Interaction method and apparatuses, computer-readable storage medium and computer program product

Abstract

The present disclosure relates to an interaction method, interaction apparatuses, a computer-readable storage medium and a computer program product, and relates to the technical field of multimedia. The interaction method comprises: receiving a first input from a user, the user controlling a virtual character in interactive multimedia content; in response to a mismatch between the first input and an original storyline of the interactive multimedia content and on the basis of the first input and the original storyline of the interactive multimedia content, determining a first target character from one or multiple first-type characters, and generating a temporary storyline, the first-type characters being virtual characters that are in the interactive multimedia content and not controlled by the user, and the temporary storyline being used for guiding the user to provide a second input for triggering the original storyline; on the basis of the first input, the original storyline and the temporary storyline, generating first interaction information of the first target character for the first input; and displaying the first interaction information of the first target character for the first input.

Description

Interaction method, device, computer-readable storage medium, and computer program product

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the application with Chinese application number 202311597162.3 and application date November 27, 2023, and claims its priority. 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 multimedia technology, and in particular to an interaction method, device, computer-readable storage medium, and computer program product. Background Art

[0004] With the development of computer and multimedia technologies, interactive multimedia content, such as electronic games and interactive TV series, has become increasingly popular. Interactive multimedia content typically follows a predefined plot. For example, at a point where the user can interact, one or more predefined options are presented to the user. Upon receiving the user's selection, the corresponding plot is triggered according to the rules set in the script.

[0005] Summary of the Invention

[0006] 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.

[0007] According to some embodiments of the present disclosure, an interaction method is provided, comprising: receiving a first input from a user, wherein the user controls a virtual character of interactive multimedia content; in response to a mismatch between the first input and an original plot of the interactive multimedia content, determining a first target character from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and generating a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; generating first interaction information of the first target character to the first input based on the first input, the original plot, and the temporary plot; and displaying the first interaction information of the first target character to the first input.

[0008] According to some embodiments of the present disclosure, an interactive apparatus is provided, comprising: an input device configured to receive a first input from a user, wherein the user controls a virtual character of interactive multimedia content; one or more processors configured to: in response to a mismatch between the first input and an original plot of the interactive multimedia content, determine a first target character from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and generate a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; and generate first interaction information of the first target character to the first input based on the first input, the original plot and the temporary plot; and a display configured to display the first interaction information of the first target character to the first input.

[0009] According to some embodiments of the present disclosure, an interactive device is provided, including: a receiving module, configured to receive a first input from a user, where the user controls a virtual character of interactive multimedia content; a first generating module, configured to determine a first target character from one or more first-type characters and generate a temporary plot based on the first input and the original plot of the interactive multimedia content in response to the first input not matching the original plot of the interactive multimedia content, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; a second generating module, configured to generate first interaction information of the first target character to the first input based on the first input, the original plot and the temporary plot; and a first display module, configured to display the first interaction information of the first target character to the first input.

[0010] According to 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 the interaction method of any embodiment described in the present disclosure based on instructions stored in the memory.

[0011] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the interactive method of any embodiment described in the present disclosure is performed.

[0012] According to some embodiments of the present disclosure, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to implement the interaction method of any embodiment described in the present disclosure.

[0013] According to some embodiments of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by a processor, cause the processor to perform the interactive method of any embodiment described in the present disclosure.

[0014] Other features, aspects 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

[0015] 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:

[0016] FIG1 shows a schematic flow chart of an interaction method according to some embodiments of the present disclosure.

[0017] FIG2 shows a schematic flow chart of a method for generating a temporary scenario according to some embodiments of the present disclosure.

[0018] FIG3 shows a schematic flow chart of a method for generating first interaction information according to some embodiments of the present disclosure.

[0019] FIG4 shows a schematic flow chart of an interaction method according to some other embodiments of the present disclosure.

[0020] FIG5 shows a flow chart of an interaction method according to yet other embodiments of the present disclosure.

[0021] FIG6 shows a flowchart of an interaction method according to some further embodiments of the present disclosure.

[0022] FIG7A shows a schematic diagram of interactions between multiple roles according to some embodiments of the present disclosure.

[0023] FIG7B shows a schematic diagram of interactions between multiple roles according to other embodiments of the present disclosure.

[0024] 8A to 8C illustrate schematic diagrams of interfaces of interactive multimedia content according to some embodiments of the present disclosure.

[0025] FIG9 shows a schematic structural diagram of an interaction device according to some embodiments of the present disclosure.

[0026] FIG10 shows a schematic structural diagram of an interaction device according to other embodiments of the present disclosure.

[0027] FIG11 shows a block diagram of some embodiments of an electronic device of the present disclosure.

[0028] FIG12 shows a schematic diagram of the structure of a computer system that may be employed according to some embodiments of the present disclosure.

[0029] 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

[0030] 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.

[0031] 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.

[0032] 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."

[0033] 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.

[0034] It should be noted that the concepts of "first" and "second" mentioned in this 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, concepts such as "first" and "second" are not intended to imply that the objects described in such a manner must be in a given order in time, space, ranking, or any other manner.

[0035] 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".

[0036] 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.

[0037] 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.

[0038] After some interactive multimedia content is generated, the interactive information that players can enter is also determined. For example, at certain points in the interactive multimedia content's plot, the user may be presented with one or more pre-set options for selection. After receiving the user's selection, the corresponding plot is triggered according to the rules set in the script. However, because the interactive multimedia content is pre-written according to the pre-set plot, it does not support user input beyond these options to advance the plot. As a result, user freedom and engagement in the game are relatively low.

[0039] In addition, some interactive multimedia content can support arbitrary user input and allow the plot to proceed completely according to the user's input. However, giving users too much freedom may lead to serious unreasonable plot progression and seriously degrade the user experience.

[0040] Therefore, a technical problem to be solved by the present disclosure is: how to enable interactive multimedia content to be automatically and reasonably advanced while giving users a certain degree of freedom, so as to improve user experience.

[0041] Figure 1 shows a flow chart of an interaction method according to some embodiments of the present disclosure. As shown in Figure 1 , the interaction method of this embodiment includes steps S102 to S108.

[0042] In step S102 , a first input from a user is received, and the user controls a virtual character of the interactive multimedia content.

[0043] In the embodiments of the present disclosure, a user refers to an object that interacts with interactive multimedia content. For example, a user can be a player, viewer, or consumer of interactive multimedia content. Interactive multimedia content includes, for example, games, interactive movies, interactive stories, and the like.

[0044] The user's first input may be, for example, a selection result of multiple options provided for the interactive multimedia content, or information freely input by the user. For example, when the interactive multimedia content provides several options and the user does not want to select any of the options, the user can still freely input the content that the user wants to express through the displayed input control; or, the interactive multimedia content may not provide any options, but instead display input controls at the nodes where the user needs to interact, so that the user can freely input the content that the user wants to express. The information freely input by the user may be, for example, natural language text. When the interactive multimedia content provides options, the natural language text may be completely different from the content of all the options, or may be exactly the same as the content of one of the options, or may have the same meaning as the content of one of the options but be expressed differently.

[0045] In some embodiments, after receiving a first input from a user, the first input can be "performed" by a virtual character controlled by the user. For example, if the first input represents a conversation, the virtual character controlled by the user can be instructed to speak the content, and the speaking process can be represented by at least one of playing the spoken content or displaying the spoken text. If the first input represents an action, the virtual character controlled by the user can be instructed to perform the action, and the action can be represented by displaying a text description of the action, an animation of the virtual character performing the action, or a combination of the two. Alternatively, the virtual character controlled by the user can be instructed not to "perform" the first input, but instead directly display the subsequent plot corresponding to the first input.

[0046] In step S104, in response to the first input not matching the original plot of the interactive multimedia content, a first target character is determined from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and a temporary plot is generated, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot.

[0047] The original plot refers to the predetermined plot of interactive multimedia content after its creation. For the same interactive multimedia content, regardless of which user consumes it, the original plot remains the same. However, due to differences in user input, the actual content displayed and the actual plot progression may differ between users as they consume the interactive multimedia content. In other words, the original plot is like a "script," used to define the main plot of the interactive multimedia content. However, some specific content of the interactive multimedia content can be personalized and generated in real time based on user input, enabling intelligent secondary creation based on the integration of the original plot and user input.

[0048] The interactive multimedia content may include multiple chapters, and the original plot may correspond to one of the multiple chapters of the interactive multimedia content, or may correspond to the entire plot of the interactive multimedia content.

[0049] If the first input is a selection from options provided by the interactive multimedia content, the first input matches the original plot of the interactive multimedia content. That is, the original plot already has a subsequent plot or multiple branching plots that need to be advanced, and the options provided also correspond to these plots. Therefore, in this case, the first input matches the original plot.

[0050] In the case where the first input is content freely input by the user, in some embodiments, if the first input matches a trigger condition in the original plot (used to trigger a plot after the current plot), then the first input can be considered to match the original plot of the interactive multimedia content; if the first input does not match the trigger condition in the original plot, then the first input can be considered to not match the original plot of the interactive multimedia content. For example, if the first input is exactly the same as the content of an option provided by the interactive multimedia content, or has the same meaning as the content of an option but is expressed differently, then the first input can be considered to match the original plot of the interactive multimedia content; if the first input is completely different from the content of all options, then the first input can be considered to not match the original plot of the interactive multimedia content.

[0051] If the first input matches the original plot of the interactive multimedia content, a subsequent plot in the original plot corresponding to the first input may be triggered. If the first input does not match the original plot of the interactive multimedia content, a temporary plot is generated. This temporary plot is a plot that does not exist in the original plot, that is, a plot automatically generated based on the user's personalized input. The temporary plot is a description of the content of the interactive multimedia content that will be displayed, which can be a general description.

[0052] The temporary scenario generation process references both the first input and the original scenario. This allows the temporary scenario to take both user input and the original scenario into account, responding to the user's input while remaining within the framework of the original scenario, making it more rational. Furthermore, the temporary scenario can guide the user in triggering the original scenario, guiding them to provide a second input to trigger the original scenario the next time they make an input.

[0053] For example, the player's character is currently at a fork in a maze, requiring the user to decide whether to take Fork A on the left or Fork B on the right. Each choice is followed by a corresponding subsequent plot in the original storyline. If the user chooses neither and instead uses the first input to indicate retreat, a temporary plot can be generated to prompt the user to make a choice. For example, the temporary plot could indicate that retreat is dangerous. Another example could be that after the user's character retreats for a while, the road behind them collapses, making further retreat impossible. Another example could be that after retreating for a while, the user discovers a new passage that leads to Fork A. This allows the user's second input to indicate a move toward that passage to connect with the original storyline.

[0054] The temporary plot requires a suitable virtual character to carry it. This virtual character is not controlled by the user and can interact with the user-controlled virtual character. Therefore, in addition to determining the temporary plot, a first target character can also be determined. Thus, the temporary plot is the content that the first target character wants to express. For example, if the temporary plot expresses the need for caution, a virtual character with a character set to be cautious can be determined as the first target character.

[0055] In some embodiments, the temporary plot may be determined first and then the first target character may be determined based on the temporary plot, or the first target character may be determined first and then the temporary plot, or the first target character and the temporary plot may be determined simultaneously.

[0056] In step S106 , first interaction information of the first target character to the first input is generated based on the first input, the original plot, and the temporary plot.

[0057] The first interactive information is used to respond to the first input, and is used to represent the visual information corresponding to the temporary plot. The first interactive information includes, for example, the dialogue text of the first target character, or options for the user to choose. In addition, it may also include one or more of actions and expressions. For example, if the temporary plot is to prompt that retreating is dangerous, the first interactive information may be the first target character saying "It's too dangerous behind, let's go forward!" For another example, the temporary plot is that after the character controlled by the user retreats for a period of time, the road behind collapses and it is impossible to retreat any further. Then the first interactive information may be that in the scene where the road behind collapses, the first target character says "There is no way to retreat anymore, now we can only go forward", and displays two options of going left front or right front.

[0058] In step S108, the first interaction information of the first target character in response to the first input is displayed, and the display method may be displaying text, displaying the expression or action of the first target character, etc.

[0059] For example, any type of first interaction information can be described using text as needed. For the first target character's spoken text, expression description text, and actions, different styles or positions can be used to express different types of text. For example, the description text of actions and expressions can be placed in brackets to distinguish them from the spoken text.

[0060] For expressions or actions, the first target character can also be instructed to perform them, further embodying and embodying the temporary plot. This approach requires the generation of corresponding multimedia resources, such as animations of the first target character. Using text descriptions, however, can reduce the amount of data required to generate these multimedia resources.

[0061] The above-described embodiment allows a user to provide a first input that does not match the original plot while viewing interactive multimedia content. Furthermore, a temporary plot can be generated in response to this first input, thereby simultaneously responding to the user's first input and guiding the user back to the original plot. Thus, the disclosed embodiments enable interactive multimedia content to reasonably advance the plot while providing a certain degree of user freedom, thereby improving the user experience.

[0062] Some embodiments of the present disclosure may generate a temporary plot or first interactive information based on artificial intelligence (AI). For example, a machine learning model is used to implement the generation process. The machine learning model used in the embodiments of the present disclosure is, for example, a generative model. The generative model is used to output target content based on the input information. The input information includes the processing basis of the generative model during the generation process, such as which information is used to perform the generation process, the requirements for the output target content, and so on. The generative model includes, for example, a model generated based on text, or a model generated based on an image, and the output of the generative model may include text, an image, or a combination of the two. Of course, the input or output of the generative model may also be data of other modalities, such as audio, video, or a combination of multiple types of data. A generative model can be a single-modal model, such as a model that generates text from text (referred to as a "text-to-text model") or a model that generates images from images (referred to as a "image-to-image model"). Alternatively, a generative model can be a cross-modal model, i.e., a model whose input and output belong to different modalities, such as a model that generates images from text (referred to as a "text-to-image model"). Alternatively, the input of a generative model can include multiple modalities, and the output can also include multiple modalities. Machine learning models can be implemented based on neural network models, such as foundation models or large language models (LLMs).

[0063] The following describes an embodiment of the AI-based generation method of the present disclosure with reference to FIG2 and FIG3 respectively.

[0064] Figure 2 shows a schematic flow chart of a method for generating a temporary scenario according to some embodiments of the present disclosure. As shown in Figure 2 , the method for generating a temporary scenario in this embodiment includes steps S202 to S204.

[0065] In step S202, the first input, the original plot, and the first prompt information are processed using a machine learning model, where the first prompt information includes an instruction to generate a temporary plot when the user input does not match the original plot.

[0066] The first prompt information is used to indicate the processing logic of the current task of the machine learning model, so that the machine learning model understands the first input and the original plot (such as natural language understanding) according to the model and generates a temporary plot. The first prompt information is expressed in a format that can be parsed by the machine learning model. The first prompt information can be preset, such as content from a template. The template can correspond to different tasks. For example, the first prompt information in step S202 can come from a template corresponding to the generation task of the temporary plot.

[0067] In some embodiments, the first prompt information may be a natural language text, for example, "Generate a plot based on the user's input and the original plot. If the user's input deviates from the original plot, the generated temporary plot must be able to connect the current state with the original plot."

[0068] When generating a temporary plot, you can also refer to the role information. In some embodiments, the first prompt information also includes role information of one or more first-type roles, and an instruction to select the first target role based on the role information. Role information, for example, includes at least one of character settings, line style, and behavioral guidance. Character settings, for example, include personality settings, basic attribute settings (such as gender, age, etc.), and so on. Thus, based on the role information of the first-type role, a suitable first target role can be selected to respond to the first input. Moreover, the generated temporary plot can also have a higher degree of match with the role that executes the plot. Based on this instruction, the role information of the first target role can have a higher degree of match with the temporary plot, making it more reasonable for the first target role to carry the temporary plot.

[0069] In step S204, the first target character output by the machine learning model and the interaction information generation indication are obtained, wherein when the first input does not match the original plot, the interaction information generation indication includes a temporary plot.

[0070] The interaction information generation instruction is used to provide a basis for generating the first interaction information. Thus, the subject responsible for generating the first interaction information can generate the first interaction information based on the temporary plot in the interaction information generation instruction. In addition to the temporary plot, the interaction information generation instruction may also include second prompt information. The second prompt information, expressed in natural language, may be, for example, "Based on the above temporary plot, generate a dialogue for the first target character." Other forms of second prompt information may also be used as needed, which will not be detailed here.

[0071] Each first-type role can be configured with an interaction information generation module. The first interaction information can be sent to the interaction information generation module corresponding to the first target role, instructing it to generate the first interaction information. The interaction information generation module that can be configured for each first-type role can also be implemented using a machine learning model. The process of generating the first interaction information using the machine learning model will be described below in an exemplary manner.

[0072] The above embodiment can automatically generate temporary plots based on artificial intelligence, thereby being able to efficiently generate temporary plots for user input based on the powerful computing power and massive prior knowledge of artificial intelligence to quickly respond to user input.

[0073] Figure 3 shows a schematic flow chart of a method for generating first interaction information according to some embodiments of the present disclosure. As shown in Figure 3, the method for generating first interaction information in this embodiment includes steps S302 to S304.

[0074] In step S302, the first input, the original plot, the temporary plot and the second prompt information are processed using a machine learning model, where the second prompt information includes the character information and the memory summary of the first target character.

[0075] The type of the machine learning model can be the same as or different from the type of the machine learning model in step S202. In the case where the two are of the same type, the machine learning model in step S202 and the machine learning model in step S302 can even be the same model, but correspond to different agents. Thus, each agent has independent input, output, and context information during the processing, but they share the computing resources provided by the same machine learning model. If needed, steps S202 and S302 can also be performed by the same agent.

[0076] The second prompt information is used to indicate the processing logic of the current task of the machine learning model, so that the machine learning model understands the first input, the original plot, and the temporary plot according to the model (for example, natural language understanding) and generates the first interaction information. The second prompt information is expressed in a format that can be parsed by the machine learning model. The second prompt information can be preset, for example, from the content in the template. For example, the second prompt information in step S302 can come from the template corresponding to the task of generating the interaction information.

[0077] In some embodiments, the second prompt information may be a natural language text, for example, "Generate a dialogue for the first target character based on the user's input, the original plot, and the temporary plot."

[0078] The memory summary of the first target character is a summary of the plot that the first target character has experienced in the interactive multimedia content. The interactive multimedia content may include one or more chapters. Assuming that the current plot has advanced to Chapter 3, if the first target character appears in Chapters 1, 2, and 3, the memory summary of the first target character is a summary of the plot that has occurred in Chapters 1 and 2; if the first target character only appears in Chapters 1 and 3, the memory summary of the first target character is a summary of the plot that has occurred in Chapter 1. In addition, the memory summary may also include a summary of the plot that has occurred in the current chapter.

[0079] In step S304, first interaction information between the first target role and the first input output by the machine learning model is obtained.

[0080] In some embodiments, a first input, an original plot, a temporary plot, and a second prompt information are input to an agent of a machine learning model corresponding to a first target character, and first interaction information output by the agent is obtained. Thus, when generating the first interaction information based on the first target character and the temporary plot, interference from other irrelevant information can be avoided, thereby improving the accuracy of content generation. When the first interaction information is represented by text, a model for generating text can be used; when the first interaction information is represented by an image, a model for generating images can be used. When the first interaction information includes both text and images, the above two models can be used simultaneously, or a generative model whose output includes both text and images can be used.

[0081] The above embodiment can automatically generate the first interactive information based on artificial intelligence, thereby being able to efficiently convert the temporary plot into interactive information based on the powerful computing power and massive prior knowledge of artificial intelligence, so as to automatically provide a basis for the subsequent display content.

[0082] Through the above-described embodiments, when the user's input deviates from the original plot, a temporary plot can be used to bring the user back. If the user repeatedly deviates from the plot, the temporary plot can be used to directly trigger the original plot. For example, if the original plot requires the user to explore the wreckage of a spaceship, but the user repeatedly indicates through the first input that they want to explore other places, a temporary plot can be generated in which the user discovers a mysterious entrance in the place they want to explore. After entering this entrance, they discover that it is exactly the wreckage of the spaceship.

[0083] Of course, when the user insists on deviating from the plot for many times, the game can also be terminated in time. The following describes the interaction methods of other embodiments of the present disclosure with reference to FIG4 .

[0084] Fig. 4 shows a flow chart of an interaction method according to some other embodiments of the present disclosure. As shown in Fig. 4 , the interaction method of this embodiment includes steps S402 to S406.

[0085] In step S402, in response to the user inputs for a specified number of consecutive times not matching the original plot, an instruction to terminate the interactive multimedia content is generated based on the first input and the original plot of the interactive multimedia content.

[0086] If the user's input for a specified number of consecutive times does not match the original plot, it means that the user's purpose is not to advance the plot. At this time, it can be ended in time. However, an overly abrupt ending may lead to a poor user experience, so a transition screen can also be generated. The instruction to terminate the interactive multimedia content is used to indicate the termination of the plot of the interactive multimedia content, so that interactive information can be further generated based on the instruction. The instruction is, for example, "generate a transition plot to transition from the user's input to the screen of game failure." In addition to natural language, other forms of expression can also be used to express the instruction, which will not be repeated here.

[0087] In some embodiments, the instruction can be generated using a machine learning model. For example, the machine learning model can be used to process the first input and the original plot of the interactive multimedia content. If the user's input does not match the original plot for a specified number of consecutive times, the machine learning model outputs an instruction to terminate the interactive multimedia content. The specific implementation of the machine learning model can be referenced in the previous embodiments and will not be repeated here.

[0088] In step S404, second interaction information is generated based on the first input, the original plot, and the instruction to terminate the interactive multimedia content, wherein the second interaction information indicates the termination of the interactive multimedia content.

[0089] The second interaction information is used to respond to the first input and transition to the game failure interface. The second interaction information can be carried by a first-type character, or it can be carried by no first-type character and represented by background images and narration. The second interaction information can be visual information.

[0090] In step S406, the second interaction information is displayed.

[0091] The display mode of the second interactive information can refer to the first interactive information, which will not be described in detail here. At the end of the second interactive information, a game end screen can be displayed.

[0092] For example, let's assume the user is currently in a maze. The original plot requires the user to choose a fork in the road ahead and move forward, but the user repeatedly inputs the reverse direction. If the temporary plot fails to guide the user, the following plot can be displayed: The player's character stays in the maze for too long, runs out of supplies, and faints, ending the game.

[0093] Through the above embodiment, the interactive multimedia content can be ended in time when the user deviates from the plot for multiple consecutive times.

[0094] The embodiments of the present disclosure can also hint at the correct option in advance through the plot when the user is faced with multiple options, so that the interactive multimedia content can continue to progress without affecting the user's viewing experience.

[0095] Fig. 5 shows a flow chart of an interaction method according to some other embodiments of the present disclosure. As shown in Fig. 5 , the interaction method of this embodiment includes steps S502 to S508.

[0096] In step S502, in response to the first input matching the branch node plot in the original plot, a second target character is determined from one or more first type characters based on the first input and the branch node plot, and a prompt plot is generated, wherein the prompt plot is used to imply a specified option from multiple options of the branch node.

[0097] A branching plot node refers to a plot node that includes multiple options, with different options corresponding to different plot branches. The process of determining the second target character from one or more first-type characters and generating the prompt plot can still be handled by the machine learning model. The specific processing method is described in the previous embodiment.

[0098] Designated options can be used to advance the plot or trigger the end of the interactive multimedia content. For example, consider two options: "climbing" and "swimming." "Climbing" advances the plot, while "swimming" triggers a game failure. In this case, the prompt could be seeing a giant crocodile in the water.

[0099] The second target character is used to carry the prompt plot. When determining the second target character, the character information of the first type of character may also be referenced so that the second target character has a higher degree of match with the prompt plot. In some embodiments, the prompt plot may be determined first, and then the second target character is determined based on the prompt plot. Alternatively, the second target character may be determined first, and then the prompt plot may be determined. Alternatively, the second target character and the prompt plot may be determined simultaneously.

[0100] In step S504, third interaction information of the second target character to the first input is generated based on the first input, the original plot and the prompt plot.

[0101] The third interaction information is similar in form to the first interaction information, but differs in function and specific content. In some embodiments, the third interaction information may also be generated by a machine learning model.

[0102] In step S506, the third interaction information of the second target character in response to the first input is displayed. Thus, the second target character can be used to hint at a designated option, so as to guide the user to continue to advance the plot.

[0103] In step S508, multiple options are displayed. The multiple options can be expressed through the second target character's speech content, or displayed as selection controls on the interface. The user can make a selection by triggering the selection control or by free input.

[0104] Through the above embodiment, a prompt plot for suggesting a specified option can be generated based on the user's input and the original plot, thereby guiding the user to continue to advance the plot while giving the user a certain degree of freedom and improving the user experience.

[0105] In some embodiments of the present disclosure, when the user input triggers the ending, in order to avoid abruptly displaying the ending content, a transition plot can be generated to make the plot progress more smoothly and naturally. The following describes the interaction method of some other embodiments of the present disclosure with reference to FIG6.

[0106] Fig. 6 shows a flow chart of an interaction method according to some further embodiments of the present disclosure. As shown in Fig. 6 , the interaction method of this embodiment includes steps S602 to S606.

[0107] In step S602 , in response to the first input matching the ending in the original plot, a transition plot is generated based on the first input and the ending, wherein the transition plot is used to transition from the current plot to the ending.

[0108] This ending can be the conclusion of a specific chapter or the ending of the entire interactive multimedia content. Since the ending is predetermined, and the user's input, while matching the original plot, may still differ slightly from it, directly following the original plot will result in an incoherent plot. For example, in the original plot, NPC 1 asks the user whether to stay on the boat or take a speedboat ashore. In the original plot, staying on the boat results in game failure, while taking a speedboat ashore triggers the ending. Unconstrained by the two options provided, the user chooses to swim ashore. In reality, the ending is triggered as long as the user-controlled virtual character reaches ashore; the method is irrelevant, so the first input still matches the original plot. To make the plot more coherent, the user-controlled virtual character can be shown swimming and then appearing soaking wet upon reaching ashore, before the ending is displayed.

[0109] If the transition plot needs to be carried by other virtual characters, a target character for carrying the transition plot can be determined from the first type of characters based on the first input and the ending.

[0110] In some embodiments, a machine learning model may be used to process the first input and the ending to generate a transition plot.

[0111] In step S604, fourth interaction information is generated based on the first input, the original plot, and the transition plot.

[0112] The fourth interaction information is similar in form to the first interaction information, but differs in function and specific content. In some embodiments, the fourth interaction information may also be generated by a machine learning model.

[0113] In step S606, the fourth interaction information is displayed.

[0114] The display method of the fourth interactive information can refer to the first interactive information, and will not be repeated here. At the end of the fourth interactive information, the screen corresponding to the ending can be displayed.

[0115] Through the above embodiment, when the ending is triggered, a transition plot can be automatically generated based on the user's input and the content of the ending, so that the displayed content can naturally transition from the user's current state to the ending, making the plot advancement of the interactive multimedia content smoother and more reasonable, and improving the user experience.

[0116] The above-mentioned embodiments exemplarily describe the automatic generation of various plot contents in interactive multimedia content. In the embodiments of the present disclosure, in addition to the first type of role, in some embodiments, a second type of role is also provided, and the second type of role is not a role in the interactive multimedia content. For example, the second type of role is not a character with a storyline in the interactive multimedia content, but a control role in the background, used for scheduling the interactive multimedia content. The above-mentioned process of generating any one of the temporary plot, prompt plot, and transition plot can be implemented through the first type of role or through the second type of role. Implementing through a certain type of role means implementing through the processing logic or processing module corresponding to the type. For example, in the case where each role corresponds to an agent of a machine learning model, implementing through the first type of role can refer to implementing through the agent of the first type of role, and implementing through the second type of role can refer to implementing through the agent of the second type of role. Implementing through an agent means inputting the information to be processed into the agent and obtaining the output of the agent as the processing result.

[0117] In some embodiments, in response to a mismatch between the first input and the original plot of the interactive multimedia content, a first target character is determined from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and a temporary plot is generated. These two scenarios are described below with reference to Figures 7A and 7B , respectively.

[0118] In some embodiments, the temporary plot is generated by the first type of character and the first target character is determined. For example, the temporary plot is generated by the last virtual character that speaks among the first type of characters, that is, the last virtual character that interacts with the user, and the first target character is determined.

[0119] Figure 7A illustrates a schematic diagram of interactions between multiple characters according to some embodiments of the present disclosure. As shown in Figure 7A , in a chapter of a game, the game progresses through interactions between the player, NPC A (a first-type character), and NPC B (another first-type character), wherein the game engine is responsible for invoking the corresponding AI agent and delivering the interaction content to the corresponding AI agent.

[0120] First, according to the game's plot, NPC A speaks and outputs interaction information. For example, the AI ​​agent corresponding to NPC A feeds the game's plot, such as the current chapter summary and ending, and NPC A's memory summary, into a machine learning model. The resulting output includes determining that NPC A's speech content is xxxx.

[0121] In addition to outputting speech content, NPC A can also provide interactive content to the player. Similarly, NPC A's corresponding AI agent, based on the game's plot, determines whether to provide options 1 and 2 as interactive content to the player. This content can be streamed back to the player. Of course, if the content only requires player input without options, a free input box is provided to the user.

[0122] The speech content of NPC A and the interactive content provided to the player can be displayed on the user interface corresponding to NPC A.

[0123] Next, the player makes a first input, for example, the player does not select any option but enters "zzzz". 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 first input to the AI ​​agent corresponding to NPC A.

[0124] The AI ​​agent corresponding to NPC A inputs the player's input "zzzz" and the original plot into a machine learning model. After obtaining the temporary plot and the first target character, NPC B, this information is then processed. The output includes the temporary plot "yyyy" for the first input and the first target character. The character interacting with the player needs to be switched to NPC B, the first target virtual character. NPC B processes NPC A's speech, the options 1 and 2 provided to the player, the player's input "zzzz", and the temporary plot yyyy generated by NPC A to generate interaction information "kkkk". This interaction information can be streamed back to the player and displayed on NPC A's corresponding user interface.

[0125] In some embodiments, a temporary plot is generated by the second type of character, and the first target character is determined. Figure 7B shows a schematic diagram of the interaction between multiple characters according to other embodiments of the present disclosure. As shown in Figure 7B, in a certain chapter of the game, the game process is promoted through the interaction between the player, the director (second type of character), and the actor A (first type of character A), wherein the game engine is responsible for calling the corresponding AI agent and passing the interaction content to the corresponding AI agent. In Figure 7B, in each round of interaction with the machine learning model, the second type of character and the actor keep a record of the historical dialogue.

[0126] 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.

[0127] The director's corresponding AI agent inputs the game's plot, such as the summary and ending of the current chapter, the interaction records of the current chapter (including the latest N chat records and the player's latest free input), and the plot summary of the previous chapter, into the machine learning model. The output obtained includes the first target character determined to be actor A and the temporary plot as "xxxx".

[0128] Based on the above output, the game engine calls the AI ​​agent corresponding to the first type of character A, and passes the interaction records of the current chapter and the temporary plot determined by the director to the AI ​​agent corresponding to actor A.

[0129] The AI ​​agent corresponding to actor A inputs the interaction records and temporary plot of the current chapter into the machine learning model. The resulting output includes the first interaction information freely entered by actor A towards the player, such as "yyyy". The interaction information "yyyy" can be streamed back to the user and displayed on the user interface corresponding to the first type of character A.

[0130] 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.

[0131] The director's AI agent, based on the game's plot, determines which options 1 and 2 should be presented to the player as interactive content. The interactive content, "Option 1 and Option 2," can be streamed back to the user. In response to the player's second input, such as selecting "Option 1," the actor'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 an output that also includes the next target character and plot.

[0132] The next target character determined may be the same as the first target character, for example, still Actor A. At this point, Actor A can continue processing Options 1 and 2, the player's selection result, and plot zzzz, output to the player to generate subsequent interactive information. This will not be further described here. Of course, the next target character determined may also be different from the first target character, for example, Actor B instead of Actor A.

[0133] In some embodiments, the image of the first target character is displayed, so that the interactive information can be conveyed more clearly and vividly. Schematic diagrams of the interface of the interactive multimedia content generated by the above embodiments of the present application are exemplarily described below with reference to Figures 8A to 8C.

[0134] In the original scenario, the cruise ship a user-controlled virtual character (set as the protagonist) and NPC 1 are on is about to sink. The protagonist and NPC 1 fall into the water, and the user is asked to choose whether to take a speedboat to shore or return to the cruise ship. If they choose to take the speedboat to shore, the protagonist and NPC 1 will be saved. In Figure 8A, interface 81 shows NPC 1 in the water, and NPC 1's dialog box 811 displays "What should we do now?" Furthermore, interface 81 displays options 812, "Take speedboat to shore," and 813, "Return to cruise ship." Interface 81 also displays an input box 814 for the user to freely enter input.

[0135] If the user selects "Go ashore by speedboat" in interface 81, the user's input matches the original plot. This triggers the content shown in interface 82 of FIG8B , for example. After reaching the shore, NPC 1's dialog box 821 displays "Great, we're finally saved!", which is the content in the original plot.

[0136] If the user inputs "swim ashore" through the input box 814 in the interface 81, although it is not exactly the same as any of the options, the input content matches the plot of "going ashore by speedboat", that is, you can be saved by going ashore, so the content in the interface 82 can still be triggered at this time.

[0137] If the user does not select an option in interface 81 but instead enters "wait for the helicopter," the user's input is neither an option provided by the original plot nor matches any of the options in the original plot. In this case, a temporary plot needs to be generated based on the original plot and the user's input. The display content corresponding to the temporary plot is, for example, the content shown in interface 83 in FIG8C , i.e., NPC 1's dialog box 831 displays "There are no helicopters nearby. Let's think about whether to go ashore or return to the ship!" This content does not appear in the original plot. Alternatively, if the user's input and the original plot indicate that the appearance of a helicopter is reasonable, a helicopter can be displayed to take the user-controlled virtual character and NPC 1 away.

[0138] Embodiments of the related apparatus and device of the present disclosure are described below with reference to FIG. 9 to FIG. 12 .

[0139] Figure 9 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure. As shown in Figure 9, the interactive device 9 of this embodiment includes: an input device 91, configured to receive a first input from a user, wherein the user controls a virtual character of interactive multimedia content; one or more processors 92, configured to: in response to the first input not matching the original plot of the interactive multimedia content, determine a first target character from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and generate a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; and generate first interaction information of the first target character to the first input based on the first input, the original plot and the temporary plot; and a display 93, configured to display the first interaction information of the first target character to the first input.

[0140] In some embodiments, the processor 92 may be configured to implement the interactive distribution of any of the aforementioned embodiments of the present disclosure.

[0141] Figure 10 shows a schematic diagram of the structure of an interactive device according to some other embodiments of the present disclosure. As shown in Figure 10, the interactive device 10 of this embodiment includes: a receiving module 101, configured to receive a first input from a user, wherein the user controls a virtual character of interactive multimedia content; a first generating module 102, configured to, in response to the mismatch between the first input and the original plot of the interactive multimedia content, determine a first target character from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and generate a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; a second generating module 103, configured to generate first interaction information of the first target character to the first input based on the first input, the original plot and the temporary plot; and a first display module 104, configured to display the first interaction information of the first target character to the first input.

[0142] In some embodiments, the first generation module 102 is further configured to: use a machine learning model to process the first input, the original plot and the first prompt information, the first prompt information including an instruction to generate a temporary plot when the user's input does not match the original plot; obtain the first target character output by the machine learning model and the interaction information generation instruction, wherein, when the first input does not match the original plot, the interaction information generation instruction includes a temporary plot.

[0143] In some embodiments, the first prompt information further includes character information of one or more first-type characters, and an instruction to select a first target character according to the character information.

[0144] In some embodiments, the second generation module 103 is further configured to: use a machine learning model to process the first input, the original plot, the temporary plot and the second prompt information, the second prompt information including the role information and memory summary of the first target character; obtain the first interaction information of the first target character to the first input output by the machine learning model.

[0145] In some embodiments, the interactive device also includes a second display module, which is configured to: generate an indication to terminate the interactive multimedia content based on the first input and the original plot of the interactive multimedia content in response to the user's input for a specified number of consecutive times not matching the original plot; generate second interaction information based on the first input, the original plot and the indication to terminate the interactive multimedia content, wherein the second interaction information indicates the termination of the interactive multimedia content; and display the second interaction information.

[0146] In some embodiments, the interactive device also includes a third display module, which is configured to: in response to the first input matching the branch node plot in the original plot, determine the second target role from one or more first type roles based on the first input and the branch node plot, and generate a prompt plot, wherein the prompt plot is used to imply a specified option from multiple options of the branch node; based on the first input, the original plot and the prompt plot, generate third interaction information of the second target role to the first input; display the third interaction information of the second target role to the first input; and display multiple options.

[0147] In some embodiments, the interactive device also includes a fourth display module, which is configured to: in response to the first input matching the ending in the original plot, generate a transition plot based on the first input and the ending, wherein the transition plot is used to transition from the current plot to the ending; generate fourth interaction information based on the first input, the original plot and the transition plot; and display the fourth interaction information.

[0148] In some embodiments, the first generation module 102 is further configured to: in response to the first input not matching the original plot of the interactive multimedia content, determine a first target character from one or more first type characters based on the first input and the original plot of the interactive multimedia content through a first type character or a second type character, and generate a temporary plot, wherein the second type character is not a character in the interactive multimedia content.

[0149] In some embodiments, the interactive multimedia content includes multiple chapters, and the original plot corresponds to one of the multiple chapters of the interactive multimedia content.

[0150] In some embodiments, the first input is natural language text, or a selection result of multiple options; the first interaction information includes dialogue text, or multiple options.

[0151] In some embodiments, the interaction device further includes a fifth display module configured to display an image of the first target character.

[0152] In some embodiments, the character information includes at least one of character settings, dialogue style, and behavioral guidelines.

[0153] It should be noted that the above-mentioned units are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the accompanying drawings to indicate that these units may not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0154] In addition, although not shown, the device may also include a memory that can store various information generated by the device and the various units contained in the device during operation, programs and data used for operation, data to be sent by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory can include but is not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Of course, the memory can also be located outside the device. Optionally, although not shown, the device may also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in an appropriate manner known in the art, for example, including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. This will not be described in detail here. In addition, the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. This will not be described in detail here.

[0155] Some embodiments of the present disclosure also provide an electronic device. Figure 11 shows a block diagram of some embodiments of the electronic device of the present disclosure. For example, in some embodiments, the electronic device 11 can be various types of devices, for example, including but not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 11 may include a display panel for displaying data and / or execution results utilized in the scheme of the present disclosure. For example, the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a flat panel, but also a curved panel or even a spherical panel.

[0156] As shown in Figure 11, the electronic device 11 of this embodiment includes a memory 111 and a processor 112 coupled to the memory 111. It should be noted that the components of the electronic device 11 shown in Figure 11 are merely exemplary and non-limiting. The electronic device 11 may also include other components as required by actual applications. The processor 112 may control the other components in the electronic device 11 to perform desired functions.

[0157] In some embodiments, the memory 111 is configured to store one or more computer-readable instructions. When the processor 112 is configured to execute the computer-readable instructions, the computer-readable instructions are executed by the processor 112 to implement the method according to any of the above embodiments. The specific implementation of each step of the method and related explanations can be found in the above embodiments, and any repetitive details are not repeated here.

[0158] For example, the processor 112 and the memory 111 may communicate with each other directly or indirectly. For example, the processor 112 and the memory 111 may communicate with each other via a network. The network may include a wireless network, a wired network, and / or any combination of wireless networks and wired networks. The processor 112 and the memory 111 may also communicate with each other via a system bus, which is not limited in this disclosure.

[0159] For example, the processor 112 can be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), 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 an X86 or ARM architecture, etc. For example, the memory 111 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 111 can include, for example, a system memory, which stores, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs. Various applications and various data can also be stored in the storage medium.

[0160] In addition, according to some embodiments of the present disclosure, when various operations / processes according to the present disclosure are implemented through software and / or firmware, the programs constituting the software can be installed from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system 12 shown in FIG12 . When the various programs are installed, the computer system can perform various functions, including those described above. FIG12 shows a schematic diagram of the structure of a computer system that can be used according to some embodiments of the present disclosure.

[0161] In Figure 12, a central processing unit (CPU) 1201 performs various processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage part 1208 to a random access memory (RAM) 1203. In the RAM 1203, data required when the CPU 1201 performs various processes, etc., is also 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 1202, RAM 1203, and storage part 1208 may be various forms of computer-readable storage media, as described below. It should be noted that although ROM 1202, RAM 1203, and storage device 1208 are shown separately in Figure 12, one or more of them may be combined or located in the same or different memory or storage modules.

[0162] The CPU 1201, the ROM 1202, and the RAM 1203 are connected to one another via a bus 1204. An input / output interface 1205 is also connected to the bus 1204.

[0163] The following components are connected to the input / output interface 1205: an input portion 1206, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output portion 1207, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), speaker, vibrator, etc.; a storage portion 1208, including a hard disk, magnetic tape, etc.; and a communication portion 1209, including a network interface card, such as a LAN card, modem, etc. The communication portion 1209 allows communication processing to be performed via a network, such as the Internet. It will be readily understood that although FIG12 shows that the various devices or modules in the electronic device 1200 communicate via the bus 1204, they may also communicate via a network or other means, where the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0164] A drive 1210 is also connected to the input / output interface 1205 as needed. A removable medium 1211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1210 as needed so that a computer program read therefrom is installed in the storage section 1208 as needed.

[0165] In the case of realizing the above-described series of processing 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 1211 .

[0166] 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, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes 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 1209, or installed from the storage device 1208, or installed from the ROM 1202. When the computer program is executed by the CPU 1201, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0167] 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 or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with 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 that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, 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.

[0168] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0169] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to perform any of the methods of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0170] 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, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0171] 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.

[0172] The modules, components, or units described in the embodiments of the present disclosure may be implemented in software or hardware. The names of the modules, components, or units do not necessarily limit the modules, components, or units themselves.

[0173] The functions described above herein 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 chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0174] The above descriptions are merely some embodiments of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present disclosure.

[0175] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present invention may be practiced without these specific details. In other cases, well-known methods, structures, and techniques are not presented in detail in order not to obscure the understanding of the description.

[0176] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0177] 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 of the interactive multimedia content; In response to the first input not matching the original plot of the interactive multimedia content, based on the first input and the original plot of the interactive multimedia content, determining a first target character from one or more first-type characters and generating a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; Based on the first input, the original plot and the temporary plot, generating first interaction information of the first target character to the first input; First interaction information of the first target character in response to the first input is displayed.

2. The interactive method according to claim 1, wherein: In response to the first input not matching the original plot of the interactive multimedia content, determining a first target role from one or more first-type roles based on the first input and the original plot of the interactive multimedia content and generating a temporary plot includes: Processing the first input, the original plot, and first prompt information using a machine learning model, the first prompt information including an instruction to generate the temporary plot if the user input does not match the original plot; Obtain a first target character output by the machine learning model and an interaction information generation indication, wherein, in a case where the first input does not match the original plot, the interaction information generation indication includes the temporary plot.

3. The interactive method according to claim 2, wherein: The first prompt information also includes role information of the one or more first-type roles, and an instruction to select the first target role according to the role information.

4. The interactive method according to any one of claims 1 to 3, wherein: The generating, based on the first input, the original plot and the temporary plot, first interaction information of the first target character to the first input comprises: Processing the first input, the original plot, the temporary plot, and second prompt information using a machine learning model, wherein the second prompt information includes role information and a memory summary of the first target role; Obtain first interaction information of the first target role to the first input output by the machine learning model.

5. The interactive method according to any one of claims 1 to 4, further comprising: In response to the user's input for a specified number of consecutive times not matching the original plot, generating an instruction to terminate the interactive multimedia content based on the first input and the original plot of the interactive multimedia content; generating second interaction information based on the first input, the original plot, and the instruction to terminate the interactive multimedia content, wherein the second interaction information indicates the termination of the interactive multimedia content; The second interaction information is displayed.

6. The interactive method according to any one of claims 1 to 5, further comprising: In response to the first input matching the branch node plot in the original plot, based on the first input and the branch node plot, a second target role is determined from the one or more first type roles, and a prompt plot is generated, wherein the prompt plot is used to suggest a specified option from a plurality of options of the branch node; Based on the first input, the original plot and the prompt plot, generating third interaction information of the second target character to the first input; displaying third interaction information of the second target role with respect to the first input; The plurality of options are displayed.

7. The interactive method according to any one of claims 1 to 6, further comprising: In response to the first input matching the ending in the original plot, based on the first input and the ending A transition plot is generated, wherein the transition plot is used to transition from the current plot to the ending; generating fourth interaction information based on the first input, the original plot, and the transition plot; The fourth interaction information is displayed.

8. The interactive method according to any one of claims 1 to 7, wherein: In response to the first input not matching the original plot of the interactive multimedia content, determining a first target role from one or more first-type roles based on the first input and the original plot of the interactive multimedia content and generating a temporary plot includes: In response to the first input not matching the original plot of the interactive multimedia content, a first target character is determined from one or more first type characters and a temporary plot is generated through a first type character or a second type character based on the first input and the original plot of the interactive multimedia content, wherein the second type character is not a character in the interactive multimedia content.

9. The interactive method according to any one of claims 1 to 8, wherein: The interactive multimedia content includes a plurality of chapters, and the original plot corresponds to one of the plurality of chapters of the interactive multimedia content.

10. The interactive method according to any one of claims 1 to 9, wherein: The first input is a natural language text, or a selection result of multiple options; The first interaction information includes a dialogue text or a plurality of options.

11. The interactive method according to any one of claims 1 to 10, further comprising: An image of the first target character is displayed.

12. The interactive method according to claim 3 or 4, wherein: The role information includes at least one of character settings, dialogue style, and behavior guidance.

13. An interactive device, comprising: an input device configured to receive a first input from a user, the user controlling a virtual character of the interactive multimedia content; One or more processors configured to: In response to the first input not matching the original plot of the interactive multimedia content, based on the first input and the original plot of the interactive multimedia content, determining a first target character from one or more first-type characters and generating a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; and Based on the first input, the original plot and the temporary plot, generating first interaction information of the first target character to the first input; and The display is configured to display first interaction information of the first target character in response to the first input.

14. An interactive device, comprising: A receiving module configured to receive a first input from a user, wherein the user controls a virtual character of the interactive multimedia content; A first generating module is configured to, in response to the first input not matching the original plot of the interactive multimedia content, determine a first target character from one or more first-type characters based on the first input and the original plot of the interactive multimedia content, and generate a temporary plot, wherein the first-type character is a virtual character in the interactive multimedia content that is not controlled by the user, and the temporary plot is used to guide the user to provide a second input for triggering the original plot; A second generating module is configured to generate first interaction information of the first target character to the first input based on the first input, the original plot and the temporary plot; The first display module is configured to display first interaction information of the first target character in response to the first input.

15. An interactive device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute a command based on instructions stored in the memory. command, and execute the interactive method as described in any one of claims 1 to 12.

16. 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 12.

17. 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 12.

18. A computer program comprising: Instructions, when executed by a processor, cause the processor to perform the interaction method according to any one of claims 1 to 12.

Images