Interaction method, interaction device and computer readable storage medium

Abstract

The invention relates to an interaction method, an interaction device and a computer readable medium, and relates to the technical field of computers. The interaction method comprises the steps that first input of a user is received, the user controls a first virtual character in a game, and the game further comprises a plurality of virtual characters which are not controlled by the user; according to the first input, through a second virtual character currently interacting with the user, a third virtual character is determined from the multiple virtual characters to serve as a target virtual character to be interacted with the user, and the second virtual character is one of the multiple virtual characters; according to the first input and the story of the game, first interaction information of the second virtual character for the first input is determined through the second virtual character; and displaying the first interaction information.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to an interaction method, an interaction device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of computer technologies and Internet technologies, video games have become increasingly popular. During the game process, there will be situations where the user has game conversations with multiple virtual characters in the same game scene.

[0003] In the related art, the plot and dialogue content of the game are both pre-determined. That is, when the game plot reaches a specified progress, the dialogue link is triggered, and the game process is advanced based on the determined dialogue content. This dialogue method is relatively rigid, with low user participation, resulting in a poor user game experience. Summary of the Invention

[0004] In view of this, embodiments of the present disclosure provide an interaction method, an interaction device, and a computer-readable storage medium, which can enable the user to independently control the dialogue content during the game process, and advance the game process based on the user's dialogue content, improving the user's participation and enhancing the user game experience.

[0005] According to a first aspect of some embodiments of the present disclosure, an interaction method is provided, including: receiving a first input from a user, where the user controls a first virtual character in the game, and the game further includes a plurality of virtual characters that are not controlled by the user; determining, according to the first input and through a second virtual character currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters; determining, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input; and displaying the first interaction information.

[0006] According to a second aspect of some embodiments of the present disclosure, an interaction device is provided, including: an input device that receives a first input from a user, where the user controls a first virtual character in the game, and the game further includes a plurality of virtual characters that are not controlled by the user; a processor configured to determine, according to the first input and through a second virtual character currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters, and determine, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input; and a display configured to display the first interaction information.

[0007] According to a third aspect of some embodiments of the present disclosure, an interaction device is provided, including: a receiving module configured to receive a first input from a user, where the user controls a first virtual character in a game, and the game further includes a plurality of second virtual characters that are not user-controlled; a first determination module configured to determine, according to the first input and through a second virtual character that is currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters; a second determination module configured to determine, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input; and a display module configured to display the first interaction information.

[0008] According to a fourth aspect of some embodiments of the present disclosure, an interaction device is provided, including: a memory; and a processor coupled to the memory, where the processor is configured to execute any of the foregoing interaction methods based on instructions stored in the memory.

[0009] According to a fifth aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, any of the foregoing interaction methods is implemented.

[0010] According to a sixth aspect of some embodiments of the present disclosure, a computer program product is provided, and when the computer program product runs on a computer, the computer is enabled to implement any of the foregoing interaction methods.

[0011] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0012] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. Description of the Drawings

[0013] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure, and together with the following detailed description, they form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings in the following description only relate to some embodiments of the present disclosure and do not constitute a limitation to the present disclosure. In the drawings:

[0014] Figure 1 A flowchart of an interaction method according to some embodiments of the present disclosure is shown;

[0015] Figure 2A , 2B A flowchart showing an interaction method according to some embodiments of the present disclosure;

[0016] Figure 2C A flowchart showing a method for generating role information according to some embodiments of the present disclosure;

[0017] Figure 3 A flowchart showing an interaction method according to some other embodiments of the present disclosure;

[0018] Figure 4 A flowchart showing an interaction method according to yet some other embodiments of the present disclosure.

[0019] Figure 5 A schematic diagram showing the interaction between multiple roles according to some embodiments of the present disclosure;

[0020] Figure 6 A block diagram showing an interaction device according to some embodiments of the present disclosure;

[0021] Figure 7 A block diagram showing an interaction device according to some other embodiments of the present disclosure;

[0022] Figure 8 A block diagram showing an interaction device according to yet some other embodiments of the present disclosure;

[0023] Figure 9 A block diagram showing an electronic device according to some embodiments of the present disclosure.

[0024] It should be understood that, for the sake of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar components. Therefore, once an item is defined in one drawing, it may not be further discussed in the subsequent drawings. Detailed Description of the Embodiments

[0025] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the drawings in the embodiments of the present disclosure. However, it is obvious that the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. The following description of the embodiments is actually only illustrative and in no way constitutes a limitation on the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0026] It should be understood that the various steps recited in the method embodiments of the present disclosure may be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard. Unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments should be construed as merely exemplary and not limiting the scope of the present disclosure.

[0027] The term "comprising" and its variants used in the present disclosure mean open terms that include at least the subsequent element / feature, but do not exclude other elements / features, that is, "including but not limited to". In addition, the term "containing" and its variants used in the present disclosure mean open terms that contain at least the subsequent element / feature, but do not exclude other elements / features, that is, "containing but not limited to". Therefore, "comprising" and "containing" are synonymous. The term "based on" means "at least partially based on".

[0028] Throughout the specification, the terms "one embodiment", "some embodiments", or "embodiments" mean that the specific features, structures, or characteristics described in connection with the embodiments are included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Moreover, the appearances of the phrases "in one embodiment", "in some embodiments", or "in embodiments" throughout the specification do not necessarily all refer to the same embodiment, but may also refer to the same embodiment.

[0029] It should be noted that the concepts such as "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules, or units. Unless otherwise specified, the concepts such as "first", "second", etc. are not intended to imply that the objects so described must be in a given order in terms of time, space, ranking, or any other way.

[0030] It should be noted that the modifications of "one" and "a plurality" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. However, the present disclosure is not limited to these specific embodiments. These specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics may be combined in any suitable manner that will be apparent to those of ordinary skill in the art from the present disclosure.

[0033] In the related art, users can only advance the predetermined game plot based on the predetermined dialogue content. In such a game interaction method, the user participation is low and the user game experience is poor. To meet the increasingly high experience requirements of users for electronic games, the embodiments of the present disclosure provide a new interaction method that can enable users to independently control the dialogue content during the game process and advance the game process based on the user's dialogue content.

[0034] Figure 1 A flowchart showing an interaction method according to some embodiments of the present disclosure is shown.

[0035] The interaction method of this embodiment can be executed on the client side or on the user side. As Figure 1 shown, the interaction method includes: Step S1, receiving a first input from the user, where the user controls a first virtual character in the game, and the game also includes a plurality of virtual characters that are not controlled by the user; Step S2, determining a third virtual character from the plurality of virtual characters as the target virtual character to interact with the user through a second virtual character that is currently interacting with the user according to the first input, where the second virtual character is one of the plurality of virtual characters; Step S3, determining first interaction information of the second virtual character for the first input according to the first input, the plot of the game, and through the second virtual character; Step S4, displaying the first interaction information.

[0036] The user may also be referred to as a "player". Each virtual character in the plurality of virtual characters may also be referred to as an "actor", for example, a non-player character (NPC), and can be implemented through an artificial intelligence (AI) agent.

[0037] The second virtual character currently interacting with the user is, for example, actor A, that is, NPC A, and the determined target virtual character to interact with the user may be the same as the second virtual character, that is, the third virtual character is also actor A. Of course, the target virtual character may also be different from the second virtual character, that is, the third virtual character is, for example, actor B different from actor A, that is, NPC B.

[0038] In some embodiments, each AI agent corresponds to a machine learning model with independent planning and behavior capabilities; different AI agents can correspond to the same machine learning model, but with different configured prompt information, such as prompt templates.

[0039] In the game, each actor corresponds to an AI agent, that is, multiple actors correspond to multiple AI agents. In the case of a single AI agent, all actors share a set of global memories, which is equivalent to one person playing all roles. Different from a single AI agent, in the case of multiple AI agents, each AI agent only knows what it should know, has its own memory, can make each role perform more focused on itself, and is more inclined to have an independent personality. The interactive experience of the game is better than that of a single AI agent playing multiple roles.

[0040] The following refers to Figures 2A - 2B to further describe the interaction method according to the embodiments of the present disclosure. Figures 2A - 2B Different from Figure 1 is that: Figure 2A Step S2A in Figure 1 is an implementation manner of step S2 in Figure 2B Step S2B in Figure 1 is another implementation manner of step S2 in Figure 2A Step S2A in Figure 2B and Figures 2A - 2B The other steps in

[0041] such as Figure 2A As shown in

[0042] The first input of the user includes the selection of an interaction option or free input. For example, when the interaction content provided to the user includes multiple interaction options, the user's input includes the selection of an interaction option. Of course, the user can also directly perform free input without selecting an interaction option.

[0043] The machine learning model is, for example, a large language model (LLM, Large Language Model) or other natural language processing (NLP natural language processing) models. For example, based on the user's conversation, through natural language processing, it can be determined that the user is speaking to NPC B. In this case, without referring to the game plot, NPC B is directly determined as the target virtual character to interact with the user.

[0044] such as Figure 2BAs shown, in step S2B, using a machine learning model, based on the first input, the plot of the game, the first prompt information, and through the second virtual character, the third virtual character is determined from the multiple virtual characters, and the first prompt information includes the character information of the multiple virtual characters.

[0045] The game may include multiple chapters. Each chapter corresponds to multiple non-user-controlled virtual characters, and the user-controlled virtual character interacts with the non-user-controlled virtual characters corresponding to each chapter. For example, in a certain chapter of the game, the user-controlled virtual character can interact with non-player characters NPC A and NPC B. As mentioned above, such interactions can be achieved through the interactions between multiple AI agents.

[0046] The plot of the game may include the game's script and interaction records. For example, the plot of the game includes at least one of the summary and ending of the current chapter, and the interaction records of the current chapter. The interaction records may include the chat records between virtual characters, and may also include the content of interaction options and the user's selection of interaction options.

[0047] The character information may include at least one of character settings, line styles, and behavior guidelines.

[0048] Next, with reference to Figure 2C , describe how to generate the character information of the multiple virtual characters. Figure 2C FIG. shows a flowchart of a character information generation method according to some embodiments of the present disclosure.

[0049] As Figure 2C shown, the character information generation method includes: step S21, obtaining general prompt information corresponding to the character attributes of the multiple virtual characters; step S22, using a machine learning model according to the type of the game to generate type prompt information corresponding to the character attributes of the multiple virtual characters; step S23, using a machine learning model according to the plot of the game to generate plot prompt information corresponding one by one to the character attributes of the multiple virtual characters; step S24, generating character information corresponding one by one to the character attributes of the multiple virtual characters according to the general prompt information, the type prompt information, and the plot prompt information.

[0050] In step S21, the general prompt information may include the behavior guidelines of the actor. For example, according to the story background, character settings, etc., the game development is advanced. In some embodiments, the general prompt information is generated by a machine learning model.

[0051] In step S22, for different types of games, the requirements for actors are different. For different types of games, the role attributes of actors will also be different. For example, the character settings and line styles may all be different. Therefore, corresponding prompt information is also required.

[0052] In step S23, for the plot of the game, different actors can correspond to more specific behavior guidelines, and each actor also has its own character settings and line styles. Therefore, for the plot of the game, more specific prompt information is required.

[0053] In step S24, a machine learning model can be used to fuse the general prompt information, type prompt information, and plot prompt information obtained in steps S21 - S23 to generate the role information of different actors.

[0054] When each actor determines the target virtual character based on the plot of the game, they need to understand both their own role information and the role information of other actors. That is, the first prompt information includes the role information of the multiple virtual characters.

[0055] In some embodiments, the first prompt information further includes interaction examples between the multiple virtual characters. For example, when actor A, who is currently interacting with the user, determines actor B as the target virtual character, the determination result of the interaction permission can be transmitted through information in a specified format. As mentioned above, the AI agent corresponding to actor A can output information in a specified format when determining to give the interaction permission to actor B through the prompt information. After receiving this information, the game engine will call the AI agent corresponding to actor NPC B to advance the game process.

[0056] After determining the target virtual character (i.e., the actor who will interact with the user next), it is also necessary to further determine the interaction content between this actor and the user. In some embodiments, a machine learning model is used to determine, according to the first input, the plot of the game, the second prompt information, and through the second virtual character, the first interaction information of the second virtual character for the first input. The second prompt information includes the role information and memory summary of the second virtual character.

[0057] As mentioned above, in some embodiments of determining the target virtual character, the first prompt information includes the role information of the multiple virtual characters. When determining the first interaction information, only the role information of the target virtual character can be used. For example, in the case of determining actor B as the target virtual character, the AI agent corresponding to actor B determines the first interaction information according to the content input by the user, the development of the game plot, and the role information of actor B.

[0058] The first interaction information may include interaction options provided to the user. The first interaction information may also include dialogue information output to the user.

[0059] The machine learning model may be the aforementioned text generation model based on natural language processing, which generates the first interaction information in text form according to text contents such as the user's first input, the plot of the game, and the second prompt information.

[0060] The machine learning model may also be an image generation model from text, such as an image generation model based on a generative adversarial network (GAN), a diffusion model, etc. Using the image generation model from text, the first interaction information in picture form can be generated according to text contents such as the user's input, the plot of the game, and the prompt information.

[0061] The machine learning model may further be an image generation model from image, which is similar to the image generation model from text and includes an image generation model from image based on a generative adversarial network, a diffusion model, etc. In the case where the user's input includes a picture, the image generation model from image can be used to generate the first interaction information in picture form.

[0062] As previously mentioned, the target virtual character, as one of the multiple virtual characters, its character information also includes at least one of character setting, line style, and behavior guidance. In some embodiments, for each of the multiple virtual characters, according to the dialogue records in each chapter, a memory summary of the chapters in which it has appeared is respectively generated and saved. For example, for the target virtual character, such as actor B, a specified AI agent can be used to generate a memory summary of the corresponding chapter according to the dialogue records of actor B in the game chapters in which it has appeared.

[0063] After determining the first interaction information, the first interaction information can be displayed on the interaction interface between the target virtual character and the user. The first interaction information of the target virtual character can be streamed back to the user.

[0064] In some embodiments, the image of the virtual character currently interacting with the user can also be displayed. For example, if the virtual character currently interacting with the user is NPC A, the image of NPC A is displayed on the user interface; as the game progresses and the virtual character currently interacting with the user becomes the previously determined target virtual character, such as NPC B, the image of NPC B is displayed on the user interface.

[0065] In the above embodiments, the user can independently control the dialogue content during the game process through the first input, and utilize the interaction between multiple AI agents corresponding to different actors to advance the game process based on the user's dialogue content through the game engine. The following is combined with Figures 3 - 4 to further describe the interaction of the game.

[0066] Figure 3 A flowchart showing an interaction method according to other embodiments of the present disclosure. Figure 3 The interaction method shown can be executed after Figure 1 the interaction method shown to further advance the game process.

[0067] As Figure 3 shown, the interaction method includes: Step S5, providing interaction content to the user through the third virtual character according to the first input, the first interaction information, and the plot of the game; Step S6, receiving a second input from the user regarding the interaction content; Step S7, determining, according to the second input, the plot of the game, and first prompt information, through the third virtual character, a fourth virtual character from the multiple virtual characters as the target virtual character to interact with the user, where the fourth virtual character is the same as or different from the second virtual character, and the first prompt information includes the character information of the multiple virtual characters; Step S8, determining, according to the second input, the plot of the game, and third prompt information of the third virtual character, through the third virtual character, second interaction information of the third virtual character for the second input, where the third prompt information includes the character information and memory summary of the third virtual character; Step S9, displaying the second interaction information.

[0068] In step S5, a machine learning model can also be used to determine the interaction content provided to the user according to the first interaction information, the plot of the game, and the character information of the third virtual character.

[0069] In step S6, similar to the first input, the second input can also include a selection of an interaction option or a free input.

[0070] In step S7, the fourth virtual character is the same as or different from the second virtual character. A fourth virtual character can be determined from the multiple virtual characters in a manner similar to that for determining the third virtual character. In a case where the target interaction object can be directly determined according to the user's second input, the determination of the fourth virtual character may not rely on the plot of the game; while in a case where the target interaction object cannot be directly determined according to the user's second input, a machine learning model is used to determine the fourth virtual character from the multiple virtual characters according to the plot of the game and the character information of the multiple virtual characters.

[0071] In step S8, the second interaction information can be determined in a manner similar to that for determining the first interaction information described above.

[0072] In step S9, the second interaction information can also be displayed in a manner similar to that for displaying the first interaction information.

[0073] Figure 4 A flowchart showing an interaction method according to still other embodiments of the present disclosure. Figure 4 The illustrated interaction method may also be performed Figure 1 after the illustrated interaction method to further advance the game process in a different interaction manner. Figure 3

[0074] As Figure 4 shown, the interaction method includes: step S7', determining, according to the first input, the first interaction information, the plot of the game, the first prompt information, and through the third virtual character, a fourth virtual character from the plurality of virtual characters as the target virtual character to interact with the user, where the fourth virtual character is the same as or different from the second virtual character, and the first prompt information includes the character information of the plurality of virtual characters; step S8', determining, according to the first input, the first interaction information, the plot of the game, the third prompt information of the third virtual character, and through the third virtual character, the second interaction information of the third virtual character for the first interaction information, where the third prompt information includes the character information and memory summary of the third virtual character; in step S9', displaying the second interaction information.

[0075] In step S7', after the third virtual character (such as actor B) outputs the first interaction information, it may not provide interaction content to the user (such as Figure 3 step S7 in ), but determine a fourth virtual character different from the second virtual character (such as actor A) according to the plot of the game, for example, actor C. In this case, the character displayed on the user interface will switch from actor B to actor C. The fourth virtual character can be determined in a similar manner to the determination of the third virtual character.

[0076] In step S8', a similar manner to the determination of the first interaction information may also be used to determine the second interaction information.

[0077] Similarly, in step S9', a similar manner to the display of the first interaction information may also be used to display the second interaction information.

[0078] The above describes different interaction manners of the game in combination with Figure 3 and Figure 4 . It should be understood that during the advancement of the game, it may be determined by the virtual character currently interacting with the user according to the plot of the game whether the game ends or enters the next chapter. That is, according to some embodiments of the present disclosure, the interaction method further includes: determining, according to the plot of the game, through the virtual character currently interacting with the user, whether the game enters the next chapter or whether the game ends.

[0079] The following will be described in combination with Figure 5To more intuitively describe how the interaction between multiple characters advances the game process.

[0080] Figure 5 A schematic diagram of the interaction between multiple characters according to some embodiments of the present disclosure is shown. As Figure 5 shown, in a certain chapter of the game, the game process is advanced through the interaction between the player, NPC A, and NPC B. Among them, the game engine is responsible for calling the corresponding AI agent and passing the interaction content to the corresponding AI agent.

[0081] In Figure 5 , the input and output of each dialogue refer to the input and output during the interaction with the machine learning model; during each round of interaction with the machine learning model, each NPC maintains a historical dialogue record.

[0082] First, according to the game plot, the starting speaking NPC in this chapter of the game, such as NPC A, outputs interaction information. For example, through the AI agent corresponding to NPC A, the game plot such as the summary and ending of the current chapter and the memory summary of NPC A are input into the machine learning model, and the output obtained includes the determined interaction information, such as "NPC A's speech xxxx", where "NPC A's speech" means speaking as NPC A, and "xxxx" after "NPC A's speech" is the speech content of NPC A according to the game plot.

[0083] In addition to outputting the speech content, NPC A can also provide interactive content to the player. Similarly, through the AI agent corresponding to NPC A, according to the game plot, it is determined to provide options 1 and 2 as interactive content to the player, such as "Interactive content options 1 and 2 provided to the player". The interactive content "options 1 and 2" can be streamed back to the player. Of course, the determined content may not include options, but instead provide a free input box to the user. The content after "the player's speech" can be regarded as the player's speech content.

[0084] The speech content of NPC A and the interactive content provided to the player can both be displayed on the user interface corresponding to NPC A.

[0085] Next, the player makes a first input, such as selecting "Option 1". In response to the player's first input, the game engine can call the AI agent corresponding to NPC A and pass the player's selection result to the AI agent corresponding to NPC A.

[0086] The AI agent corresponding to NPC A, similar to the processing of determining interaction information before, further inputs the player's selection result into the machine learning model. The obtained output includes the first interaction information for the first input and the first target virtual character. For example, "The speech of NPC A yyyy designates NPC B", where "The speech of NPC A" means the speech of NPC A, "yyyy" is the speech content of NPC A according to the game plot, and "designates NPC B" means switching the character interacting with the player to NPC B, which is the first target virtual character. The first interaction information "yyyy" can be streamed back to the player and displayed on the user interface corresponding to NPC A.

[0087] Based on the above output, the game engine calls the AI agent corresponding to NPC B and passes the interaction record of the current chapter to the AI agent corresponding to NPC B.

[0088] Then, the AI agent corresponding to NPC B inputs the interaction record of the current chapter, including the speech content of NPC A, the interactive content provided to the player, and the player's selection result, into the machine learning model. The obtained output includes the second interaction information of NPC B for the player's selection result, such as "The speech of NPC B zzzz". The second interaction information "zzzz" can be streamed back to the player and displayed on the user interface corresponding to NPC B.

[0089] Similar to the processing of determining the first interaction information and the target virtual character before, the AI agent corresponding to NPC B inputs the interaction record of the current chapter into the machine learning model. The obtained output, in addition to the second interaction information, also includes the second target virtual character determined to further interact with the player. The determined second target virtual character may be the same as the first target virtual character. For example, it is still NPC A, expressed as "designates NPC A", that is, switching the character interacting with the player to NPC A.

[0090] Accordingly, the game engine continues to call the AI agent corresponding to NPC A and passes the second interaction information "zzzz" output by the AI agent corresponding to NPC B to the AI agent corresponding to NPC A.

[0091] Of course, the determined second target virtual character may also be different from the first target virtual character. For example, it is not NPC A but NPC C. The output may include "designates NPC C", that is, switching the character interacting with the player to NPC C. Accordingly, the game engine will call the AI agent corresponding to NPC C and pass the second interaction information "zzzz" output by the AI agent corresponding to NPC B to the AI agent corresponding to NPC C.

[0092] Then, the AI agent corresponding to the second target virtual character inputs the foregoing further interaction record into the machine learning model, and the obtained output includes the second interaction information of the second target virtual character for the player, such as "aaaa". The interaction information "aaaa" can be streamed back to the user and displayed on the user interface corresponding to the second target virtual character.

[0093] If the AI agent corresponding to the second target virtual character determines that the game has reached the end node according to the game's plot, it can output a game over prompt, such as "vvvv [Game Over]". The game over can be expressed in the form of the system voiceover "vvvv", and this part of the content can be invisible to the user and not streamed back to the user. Of course, a game over animation can also be displayed.

[0094] It should be understood that the content 1 of the system voiceover can, in addition to indicating the game over, also indicate the invocation of the combat template, parameter changes, entering the next chapter, game failure, etc.

[0095] If the AI agent corresponding to the second target virtual character determines that the current chapter of the game has ended and the game proceeds to the next chapter according to the game's plot, it can output a prompt that the game is about to enter the next chapter. For example, it can be expressed in the form of the system voiceover "wwww" that the game is about to enter the next chapter.

[0096] At the end of the current chapter, the interaction record of the current chapter will serve as the plot summary of the chapter for relevant characters (such as NPCs appearing in this chapter) to call. Of course, if the current chapter is the ending chapter of the game, an animation indicating game success can also be displayed.

[0097] At the end of each chapter of the game, a specific AI agent can determine which characters have appeared in that chapter and generate a list of NPCs appearing in that chapter. And, based on the perspective of each NPC in the NPC list, a memory summary of the NPC is generated based on the complete global content of the previous chapter of the game.

[0098] The above is the interaction method provided by the present disclosure embodiment. Next, refer to Figures 6 - 8 Describe an interaction device according to an embodiment of the present disclosure, which is used to execute the above interaction method.

[0099] Figure 6 Show a block diagram of an interaction device according to some embodiments of the present disclosure. As Figure 6 shown, the interaction device 6 includes:

[0100] An input device 61, configured to receive a first input from a user who controls a first virtual character in a game, where the game further includes a plurality of non-user-controlled virtual characters; a processor 63, configured to: determine, according to the first input and through a second virtual character currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters;

[0101] Determine, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input;

[0102] and

[0103] A display 65, configured to display the first interaction information.

[0104] The input device 61 is configured to execute Figure 1 step S1. The input device 61 is a device for the user to input information such as text, sound, and images, and may include a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, etc.

[0105] The processor 63 is configured to execute Figure 1 step S2-step S3. The processor 63 can be embodied as various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The central processing unit (CPU) can be of the X86 or ARM architecture, etc.

[0106] In addition, although not shown, the interaction device 6 may also include a memory, which can store various information generated during the operation of the interaction device 6, programs and data for operation, etc. Of course, the memory can also be located outside the interaction device.

[0107] The processor 63 can run computer-readable instructions stored in the memory to implement the interaction method in the above embodiments, and control other components in the interaction device 6 to perform desired functions.

[0108] The display 65 is configured to execute Figure 1 step S4.

[0109] Figure 7 The block diagram of an interaction device according to other embodiments of the present disclosure is shown.

[0110] As Figure 7As shown, the interaction device 7 includes: a receiving module 71 configured to receive a first input from a user who controls a first virtual character in a game, where the game also includes a plurality of second virtual characters that are not controlled by the user; a first determination module 72 configured to determine, based on the first input and through a second virtual character currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters; a second determination module 73 configured to determine, based on the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input; and a display module 74 configured to display the first interaction information.

[0111] The interaction device 7 can be used to execute Figure 1 steps S1 - S4.

[0112] Figure 8 The block diagram of an interaction device according to some other embodiments of the present disclosure is shown.

[0113] As Figure 8 shown, the interaction device 8 includes: a memory 81; and a processor 82 coupled to the memory 81, where the processor 82 is configured to execute the interaction method described in any of the foregoing embodiments based on instructions stored in the memory 81.

[0114] The memory 81 is used to store one or more computer-readable instructions. The memory 81 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The memory 81 may store, for example, an operating system, application programs, a boot loader (BootLoader), a database, and other programs, or may also store various application programs and various data.

[0115] The processor 82 is used to run computer-readable instructions to implement the interaction method described in any of the foregoing embodiments. For the specific implementation of each step of the interaction method, reference may be made to the above embodiments, and repeated parts will not be elaborated here.

[0116] The processor 82 and the memory 81 may communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 may communicate through a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 82 and the memory 81 may also communicate with each other through a system bus, and the present disclosure does not limit this.

[0117] It should be noted that Figure 8 The components of the interaction device 8 shown are exemplary rather than restrictive. According to actual application requirements, the interaction device 8 may also have other components. The processor 82 can interact with other components in the interaction device 8 to perform desired functions.

[0118] The interaction device can be implemented in software, firmware, and / or hardware, and can be integrated into an electronic device installed with relevant application programs.

[0119] Figure 9 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0120] Figure 9 The electronic device 9 shown can be a computer system with a dedicated hardware structure, and can perform corresponding functions when installed with relevant application programs.

[0121] The electronic device includes but is not limited to mobile terminals such as smart phones, laptop computers, personal digital assistants (PDAs), tablet personal computers (Tablet PCs), portable multimedia players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0122] As Figure 9 shown, the central processing unit (CPU) 91 executes various processes according to the programs stored in the read-only memory (ROM) 92 or the programs loaded from the storage section 98 into the random access memory (RAM) 93. In the RAM 93, data required when the CPU 91 executes various processes, etc., is stored as needed. The central processing unit is merely exemplary, and it can also be other types of processors, such as the various processors described above. The ROM 92, RAM 93, and storage section 98 can be various forms of computer-readable storage media. It should be noted that although Figure 9 the ROM 92, RAM 93, and storage section 98 are shown separately, one or more of them can be combined, or located in the same or different memories or storage modules.

[0123] The CPU 91, ROM 92, and RAM 93 are connected to each other via a bus 94. The input / output interface 95 is also connected to the bus 94.

[0124] The following components are connected to the input / output interface 95: an input section 96 such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output section 97 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage section 98 including a hard disk, a magnetic tape, etc.; and a communication section 99 including a network interface card such as a LAN card, a modem, etc. The communication section 99 allows communication processing to be performed via a network such as the Internet. It is easily understandable that although Figure 9 each device or module in the electronic device 9 shown in

[0125] communicates through the bus 94, they may also communicate through a network or other means, where the network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0126] When implementing the above series of processes by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 911.

[0127] According to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product that, when running on a computer, causes the computer to implement the interaction method described in any of the foregoing embodiments. The computer program product includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 99, or installed from the storage section 98, or installed from the ROM 92. When the computer program is executed by the CPU 91, the interaction method of the embodiment of the present disclosure is executed.

[0128] It should be noted that in the context of the present disclosure, a computer-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0129] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination of the two.

[0130] Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, a computer-readable storage media can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. A computer program is stored on the computer-readable storage media, and when the program is executed by a processor, the interactive method described in any of the foregoing embodiments is implemented.

[0131] A computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0132] The above computer-readable medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0133] In some embodiments, a computer program is also provided, including: instructions that, when executed by a processor, cause the processor to execute the interactive method of any of the above embodiments. For example, the instructions can be embodied as computer program code.

[0134] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The foregoing programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, execute as a stand-alone software package, execute partially on the user's computer and partially on a remote computer, or execute entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a portion of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0136] The functions described above may be performed, at least in part, by one or more hardware logic components. By way of example and not limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and the like.

[0137] Although some specific embodiments of the present disclosure have been described in detail by way of example, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art should understand that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. An interaction method, comprising: receiving a first input from a user, where the user controls a first virtual character in a game, and the game further includes a plurality of non-user-controlled virtual characters; determining, according to the first input and through a second virtual character currently interacting with the user, a third virtual character from the plurality of virtual characters as a target virtual character to interact with the user, where the second virtual character is one of the plurality of virtual characters; determining, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input; displaying the first interaction information.

2. The interaction method according to claim 1, wherein determining the third virtual character from the plurality of virtual characters according to the first input and through the second virtual character includes: using a machine learning model to determine the third virtual character from the plurality of virtual characters according to the first input, the plot of the game, first prompt information, and through the second virtual character, where the first prompt information includes the character information of the plurality of virtual characters; or using a machine learning model to determine a target interaction object pointed to by the content of the first input, and determining the third virtual character from the plurality of virtual characters according to the target interaction object.

3. The interaction method according to claim 1, wherein determining, according to the first input, the plot of the game, and through the second virtual character, first interaction information of the second virtual character for the first input includes: using a machine learning model to determine, according to the first input, the plot of the game, second prompt information, and through the second virtual character, first interaction information of the second virtual character for the first input, where the second prompt information includes the character information and memory summary of the second virtual character.

4. The interaction method according to claim 1, further comprising: obtaining general prompt information corresponding to the character attributes of the plurality of virtual characters; generating, according to the type of the game and using a machine learning model, type prompt information corresponding to the character attributes of the plurality of virtual characters; generating, according to the plot of the game and using a machine learning model, plot prompt information corresponding one-to-one to the character attributes of the plurality of virtual characters; generating, according to the general prompt information, the type prompt information, and the plot prompt information, character information corresponding one-to-one to the character attributes of the plurality of virtual characters.

5. The interaction method according to claim 2, wherein the first prompt information further includes interaction examples between the plurality of virtual characters.

6. The interaction method according to claim 3, wherein the game includes a plurality of chapters, and the interaction method further includes: generating and saving, for each of the plurality of virtual characters, a memory summary of the chapters in which it has appeared according to the dialogue records in each chapter.

7. The interaction method according to any one of claims 1 to 6, further comprising: Provide interaction content to the user according to the first input, the first interaction information, the plot of the game, and through the third virtual character; Receive a second input from the user for the interaction content; According to the second input, the plot of the game, the first hint information, and through the third virtual character, determine a fourth virtual character from the multiple virtual characters as the target virtual character to interact with the user, where the fourth virtual character is the same as or different from the second virtual character, and the first hint information includes the character information of the multiple virtual characters; According to the second input, the plot of the game, the third hint information of the third virtual character, and through the third virtual character, determine the second interaction information of the third virtual character for the second input, where the third hint information includes the character information and memory summary of the third virtual character; Display the second interaction information.

8. The interaction method according to any one of claims 1 to 6, further comprises: According to the first input, the first interaction information, the plot of the game, the first hint information, and through the third virtual character, determine a fourth virtual character from the multiple virtual characters as the target virtual character to interact with the user, where the fourth virtual character is the same as or different from the second virtual character, and the first hint information includes the character information of the multiple virtual characters; According to the first input, the first interaction information, the plot of the game, the third hint information of the third virtual character, and through the third virtual character, determine the second interaction information of the third virtual character for the first interaction information, where the third hint information includes the character information and memory summary of the third virtual character; Display the second interaction information.

9. The interaction method according to any one of claims 1 to 6, wherein, The game includes multiple chapters, and the interaction method further comprises: According to the plot of the game, determine whether the game enters the next chapter or whether the game ends through the virtual character currently interacting with the user.

10. The interaction method according to any one of claims 1 to 6, further comprises: Display the image of the virtual character currently interacting with the user.

11. The interaction method according to any one of claims 1 to 6, wherein: The input of the user includes the selection of interaction options or free input; and / or The plot of the game includes at least one of the plot summary and ending of the current chapter, and the interaction record of the current chapter; and / or The first interaction information includes the interaction options provided to the user.

12. The interaction method according to any one of claims 3 to 6, wherein, The character information includes at least one of character setting, line style, and behavior guidance.

13. An interaction device, comprises: An input device that receives a first input from the user, where the user controls a first virtual character in the game, and the game also includes multiple non-user-controlled virtual characters; A processor configured to: Determine a third virtual character from the multiple virtual characters as the target virtual character to interact with the user through a second virtual character currently interacting with the user according to the first input, where the second virtual character is one of the multiple virtual characters; Determine first interaction information of the second virtual character for the first input according to the first input, the plot of the game, and through the second virtual character; A display configured to display the first interaction information.

14. An interaction device comprising: A receiving module configured to receive a first input from a user, where the user controls a first virtual character in a game, and the game further includes a plurality of second virtual characters that are not user-controlled; A first determination module configured to determine a third virtual character from the multiple virtual characters as the target virtual character to interact with the user through a second virtual character currently interacting with the user according to the first input, where the second virtual character is one of the multiple virtual characters; A second determination module configured to determine first interaction information of the second virtual character for the first input according to the first input, the plot of the game, and through the second virtual character; A display module configured to display the first interaction information.

15. An interaction device comprising: A memory; and A processor coupled to the memory, where the processor is configured to execute the interaction method according to any one of claims 1 to 12 based on instructions stored in the memory.

16. A computer-readable storage medium having a computer program stored thereon, where the program, when executed by a processor, implements the interaction method according to any one of claims 1 to 12.

17. A computer program product, when the computer program product runs on a computer, causes the computer to implement the interaction method according to any one of claims 1 to 12.

Images