Intelligent agent dialogue generation method, dialogue control method, equipment and medium

Abstract

The invention provides an agent dialogue generation method, a dialogue control method, equipment and a medium, and the agent dialogue generation method comprises the steps: obtaining the personal basic information of a plurality of agents in a preset game scene, generating the game playing method information of each agent according to the personal basic information of each agent, and adopting the game playing method information of each agent to generate the dialogue information of each agent. And generating a dialogue content cue word of each agent under the game playing method corresponding to the game playing method information, and according to the dialogue content cue word, respectively generating dialogue content of each agent by adopting a preset large model. The game playing method information is generated based on the human setting basic information of the agents, the dialogue contents of different agents are generated in batches by using a large model, the efficiency is high, and the dialogue contents are matched with human setting of the agents, so that the dialogue contents have individuation and diversity, it is ensured that different agents in the game can provide different dialogue experiences for players, and the user experience is improved. And the game immersion and interactivity are improved.

Description

Technical Field

[0001] The present application relates to the field of game technology, and more specifically, to an intelligent agent dialogue generation method, dialogue control method, device and medium. Background Art

[0002] With the rapid development of the game industry, the role of non-player characters (NPC) in the game world is becoming increasingly important. It can not only promote the plot and deliver tasks, but also enrich the game world, add vitality to the game world, and make the game world look more real.

[0003] Currently, dialogue generation tools based on artificial intelligence (AI) technology can enable NPCs to make natural responses that are relevant to the context. However, these tools are usually limited to dialogue generation and lack deep integration of NPC character backgrounds. The generated dialogue content may not match the NPC in the game scene and the generation efficiency is low. Summary of the invention

[0004] In view of this, the embodiments of the present application provide an intelligent agent dialogue generation method, a dialogue control method, a device and a medium to solve the problem of being limited to dialogue generation, lacking deep integration of the NPC character background, the generated dialogue content may not match the NPC in the game scene and the generation efficiency is low.

[0005] In a first aspect, an embodiment of the present application provides a method for generating an intelligent agent dialogue, comprising:

[0006] Get basic character information of multiple agents in the preset game scene;

[0007] Generate game play information of each intelligent agent according to basic information of the personality of each intelligent agent;

[0008] Using the game play information of each agent, generating a dialogue content prompt word for each agent under the game play corresponding to the game play information;

[0009] According to the prompt words of the conversation content, a preset large model is used to generate the conversation content of each intelligent agent respectively.

[0010] In a second aspect, the embodiment of the present application further provides a dialogue control method, including:

[0011] Get the dialogue content entered by the player for the target agent;

[0012] Detecting the conversation content of the player to obtain the game progress information of the player under the game play corresponding to the target agent;

[0013] Based on the game process information and the pre-generated dialogue content of the target intelligent agent, reply content corresponding to the player dialogue content is generated, wherein the pre-generated dialogue content is dialogue content generated by the intelligent agent dialogue generation method described in any one of the first aspects.

[0014] In a third aspect, the embodiment of the present application further provides an agent dialogue generation device, comprising:

[0015] The acquisition module is used to obtain basic information about the personalities of multiple agents in a preset game scene;

[0016] A generation module, used to generate game play information of each agent according to basic information of the personality of each agent;

[0017] The generation module is further used to use the game play information of each agent to generate a dialogue content prompt word for each agent under the game play corresponding to the game play information;

[0018] The generation module is also used to generate the dialogue content of each intelligent agent according to the dialogue content prompt words and using a preset large model.

[0019] In a fourth aspect, the embodiment of the present application further provides a dialogue control device, including:

[0020] An acquisition module, used to acquire the player dialogue content input by the player for the target intelligent agent in the preset game scene;

[0021] A detection module, used to detect the conversation content of the player and obtain the game progress information of the player under the game play corresponding to the target agent;

[0022] A generation module is used to generate reply content corresponding to the dialogue content based on the game process information and the pre-generated dialogue content of the target intelligent agent, wherein the pre-generated dialogue content is dialogue content generated by the intelligent agent dialogue generation method described in any one of the first aspects.

[0023] In the fifth aspect, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and the processor executes the machine-readable instructions to execute the method described in any one of the first aspect or the second aspect.

[0024] In a sixth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the first aspect or the second aspect is executed.

[0025] The present application provides a method for generating dialogues of intelligent agents, a method for controlling dialogues, a device and a medium, wherein the method for generating dialogues of intelligent agents includes: obtaining basic information of the personalities of multiple intelligent agents in a preset game scene, generating gameplay information of each intelligent agent based on the basic information of the personalities of each intelligent agent, using the gameplay information of each intelligent agent to generate dialogue content prompts for each intelligent agent under the gameplay corresponding to the gameplay information, and using a preset large model to generate dialogue content for each intelligent agent based on the dialogue content prompts. The embodiment of the present application generates gameplay information based on the basic information of the personalities of the intelligent agent, and uses a large model to batch generate dialogue content of the intelligent agent, which is highly efficient and matches the intelligent agent, so that the dialogue content is personalized and diverse, ensuring that different intelligent agents in the game can provide different dialogue experiences for players, and enhancing the immersion and interactivity of the game. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 1 ;

[0028] Figure 2 Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 2 ;

[0029] Figure 3 Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 3 ;

[0030] Figure 4 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 1 ;

[0031] Figure 5 Schematic diagram of the dialogue interface provided in the embodiment of the present application Figure 1 ;

[0032] Figure 6 Schematic diagram of the dialogue interface provided in the embodiment of the present application Figure 2;

[0033] Figure 7 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 2 ;

[0034] Figure 8 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 3 ;

[0035] Fig. 9 A schematic diagram of the structure of an intelligent agent dialogue generation device provided in an embodiment of the present application;

[0036] Fig.10 A schematic diagram of the structure of a dialogue control device provided in an embodiment of the present application;

[0037] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0039] First, the terms involved in this embodiment are explained:

[0040] 1. Large Language Model

[0041] The big model is a language model consisting of an artificial neural network with many parameters (usually billions of weights or more), which is trained on a large amount of unlabeled text using self-supervised learning or semi-supervised learning, and can understand and generate human language. It is a model based on deep learning technology, which mainly understands and masters the grammar, semantics and contextual relationships of the language by learning from a large amount of text data. The big model has powerful text understanding and generation capabilities and can be used to handle various natural language processing tasks, such as machine translation, text summarization, question-answering systems, etc.

[0042] 2. Non-Player Character (NPC)

[0043] Game NPCs refer to non-player characters that play a specific role in the game and can interact with players according to the rules and situations preset by the program. In many games, NPCs play a key role, such as providing tasks, trading items, providing information, etc.

[0044] 3. Prompt

[0045] Prompt can be understood as a way to start a machine learning model. It is a piece of text or sentence that guides the machine learning model to generate output of a specific type, topic or format. In the field of natural language processing, prompts usually consist of a question or task description, such as "write me an article about artificial intelligence", "translate this English sentence into French", and so on.

[0046] The agent dialogue generation method and dialogue control method in one embodiment of the present application can be run on a local terminal device or a server. When the agent dialogue generation method and dialogue control method are run on a server, the method can be implemented and executed based on a cloud interaction system, wherein the cloud interaction system includes a server and a client device.

[0047] In an optional embodiment, various cloud applications can be run under the cloud interaction system, such as cloud games. Taking cloud games as an example, cloud games refer to a game mode based on cloud computing. In the operation mode of cloud games, the operating body of the game program and the main body of the game screen presentation are separated. The storage and operation of the intelligent agent dialogue generation method and the dialogue control method are completed on the cloud game server. The role of the client device is used for data reception, transmission and presentation of the game screen. For example, the client device can be a display device with data transmission function close to the user side, such as a mobile terminal, a TV, a computer, a handheld computer, etc.; but the cloud game server in the cloud is used for information processing. When playing the game, the player operates the client device to send an operation instruction to the cloud game server. The cloud game server runs the game according to the operation instruction, encodes and compresses the game screen and other data, and returns it to the client device through the network. Finally, the client device decodes and outputs the game screen.

[0048] In an optional embodiment, taking a game as an example, a local terminal device stores a game program and is used to present a game screen. The local terminal device is used to interact with the player through a graphical user interface, that is, the game program is downloaded and installed by an electronic device and run conventionally. The local terminal device may provide the graphical user interface to the player in a variety of ways, for example, it may be rendered and displayed on a display screen of the terminal, or provided to the player through a holographic projection. For example, the local terminal device may include a display screen and a processor, the display screen is used to present a graphical user interface, the graphical user interface includes a game screen, and the processor is used to run the game, generate a graphical user interface, and control the display of the graphical user interface on the display screen.

[0049] In one possible implementation, an embodiment of the present invention provides an intelligent agent dialogue generation method and a dialogue control method, providing a graphical user interface through a terminal device, wherein the terminal device can be the local terminal device mentioned above, or it can be a client device in the cloud interaction system mentioned above.

[0050] At present, dialogue generation tools based on artificial intelligence (AI) technology can enable NPCs to make natural responses relevant to the context, but these tools are usually limited to dialogue generation and lack deep integration of the NPC's background. The generated dialogue content may not match the NPC in the game scene and the generation efficiency is low. In addition, in large-scale games such as role-playing games (RPGs) and open worlds, the number of non-player characters (NPCs) is usually very large. For example, the number of NPCs in some games can easily reach thousands or even more. At present, there is also a problem of insufficient efficiency in generating NPC dialogue content, making it difficult to support batch generation of NPC dialogue content.

[0051] Based on this, in order to enhance the sense of immersion and experience, the present application provides a solution for automatic batch generation of dialogue content of intelligent agents, which can batch set the basic information of the personalities of intelligent agents, generate gameplay information based on the basic information of the personalities of intelligent agents, and use large models to batch generate dialogue content of intelligent agents, which greatly improves the efficiency of creating dialogue content of intelligent agents in large-scale game development. The use of large models can efficiently implement the generation process of dialogue content, greatly reducing manual intervention and repetitive work. Moreover, the dialogue content of the intelligent agent does not deviate from the background of the game story, has a unique background setting, and matches the intelligent agent, so that the dialogue content is personalized and diverse, ensuring that different intelligent agents in the game can provide players with different dialogue experiences, thereby enhancing the immersion and interactivity of the game.

[0052] Figure 1Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 1 The execution subject of this embodiment may be an electronic device, such as a local terminal device or a server.

[0053] like Figure 1 As shown, the method may include:

[0054] S101. Obtain basic character information of multiple intelligent agents in a preset game scene.

[0055] Among them, the intelligent agent is an NPC, and the preset game scene includes multiple intelligent agents. The basic personality information of the intelligent agent is used to indicate the basic personality of the intelligent agent in the preset game scene. The basic personality information may include at least one of name, age, identity, gender, location, personality, and background. Among them, the name can be, for example, "Zhang San" or "Li Si", the age can be, for example, "20 years old" or "25 years old", the identity can be, for example, "weak scholar" or "killer", the personality can be, for example, "sensitive" or "cowardly", the location is used to indicate the position of the intelligent agent in the preset game scene, such as "in the valley" or "in the woods", and the background is used to indicate the story line of the intelligent machine in the preset game scene, for example, "losing both parents", "alcoholic", "obsessed with anthers, and has never been sure that anthers can cure eye diseases".

[0056] Developers can set the basic personality information of each intelligent entity according to the actual needs of the game, and input the basic personality information of each intelligent entity into the electronic device.

[0057] S102. Generate game play information for each intelligent agent based on basic personality information of each intelligent agent.

[0058] The gameplay information of each intelligent agent is generated based on the basic personality information of each intelligent agent, wherein the gameplay information is used to indicate the gameplay of each intelligent agent determined based on the basic personality information of each intelligent agent, and the gameplay information is used to indicate the player's gameplay for each intelligent agent. The gameplay information may include, for example, game goal information and game strategy information, wherein the game goal information is used to indicate the game goal that the player wants to achieve by conquering the intelligent agent, and the game strategy information is used to indicate the game strategy adopted by the player to achieve the game goal.

[0059] For example, if the basic character information is "Zhang San is a 20-year-old weak scholar who lost both his parents", the corresponding game goal can be "persuade Zhang San to find a way to let go of his grief", and the game strategies can include "providing the consequences of continued grief" and "providing other ways of commemoration".

[0060] For example, if the basic character information is "Li Si is a researcher obsessed with anthers, and has never been sure that anthers can cure eye diseases", the corresponding game goal can be "Convince Li Si that anthers can definitely cure eye diseases", and game strategies can include "Provide books on anthers for treating eye diseases", "Provide information about people who have successfully used anthers to treat eye diseases", and "Suggest contacting an older herbalist".

[0061] For another example, if the basic character information is "Wang Yi is sensitive and timid", then the corresponding game goal is "persuading Wang Yi to muster up the courage to confess to the woman", and the game strategy may include "providing evidence that the woman has a good impression of Wang Yi".

[0062] In an optional implementation, the above step S102, generating the game play information of each agent according to the basic personality information of each agent, may include:

[0063] According to the basic information of the personality of each intelligent agent and the first prompt word, a preset large model is used to generate detailed personality information, game goal information and game strategy information of each intelligent agent. The gameplay information includes: detailed personality information, game goal information and game strategy information.

[0064] Among them, the first prompt word is used to guide the preset large model to generate detailed personality information, game goal information and game strategy information of each intelligent agent, and the first prompt word can be PromptA.

[0065] The basic personality information of each intelligent agent and the first prompt word are input into the preset large model to generate the detailed personality information, game goal information and game strategy information of each intelligent agent, wherein the detailed personality information is used to indicate the specific detailed personality of each intelligent agent. For example, the basic personality information is "Li Si is a researcher obsessed with anthers, and has never been sure that anthers can treat eye diseases"; the detailed personality information is "Li Si is a researcher obsessed with anthers. He heard that someone used anthers to cure his eyes and he was very interested in this anther. However, due to the lack of conclusive evidence, he has never been sure of the miraculous effect of anthers. He respects the older herbal masters and often asks them for advice."

[0066] It is worth mentioning that it is also possible to check whether the generated game objectives and game strategies are consistent with the worldview corresponding to the preset game scene. If not, the first prompt word is regenerated, and the regenerated first prompt word and the basic information of the character are used to generate detailed character information, game objective information and game strategy information. Among them, if the game objectives and game strategies do not meet the storyline development of the preset game scene, they do not meet the worldview of the preset game scene. For example, if the game objectives no longer exist in the development of the storyline, the game objectives do not meet the development of the storyline.

[0067] S103, using the game play information of each intelligent agent to generate dialogue content prompt words for each intelligent agent under the game play corresponding to the game play information.

[0068] The gameplay information of each intelligent agent is used to generate dialogue content prompts for each intelligent agent under the gameplay corresponding to the gameplay information, wherein the dialogue content prompts are used to guide the preset large model to generate the dialogue content between each intelligent agent and the player, and the dialogue content prompts are related to the gameplay corresponding to the gameplay information of each intelligent agent, that is, related to the detailed personality information, game goal information and game strategy information of each intelligent agent.

[0069] In an optional implementation, each of the above step S103, using the game play information of each agent to generate a conversation content prompt word for each agent under the game play information corresponding to the game play information, may include:

[0070] According to the game play information of each intelligent agent and the second prompt word, a preset large model is used to generate the dialogue content prompt word.

[0071] The second prompt is used to guide the preset large model to generate prompts for each dialogue content. The second prompt can be PromptB. The gameplay information of each agent and the second prompt are input into the preset large model to generate prompts for the dialogue content of each agent. The prompt for the dialogue content can be PromptC. In this way, AI technology can be used to batch generate a set of prompts for the dialogue content of multiple agents, namely, the PromptC set.

[0072] In an optional implementation, based on the game play information, second prompt words, character constraint information, and safety constraint information of each agent, a preset large model is used to generate dialogue content prompt words.

[0073] Among them, the character constraint information is used to indicate the character constraints of the intelligent agent in the preset game scene, for example, it may include the inability to speak without being separated from the identity, that is, the speech constraint; the safety constraint information is used to indicate the safety constraints of the intelligent agent in the preset game scene, for example, it may include sensitive topic constraints and political topic constraints.

[0074] S104. Based on the prompt words of the conversation content, a preset large model is used to generate the conversation content of each intelligent agent.

[0075] Input the conversation content prompt words into the preset large model, and generate the conversation content of each intelligent agent respectively, so that each intelligent agent can be controlled to have a conversation with the player under the corresponding game play based on the conversation content. Among them, the conversation content includes: the reply content to the player's conversation content input by the player. It should be noted that if the basic information of the personality of multiple intelligent agents is input, according to the method of the embodiment of the present application, the conversation content corresponding to multiple intelligent agents can be generated in batches to improve efficiency.

[0076] It is worth noting that if the generated dialogue content does not meet the preset requirements, the second prompt word can be adjusted to regenerate the dialogue content prompt word using the adjusted second prompt word, and the dialogue content of the agent is regenerated using the regenerated dialogue content prompt word. Thus, the dialogue content that meets the preset requirements is generated by improving the generation quality of the dialogue content prompt word.

[0077] In addition, since the generation quality of the preset large model is uncontrollable, a format verification algorithm can also be used to perform format verification on the dialogue content prompt words to ensure the stability of the dialogue content prompt words during a large-scale output process.

[0078] In this embodiment, based on the basic information of the intelligent agent's personality, the gameplay information is generated, and the dialogue content of the intelligent agent is generated in batches using a large model, which greatly improves the efficiency of creating the dialogue content of the intelligent agent in large-scale game development. The use of the large model can efficiently implement the generation process of the dialogue content, greatly reducing manual intervention and repetitive work. In addition, the dialogue content of the intelligent agent does not deviate from the background of the game story, has a unique background setting, is highly efficient and matches the personality of the intelligent agent, so that the dialogue content is personalized and diverse, ensuring that different intelligent agents in the game can provide players with different dialogue experiences, thereby enhancing the immersion and interactivity of the game.

[0079] Figure 2 Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 2 ,like Figure 2 As shown, in an optional implementation, the method may further include:

[0080] S201. According to the personality adjustment operation for the first intelligent agent, adjust the basic personality information of the first intelligent agent.

[0081] Among them, the first intelligent agent is any one or more of the multiple intelligent agents. For example, based on the conversation content of each intelligent agent, through blind test scoring, an intelligent agent with outstanding personality characteristics and strong interest is selected from the multiple intelligent agents as the first intelligent agent.

[0082] The developer can input a character adjustment operation for the first intelligent agent according to actual game requirements, and adjust the basic character information of the first intelligent agent according to the character adjustment operation.

[0083] S202. Regenerate the game play information of the first intelligent agent based on the adjusted basic character information.

[0084] S203. Update the conversation content of the first agent based on the regenerated game play information of the first agent.

[0085] Based on the adjusted basic information of the character, the gameplay information of the first intelligent agent is regenerated, and the regenerated gameplay information of the first intelligent agent is used to generate dialogue content prompts for the first intelligent agent under the gameplay corresponding to the regenerated gameplay information, and based on the regenerated dialogue content prompts, a preset large model is used to update the dialogue content of the first intelligent agent.

[0086] In this embodiment, after generating the dialogue content of the first intelligent agent, the basic personality information of the first intelligent agent can be adjusted through secondary editing, and the dialogue content of the first intelligent agent can be updated, thereby adjusting the dialogue logic and interactive content of the first intelligent agent, supporting the customization of more content, enhancing the playability of the dialogue of the first intelligent agent, improving the fun of its replies, and improving the player's gaming experience.

[0087] Figure 3 Schematic diagram of the process of the agent dialogue generation method provided in the embodiment of the present application Figure 3 ,like Figure 3 As shown, in an optional implementation, the method may further include:

[0088] S301. Adjust the game play information of the second agent according to the game play adjustment operation for the second agent.

[0089] The second agent is any one or more of the multiple agents. For example, based on the conversation content of each agent, an agent with outstanding personality traits and strong interest is selected from the multiple agents through blind test scoring as the second agent.

[0090] According to actual game needs, a gameplay adjustment operation for the second intelligent agent can be input, and the game play information of the second intelligent agent can be adjusted according to the gameplay adjustment operation. For example, at least one of the second intelligent agent's character details, game goal information, and game strategy information can be adjusted.

[0091] S302. Generate, based on the adjusted gameplay information, a dialogue content prompt for the second agent under the gameplay corresponding to the adjusted gameplay information.

[0092] S303: Update the conversation content of the second agent according to the regenerated conversation content prompt words.

[0093] According to the adjusted or updated gameplay information, the dialogue content prompt words of the second agent under the adjusted gameplay corresponding to the gameplay are generated, and according to the re-generated dialogue content prompt words, the preset large model is used to update the dialogue content of the second agent.

[0094] In an optional embodiment, the method may further include:

[0095] S304. According to the dialogue adjustment operation for the third intelligent agent, adjust the dialogue content of the third intelligent agent.

[0096] Among them, the third intelligent agent is any one or more of the multiple intelligent agents. For example, based on the conversation content of each intelligent agent, through blind test scoring, an intelligent agent with outstanding personality characteristics and strong interest is selected from the multiple intelligent agents as the third intelligent agent.

[0097] Developers can input dialogue adjustment operations for the third agent based on actual game needs and adjust the dialogue content of the third agent, that is, adjust the reply content returned to the player based on the player's dialogue content.

[0098] In this embodiment, after generating the dialogue content of the second intelligent agent, the gameplay information of the second intelligent agent can be adjusted through secondary editing, and the dialogue content of the second intelligent agent can be updated, thereby adjusting the dialogue logic and interactive content of the second intelligent agent, supporting customization of more content, enhancing the playability of the dialogue of the second intelligent agent, improving the interestingness of its replies, and improving the player's gaming experience. Moreover, after generating the dialogue content of the third intelligent agent, the dialogue content of the third intelligent agent can be adjusted through secondary editing, thereby adjusting the dialogue logic and interactive content of the third intelligent agent, supporting customization of more content, enhancing the playability of the dialogue of the third intelligent agent, improving the interestingness of its replies, and improving the player's gaming experience.

[0099] Figure 4 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 1 The execution subject of this embodiment can be an electronic device, such as a local terminal device that can run the game. Based on the above embodiment, this embodiment is applied to enable players to better communicate with the intelligent agent during the actual operation of the game and read the dialogue content that better matches the intelligent agent's personality.

[0100] like Figure 4 As shown, the method may include:

[0101] S401, obtaining the player dialogue content input by the player for the target intelligent agent.

[0102] During the game, the player can input a dialogue trigger operation through the graphical user interface, and in response to the dialogue trigger operation, a dialogue interface is displayed, wherein the dialogue trigger operation can be a touch operation acting on a dialogue control in the graphical user interface.

[0103] The target intelligent agent is any one of multiple intelligent agents. A dialog box can be provided in the dialogue interface. The player enters the player dialogue content for the target intelligent agent in the dialog box and displays it on the chat interface. In this way, the electronic device can obtain the player dialogue content for the target intelligent agent entered by the player, and the player dialogue content is text dialogue content.

[0104] A voice input control can also be provided in the dialogue interface. Players can click the voice input control to input player dialogue content for the target intelligent body. The player dialogue content is voice dialogue content. Of course, the electronic device can also convert the voice dialogue content into text dialogue content when collecting the voice dialogue content and display it in the chat interface.

[0105] Through voice recognition technology, players no longer need to type to communicate with the intelligent agent. They can get a response from the intelligent agent by speaking naturally, allowing the communication between players and intelligent agents to reach a new dimension and improving the gaming experience.

[0106] S402: Detect the player's conversation content to obtain the player's game progress information under the game play corresponding to the target intelligent agent.

[0107] Specifically, the player's conversation content is detected to obtain the player's game progress information under the game play corresponding to the target intelligent agent, wherein the game progress information is used to indicate whether the player meets the preset clearance conditions under the game play corresponding to the target intelligent agent.

[0108] The preset clearance condition may, for example, be that the cumulative number of times the game strategy of the target intelligent entity is triggered by the player's conversation content reaches a preset number of times. If the cumulative number of times the game strategy of the target intelligent entity is triggered by the player's conversation content reaches the preset number of times, it is determined that the player meets the preset clearance condition under the corresponding gameplay of the target intelligent entity. If the cumulative number of times the game strategy of the target intelligent entity is triggered by the player's conversation content does not reach the preset number of times, it is determined that the player does not meet the preset clearance condition under the corresponding gameplay of the target intelligent entity. The preset number of times may, for example, be 1 or 2 times.

[0109] See also Figure 5 , the target agent’s reply is “I heard that there is a record in an ancient book”, and the player’s dialogue is “I know where it is”. It can be seen that “I know where it is” triggers the game strategy of “providing books that provide anthers to treat eye diseases”, and the cumulative number of triggers is 1.

[0110] It is worth noting that if the player conversation content is consistent with the game strategy of the target intelligent agent, it means that the player conversation content triggers the game strategy of the target intelligent agent, and the cumulative number of triggers is 1. If the conversation contents of both players trigger the game strategy of the target intelligent agent, the cumulative number of triggers is 2. The number of game strategies includes but is not limited to one, and the cumulative number of triggers is for all game strategies, not for the same game strategy.

[0111] S403: Generate reply content corresponding to the player's dialogue content based on the game process information and the pre-generated dialogue content of the target intelligent agent.

[0112] Among them, the pre-generated dialogue content is the dialogue content of the target intelligent agent generated by the above-mentioned intelligent agent dialogue generation method.

[0113] The pre-generated dialogue content may include: clearance words for the player's dialogue content when the player meets the preset clearance conditions under the corresponding game play of the target intelligent agent, and reply words for the player's dialogue content when the player does not meet the preset clearance conditions.

[0114] There are two situations where the player does not meet the preset clearance conditions: one is that the player's conversation content triggers the game strategy, but does not meet the preset number of times, and the other is that the player's conversation content does not trigger the game strategy. Accordingly, when the player does not meet the preset clearance conditions, the reply words for the player's conversation content include: the reply words when the player's conversation content triggers the game strategy, and the reply words when the player's conversation content does not trigger the game strategy, wherein the number of game strategies includes but is not limited to one, and different game strategies may correspond to different reply words. Therefore, according to the game process information and the pre-generated conversation content of the target intelligent body, the reply content corresponding to the player's conversation content can be generated and displayed on the conversation interface.

[0115] In an optional embodiment, if the game progress information indicates that the player meets the preset clearance conditions of the target agent under the corresponding game play, the clearance words in the pre-generated dialogue content are determined as the reply content.

[0116] Among them, the pre-generated dialogue content may include: the clearance dialogue when the player meets the preset clearance conditions under the corresponding game play of the target intelligent agent.

[0117] If the game progress information indicates that the player meets the preset clearance conditions, that is, the cumulative number of times the player's dialogue content triggers the game strategy of the target intelligent agent reaches the preset number of times, then the clearance words are determined from the pre-generated dialogue content as the reply content.

[0118] In an optional embodiment, if the game progress information indicates that the player does not meet the preset clearance conditions of the target agent under the corresponding game play, the corresponding reply words are matched in the pre-generated dialogue content as the reply content.

[0119] The pre-generated dialogue content may include: reply words for different player dialogue contents when the player does not meet the preset clearance conditions, wherein the player dialogue content when the player does not meet the preset clearance conditions includes two situations, one is that the player dialogue content triggers the game strategy, and the other is that the player dialogue content does not trigger the game strategy. Therefore, the reply words include: reply words when the player dialogue content triggers the game strategy and reply words when the game strategy is not triggered.

[0120] If the game progress information indicates that the player does not meet the preset clearance conditions, and the player's dialogue content triggers the game strategy of the target agent corresponding to the gameplay, the reply words when the game strategy is triggered are matched from the pre-generated dialogue content as the reply content.

[0121] If the game progress information indicates that the player does not meet the preset clearance conditions and the player's dialogue content does not trigger the game strategy, the reply words when the game strategy is determined not to be triggered are matched from the pre-generated dialogue content as the reply content.

[0122] For example, the game strategies include "providing books on flower medicine for treating eye diseases", "providing information about people who have successfully used flower medicine for treating eye diseases", "suggesting contacting an older herbalist", and the preset number of times is 2. Figure 5 Schematic diagram of the dialogue interface provided in the embodiment of the present application Figure 1 ,like Figure 5 As shown, the target agent's dialogue content is "I have heard of magical herbs that are said to make people's eyes bright", and the player's dialogue content is "No". It can be seen that the player's input "visible" did not trigger the game strategy, so the reply speech when the game strategy was not triggered was "I heard that there is a record in an ancient book", and the player's dialogue content is "I know where it is". It can be seen that "I know where it is" triggered the game strategy of "providing books with flower essences to treat eye diseases", and the cumulative number of triggers is 1. The reply speech under the game strategy of "providing books with flower essences to treat eye diseases" is "If it is really recorded in ancient books, that would be great", and the player's dialogue content is "I saw it at a herbal medicine master", it can be seen that "I saw it at a herbal medicine master" also triggered the game strategy of "providing books with flower essences to treat eye diseases", and the cumulative number of triggers is 2. At this point, the player meets the preset clearance conditions, and the target agent's clearance speech is "Great, I will definitely read books carefully to study herbs."

[0123] For example, the game strategy includes "providing the consequences of continued grief", "providing other ways to commemorate", and the preset number of times is 2. Figure 6 Schematic diagram of the dialogue interface provided in the embodiment of the present application Figure 2 ,like Figure 6As shown, the target agent's dialogue content is "My parents left me alone and helpless", and the player's dialogue content is "It's not good for your health to be sad all the time, and your parents must want you to cheer up", it can be seen that the player's input "It's not good for your health to be sad all the time, and your parents must want you to cheer up" triggered the game strategy of "providing the consequences of continued grief", and the cumulative number of triggers is 1. The reply under the game strategy of "providing the consequences of continued grief" is "Having said that, my parents are gone, and there is no hope in this world", and the player's dialogue content is "You can commemorate your parents in your heart", it can be seen that the player's input "You can commemorate your parents in your heart, so that your parents will not disappear" triggered the game strategy of "providing other ways of commemoration", and the cumulative number of triggers is 2. At this point, the player meets the preset clearance conditions, and the clearance speech of the target agent is "Thank you for your guidance, I will remember it in my heart."

[0124] In this embodiment, the target agent is controlled to have a conversation with the player based on the target agent's dialogue content, and the target agent can respond to the player vividly, which greatly enhances the immersion and interactivity of the game.

[0125] Figure 7 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 2 ,like Figure 7 As shown, in an optional implementation, the above step S402, detecting the player's conversation content to obtain the player's game progress information under the game play corresponding to the target agent, may include:

[0126] S501: Detect the player's conversation content and obtain the detection result.

[0127] S502. Obtain the game progress information of the player under the game play corresponding to the target intelligent agent according to the cumulative number of triggering of the game strategy.

[0128] The player conversation content is detected to obtain the detection result of the player conversation content. The detection result is used to indicate whether the player conversation content triggers the game strategy of the target intelligent agent under the corresponding game play and the cumulative number of triggering of the game strategy.

[0129] If the cumulative number of triggering of the game strategy reaches the preset number of times, it is determined that the player meets the preset clearance conditions under the corresponding game play of the target intelligent agent. If the cumulative number of triggering of the game strategy does not reach the preset number of times, it is determined that the player does not meet the preset clearance conditions under the corresponding game play of the target intelligent agent, and then the game progress information of the player under the corresponding game play of the target intelligent agent is obtained.

[0130] Figure 8 Schematic diagram of the process of the dialogue control method provided in the embodiment of the present application Figure 3 ,like Figure 8 As shown, in an optional implementation, the method may further include:

[0131] S601. Generate dialogue animation information of the target intelligent agent according to the reply content.

[0132] S602. According to the dialogue animation information, an animation is rendered for the target agent in a preset game scene, and / or an animation corresponding to the dialogue animation information is rendered and displayed at a preset display position of the reply content.

[0133] Analyze the reply content to generate a dialogue animation of the target intelligent agent. The dialogue animation may include facial expression animation information and / or body animation information. The facial expression animation information may include, for example, shining eyes, frowning and shaking head, nodding with joy, etc. The body animation information may include, for example, raising both hands, waving with one hand, jumping with both legs, etc.

[0134] According to the dialogue animation information, an animation is rendered for the target intelligent agent in the preset game scene, wherein the preset game scene includes a three-dimensional model of the target intelligent agent, and / or, an animation corresponding to the dialogue animation information is rendered and displayed at a preset display position of the reply content, wherein the reply content is displayed in the dialogue interface, and the preset display position is the preset display position of the reply content in the dialogue interface, see Figure 5 The (eyes shining), (frown and shake head), and (nod head happily) in the picture respectively represent the animation of eyes shining, the animation of frowning and shaking head, and the animation of nodding head happily. Figure 6 The same applies to (takes a sip of wine, tears in his eyes), (shakes his head and sighs), (eyes regain their spirits).

[0135] In this embodiment, based on the animation generation technology, when the player talks with the target intelligent agent, the intelligent agent can respond to the player's dialogue with vivid expressions and natural movements, which greatly enhances the immersion and interactivity of the game.

[0136] Fig. 9 This is a schematic diagram of the structure of an intelligent agent dialogue generation device provided in an embodiment of the present application, which can be integrated into an electronic device.

[0137] like Fig. 9 As shown, the device may include:

[0138] An acquisition module 701 is used to acquire basic character information of multiple agents in a preset game scene;

[0139] A generation module 702, for generating game play information of each agent according to basic character information of each agent;

[0140] The generation module 702 is further used to use the game play information of each agent to generate a dialogue content prompt word for each agent under the game play information corresponding to the game play information;

[0141] The generation module 702 is also used to generate the dialogue content of each intelligent agent according to the dialogue content prompt words and using the preset large model.

[0142] In an optional implementation, the generating module 702 is specifically configured to:

[0143] According to the basic information of the personality of each intelligent agent and the first prompt word, a preset large model is used to generate detailed personality information, game goal information and game strategy information for each intelligent agent; the gameplay information includes: detailed personality information, game goal information and game strategy information.

[0144] In an optional implementation, the generating module 702 is specifically configured to:

[0145] According to the game play information of each intelligent agent and the second prompt word, a preset large model is used to generate the dialogue content prompt word.

[0146] In an optional embodiment, the device further comprises:

[0147] An adjustment module 703 is used to adjust basic personality information of the first agent according to a personality adjustment operation for the first agent;

[0148] The generation module 702 is further used to regenerate the game play information of the first agent according to the adjusted basic character information;

[0149] The updating module 704 is used to update the dialogue content of the first agent according to the regenerated game play information of the first agent.

[0150] In an optional implementation, the adjustment module 703 is further configured to:

[0151] Adjusting the game play information of the second agent according to the game play adjustment operation for the second agent;

[0152] The generation module 702 is further used to generate, according to the adjusted game play information, a dialogue content prompt word of the second agent under the game play information corresponding to the adjusted game play information;

[0153] The updating module 704 is also used to update the conversation content of the second agent according to the regenerated conversation content prompt words.

[0154] In an optional implementation, the adjustment module 703 is further configured to:

[0155] According to the dialogue adjustment operation for the third intelligent agent, the dialogue content of the third intelligent agent is adjusted to control the third intelligent agent to communicate with the player under the corresponding game play based on the adjusted dialogue content.

[0156] In this embodiment, the acquisition module is used to acquire basic character information of multiple agents in a preset game scene, the generation module is used to generate game play information of each agent based on the basic character information of each agent, the generation module is also used to use the game play information of each agent to generate dialogue content prompts for each agent under the game play information corresponding to the game play information, and the generation module is also used to use the preset large model to generate the dialogue content of each agent respectively based on the dialogue content prompts. Based on the basic character information of the agent, the game play information is generated, and the dialogue content of the agent is generated in batches using the large model, so that the dialogue content has personalization and diversity, ensuring that different agents in the game can provide different dialogue experiences for players, and enhancing the immersion and interactivity of the game.

[0157] Fig.10 This is a schematic diagram of the structure of a dialogue control device provided in an embodiment of the present application, which can be integrated into an electronic device.

[0158] like Fig.10 As shown, the device may include:

[0159] An acquisition module 801 is used to acquire the player dialogue content input by the player for the target agent in the preset game scene;

[0160] The detection module 802 is used to detect the player's dialogue content and obtain the player's game progress information under the game play corresponding to the target agent;

[0161] The generation module 803 is used to generate reply content corresponding to the player's dialogue content based on the game process information and the pre-generated dialogue content of the target intelligent agent, wherein the pre-generated dialogue content is the dialogue content generated by the intelligent agent dialogue generation method.

[0162] In an optional implementation, the detection module 802 is further configured to:

[0163] Detect the player's conversation content and obtain the detection result, which is used to indicate whether the conversation content triggers the game strategy of the target agent under the corresponding game play and the cumulative number of times the game strategy is triggered;

[0164] According to the cumulative triggering times of the game strategy, the game progress information of the player under the corresponding game play of the target intelligent agent is obtained.

[0165] In an optional implementation, the generating module 803 is specifically configured to:

[0166] If the game progress information indicates that the player meets the preset clearance conditions under the corresponding game play of the target agent, the clearance words in the pre-generated dialogue content are determined as the reply content.

[0167] In an optional implementation, the generating module 803 is specifically configured to:

[0168] If the game progress information indicates that the player does not meet the preset clearance conditions of the target agent under the corresponding game play, the corresponding reply words are matched in the pre-generated dialogue content to generate the reply content.

[0169] In an optional implementation, the generating module 803 is further configured to:

[0170] Generate dialogue animation information of the target agent based on the reply content;

[0171] The rendering module 804 is used to perform animation rendering on the target intelligent agent in the preset game scene according to the dialogue animation information, and / or to render and display the animation corresponding to the dialogue animation information at the preset display position of the reply content.

[0172] In this embodiment, the acquisition module is used to acquire the player dialogue content input by the player for the target agent in the preset game scene, the detection module is used to detect the player dialogue content and obtain the game process information of the player under the game play corresponding to the target agent, and the generation module is used to generate the reply content corresponding to the dialogue content according to the game process information and the pre-generated dialogue content of the target agent. Based on the dialogue content of the target agent, the target agent is controlled to have a dialogue with the player, and the target agent can respond to the player vividly, which greatly enhances the immersion and interactivity of the game.

[0173] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Fig.11 As shown, the device may include: a processor 1001, a memory 1002 and a bus 1003, the memory 1002 stores machine-readable instructions executable by the processor 1001, when the electronic device is running, the processor 1001 communicates with the memory 1002 through the bus 1003, and the processor 1001 executes the machine-readable instructions to perform the following steps:

[0174] Get basic character information of multiple agents in the preset game scene;

[0175] Generate game play information for each agent based on the basic information of each agent’s personality;

[0176] Using the game play information of each agent, generating a dialogue content prompt word for each agent under the game play information corresponding to the game play information;

[0177] According to the prompt words of the conversation content, the preset large model is used to generate the conversation content of each intelligent agent.

[0178] In an optional implementation, the game play information of each agent is generated based on the basic information of the personality of each agent, including:

[0179] According to the basic information of the personality of each intelligent agent and the first prompt word, a preset large model is used to generate detailed personality information, game goal information and game strategy information for each intelligent agent; the gameplay information includes: detailed personality information, game goal information and game strategy information.

[0180] In an optional implementation, the game play information of each agent is used to generate a dialogue content prompt word of each agent under the game play corresponding to the game play information, including:

[0181] According to the game play information of each intelligent agent and the second prompt word, a preset large model is used to generate the dialogue content prompt word.

[0182] In an optional embodiment, the method further comprises:

[0183] According to the personality adjustment operation for the first agent, adjust the basic personality information of the first agent;

[0184] Regenerate the gameplay information of the first agent based on the adjusted basic character information;

[0185] Update the conversation content of the first agent based on the regenerated gameplay information of the first agent.

[0186] In an optional embodiment, the method further comprises:

[0187] Adjusting the game play information of the second agent according to the game play adjustment operation for the second agent;

[0188] Generate, according to the adjusted game play information, a dialogue content prompt word of the second agent under the game play corresponding to the adjusted game play information;

[0189] Update the conversation content of the second agent based on the regenerated conversation content prompt words.

[0190] In an optional embodiment, the method further comprises:

[0191] According to the dialogue adjustment operation for the third intelligent agent, the dialogue content of the third intelligent agent is adjusted to control the third intelligent agent to communicate with the player under the corresponding game play based on the adjusted dialogue content.

[0192] Alternatively, perform the following steps:

[0193] Get the player dialogue content entered by the player for the target agent;

[0194] Detect the player's conversation content and obtain the player's game progress information under the corresponding game play of the target agent;

[0195] According to the game process information and the pre-generated dialogue content of the target intelligent agent, the reply content corresponding to the player's dialogue content is generated, wherein the pre-generated dialogue content is the dialogue content generated by the intelligent agent dialogue generation method.

[0196] In an optional implementation, the player's conversation content is detected to obtain the player's game progress information under the game play corresponding to the target agent, including:

[0197] Detect the player's conversation content and obtain the detection result, which is used to indicate whether the player's conversation content triggers the game strategy of the target agent under the corresponding game play and the cumulative number of times the game strategy is triggered;

[0198] According to the cumulative triggering times of the game strategy, the game progress information of the player under the corresponding game play of the target intelligent agent is obtained.

[0199] In an optional implementation, based on the game process information and the pre-generated dialogue content of the target agent, the reply content corresponding to the player's dialogue content is generated, including:

[0200] If the game progress information indicates that the player meets the preset clearance conditions under the corresponding game play of the target agent, the clearance words in the pre-generated dialogue content are determined as the reply content.

[0201] In an optional implementation, based on the game process information and the pre-generated dialogue content of the target agent, the reply content corresponding to the player's dialogue content is generated, including:

[0202] If the game progress information indicates that the player does not meet the preset clearance conditions of the target agent under the corresponding game play, the corresponding reply words are matched in the pre-generated dialogue content as the reply content.

[0203] In an optional embodiment, the method further comprises:

[0204] Generate dialogue animation information of the target agent based on the reply content;

[0205] According to the dialogue animation information, the target intelligent agent in the preset game scene is animated, and / or the animation corresponding to the dialogue animation information is rendered and displayed at the preset display position of the reply content.

[0206] In this embodiment, the processor executes machine-readable instructions to obtain basic character information of multiple agents in a preset game scene, generate game play information of each agent according to the basic character information of each agent, use the game play information of each agent to generate dialogue content prompt words of each agent under the game play corresponding to the game play information, and use the preset large model to generate the dialogue content of each agent according to the dialogue content prompt words. Based on the basic character information of the agent, the game play information is generated, and the dialogue content of the agent is generated in batches using the large model, so that the dialogue content has personalization and diversity, ensuring that different agents in the game can provide different dialogue experiences for players, and improving the immersion and interactivity of the game, or obtaining the player dialogue content input by the player for the target agent, detecting the player dialogue content, obtaining the game process information of the player under the game play corresponding to the target agent, and generating the reply content corresponding to the dialogue content according to the game process information and the pre-generated dialogue content of the target agent. Based on the dialogue content of the target agent, the target agent is controlled to have a dialogue with the player, and the target agent can reply to the player in a vivid way, which greatly improves the immersion and interactivity of the game.

[0207] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps:

[0208] Get basic character information of multiple agents in the preset game scene;

[0209] Generate game play information for each agent based on the basic information of each agent’s personality;

[0210] Using the game play information of each agent, generating a dialogue content prompt word for each agent under the game play information corresponding to the game play information;

[0211] According to the prompt words of the conversation content, a preset large model is used to generate the conversation content of each intelligent agent respectively.

[0212] In an optional implementation, the game play information of each agent is generated based on the basic information of the personality of each agent, including:

[0213] According to the basic information of the personality of each intelligent agent and the first prompt word, a preset large model is used to generate detailed personality information, game goal information and game strategy information for each intelligent agent; the gameplay information includes: detailed personality information, game goal information and game strategy information.

[0214] In an optional implementation, the game play information of each agent is used to generate a dialogue content prompt word of each agent under the game play corresponding to the game play information, including:

[0215] According to the game play information of each intelligent agent and the second prompt word, a preset large model is used to generate the dialogue content prompt word.

[0216] In an optional embodiment, the method further comprises:

[0217] According to the personality adjustment operation for the first agent, adjust the basic personality information of the first agent;

[0218] Regenerate the gameplay information of the first agent based on the adjusted basic character information;

[0219] Update the conversation content of the first agent based on the regenerated gameplay information of the first agent.

[0220] In an optional embodiment, the method further comprises:

[0221] Adjusting the game play information of the second agent according to the game play adjustment operation for the second agent;

[0222] Generate, according to the adjusted game play information, a dialogue content prompt word of the second agent under the game play corresponding to the adjusted game play information;

[0223] Update the conversation content of the second agent based on the regenerated conversation content prompt words.

[0224] In an optional embodiment, the method further comprises:

[0225] According to the dialogue adjustment operation for the third intelligent agent, the dialogue content of the third intelligent agent is adjusted to control the third intelligent agent to communicate with the player under the corresponding game play based on the adjusted dialogue content.

[0226] Alternatively, perform the following steps:

[0227] Get the player dialogue content entered by the player for the target agent;

[0228] Detect the player's conversation content and obtain the player's game progress information under the corresponding game play of the target agent;

[0229] According to the game process information and the pre-generated dialogue content of the target intelligent agent, the reply content corresponding to the player's dialogue content is generated, wherein the pre-generated dialogue content is the dialogue content generated by the intelligent agent dialogue generation method.

[0230] In an optional implementation, the player's conversation content is detected to obtain the player's game progress information under the game play corresponding to the target agent, including:

[0231] Detect the player's conversation content and obtain the detection result, which is used to indicate whether the player's conversation content triggers the game strategy of the target agent under the corresponding game play and the cumulative number of times the game strategy is triggered;

[0232] According to the cumulative triggering times of the game strategy, the game progress information of the player under the corresponding game play of the target intelligent agent is obtained.

[0233] In an optional implementation, based on the game process information and the pre-generated dialogue content of the target agent, the reply content corresponding to the player's dialogue content is generated, including:

[0234] If the game progress information indicates that the player meets the preset clearance conditions under the corresponding game play of the target agent, the clearance words in the pre-generated dialogue content are determined as the reply content.

[0235] In an optional implementation, based on the game process information and the pre-generated dialogue content of the target agent, the reply content corresponding to the player's dialogue content is generated, including:

[0236] If the game progress information indicates that the player does not meet the preset clearance conditions of the target agent under the corresponding game play, the corresponding reply words are matched in the pre-generated dialogue content as the reply content.

[0237] In an optional embodiment, the method further comprises:

[0238] Generate dialogue animation information of the target agent based on the reply content;

[0239] According to the dialogue animation information, the target intelligent agent in the preset game scene is animated, and / or the animation corresponding to the dialogue animation information is rendered and displayed at the preset display position of the reply content.

[0240] In this embodiment, when the computer program is executed by the processor, the processor executes to obtain basic character information of multiple agents in a preset game scene, generate game play information of each agent according to the basic character information of each agent, use the game play information of each agent to generate the dialogue content prompt words of each agent under the game play corresponding to the game play information, and use the preset large model according to the dialogue content prompt words to generate the dialogue content of each agent respectively. Based on the basic character information of the agent, the game play information is generated, and the dialogue content of the agent is generated in batches using the large model, so that the dialogue content has personalization and diversity, ensuring that different agents in the game can provide different dialogue experiences for players, and improving the immersion and interactivity of the game, or obtaining the player dialogue content input by the player for the target agent, detecting the player dialogue content, obtaining the game process information of the player under the game play corresponding to the target agent, and generating the reply content corresponding to the dialogue content according to the game process information and the pre-generated dialogue content of the target agent. Based on the dialogue content of the target agent, the target agent is controlled to have a dialogue with the player, and the target agent can reply to the player in a vivid way, which greatly improves the immersion and interactivity of the game.

[0241] In the embodiment of the present application, when the computer program is run by the processor, other machine-readable instructions can also be executed to execute other methods such as those in the embodiment. For the specific execution method steps and principles, please refer to the description of the embodiment, which will not be repeated here.

[0242] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0243] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0244] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0245] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0246] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0247] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for generating intelligent agent dialogue, characterized in that: include: Get basic character information of multiple agents in the preset game scene; Generate game play information of each intelligent agent according to basic information of the personality of each intelligent agent; Using the game play information of each agent, generating a dialogue content prompt word for each agent under the game play corresponding to the game play information; According to the prompt words of the conversation content, a preset large model is used to generate the conversation content of each intelligent agent respectively.

2. The method according to claim 1, characterized in that The generating of the game play information of each agent according to the basic information of the personality of each agent includes: According to the basic character information of each intelligent agent and the first prompt word, the preset large model is used to generate the detailed character information, game goal information and game strategy information of each intelligent agent; the game play information includes: the detailed character information, the game goal information and the game strategy information.

3. The method according to claim 1, characterized in that The step of using the game play information of each agent to generate a dialogue content prompt word for each agent under the game play corresponding to the game play information includes: The preset large model is used to generate the dialogue content prompt words according to the game play information of each intelligent agent and the second prompt words.

4. The method according to claim 1, characterized in that: The method further comprises: According to the personality adjustment operation for the first agent, adjust the basic personality information of the first agent; Regenerate the game play information of the first agent according to the adjusted basic character information; Update the conversation content of the first agent based on the regenerated game play information of the first agent.

5. The method according to claim 1, characterized in that The method further comprises: Adjusting the game play information of the second agent according to the game play adjustment operation for the second agent; According to the adjusted game play information, generating a dialogue content prompt word of the second agent under the game play corresponding to the adjusted game play information; The conversation content of the second agent is updated according to the regenerated conversation content prompt words.

6. The method according to claim 1, characterized in that The method further comprises: According to the dialogue adjustment operation for the third agent, the dialogue content of the third agent is adjusted.

7. A dialogue control method, characterized in that: include: Get the player dialogue content entered by the player for the target agent; Detecting the conversation content of the player to obtain the game progress information of the player under the game play corresponding to the target agent; Based on the game process information and the pre-generated dialogue content of the target intelligent agent, reply content corresponding to the player dialogue content is generated, wherein the pre-generated dialogue content is dialogue content generated by the intelligent agent dialogue generation method described in any one of claims 1-6.

8. The method according to claim 7, characterized in that The detecting of the player's conversation content to obtain the game process information of the player under the game play corresponding to the target agent includes: Detecting the player conversation content to obtain a detection result, wherein the detection result is used to indicate whether the player conversation content triggers a game strategy under the corresponding game play of the target agent and the cumulative number of times the game strategy is triggered; According to the accumulated triggering times of the game strategy, the game progress information of the player under the game play corresponding to the target agent is obtained.

9. The method according to claim 7, characterized in that: Generating reply content corresponding to the player's dialogue content according to the game process information and the pre-generated dialogue content of the target agent includes: If the game progress information indicates that the player meets the preset clearance conditions under the corresponding game play of the target agent, the clearance words in the pre-generated dialogue content are determined as the reply content.

10. The method according to claim 7, characterized in that Generating reply content corresponding to the player's dialogue content according to the game process information and the pre-generated dialogue content of the target agent includes: If the game progress information indicates that the player does not meet the preset clearance conditions under the corresponding game play of the target agent, the corresponding reply words are matched in the pre-generated dialogue content as the reply content.

11. The method according to claim 7, characterized in that The method further comprises: Generate dialogue animation information of the target intelligent agent according to the reply content; According to the dialogue animation information, the target intelligent agent in the preset game scene is animated, and / or the animation corresponding to the dialogue animation information is rendered and displayed at a preset display position of the reply content.

12. An intelligent agent dialogue generation device, characterized in that: include: The acquisition module is used to obtain basic information about the personalities of multiple agents in a preset game scene; A generation module, used to generate game play information of each agent according to basic information of the personality of each agent; The generation module is further used to use the game play information of each agent to generate a dialogue content prompt word for each agent under the game play corresponding to the game play information; The generation module is also used to generate the dialogue content of each intelligent agent according to the dialogue content prompt words and using a preset large model.

13. A dialogue control device, characterized in that: include: An acquisition module, used to acquire the player dialogue content input by the player for the target intelligent agent in the preset game scene; A detection module, used to detect the conversation content of the player and obtain the game progress information of the player under the game play corresponding to the target agent; A generation module is used to generate reply content corresponding to the dialogue content based on the game process information and the pre-generated dialogue content of the target intelligent agent, wherein the pre-generated dialogue content is dialogue content generated by the intelligent agent dialogue generation method described in any one of claims 1-6.

14. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and the processor executes the machine-readable instructions to perform the method described in any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is executed.

Images