Interaction method, interaction apparatus and computer-readable storage medium

Abstract

The present disclosure relates to the technical field of computers, and relates to an interaction method, an interaction apparatus and a computer-readable medium. The interaction method comprises: receiving a first input from a user, wherein the user controls a virtual character in a game; on the basis of the first input, determining a first target character from among a plurality of second-type characters by means of a first-type character, wherein the first-type character is not a character in the game, the second-type characters are virtual characters not controlled by the user in the game, and the first-type character is used for guiding the interaction of the second-type characters in the game; on the basis of the first input and the plot of the game, by means of the first-type character, determining first interaction content of the first target character for the first input; on the basis of the first interaction content, determining first interaction information of the first target character for the first input, wherein the first interaction information is the same as or different from the first interaction content; and displaying the first interaction information.

Description

Interaction method, interaction device and computer-readable storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on and claims priority to an application filed in China with application number 202311598806.0 and filing date November 27, 2023. The disclosed content of the Chinese application is hereby introduced as a whole into this application. Technical Field

[0003] The present disclosure relates to the field of computer technology, and in particular to an interaction method, an interaction device, and a computer-readable storage medium. Background Art

[0004] With the rapid development of computer technology and Internet technology, electronic games are becoming more and more popular. During the game process, you may encounter situations where you have game conversations with multiple virtual characters in the same game scene.

[0005] In related technologies, the game plot and dialogue content are pre-determined. When the game plot reaches a specified progress, a dialogue session is triggered, and the game progresses based on the predetermined dialogue content. This dialogue method is relatively rigid, low user engagement, and poor user experience.

[0006] Summary of the Invention

[0007] In view of this, the embodiments of the present disclosure propose an interaction method, an interaction device and a computer-readable storage medium, which can enable users to independently control the content of conversations during the game, advance the game process based on the user's conversation content, increase user participation, and enhance the user's gaming experience.

[0008] 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, wherein the user controls a virtual character in a game; determining a first target character from a plurality of second-type characters based on the first input, the plot of the game, and through a first-type character, and determining a first interaction content of the first target character with respect to the first input, wherein the first-type character is not a character in the game, the second-type character is a virtual character in the game that is not controlled by the user, and the first-type character is used to guide the interaction of the second-type character in the game; determining first interaction information of the first target character with respect to the first input based on the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; and displaying the first interaction information.

[0009] According to a second aspect of some embodiments of the present disclosure, an interaction apparatus is provided, comprising: an input device configured to receive input from a user, wherein the user controls a virtual character in a game; one or more processors configured to: determine a first target character from a plurality of second-type characters through a first-type character based on the first input of the user and the plot of the game, and determine a first interaction content of the first target character with respect to the first input, wherein the first-type character is not a character in the game, the second-type character is a virtual character in the game that is not controlled by the user, and the first-type character is used to guide the interaction of the second-type character in the game; determine first interaction information of the first target character with respect to the first input based on the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; and a display configured to display the first interaction information of the first target character with respect to the first input.

[0010] According to a third aspect of some embodiments of the present disclosure, an interaction device is provided, including: a receiving module, configured to receive input from a user, wherein the user controls a virtual character in a game; a first determination module, configured to determine a first target character from multiple second-type characters based on the first input, the plot of the game, and a first-type character, and determine a first interaction content of the first target character with respect to the first input, wherein the first-type character is not a character in the game, and the second-type character is a virtual character in the game that is not controlled by the user, and the first-type character is used to guide the interaction of the second-type character in the game; a second determination module, configured to determine first interaction information of the first target character with respect to the first input based on the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; and a display module, configured to display the first interaction information of the first target character with respect to the first input.

[0011] According to a fourth aspect of some embodiments of the present disclosure, an interaction device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned interaction methods based on instructions stored in the memory.

[0012] 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 one of the aforementioned interaction methods is implemented.

[0013] According to a sixth aspect of some embodiments of the present disclosure, a computer program product is provided, which, when executed on a computer, enables the computer to implement any one of the aforementioned interaction methods.

[0014] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0015] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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. Each of the drawings, together with the following detailed description, is included in this specification and forms a part of the specification to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation of the present disclosure. In the drawings:

[0017] FIG1 shows a flow chart of an interaction method according to some embodiments of the present disclosure;

[0018] 2A and 2B show flow charts of interaction methods according to some embodiments of the present disclosure;

[0019] FIG2C shows a flowchart of a method for generating role information according to some embodiments of the present disclosure;

[0020] FIG3 shows a flow chart of an interaction method according to some other embodiments of the present disclosure;

[0021] FIG4 shows a flowchart of an interaction method according to still other embodiments of the present disclosure.

[0022] FIG5 shows a schematic diagram of interactions between multiple roles according to some embodiments of the present disclosure;

[0023] FIG6 shows a block diagram of an interaction device according to some embodiments of the present disclosure;

[0024] FIG7 shows a block diagram of an interaction device according to some other embodiments of the present disclosure;

[0025] FIG8 shows a block diagram of an interaction device according to yet other embodiments of the present disclosure;

[0026] FIG9 illustrates a block diagram of an electronic device according to some embodiments of the present disclosure.

[0027] It should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not necessarily drawn to scale. The same or similar reference numerals are used throughout the drawings to indicate the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. However, it is obvious that the embodiments described are only some embodiments of the present disclosure, rather than all embodiments. The following description of the embodiments is actually only illustrative and is in no way intended to limit 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 being limited to the embodiments described herein.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in different orders and / or performed 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 respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0030] As used in this disclosure, the term "include" and its variations are intended to be open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to." Furthermore, the term "comprise" and its variations are intended to be open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to." Therefore, "include" and "include" are synonymous. The term "based on" means "based, at least in part, on."

[0031] Reference throughout this specification to "one embodiment," "some embodiments," or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is 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," and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but may.

[0032] It should be noted that the terms "first," "second," and so forth mentioned in this disclosure are used solely to distinguish between different devices, modules, or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules, or units. Unless otherwise specified, terms such as "first," "second," and so forth are not intended to imply that the objects described in such terms must be ordered temporally, spatially, in ranking, or in any other manner.

[0033] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0034] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0035] The following detailed description of the embodiments of the present disclosure is provided in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail 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 skilled in the art from this disclosure.

[0036] In related technologies, users can only advance predetermined game plots based on predetermined conversation content. This game interaction method results in low user engagement and a poor gaming experience. To meet users' increasingly demanding gaming experience, the disclosed embodiments provide a new interaction method that allows users to independently control the conversation content during the game and advance the game based on the user's conversation content.

[0037] FIG1 shows a schematic flow chart of an interaction method according to some embodiments of the present disclosure.

[0038] The interaction method of this embodiment can be executed on the client side or on the user side. As shown in Figure 1, the interaction method includes: step S1, receiving a first input from a user, wherein the user controls a virtual character in the game; step S2, based on the first input and through a first type of character, determining a first target character from a plurality of second type characters, wherein the first type of character is not a character in the game, and the second type of character is a virtual character in the game that is not controlled by the user, and the first type of character is used to guide the interaction of the second type of character in the game; step S3, based on the first input, the plot of the game, and through the first type of character, determining the first interaction content of the first target character to the first input; step S4, based on the first interaction content, determining the first interaction information of the first target character for the first input, wherein the first interaction information is the same as or different from the first interaction content; step S5, displaying the first interaction information.

[0039] The user may also be referred to as a "player." The first-type character, which directs the interactions of the second-type character in the game, may also be referred to as a "director" and may be implemented through an artificial intelligence (AI) agent. The second-type character, which may also be referred to as an "actor," may be a non-player character (NPC) and may also be implemented through an AI agent.

[0040] 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 be configured with different prompt information, such as prompt templates.

[0041] In the game, each actor corresponds to an AI agent, meaning multiple actors correspond to multiple AI agents. With a single AI agent, all actors share a global memory, effectively one person playing all roles. Unlike a single AI agent, with multiple AI agents, each knows only what it needs to know and carries its own unique memory. This allows each character to focus more fully on their performance and develop a more independent personality. This results in a more interactive gaming experience than with a single AI agent playing multiple roles.

[0042] The following further describes the interaction method according to an embodiment of the present disclosure with reference to Figures 2A-2B. Figures 2A-2B differ from Figure 1 in that step S2A in Figure 2A is one implementation of step S2 in Figure 1, and step S2B in Figure 2B is another implementation of step S2 in Figure 1. Steps S2A and S2B in Figure 2A and 2B will be described in detail below, and the other steps will not be repeated.

[0043] As shown in FIG2A , in step S2A, a machine learning model is used to determine the target interaction object to which the content of the first input points, and the first target role is determined from the multiple second-type roles based on the target interaction object.

[0044] The user's first input includes a selection of an interactive option or a free input. For example, when the interactive content provided by the first-type character to the user includes multiple interactive options, the user's input includes a selection of an interactive option. Of course, the user may also directly input a free input without selecting an interactive option.

[0045] Machine learning models, such as large language models (LLMs) or other natural language processing (NLP) models, can be used. For example, based on the user's conversation, natural language processing can determine that the user is speaking to NPC B. In this case, the director can directly identify NPC B as the first target character without referring to the game's plot.

[0046] As shown in Figure 2B, in step S2B, a machine learning model is used to determine the first target character from the multiple second-type characters based on the user's first input, the plot of the game, and the first prompt information. The first prompt information includes the character information of the first-type character and the character information of the multiple second-type characters.

[0047] The game may include multiple chapters, each corresponding to at least one second-type character, and the user-controlled virtual character may interact with the second-type character corresponding to each chapter. For example, in a chapter of the game, the user-controlled virtual character may interact with non-player characters NPC A and NPC B. As previously described, such interactions may be implemented through interactions between multiple AI agents.

[0048] The game plot may include the game script and interaction logs. For example, the game plot may include at least one of the following: the summary and ending of the current chapter, the interaction logs of the current chapter, and the plot summary of the previous chapter. The interaction logs may include chat logs between virtual characters, as well as the content of interaction options and the user's selection of those interaction options.

[0049] The character information may include at least one of character settings, dialogue style, and behavioral guidance.

[0050] 2C , how to generate the role information of the first type of role and the role information of the plurality of second type of roles will be described. FIG2C shows a flow chart of a method for generating role information according to some embodiments of the present disclosure.

[0051] As shown in Figure 2C, the character information generation method includes: step S21, obtaining first general prompt information and second general prompt information corresponding to the character attributes of the first type of character and the second type of character, respectively; step S22, using a machine learning model according to the type of the game, generating first type prompt information and second type prompt information corresponding one-to-one to the character attributes of the first type of character and the second type of character, respectively; step S23, using a machine learning model according to the plot of the game, generating first plot prompt information and second plot prompt information corresponding one-to-one to the character attributes of the first type of character and the second type of character, respectively; step S24, generating character information of the first type of character according to the first general prompt information, the first type prompt information, and the first plot prompt information; step S25, generating character information of the second type of character according to the second general prompt information, the second type prompt information, and the second plot prompt information.

[0052] In step S21, for a first type of role, such as a director, the corresponding first general prompt information may include the director's behavioral guidance, for example, advancing the game according to the story background and script, including transmitting information between various roles and providing instructions to each role on how to interact. For a second type of role, such as an actor, the corresponding first general prompt information may include the actor's behavioral guidance, for example, advancing the game according to the story background, role settings, and the director's instructions.

[0053] In some embodiments, the first general prompt information and the second general prompt information are respectively generated by machine learning models.

[0054] In step S22, different types of games have different requirements for directors and actors. For different types of games, the role attributes of the director and the role attributes of the actors will be different, such as the character settings and the line styles may be different, so different prompt information is also needed.

[0055] In step S23, the director and actors can provide more specific behavioral instructions for the game plot. Each actor has his or her own character setting and line style. Therefore, more specific prompt information is needed for the game plot.

[0056] In step S24, a machine learning model may be used to fuse the first general prompt information, the first type prompt information, and the first plot prompt information obtained in steps S21-S23 to generate the director's role information.

[0057] In step S25, a machine learning model may be used to fuse the second general prompt information, the second type prompt information, and the second plot prompt information obtained in steps S21-S23 to generate role information of different actors.

[0058] When the director determines the first target role based on the plot of the game, he needs to understand both his own role information (ie, the role information of the first type of role) and the role information of the actors (ie, the role information of multiple second type of roles).

[0059] In some embodiments, the first prompt information also includes examples of interactions between the first type of character and the second type of character. For example, if the director determines that actor A is the first target character, the director can use a message in a specified format to convey the result of the interaction permission determination. As previously described, the director's corresponding AI agent can output a message in a specified format when determining to grant interaction permission to actor A through prompt information. After receiving this message, the game engine will call the AI ​​agent corresponding to actor NPC A to advance the game process.

[0060] After the director determines the first target character (i.e., the actor who will interact with the user next), he or she may need to further instruct the actor on the content of the interaction with the user. In some embodiments, a machine learning model is used to determine the first interaction content of the first target character in response to the first input based on the user's first input, the game's plot, and the first prompt information.

[0061] As previously described, the first prompt information includes the character information of the first type of character and the character information of the multiple second types of characters. When determining the first interactive content, only the character information of the first target character may be used. For example, if the director determines actor A as the first target character, the director determines the first interactive content based on the user input, the game's plot development, and actor A's character information. In this case, the determined first interactive content may also be delivered to actor A via a message in a specified format.

[0062] The machine learning model can be the text generation model based on natural language processing mentioned above, which generates the first interactive content in text form according to the user's first input, the plot of the game, the first prompt information and other text content.

[0063] The machine learning model may also be a text-based graph model, such as one based on a generative adversarial network (GAN) or a diffusion model. Using a text-based graph model, the first interactive content in the form of an image can be generated based on text content such as user input, game plot, and prompt information.

[0064] The machine learning model may also be a graph-based model, similar to a text-based model, including graph-based models based on generative adversarial networks, diffusion models, etc. When the user input includes an image, the graph-based model may be used to generate the first interactive content in the form of an image.

[0065] After using a machine learning model to determine the first interaction content of the first target role to the first input, the first target role further determines first interaction information based on the first interaction content.

[0066] In some embodiments, the first target character directly uses the first interaction content determined by the director as the first interaction information for the first input.

[0067] In other embodiments, a machine learning model is used to determine first interaction information of the first target character in response to the first input based on the first input, the first interaction content, and second prompt information, where the second prompt information includes the character information and memory summary of the first target character. For example, the AI ​​agent corresponding to actor A determines first interaction content corresponding to the actor's character information based on the first interaction content determined by the director.

[0068] As previously mentioned, the first target character, as one of multiple second-type characters, also has character information that includes at least one of character settings, dialogue style, and behavioral guidelines. In some embodiments, for each second-type character, a memory summary for each chapter in which the character appears is generated and saved based on the dialogue records in each chapter. For example, for the first target character, such as actor A, a designated AI agent can be used to generate a memory summary for each chapter based on the dialogue records in the game chapters in which actor A appears.

[0069] After determining the first interaction information, the first interaction information can be displayed on an interface between the first target character and the user. The first interaction information of the first target character can be streamed back to the user. In some embodiments, an image of the first target character can also be displayed. For example, an image of the first target character can be displayed on the user interface.

[0070] In the above embodiment, the user can autonomously control the conversation content during the game through the first input, and the game engine uses the interaction between multiple AI agents corresponding to the director and actors to advance the game based on the user's conversation content. The following further describes the game interaction with Figures 3 and 4.

[0071] Figure 3 shows a flow chart of an interaction method according to some other embodiments of the present disclosure. The interaction method shown in Figure 3 can be executed after the interaction method shown in Figure 1 to further advance the game process.

[0072] As shown in Figure 3, the interaction method includes: step S6, providing interactive content to the user through the first type of character based on the first interactive information and the plot of the game; step S7, receiving the second input of the user for the interactive content; step S8, determining a second target character from the multiple second type characters through the first type of character based on the second input and the plot of the game, and determining the second interactive content of the second target character for the second input; step S9, determining the second interactive information of the second target character for the second input based on the second interactive content, wherein the second interactive information is the same as or different from the second interactive content; step S10, displaying the second interactive information.

[0073] In step S6, a machine learning model may also be used to determine the interactive content provided to the user based on the first interactive information, the plot of the game, and the character information of the first type of character.

[0074] In step S7 , similar to the first input, the second input may also include a selection of an interactive option or a free input.

[0075] In step S8, the second target character is the same as or different from the first target character. The second target character can be determined from the plurality of second-type characters in a manner similar to that used to determine the first target character. If the target interaction object can be directly determined based on the user's second input, the second target character can be determined independently of the game's plot. If the target interaction object cannot be directly determined based on the user's second input, a machine learning model is used to determine the second target character from the plurality of second-type characters based on the game's plot and the character information of the plurality of second-type characters.

[0076] Likewise, the second interaction content of the second target character to the second input may be determined in a manner similar to the aforementioned determination of the first interaction content.

[0077] In step S9 , the second interaction information may also be determined in a manner similar to that of determining the first interaction information.

[0078] Likewise, in step S10 , the second interaction information may be displayed in a manner similar to that of displaying the first interaction information.

[0079] Figure 4 shows a flow chart of an interaction method according to some further embodiments of the present disclosure. The interaction method shown in Figure 4 can also be executed after the interaction method shown in Figure 1 to further advance the game process in an interaction manner different from that shown in Figure 3.

[0080] As shown in Figure 4, the interaction method includes: step S8', based on the first interaction information and the plot of the game, determining a third target character from the multiple second type characters through the first type character, and determining the third interaction content of the third target character to the first interaction information, wherein the third target character is different from the first target character; step S9', based on the third interaction content, determining the third interaction information of the second target character for the second input, wherein the third interaction information is the same as or different from the third interaction content; in step S10', displaying the third interaction information.

[0081] In step S8', after the first target character outputs the first interaction information, instead of providing the user with interaction content (as in step S6 in FIG3 ), a third target character, such as actor B, different from the first target character (e.g., actor A) may be determined based on the game plot, and the interaction content for actor B may be further determined. In this case, the character displayed on the user interface will switch from actor A to actor B.

[0082] The third target role can be determined in a similar manner as the first target role. The third interaction content can be determined in a similar manner as the first interaction content. Detailed description is omitted here.

[0083] In step S9 ′, the third interaction information may also be determined in a manner similar to that of determining the first interaction information.

[0084] Likewise, in step S10 ′, the third interaction information may be displayed in a manner similar to that of displaying the first interaction information.

[0085] The above describes different game interaction modes in conjunction with Figures 3 and 4. It should be understood that during the game's progression, the director can determine whether the game has ended or whether to proceed to the next chapter based on the game's plot. According to some embodiments of the present disclosure, the interaction method further includes: determining whether the game has entered the next chapter or whether the game has ended based on the game's plot, using the first type of character.

[0086] The following uses Figure 5 to more intuitively describe how the interaction between multiple characters advances the game process.

[0087] Figure 5 illustrates a schematic diagram of interactions between multiple characters according to some embodiments of the present disclosure. As shown in Figure 5 , in a chapter of a game, the game progresses through interactions between the player, director, and actor A. The game engine is responsible for invoking the corresponding AI agent and delivering the interaction content to the corresponding AI agent.

[0088] In Figure 5, the input and output of each dialogue refer to the input and output during the interaction with the machine learning model; in each round of interaction with the machine learning model, the director and actor keep a record of the historical dialogue.

[0089] First, the player makes a first input, such as a free input. The game engine calls the AI ​​agent corresponding to the director and passes the player's free input to the AI ​​agent corresponding to the director.

[0090] The director's corresponding AI agent inputs the game's plot, such as the current chapter's summary and ending, the current chapter's interaction records (including the latest N chat records and the player's latest free input), and the previous chapter's plot summary, into a machine learning model. The output includes a determined first target character and a first interaction content, such as "specify actor Axxxx" or "specify NPC A xxxx," where "actor A" or "NPC A" is the determined target character, and "xxxx" is the interaction content instructed by the director to actor A based on the game's plot.

[0091] Based on the above output, the game engine calls the AI ​​agent corresponding to actor A and passes the interaction records of the current chapter and the interaction content determined by the director to the AI ​​agent corresponding to actor A.

[0092] The AI ​​agent corresponding to actor A feeds the interaction records for the current chapter and the interaction content determined by the director into a machine learning model. The resulting output includes the first interaction information freely entered by actor A in response to the player, such as "yyyy." This interaction information "yyyy" can be streamed back to the user and displayed on actor A's corresponding user interface.

[0093] The game engine continues to call the AI ​​agent corresponding to the director, and passes the interaction information output by the AI ​​agent corresponding to actor A to the AI ​​agent corresponding to the director.

[0094] The director's AI agent, based on the game's plot, determines which options 1 and 2 are to be presented to the player as interactive content. The interactive content, "Option 1, Option 2," can be streamed back to the user. In response to the player's second input, such as selecting "Option 1," the director's AI agent, similar to the process for determining the first target character, further inputs the player's selection into the machine learning model, resulting in output also including the determined second target character and the second interactive content.

[0095] The second target character determined may be the same as the first target character, for example, still actor A. Accordingly, the interaction content determined for the second target character can be expressed as "Specify NPC A zzzz." Of course, the second target character determined may also be different from the first target character, for example, not actor A but actor B. Accordingly, the output may include "Specify NPC B."

[0096] The AI ​​agent corresponding to the second target character, such as actor A, then feeds the aforementioned further interaction records and the interaction content determined by the director into the machine learning model. The resulting output includes the second target character's interaction information regarding the player's Option 1, such as "cccc." The interaction information "cccc" can be streamed back to the user and displayed on the user interface corresponding to the second target character.

[0097] Next, if the director determines the game has reached its end point based on the plot, they can output a game-ending prompt. For example, the system could use a voiceover like "vvvv" to indicate the game is over. Of course, a game-ending animation could also be displayed.

[0098] Similarly, if the director determines based on the game's plot that the current chapter has concluded and the game is moving on to the next chapter, a prompt indicating the upcoming chapter can be displayed. For example, a system voiceover could convey the impending entry into the next chapter with "wwww." At the end of the current chapter, the interaction log for that chapter serves as a plot summary for relevant characters (such as the director and the actors appearing in that chapter). Of course, if the current chapter is the final chapter of the game, an animation indicating the game's success can also be displayed.

[0099] The above is the interaction method provided by the embodiment of the present disclosure. The following describes an interaction device according to an embodiment of the present disclosure with reference to Figures 6 to 8, which is used to perform any of the above interaction methods.

[0100] FIG6 shows a block diagram of an interaction device according to some embodiments of the present disclosure. As shown in FIG6 , the interaction device 6 includes:

[0101] An input device 61 is configured to receive a first input from a user, the user controlling a virtual character in the game;

[0102] Processor 63 is configured to: determine a first target character from a plurality of second-type characters based on the first input of the user through a first-type character, wherein the first-type character is not a character in the game, the second-type character is a virtual character in the game that is not controlled by the user, and the first-type character is used to guide the interaction of the second-type character in the game; determine a first interaction content of the first target character with respect to the first input through the first-type character based on the first input, the plot of the game, and the first-type character; determine first interaction information of the first target character with respect to the first input based on the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; and

[0103] The display 65 is configured to display the first interaction information.

[0104] The input device 61 is configured to execute step S1 of Figure 1. The input device 61 is a device used by a user to input text, sound, image and other information, and may include a touch screen, touchpad, keyboard, mouse, image sensor, microphone and the like.

[0105] Processor 63 is configured to execute steps S2-S4 of FIG1 . 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, or discrete hardware components. The central processing unit (CPU) can be of X86 or ARM architecture, etc.

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

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

[0108] The display 65 is configured to perform step S5 of FIG. 1 .

[0109] FIG7 shows a block diagram of an interaction device according to some other embodiments of the present disclosure.

[0110] As shown in Figure 7, the interactive device 7 includes: a receiving module 71, configured to receive input from a user, where the user controls a virtual character in the game; a first determination module 72, configured to determine a first target character from multiple second-type characters based on the first input and through a first-type character, wherein the first-type character is not a character in the game, the second-type character is a virtual character in the game that is not controlled by the user, and the first-type character is used to guide the interaction of the second-type character in the game; a second determination module 73, configured to determine the first interaction content of the first target character to the first input based on the first input, the plot of the game, and through the first-type character; a third determination module 74, configured to determine the first interaction information of the first target character for the first input based on the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; and a display module 75, configured to display the first interaction information.

[0111] The interaction device 7 can be used to execute steps S1 to S5 of FIG. 1 .

[0112] FIG8 shows a block diagram of an interaction device according to yet other embodiments of the present disclosure.

[0113] As shown in FIG8 , the interaction device 8 includes: a memory 81 ; and a processor 82 coupled to the memory 81 , wherein the processor 82 is configured to execute the interaction method described in any of the aforementioned embodiments based on instructions stored in the memory 81 .

[0114] Memory 81 is used to store one or more computer-readable instructions. 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. Memory 81 may, for example, store an operating system, application programs, a boot loader, databases, and other programs, as well as various application programs and data.

[0115] The processor 82 is used to execute computer-readable instructions to implement the interaction method described in any of the above embodiments. The specific implementation of each step of the interaction method can be found in the above embodiments, and the repeated parts are not repeated here.

[0116] The processor 82 and the memory 81 can communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 82 and the memory 81 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0117] It should be noted that the components of the interactive device 8 shown in FIG8 are merely exemplary and non-limiting. The interactive device 8 may also have other components according to actual application requirements. The processor 82 may control other components in the interactive device 8 to perform desired functions.

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

[0119] FIG9 illustrates a block diagram of an electronic device according to some embodiments of the present disclosure.

[0120] The electronic device 9 shown in FIG. 9 may be a computer system with a dedicated hardware structure, which can execute corresponding functions when a relevant application program is installed.

[0121] Electronic devices include, but are not limited to, mobile terminals such as smart phones, laptops, personal digital assistants (PDAs), tablet personal computers (Tablet PCs), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., as well as fixed terminals such as digital televisions, desktop computers, etc.

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

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

[0124] The following components are connected to the input / output interface 95: an input portion 96, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output portion 97, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), speaker, vibrator, etc.; a storage portion 98, including a hard disk, magnetic tape, etc.; and a communication portion 99, including a network interface card, such as a LAN card, modem, etc. The communication portion 99 allows communication processing to be performed via a network, such as the Internet. It will be readily understood that although FIG9 shows that the various devices or modules in the electronic device 9 communicate via bus 94, they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0125] A drive 910 is also connected to the input / output interface 95 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 910 as needed so that a computer program read therefrom is installed in the storage section 98 as needed.

[0126] When the above-described series of processing is implemented 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 process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which, when running on a computer, enables the computer to implement the interactive method described in any of the aforementioned embodiments. The computer program product includes a computer program carried on a computer-readable medium, which contains program code 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 part 98, or installed from the ROM 92. When the computer program is executed by the CPU 91, the interactive 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 may contain or store a program for use by an instruction execution system, apparatus, or device or for use in conjunction with an instruction execution system, apparatus, or device.

[0129] The computer readable medium may be a computer readable storage medium, or 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 thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device. A computer program is stored on a computer-readable storage medium that, when executed by a processor, implements the interactive method described in any of the foregoing embodiments.

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

[0132] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0133] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to perform the interaction method of any of the above embodiments. For example, the instructions may be embodied as computer program codes.

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

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with 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. For example, and without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0137] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art will appreciate 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 will appreciate that modifications may be made to the above embodiments 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 interactive method, comprising: receiving a first input from a user, the user controlling a virtual character in a game; Determining a first target character from a plurality of second type characters according to the first input and through a first type character, wherein the first type character is not a character in the game, the second type character is a virtual character in the game that is not controlled by a user, and the first type character is used to guide the interaction of the second type character in the game; Determining, according to the first input, the plot of the game, and through the first type of character, a first interaction content of the first target character with respect to the first input; determining, according to the first interaction content, first interaction information of the first target role in response to the first input, wherein the first interaction information is the same as or different from the first interaction content; The first interaction information is displayed.

2. The interactive method according to claim 1, wherein: Determining a first target role from a plurality of second type roles comprises: Determining the first target character from the plurality of second-type characters by using a machine learning model according to the first input of the user, the plot of the game, and first prompt information, wherein the first prompt information includes character information of the first-type character and character information of the plurality of second-type characters; or A machine learning model is used to determine a target interaction object to which the content of the first input points, and the first target role is determined from among the multiple second-type roles based on the target interaction object.

3. The interactive method according to claim 2, wherein: Determining the first interaction content of the first target role with respect to the first input includes: A machine learning model is used to determine a first interaction content of the first target character with respect to the first input according to the first input of the user, the plot of the game, and the first prompt information.

4. The interactive method according to any one of claims 1 to 3, wherein: Determining, according to the first interaction content, first interaction information of the first target role with respect to the first input includes: Using a machine learning model, first interaction information of the first target character for the first input is determined according to the first input, the first interaction content, and second prompt information, wherein the second prompt information includes character information and a memory summary of the first target character.

5. The interactive method according to claim 3, further comprising: Acquire first general prompt information and second general prompt information corresponding to the role attributes of the first type of role and the second type of role respectively; According to the type of the game, using a machine learning model, generating first type prompt information and second type prompt information corresponding to the role attributes of the first type of role and the second type of role respectively; According to the plot of the game, using a machine learning model, generating first plot prompt information and second plot prompt information corresponding to the character attributes of the first type of character and the second type of character, respectively; Generate character information of the first type of character according to the first general prompt information, the first type prompt information, and the first plot prompt information; Generate character information of the second type of character according to the second general prompt information, the second type prompt information, and the second plot prompt information.

6. The interactive method according to claim 3, wherein: The first prompt information also includes an interaction example between the first type of character and the second type of character.

7. The interactive method according to claim 4, wherein: The game includes a plurality of chapters, each chapter corresponds to at least one second-type character, and the virtual character controlled by the user interacts with the second-type character corresponding to each chapter. The interaction method further comprises: Based on the dialogue records in each chapter, for each second-type character, a memory summary of the chapters in which the character appeared is generated and saved.

8. The interactive method according to any one of claims 1 to 7, further comprising: providing interactive content to the user through the first type of character according to the first interactive information and the plot of the game; receiving a second input from the user regarding the interactive content; According to the second input and the plot of the game, a second target character is determined from the plurality of second type characters through the first type character, and a second interaction content of the second target character to the second input is determined, wherein the second target character is the same as or different from the first target character; determining, according to the second interaction content, second interaction information of the second target role with respect to the second input, wherein the second interaction information is the same as or different from the second interaction content; The second interaction information is displayed.

9. The interactive method according to any one of claims 1 to 7, further comprising: According to the first interactive information and the plot of the game, through the first type of character, from the plurality of Determining a third target role from the second type of roles, and determining a third interaction content of the third target role to the first interaction information, wherein the third target role is different from the first target role; Determining, according to the third interaction content, third interaction information of the second target role in response to the second input, wherein the third interaction information is the same as or different from the third interaction content; The third interaction information is displayed.

10. The interactive method according to any one of claims 1 to 7, wherein: The game includes multiple chapters, and the interactive method further includes: According to the plot of the game, whether the game enters the next chapter or whether the game ends is determined through the first type of character.

11. The interactive method according to any one of claims 1 to 7, further comprising: An image of the first target character is displayed.

12. The interactive method according to any one of claims 1 to 7, wherein: The user input includes a selection of an interactive option or a free input; and / or The plot of the game includes at least one of the summary and ending of the current chapter, the interaction record of the current chapter, and the plot summary of the previous chapter.

13. The interactive method according to any one of claims 2 to 7, wherein: The role information includes at least one of character settings, dialogue style, and behavior guidance.

14. An interactive device, comprising: an input device configured to receive input from a user controlling a virtual character in the game; The processor is configured as: Determining a first target character from a plurality of second type characters according to a first input of the user and through a first type character, wherein the first type character is not a character in the game, the second type character is a virtual character in the game that is not controlled by the user, and the first type character is used to guide the interaction of the second type character in the game; Determining, according to the first input, the plot of the game, and through the first type of character, a first interaction content of the first target character with respect to the first input; determining, according to the first interaction content, first interaction information of the first target role in response to the first input, wherein the first interaction information is the same as or different from the first interaction content; A display is configured to display the first interaction information.

15. An interactive device, comprising: A receiving module configured to receive input from a user, wherein the user controls a virtual character in the game; A first determination module is configured to determine a first target character from a plurality of second type characters according to the first input and through a first type character, wherein the first type character is not a character in the game, the second type character is a virtual character in the game that is not controlled by a user, and the first type character is used to guide the interaction of the second type character in the game; A second determination module is configured to determine, based on the first input, the plot of the game, and the first type of character, a first interaction content of the first target character with respect to the first input; A third determining module is configured to determine first interaction information of the first target role with respect to the first input according to the first interaction content, wherein the first interaction information is the same as or different from the first interaction content; The display module is configured to display the first interaction information.

16. An interactive device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the interaction method according to any one of claims 1 to 13 based on instructions stored in the memory.

17. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the interactive method according to any one of claims 1 to 13.

18. A computer program product, when the computer program product is run on a computer, enables the computer to implement the interactive method according to any one of claims 1 to 13.

Images