objectives, quests and plots, levels and challenges, etc. A corpus model is a model built based on large amounts of text data for processing and understanding natural language. By learning and analyzing story background information and gameplay information, the corpus model captures language patterns, regularities, and semantic information, thereby generating a mapping relationship between semantic prompts and basic response information.

[0059] The embodiment of the present application obtains story background information and game play information, performs model training based on the story background information and game play information, and generates a corpus model, which can improve the accuracy of basic response information and the efficiency of determining basic response information.

[0060] Figure 3This is a process diagram of a method for generating response information of a game assistant provided in an embodiment of the present application. Figure 3 As shown, after the game assistant response information is generated, the feedback information of the game player is received in real time, and the feedback information is analyzed to determine whether the feedback information is positive feedback information or negative feedback information. If it is positive feedback information, the game continues to play the next round, and the response information is generated based on the mapping relationship generated by the corpus model. If it is negative feedback information, the corpus model is re-trained according to the negative feedback information, thereby improving the accuracy of the game assistant response information.

[0061] Figure 4 This is a flow chart of a method for generating an activity value provided by an embodiment of the present application. Figure 4 Shown, including:

[0062] Step S1021: performing social scope analysis on the social behavior data to determine the social frequency and social mode, and generating a first activity value according to the social frequency and social mode.

[0063] Step S1022: performing social content analysis on the social behavior data to determine the type of the social content, and determining a second activity value according to the type of the social content.

[0064] Social frequency refers to how often gamers engage in various social interactions within a certain period of time. A higher frequency indicates a more active gamer. Social methods refer to the various methods and channels used by virtual characters in the game to interact and communicate, such as through voice communication, chat windows, or text input boxes. Gamers who communicate through voice are considered more active, while those who communicate through chat are less active. Types of social content can include sharing tasks or strategies, emotional connections, and storylines.

[0065] In one embodiment, the social behavior data is parsed for social scope to determine the social frequency and social method, and then, according to preset activity value determination rules, activity values corresponding to the social frequency and social method are determined. The activity values corresponding to the social frequency and social method are accumulated and calculated to obtain a first activity value. The social behavior data is parsed for social content to determine the type of social content, and a corresponding second activity value is determined based on the preset activity values corresponding to each social content type.

[0066] In this embodiment of the present application, social behavior data is analyzed for social scope to determine social frequency and social methods, and a first activity value is generated based on the social frequency and social methods. Social behavior data is analyzed for social content to determine the type of social content, and a second activity value is determined based on the type of social content. In this solution, the first activity value is determined based on social frequency and social methods, and the second activity value is determined based on the type of social content. This allows for analysis of user activity based on a variety of actual game player behavior data, improving the accuracy of the first and second activity values.

[0067] In one embodiment, a first activity value is generated based on the social frequency and the social mode, including: respectively determining the target activity value corresponding to the range of the social frequency and the activity weighting parameter corresponding to the social mode; calculating the first activity value based on the target activity value and the activity weighting parameter, the social modes include one-to-one social and one-to-many social, and the activity weighting parameter corresponding to the one-to-one social is smaller than the activity weighting parameter corresponding to the one-to-many social. Among them, the activity weighting parameter is a numerical value used to measure and adjust the relative importance of different factors in the activity calculation. One-to-one social refers to communicating with other game players through private chat on the game platform, and one-to-many social refers to communicating with other game players through public communication windows on your game platform, such as group chat. It is understandable that if a game player communicates in a one-to-one manner, it can be considered that the game character usually communicates with a small number of players, or is unwilling to communicate in a public communication window, and the game player is introverted. In this case, the game player's activity level can be determined to be low. If the game player communicates in a one-to-many manner, it can be considered that the game character usually communicates with a large number of players, likes to communicate in a public communication window, and is extroverted. In this case, the game player's activity level can be determined to be high. Therefore, the activity weighting parameter corresponding to one-to-one social interaction is smaller than the activity weighting parameter corresponding to one-to-many social interaction. In one embodiment, the range of the current game player's social frequency is determined based on a preset pre-divided social frequency range, and the target activity value corresponding to the range is determined. The activity weighting parameter corresponding to the social method is determined, and the target activity value is multiplied by the activity weighting parameter to obtain a first activity value.

[0068] This embodiment of the present application determines a target activity value corresponding to the range of social frequency and an activity weighting parameter corresponding to the social mode, and then calculates a first activity value based on the target activity value and the activity weighting parameter. In this solution, the first activity value is determined by combining the social frequency and the social mode, fully considering the impact of these two factors on activity, thereby improving the accuracy of the first activity value.

[0069] In one embodiment, the types of social content include skill interaction types and non-skill interaction types, and the second activity value is determined according to the type of social content, including: when the type of social content is a skill interaction type, determining the second activity value to be a first preset value; when the type of social content is a non-skill interaction type, determining the second activity value to be a second preset value, and the first preset value is greater than the second preset value. Among them, the skill interaction type means that the social content is the communication content of game skills or game strategies, and the non-skill interaction type means that the social content is not the communication of game operation behavior, such as emotional communication, simple greetings, etc. For example, when the type of social content is a skill interaction type, the second activity value is determined to be a first preset value, such as 60%; when the type of social content is a non-skill interaction type, the second activity value is determined to be a second preset value, such as 40%.

[0070] In this embodiment of the present application, when the social content is of a skill-based interaction type, the second activity value is determined to be a first preset value; when the social content is of a non-skill-based interaction type, the second activity value is determined to be a second preset value, where the first preset value is greater than the second preset value. This solution allows the game player's activity to be determined based on their actual interaction content, thereby improving the accuracy of the second activity value.

[0071] Figure 5 This is a flow chart of a basic response information adjustment method provided by an embodiment of the present application. Figure 5 Shown, including:

[0072] Step S1031: Determine the response information type corresponding to the activity level. If the response information type is a basic information type, perform natural language conversion on the basic response content information to obtain natural language response content, and adjust the basic response tone information according to the response tone data.

[0073] Step S1032: When the response information type is a non-basic information type, the basic response content information is adjusted to obtain personalized response content, and the basic response tone information is adjusted according to the response tone data.

[0074] Among them, the response information volume type is determined by comparing the data volume of the response sentence with the data volume of the basic response information, and may include a basic information volume type and a non-basic information volume type, wherein the basic information volume type refers to the information volume of the response information being the same or similar to the information volume of the basic response information, and the non-basic information volume type refers to the information volume of the response information being much larger than the information volume of the basic response information. Natural language conversion refers to converting one form of natural language expression into another form to meet different application requirements or achieve specific language processing goals, such as converting formal written language into colloquial expressions. Natural language response content refers to responses or answers to questions, requests or specific situations in the form of natural language. Optionally, basic response information includes basic response content information and basic response tone information. Among them, basic response content information refers to response text that meets the basic response mode, and basic response tone data refers to the tone data, speech speed data, and volume data of the game's default game assistant. In one embodiment, a mapping relationship between activity level and response information type is pre-set, and the corresponding response information type is determined to be a basic information type or a non-basic information type based on the activity level. It is understood that the higher the game player's activity level, the more extroverted the game player is. The basic response information can be polished, such as by adding modifiers or onomatopoeia, or converting the basic response content into more humorous content, thereby increasing the diversity and flexibility of the response content. The lower the game player's activity level, the more introverted the game player is. Simply converting the basic response content into more colloquial natural language is sufficient. Therefore, it can be pre-set that higher activity levels correspond to non-basic information types, and lower activity levels correspond to basic information types. In the case where the response information type is a basic information type, the basic response content information is converted into natural language to obtain natural language response content, and the pitch data, speech speed data, and volume data corresponding to the basic response tone are adjusted according to the response tone data to obtain the adjusted target response tone data, and the natural language response content and the target response tone are subjected to speech synthesis operations to generate intelligent interactive voice information that contains both the response content and the target response tone. In the case where the response information type is a non-basic information type, the response content of the basic response information can be polished to obtain personalized response content, and the pitch data, speech speed data, and volume data corresponding to the basic response tone are adjusted according to the response tone data to obtain the adjusted target response tone data, and the personalized response content and the target response tone are subjected to speech synthesis operations to generate intelligent interactive voice information that contains both personalized response content and the target response tone.

[0075] The embodiment of the present application determines the response information type corresponding to the activity level. When the response information type is a basic information type, the basic response content information is converted into natural language to obtain natural language response content, and the basic response tone information is adjusted according to the response tone data. When the response information type is a non-basic information type, the basic response content information is adjusted to obtain personalized response content, and the basic response tone information is adjusted according to the response tone data. In the above scheme, it is possible to determine whether the basic response content information needs to be polished based on the activity level of the game player, thereby generating intelligent interactive voice information that meets the user's needs, improving the flexibility and diversity of the intelligent interactive voice information, and also enhancing the game player's experience.

[0076] In one embodiment, after generating the game assistant response information, it also includes: obtaining game progress data in real time, performing status analysis on the game progress data to determine the character growth value within a preset time period; comparing the character growth value with a preset growth threshold, and generating a corresponding type of intelligent interaction statement based on the comparison result; performing a speech synthesis operation on the adjustment result of the intelligent interaction statement and the basic response tone information to generate game assistant intelligent interaction information.

[0077] Game progress data refers to a collection of information used to record the various states and progress achieved by a player during the game. This data can reflect the player's in-game growth, achievements, and current game stage. Character growth value is a quantitative indicator used to measure the development and progress of a character in the game, and can include experience points, skill level increases, and equipment acquisition. In one embodiment, game progress data is acquired in real time, parsed to determine the player's character growth value within a preset time period, and then compared with a preset growth threshold. Based on the comparison result, it is determined whether a change has occurred and the extent of the change. It is understood that if a player's character growth value does not change within the preset time period, or the change is minimal, it can be considered that the player has encountered difficulties and obstacles, or is in a poor state. In this case, the game assistant can generate encouraging intelligent interaction statements and perform speech synthesis operations on these encouraging intelligent interaction statements with the adjusted response tone information to generate game assistant intelligent interaction information on the current game progress. If the character growth value of a game player changes significantly within the preset time, it can be considered that the current game player is in a good state. At this time, the game assistant can generate a praiseworthy intelligent interaction statement, and perform voice synthesis operation on the praiseworthy intelligent interaction statement and the adjusted response tone information to generate game assistant intelligent interaction information of the current game progress.

[0078] The embodiment of the present application obtains game progress data in real time, performs status analysis on the game progress data to determine the character growth value within a preset time period; compares the character growth value with a preset growth threshold, and generates a corresponding type of intelligent interaction statement based on the comparison result; and performs speech synthesis on the adjustment result of the intelligent interaction statement and basic response tone information to generate game assistant intelligent interaction information. In the above scheme, intelligent interaction statements that match the current game player status can be generated based on the game progress data, thereby improving the intelligence level of the game assistant, increasing the diversity of intelligent interaction information, and enhancing the game player's gaming experience.

[0079] Figure 6 This is a schematic diagram of the structure of a response information generating device for a game assistant provided in an embodiment of the present application. Figure 6 Shown, including:

[0080] Data acquisition module 21, for acquiring game behavior data and player conversation information in real time, performing semantic analysis on the player conversation information, and determining basic response information corresponding to the semantic analysis results. The game behavior data includes social behavior data, offensive behavior data, and defensive behavior data;

[0081] A first data analysis module 22 is configured to perform social scope analysis and social content analysis on the social behavior data;

[0082] An activity level determination module 23 is configured to generate a first activity value based on the social scope analysis result, generate a second activity value based on the social content analysis result, and determine the activity level of the game character based on the first activity value, the second activity value, and preset level parameters;

[0083] A second data analysis module 24 is configured to analyze the attack behavior data and the defense behavior data for operation duration, and obtain a ratio of the attack operation duration to the defense operation duration based on the analysis result;

[0084] The response information generation module 25 is used to compare the duration ratio with the preset duration ratio range, determine the player's game style based on the comparison result, and determine the response tone data associated with the player's game style, adjust the basic response information according to the activity level and the response tone data, and generate game assistant response information.

[0085] The embodiment of the present application acquires game behavior data and player conversation information in real time, performs semantic analysis on the player conversation information, determines basic response information corresponding to the semantic prompt words in the semantic analysis results, and the game behavior data includes social behavior data, attack behavior data, and defense behavior data; performs social scope analysis and social content analysis on the social behavior data, and obtains corresponding first activity value and second activity value based on the analysis results, and determines the activity level of the game character based on the first activity value, the second activity value, and a preset level parameter; analyzes the operation duration of the attack behavior data and the defense behavior data to obtain the duration ratio of the attack operation duration to the defense operation duration, determines the response tone data associated with the player's game style based on the duration ratio, adjusts the basic response information based on the activity level and response tone data, and generates game assistant response information. It can analyze the activity level of game players in complex game backgrounds and gameplay, determine the player's personality or game style based on the player's activity level, and thus generate game assistant response information that meets the user's game style or matches the player's personality, thereby improving the flexibility and diversity of the game assistant response information and enhancing the game player's gaming experience.

[0086] In a possible embodiment, the first data parsing module 22 is specifically configured to:

[0087] Performing social scope analysis on the social behavior data to determine the social frequency and social mode;

[0088] The activity level determination module 23 is specifically used to:

[0089] generating a first activity value according to the social frequency and the social manner;

[0090] The first data parsing module 22 is specifically used for:

[0091] Performing social content analysis on the social behavior data to determine the type of social content;

[0092] The activity level determination module 23 is specifically used to:

[0093] A second activity value is determined according to the type of the social content.

[0094] In a possible embodiment, the activity level determination module 23 is specifically configured to:

[0095] Determining target activity values corresponding to the range of the social frequency and activity weighting parameters corresponding to the corresponding social modes;

[0096] A first activity value is calculated according to the target activity value and the activity weighting parameter, the social mode includes one-to-one social interaction and one-to-many social interaction, and the activity weighting parameter corresponding to the one-to-one social interaction is smaller than the activity weighting parameter corresponding to the one-to-many social interaction.

[0097] In a possible embodiment, the activity level determination module 23 is specifically configured to:

[0098] When the type of the social content is a skill interaction type, the second activity value is determined to be a first preset value; when the type of the social content is a non-skill interaction type, the second activity value is determined to be a second preset value, and the first preset value is greater than the second preset value.

[0099] In a possible embodiment, the response information generating module 25 is specifically configured to:

[0100] Determining a response information type corresponding to the activity level, and if the response information type is a basic information type, performing natural language conversion on the basic response content information to obtain natural language response content, and adjusting the basic response tone information according to the response tone data;

[0101] In the case where the response information type is a non-basic information type, the basic response content information is adjusted to obtain personalized response content, and the basic response tone information is adjusted according to the response tone data.

[0102] In one possible embodiment, the intelligent interaction information generation module is used to:

[0103] Acquire game progress data in real time, and perform status analysis on the game progress data to determine the character growth value within a preset time period;

[0104] Comparing the character growth value with a preset growth threshold, and generating a corresponding type of intelligent interaction statement according to the comparison result;

[0105] A speech synthesis operation is performed on the adjustment result of the intelligent interaction statement and the basic response tone information to generate game assistant intelligent interaction information.

[0106] In a possible embodiment, the mapping relationship generation module is used to:

[0107] Get story background information and gameplay information;

[0108] The story background information and the game play information are input into a pre-trained corpus model to generate a mapping relationship between semantic prompt words and basic response information.

[0109] An embodiment of the present application also provides an electronic device, and the game assistant response information generation device can integrate a game assistant response information generation device provided in an embodiment of the present application. Figure 7 This is a schematic diagram of the structure of a game assistant response information generating device provided in an embodiment of the present application, with reference to Figure 7 The game assistant's response information generating device includes: an input device 33, an output device 34, a memory 32, and one or more processors 31; the memory 32 is used to store one or more programs; when the one or more programs are executed by the one or more processors 31, the one or more processors 31 implement the game assistant's response information generating method provided in the above embodiment. The input device 33, the output device 34, the memory 32, and the processor 31 can be connected by a bus or other means. Figure 7 The bus connection is taken as an example.

[0110] The memory 32, as a computing device readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the response information generation method of the game assistant provided in any embodiment of the present application. The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function; the data storage area can store data created according to the use of the device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include a memory remotely located relative to the processor 31, and these remote memories can be connected to the device via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0111] The input device 33 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 34 may include a display device such as a display screen.

[0112] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, that is, realizes the above-mentioned method of generating response information of the game assistant.

[0113] The above-mentioned game assistant response information generation device, equipment and computer can be used to execute the game assistant response information generation method provided by any of the above-mentioned embodiments, and have corresponding functions and beneficial effects.

[0114] The present application also provides a storage medium storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute the method for generating response information of a game assistant provided in the above embodiment. The method for generating response information of a game assistant includes:

[0115] Acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to semantic prompt words in the semantic analysis results, wherein the game behavior data includes social behavior data, offensive behavior data, and defensive behavior data;

[0116] Performing social scope analysis and social content analysis on the social behavior data, and obtaining a corresponding first activity value and a second activity value according to the analysis results, and determining an activity level of the game character according to the first activity value, the second activity value, and a preset level parameter;

[0117] The attack behavior data and the defense behavior data are analyzed for operation duration to obtain the ratio of the attack operation duration to the defense operation duration, and the response tone data associated with the player's game style is determined based on the duration ratio. The basic response information is adjusted according to the activity level and the response tone data to generate game assistant response information.

[0118] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROMs, floppy disks, or tape drives; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or it may be located in a different second computer system that is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that can reside in different locations (e.g., in different computer systems connected via a network). The storage medium can store program instructions (e.g., embodied as a computer program) that can be executed by one or more processors.

[0119] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present application, whose computer-executable instructions are not limited to the method for generating response information of the game assistant as described above, can also execute related operations in the method for generating response information of the game assistant provided in any embodiment of the present application.

[0120] The game assistant's response information generation device, equipment and storage medium provided in the above embodiments can execute the game assistant's response information generation method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the game assistant's response information generation method provided in any embodiment of the present application.

[0121] The above are only preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that are possible for those skilled in the art will not depart from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include more other equivalent embodiments without departing from the concept of the present application. The scope of the present application is determined by the scope of the claims.

Claims

1. A method for generating response information of a game assistant, characterized in that: include: Acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to semantic prompt words in the semantic analysis results, wherein the game behavior data includes social behavior data, offensive behavior data, and defensive behavior data; Performing social scope analysis and social content analysis on the social behavior data, and obtaining a corresponding first activity value and a second activity value according to the analysis results, and determining an activity level of the game character according to the first activity value, the second activity value, and a preset level parameter; The attack behavior data and the defense behavior data are analyzed for operation duration to obtain the ratio of the attack operation duration to the defense operation duration, and the response tone data associated with the player's game style is determined based on the duration ratio. The basic response information is adjusted according to the activity level and the response tone data to generate game assistant response information.

2. The method for generating response information of a game assistant according to claim 1, wherein: The performing social scope parsing and social content parsing on the social behavior data, and obtaining corresponding first activity value and second activity value according to the parsing results, includes: Performing social scope analysis on the social behavior data to determine a social frequency and a social method, and generating a first activity value according to the social frequency and the social method; The social behavior data is subjected to social content analysis to determine a type of social content, and a second activity value is determined according to the type of social content.

3. The method for generating response information of a game assistant according to claim 2, wherein: Generating a first activity value according to the social frequency and the social manner includes: Determining target activity values corresponding to the range of the social frequency and activity weighting parameters corresponding to the social modes; A first activity value is calculated according to the target activity value and the activity weighting parameter, the social mode includes one-to-one social interaction and one-to-many social interaction, and the activity weighting parameter corresponding to the one-to-one social interaction is smaller than the activity weighting parameter corresponding to the one-to-many social interaction.

4. The method for generating response information of a game assistant according to claim 2, wherein: The type of the social content includes a skill interaction type and a non-skill interaction type, and determining the second activity value according to the type of the social content includes: When the type of the social content is a skill interaction type, the second activity value is determined to be a first preset value; when the type of the social content is a non-skill interaction type, the second activity value is determined to be a second preset value, and the first preset value is greater than the second preset value.

5. The method for generating response information of a game assistant according to claim 1, wherein: The basic response information includes basic response content information and basic response tone information, and the adjusting the basic response information according to the activity level and the response tone data includes: Determining a response information type corresponding to the activity level, and if the response information type is a basic information type, performing natural language conversion on the basic response content information to obtain natural language response content, and adjusting the basic response tone information according to the response tone data; In the case where the response information type is a non-basic information type, the basic response content information is adjusted to obtain personalized response content, and the basic response tone information is adjusted according to the response tone data.

6. The method for generating response information of a game assistant according to claim 5, characterized in that: After generating the game assistant response information, the method further includes: Acquire game progress data in real time, and perform status analysis on the game progress data to determine the character growth value within a preset time period; Comparing the character growth value with a preset growth threshold, and generating a corresponding type of intelligent interaction statement according to the comparison result; A speech synthesis operation is performed on the adjustment result of the intelligent interaction statement and the basic response tone information to generate game assistant intelligent interaction information.

7. The method for generating response information of a game assistant according to claim 1, wherein: Before obtaining the game behavior data and player conversation information in real time, the method further includes: Get story background information and gameplay information; A corpus model is trained based on the story background information and the game play information to generate a prediction model, and the corpus model is used to determine a mapping relationship between semantic prompt words and basic response information.

8. A device for generating response information of a game assistant, characterized in that: include: A data acquisition module is used to acquire game behavior data and player conversation information in real time, perform semantic analysis on the player conversation information, and determine basic response information corresponding to the semantic analysis results. The game behavior data includes social behavior data, offensive behavior data, and defensive behavior data; A first data analysis module is used to perform social scope analysis and social content analysis on the social behavior data; An activity level determination module, configured to generate a first activity value based on the social scope analysis result, generate a second activity value based on the social content analysis result, and determine the activity level of the game character based on the first activity value, the second activity value, and preset level parameters; A second data analysis module is used to analyze the attack behavior data and the defense behavior data for operation duration, and obtain a ratio of the attack operation duration to the defense operation duration according to the analysis result; A response information generation module is used to compare the duration ratio with a preset duration ratio range, determine the player's gaming style based on the comparison result, and determine the response tone data associated with the player's gaming style, adjust the basic response information based on the activity level and the response tone data, and generate game assistant response information.

9. An electronic device, comprising: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the response information generation method of the game assistant as described in any one of claims 1-7.

10. A storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to execute the method for generating response information of a game assistant according to any one of claims 1 to 7.

Images