WO2025113282A1 - 交互方法、装置、电子设备以及计算机可读存储介质 - Google Patents

交互方法、装置、电子设备以及计算机可读存储介质 Download PDF

Info

Publication number
WO2025113282A1
WO2025113282A1 PCT/CN2024/133258 CN2024133258W WO2025113282A1 WO 2025113282 A1 WO2025113282 A1 WO 2025113282A1 CN 2024133258 W CN2024133258 W CN 2024133258W WO 2025113282 A1 WO2025113282 A1 WO 2025113282A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
virtual character
character
dimension
dialogue
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/133258
Other languages
English (en)
French (fr)
Inventor
林佩吟
张子健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Publication of WO2025113282A1 publication Critical patent/WO2025113282A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/50—Controlling the output signals based on the game progress
    • A63F13/52—Controlling the output signals based on the game progress involving aspects of the displayed game scene
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/50—Controlling the output signals based on the game progress
    • A63F13/53—Controlling the output signals based on the game progress involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game
    • A63F13/533—Controlling the output signals based on the game progress involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game for prompting the player, e.g. by displaying a game menu
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/50—Controlling the output signals based on the game progress
    • A63F13/53—Controlling the output signals based on the game progress involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game
    • A63F13/537—Controlling the output signals based on the game progress involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game using indicators, e.g. showing the condition of a game character on screen
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/55—Controlling game characters or game objects based on the game progress

Definitions

  • the present disclosure relates to the field of computer technology, and in particular to an interaction method, device, electronic device, and computer-readable storage medium.
  • Interactive multimedia content For example, games, interactive TV series, interactive movies, etc., in which users can control virtual characters to interact with non-player characters during the experience.
  • the content of this interaction is often set.
  • an interaction method comprising: displaying a dialogue interface between a first virtual character and a second virtual character, wherein the first virtual character and the second virtual character are virtual characters in interactive multimedia content, and the first virtual character is a virtual character controlled by a user; receiving dialogue information with the second virtual character input by the user; and determining information of a character attribute variable of at least one dimension based on the dialogue information, wherein the character attribute variable of at least one dimension affects the development of the plot of the interactive multimedia content.
  • an interactive device comprising: a display module, configured to display a dialogue interface between a first virtual character and a second virtual character, wherein the first virtual character and the second virtual character are virtual characters in interactive multimedia content, and the first virtual character is a virtual character controlled by a user; a receiving module, configured to receive dialogue information with the second virtual character input by the user; and a determining module, configured to determine information of a character attribute variable of at least one dimension based on the dialogue information, wherein the character attribute variable of at least one dimension affects the development of the plot of the interactive multimedia content.
  • an electronic device comprising: a memory; and a processor coupled to the memory, the processor being configured to execute any of the embodiments of the present disclosure based on instructions stored in the memory.
  • Example of interactive method comprising: a processor; and a processor coupled to the memory, the processor being configured to execute any of the embodiments of the present disclosure based on instructions stored in the memory. Example of interactive method.
  • a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the interactive method of any embodiment of the present disclosure is performed.
  • a computer program comprising instructions, which, when executed by a processor, enable the processor to implement the interactive method of any embodiment of the present disclosure.
  • a computer program product comprising instructions, which, when executed by a processor, enable the processor to implement the interactive method of any embodiment of the present disclosure.
  • FIG1 is a schematic flow chart showing an interaction method according to some embodiments of the present disclosure.
  • FIG2 is a schematic diagram showing an interface of some embodiments of the present disclosure.
  • FIG3 is a schematic diagram showing interfaces of other embodiments of the present disclosure.
  • FIG4 is a schematic diagram showing an interface of yet other embodiments of the present disclosure.
  • FIG5 is a schematic flow chart showing interaction methods according to other embodiments of the present disclosure.
  • FIG. 6 is a schematic flow chart showing an interaction method according to some other embodiments of the present disclosure.
  • FIG7 is a schematic diagram showing the structure of an interaction device in some embodiments of the present disclosure.
  • FIG8 is a schematic diagram showing the structure of an electronic device according to some embodiments of the present disclosure.
  • FIG. 9 is a schematic diagram showing the structure of a computer system according to some embodiments of the present disclosure.
  • references throughout this specification to "one embodiment,” “some embodiments,” or “an embodiment” mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention.
  • 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.”
  • the appearances of the phrases “in one embodiment,” “in some embodiments,” or “in an embodiment” in various places throughout this specification do not necessarily all refer to the same embodiment, but may do so.
  • the content of the dialogue between the user-controlled virtual character and the non-player character is set, relatively fixed and mechanical, and the plot of the interactive multimedia is also set, and the plot and the dialogue are completely separated.
  • the current interaction mode leads to relatively low efficiency and effect of the interaction.
  • the present disclosure proposes an interaction method to improve the efficiency and effect of interaction.
  • Fig. 1 is a flow chart of some embodiments of the interactive method disclosed herein. As shown in Fig. 1 , the method of this embodiment includes: steps S102 to S106.
  • step S102 a dialogue interface between the first virtual character and the second virtual character is displayed.
  • the first virtual character and the second virtual character are virtual characters in the interactive multimedia content, and the first virtual character is a virtual character controlled by the user.
  • the second virtual character can be a non-player character (NPC).
  • NPC non-player character
  • the interactive multimedia content is a game, an interactive TV series, an interactive movie, etc., and is not limited to the examples given.
  • GUI graphical user interface
  • the dialog interface is displayed in response to a user's triggering operation.
  • the user's triggering operation may be an operation of opening interactive multimedia content, an operation of triggering a dialog control, or an operation such as voice wake-up, and is not limited to the examples cited.
  • step S104 dialogue information between the user and the second virtual character is received.
  • the dialogue interface may also display a dialogue input area for receiving input dialogue information.
  • the dialogue information may be input in any form such as text or voice.
  • the user may have a dialogue with the second virtual character on any topic of interest, which may be related to the plot, characters, etc. of the interactive multimedia content, or may be unrelated to the plot, characters, etc. of the interactive multimedia content.
  • step S106 information of at least one dimension of role attribute variables is determined according to the dialogue information.
  • the character attribute variables of at least one dimension affect the development of the plot of the interactive multimedia content. For example, when the information of the character attribute variables of at least one dimension is different, the plot of the interactive multimedia content will develop into different branches.
  • the at least one dimension of the character attribute variable includes: at least one of the first dimension of the character attribute variable and the second dimension of the character attribute variable.
  • the first dimension is used to represent the first virtual character and the second virtual character.
  • the first dimension is used to represent the relationship between the two characters, and the second dimension is used to represent the ability of the first virtual character.
  • the dialogue between the first virtual character and the second virtual character can affect the relationship between the two characters, and can also affect the ability of the first virtual character.
  • the role attribute variables of the first dimension may include one or more first variables.
  • the one or more first variables may include one or more variables of positive emotions and/or one or more variables of negative emotions.
  • variables of positive emotions include favorability, intimacy, trust, etc.
  • negative emotions include alienation, ashamed value, etc., without limitation to the examples given.
  • the character attribute variables of the second dimension may include one or more second variables.
  • the one or more second variables include: force value, life value, intelligence value, physical value, etc., which are used to represent one or more variables of the ability of the first virtual character.
  • the information of the role attribute variable of the first dimension may be at least one of the values, levels, change values, and change levels of one or more first variables.
  • the information of the role attribute variable of the second dimension may be at least one of the values, levels, change values, and change levels of one or more second variables.
  • the one or more first variables and the one or more second variables may be quantified by numerical values or levels, etc., without limitation to the examples given.
  • the first virtual character controlled by the user can have a dialogue with the second virtual character, and the dialogue interface between the first virtual character and the second virtual character is displayed.
  • information of the character attribute variable of at least one dimension can be determined according to the dialogue information, thereby affecting the development of the plot of the interactive multimedia content.
  • the user can affect the character attribute variable through the interactive mode of dialogue with the second virtual character, thereby affecting the development of the plot of the interactive multimedia content. Closely linking the interactive process with the plot of the interactive multimedia content makes it easier to attract users to interact, expands the interactive form of the interactive multimedia content, and improves the effectiveness and effect of the interactive process.
  • the second virtual character is a character having a preset relationship with the first virtual character, and in response to the user's calling out operation of the second virtual character, a dialogue interface between the first virtual character and the second virtual character is displayed.
  • the preset relationship between the first virtual character and the second virtual character can be a positive relationship or a negative relationship.
  • the first virtual character and the second virtual character can have a positive relationship such as partners, lovers, allies, or a negative relationship such as enemies, opponents, etc.
  • the preset relationship between the first virtual character and the second virtual character is generated in response to a user's operation of establishing a relationship between the first virtual character and the second virtual character.
  • the user's selection of the second virtual character and the type of the preset relationship may be received, the preset relationship between the first virtual character and the second virtual character may be determined, and the preset relationship may be displayed.
  • the first virtual character is used as the second virtual character, and a preset relationship between the first virtual character and the second virtual character is configured. For example, a relationship configuration interface is displayed, one or more virtual characters that can be configured are displayed, and an operation of setting virtual character A as the partner of the first virtual character and setting virtual character B as the enemy of the first virtual character is received.
  • the second virtual character that forms a different type of preset relationship with the first virtual character can be configured into different preset groups. For example, a trigger operation of the user to add the second virtual character to the selected preset group is received, and prompt information for adding the second virtual character to the preset group is displayed. For example, the prompt information for the second virtual character to join the preset group is "A becomes your partner".
  • Information of one or more virtual characters in the preset group can also be displayed, for example, the name, introduction and/or image of one or more virtual characters are displayed, and the examples are not limited thereto.
  • a user selection operation on a preset group is received, information of one or more virtual characters in the preset group is displayed, a user selection operation on a second virtual character is received; and a dialogue interface between the first virtual character and the second virtual character is displayed.
  • the plot develops in the interactive multimedia content, different virtual characters may appear, and the plot direction affects the unlocked virtual characters.
  • the user may select the virtual character that appears as the second virtual character, and configure a preset relationship between the first virtual character and the second virtual character.
  • a first control is displayed to add the second virtual character to a preset group, wherein adding the second virtual character to the preset group indicates that the first virtual character and the second virtual character form a preset relationship; a user's triggering operation on the first control is received; and a prompt message to add the second virtual character to the preset group is displayed.
  • the second virtual character in response to the user controlling the first virtual character to complete a preset task and/or the plot develops to a second preset plot node in the interactive multimedia content, the second virtual character is unlocked and displayed.
  • the second virtual character can be added to the preset group by the user triggering the first control, or automatically added to the preset group by the user's advance configuration.
  • the target characteristics of the virtual characters added to different preset groups configured in advance by the user are received, and when the unlocked second virtual character meets the target characteristics, it is automatically added to the corresponding preset group.
  • the user configures the virtual character called partner as the leading role of the X camp, and when the unlocked virtual character meets the characteristics, the unlocked virtual character is added to the partner group.
  • a relationship configuration interface may be displayed, and a first control for adding the second virtual character to the preset group may be displayed in the relationship configuration interface.
  • a first control may be set after each virtual character.
  • a display interface of the second virtual character may be displayed, and a first control for adding the second virtual character to the preset group may be displayed in the display interface of the second virtual character.
  • the first control is displayed in the current interface.
  • the first control can be displayed and triggered in any form, and is not limited here.
  • the image of the second virtual character that appears in the display interface of the interactive multimedia content can be directly used as the first control, and the user's click on the image of the second virtual character can be used as a trigger for the first control.
  • the second virtual character is directly added to the preset group, and prompt information is displayed.
  • multiple candidate preset relationships are displayed, the user's selection of a candidate preset relationship (or candidate preset grouping) is received, and prompt information for adding the second virtual character to the selected candidate preset group is displayed.
  • a prompt message “A becomes your partner” may be displayed in the display interface of the second virtual character.
  • a user operation on a second control of a preset group is received; information of one or more virtual characters in the preset group is displayed; a user selection operation on a second virtual character is received; and a dialogue interface between the first virtual character and the second virtual character is displayed.
  • the second controls of the multiple preset groups can be displayed, and the user's trigger operation on the second control of any preset group can be received to display the information of one or more virtual characters in the selected preset group.
  • the information of each virtual character may include: at least one of the name and image, but is not limited to the examples given.
  • a second control can be displayed, which can be displayed with the name of the preset group, such as "Partner".
  • the user can click on the "Partner" control to display one or more virtual characters who have become partners with the first virtual character.
  • the avatars of multiple virtual characters can be displayed.
  • a third control may be set, such as the “all” control shown in FIG. 4 , in response to the user triggering the third control to display information of some hidden virtual characters.
  • a dialogue interface between the first virtual character and the second virtual character C is displayed.
  • initial dialogue information of the second virtual character is displayed in the dialogue interface, wherein the initial dialogue information of the second virtual character is generated according to character setting information of the second virtual character.
  • the dialogue interface can also display the standing picture (or dynamic image), background, etc. of the second virtual character, and display the initial dialogue information of the second virtual character.
  • the initial dialogue information of different second virtual characters is different, and can be generated according to the character setting information of the second virtual character.
  • the character setting information of the second virtual character is input into the machine learning model to generate the dialogue information of the second virtual character.
  • the character setting information may include: description information of at least one of the character's background information, gender, personality, age, and language style, not limited to the examples given.
  • the character setting information of the second virtual character can also be input into the machine learning model to generate a standing picture or dynamic image of the second virtual character, and the background information can be input into the machine learning model to generate the background, etc.
  • the machine learning model in the present disclosure may be an AI (Artificial Intelligence) model, a large model, etc., and may specifically be a neural network model, a deep learning model, a large language model (LLM), a generative model, etc.
  • a generative model is, for example, AIGC (Artificial Intelligence Generated Content), which may be a text generation model, an image generation model, a video generation model, a speech generation model, or a multimodal generation model, etc., and is not limited to the examples given.
  • the dialogue interface may display a voice input control or a text input area for receiving dialogue information input by a user, and is not limited to the examples given.
  • voice recognition may be performed first to convert the voice into text, and information of at least one dimension of role attribute variables may be determined based on the text corresponding to the dialogue information.
  • determining information of at least one dimension of character attribute variables based on dialogue information includes: determining information of at least one dimension of character attribute variables based on dialogue information and one or more historical dialogue information between the first virtual character and the second virtual character.
  • the information of the character attribute variable of at least one dimension can be determined based on the conversation information currently input by the user and one or more historical conversation information.
  • the one or more historical conversation information can be historical conversation information within a preset time, or a preset number of historical conversation information, or historical conversation information from the first conversation information after entering the conversation interface to the currently input conversation information, and is not limited to the examples given. Combining the currently input conversation information and the historical conversation information, the meaning of the conversation can be understood more accurately, thereby more accurately determining the information of the character attribute variable of at least one dimension.
  • Fig. 5 is a flow chart of some other embodiments of the interactive method disclosed in the present invention. As shown in Fig. 5, determining information of at least one dimension of role attribute variables according to the dialogue information includes: Steps S502 to S504.
  • step S502 the dialogue information is parsed to determine whether the dialogue information is associated with at least one dimension of a role attribute variable.
  • a machine learning model can be used to analyze the conversation information (and one or more historical conversation information) It is understood that it is determined whether the dialogue information is associated with the role attribute variable of the first dimension and/or whether the dialogue information is associated with the role attribute variable of the second dimension.
  • step S504 when the dialogue information is associated with the role attribute variable of at least one dimension, the machine learning model is used to determine the information of the role attribute variable of at least one dimension based on the dialogue information and the prompt information corresponding to the role attribute variable of at least one dimension.
  • the prompt information corresponding to the role attribute variable of at least one dimension is used to assist the machine learning model in understanding the relationship between the dialogue information and the role attribute variable of at least one dimension, as well as the impact on the role attribute variable of at least one dimension.
  • the prompt information when the character attribute variables of at least one dimension include the character attribute variables of the first dimension, the prompt information includes emotion influencing factor information and/or character setting information of the second virtual character; when the character attribute variables of at least one dimension include the character attribute variables of the second dimension, the prompt information includes ability influencing factor information of the first virtual character.
  • the emotion influencing factor information of the second virtual character includes at least one of a favorability example, an intimacy example, a trust example, a distance example, and a disappointment value example.
  • the favorability example can be a text used to describe sentences, situations, and/or events that affect the favorability of the second virtual character to other virtual characters, and is not limited to the examples cited. Other examples are similar to the favorability example and are not repeated here.
  • the ability influencing factor information of the first virtual character includes at least one of a force value example, a life value example, an intelligence value example, and a physical value example.
  • the force value example can be a text for describing a sentence, a situation, and/or an event that affects the force value of the second virtual character, and is not limited to the examples cited. Other examples are similar to the force value example and are not repeated here.
  • a machine learning model is used to determine the information of the character attribute variables of the first dimension based on the dialogue information and the emotion influencing factor information of the second virtual character.
  • the dialogue information (and one or more pieces of historical dialogue information) and the emotion influencing factor information of the second virtual character can be input into the machine learning model to obtain the output information of the role attribute variable of the first dimension.
  • a machine learning model is used to determine the information of the character attribute variables of the first dimension based on the dialogue information, the emotion influencing factor information of the second virtual character, and the character setting information of the second virtual character.
  • the dialogue information (and one or more historical dialogue information), the emotional influencing factor information of the second virtual character and the character setting information of the second virtual character can be input into the machine learning model to obtain the output information of the role attribute variable of the first dimension.
  • the information of the role attribute variable of the first dimension representing the relationship between the first virtual character and the second virtual character is determined, which improves the accuracy and helps to improve the accuracy of the subsequent determination of the plot development of the interactive multimedia content.
  • a machine learning model is used to determine information on the character attribute variables of the second dimension based on the dialogue information and the information on factors affecting the ability of the first virtual character.
  • the dialogue information (and one or more pieces of historical dialogue information) and the information on factors affecting the ability of the first virtual character may be input into a machine learning model to determine information on the role attribute variables of the second dimension.
  • Combining the dialogue information with the information on the factors influencing the ability of the first virtual character to determine the information on the character attribute variables of the second dimension representing the ability of the second virtual character improves accuracy and helps to improve the accuracy of subsequent determination of the plot development of the interactive multimedia content.
  • the relationship between the first virtual character and the second virtual character and/or the ability of the second virtual character is affected, thereby affecting the plot development of the interactive multimedia content, which is conducive to increasing the user's interest and motivation for interaction and improving the frequency, effectiveness and effect of interactive interactions.
  • the user can have a dialogue with the second virtual character related to the plot, and in this case, it can also be processed accordingly.
  • the dialogue information is parsed to determine whether the dialogue information is associated with the plot of the interactive multimedia content; when the dialogue information is associated with the plot of the interactive multimedia content, a machine learning model is used to determine information of the character attribute variable in at least one dimension based on the dialogue information, prompt information corresponding to the character attribute variable in at least one dimension, and summary information of the historical plot experienced by the first virtual character.
  • a machine learning model may be used to understand the dialogue information (and one or more historical dialogue information) to determine whether the dialogue information is related to the plot of the interactive multimedia content. For example, if the dialogue information involves historical plots, characters (roles) in the interactive multimedia content, etc., it can be considered that the dialogue information is related to the plot of the interactive multimedia content.
  • the summary information of the historical plot may be extracted based on all the historical plots experienced by the first virtual character.
  • the summary of the historical plot includes event description information of each chapter experienced by the first virtual character.
  • the dialogue information (and one or more historical dialogue information), prompt information corresponding to at least one dimension of the character attribute variable, and summary information of the historical plot experienced by the first virtual character can be input into the machine learning model to obtain information of at least one dimension of the character attribute variable as output.
  • the interactive behavior and the plot can be more closely combined, and the information of at least one dimension of character attribute variables can be more accurately determined, thereby more accurately influencing the development of the plot of the interactive multimedia content.
  • the specific content of the prompt information corresponding to the role attribute variable of at least one dimension and the method for determining the role attribute variable of at least one dimension can refer to the combination of one or more of the above embodiments, which will not be repeated here.
  • information of at least one dimension of role attribute variables is displayed.
  • Information about at least one dimension of character attribute variables can be displayed in the dialogue interface.
  • the dialogue interface can display the second virtual character's favorability toward the first virtual character, and can also display information about changes in favorability after the dialogue.
  • the dialogue interface can also display information about changes in the first virtual character's force value, etc., without limitation to the examples given.
  • Fig. 6 is a flow chart of some other embodiments of the interactive method disclosed in the present invention. As shown in Fig. 6, the method of this embodiment includes: steps S602 to S622.
  • step S602 in response to the interactive multimedia content reaching a second preset plot node and/or the first virtual character completing a preset task, the second virtual character is unlocked and displayed.
  • step S604 a first control for adding the second virtual character to a preset group is displayed.
  • step S606 in response to the user's triggering operation on the first control, prompt information for adding the second virtual character to the preset group is displayed.
  • step S608 in response to the user's operation on the second control of the preset group, information of one or more virtual characters in the preset group is displayed.
  • step S610 in response to the user's selection operation on the second virtual character, a dialogue interface between the first virtual character and the second virtual character is displayed.
  • step S612 dialogue information between the user and the second virtual character is received.
  • Steps S602 to S612 may refer to the aforementioned embodiment and will not be described in detail here.
  • step S614 reply information of the second virtual character is generated according to the dialogue information and the character setting information of the second virtual character.
  • the conversation information is parsed to determine whether the conversation information is consistent with the interactive multimedia content. Plot related; when the dialogue information is related to the plot of the interactive multimedia content, the reply information of the second virtual character is generated according to the dialogue information, the character setting information of the second virtual character and the summary information of the historical plot experienced by the first virtual character.
  • a machine learning model can be used to understand the dialogue information (and one or more historical dialogue information) to determine whether the dialogue information is related to the plot of the interactive multimedia content.
  • the summary information of the historical plot can be extracted based on all the historical plots experienced by the first virtual character.
  • the character setting information of the second virtual character can reflect the characteristics of the second virtual character, such as the character personality and language style.
  • the generated reply information will reply to the plot-related content involved in the dialogue information input by the user, and reflect the language style of the second virtual character.
  • Different second virtual characters may correspond to different agents of the machine learning model or different machine learning models, and different agents or different machine learning models may correspondingly store the plots experienced by the first virtual character.
  • the user After storing historical data such as the user's progress in the interactive multimedia content (the plots experienced), the user can have a dialogue with the second virtual character based on the plot or experience, etc.
  • the dialogue information, the character setting information of the second virtual character, and the summary information of the historical plot are combined to generate the reply information of the second virtual character, so that the second virtual character can have a dialogue and chat with the first virtual character based on the plot, thereby improving the fun, effectiveness and effect of the interaction.
  • the reply information of the second virtual character is generated according to the dialogue information and the character setting information of the second virtual character.
  • the user can also have a conversation with the second virtual character that is not related to the plot, and the second virtual character can also generate a corresponding reply, and the replies of different first virtual characters will reflect different language styles due to different character setting information.
  • step S616 the reply information of the second virtual character is displayed.
  • the reply information may be displayed in the reply area corresponding to the second virtual character, or may be played in the form of voice, without being limited to the examples given.
  • step S618 information of at least one dimension of role attribute variables is determined based on the dialogue information.
  • Step S618 can refer to the above-mentioned embodiment and will not be described in detail here. Step S618 and step S614 can be executed in parallel or in a sequence.
  • step S620 plot development information of the interactive multimedia content is determined based on information of the character attribute variable of at least one dimension.
  • the information of the character attribute variable of at least one dimension can affect the development of the plot of the interactive multimedia content.
  • the information of the character attribute variables determines the plot after the first preset plot node.
  • the plot development information of the interactive multimedia content includes the plot after the first preset plot node.
  • One or more first preset plot nodes may be set in the interactive multimedia content, and each first preset plot node may be configured with a corresponding plot determination condition, and the information of the character attribute variable of at least one dimension is compared with the plot determination condition corresponding to the first preset plot node, so as to determine the plot branch of the plot direction after the first preset plot node.
  • the plot determination condition includes one or more thresholds corresponding to the character attribute variable of at least one dimension.
  • different plot branches correspond to different thresholds, and the development of the plot can be determined according to the comparison of the information of the character attribute variable of at least one dimension with the threshold corresponding to each plot branch.
  • the increase or decrease of the favorability can affect the direction of the ending, and can affect whether the second virtual character becomes the final partner of the first virtual character, etc. For example, when the favorability of the second virtual character to the first virtual character is the first value, the plot goes to the first branch, and when the favorability of the second virtual character to the first virtual character is the second value, the plot goes to the second branch.
  • a machine learning model is used to generate plot development information of the interactive multimedia content.
  • the plot can be generated in real time based on the information of at least one dimension of the character attribute variable and the historical plot.
  • the user's dialogue information and the historical plot experienced can reflect the user's personality and experience of the interactive multimedia content. Therefore, a personalized plot can be generated and improved for the user to further improve the effect of the interaction and the effect of the interactive multimedia content.
  • step S622 a plot page corresponding to the plot development information is displayed.
  • a screen corresponding to the plot after the first preset plot node is displayed.
  • guidance information for the second virtual character to reply is displayed, wherein the guidance information is used to guide the user to return to the interactive multimedia content.
  • the dialogue information is parsed to determine whether it includes information indicating that the user wants to terminate the interactive multimedia content, and guidance information can be generated based on the dialogue information and the character setting information of the second virtual character to guide the user to return to the interactive multimedia content.
  • the card prompt information or comfort information to the user, so that the user can continue to experience the interactive multimedia content.
  • Each second virtual character may correspond to a Bot (robot or automated program) that can communicate with the user, influence the development of the plot, and guide the user's behavior, so that the interaction between the user and the second virtual character and the interactive multimedia content can interact and promote each other, thereby improving the overall operability and interactive experience of the interactive multimedia content.
  • Bot robot or automated program
  • each machine learning model including a machine learning model for determining initial conversation information, a machine learning model for understanding conversation information, a machine learning model for determining information of at least one dimension of character attribute variables, a machine learning model for generating reply information, and a machine learning model for generating plot information, may be the same model or different models.
  • the disclosed solution can affect the virtual characters that users can unlock by realizing the direction of the plot, and users can interact with the virtual characters according to the plot, and the interactive content with the virtual characters can in turn affect the direction of the plot.
  • the present disclosure also provides an interaction device, which is described below in conjunction with FIG. 7 .
  • FIG7 is a structural diagram of some embodiments of the interactive device of the present disclosure.
  • the interactive device 70 of this embodiment includes: a display module 710 , a receiving module 720 , and a determining module 730 .
  • the display module 710 is configured to display a dialogue interface between a first virtual character and a second virtual character, wherein the first virtual character and the second virtual character are virtual characters in interactive multimedia content, and the first virtual character is a virtual character controlled by a user.
  • the receiving module 720 is configured to receive dialogue information input by the user with the second virtual character.
  • the determination module 730 is configured to determine information of at least one dimension of a character attribute variable according to the dialogue information, wherein the at least one dimension of the character attribute variable affects the development of the plot of the interactive multimedia content.
  • the determination module 730 is configured to parse the dialogue information to determine whether the dialogue information is associated with the role attribute variable of at least one dimension; when the dialogue information is associated with the role attribute variable of at least one dimension, a machine learning model is used to determine the information of the role attribute variable of at least one dimension based on the dialogue information and the prompt information corresponding to the role attribute variable of at least one dimension.
  • the character attribute variables of at least one dimension include character attribute variables of a first dimension
  • the first dimension is used to represent the relationship between the first virtual character and the second virtual character
  • the prompt information includes emotional influencing factor information of the second virtual character
  • the determination module 730 is configured to determine the information of the character attribute variables of the first dimension based on the dialogue information and the emotional influencing factor information of the second virtual character using a machine learning model.
  • the character attribute variables of at least one dimension include character attribute variables of a second dimension, where the second dimension is used to represent the ability of the first virtual character, and the prompt information includes: information on factors affecting the ability of the first virtual character.
  • the determination module 730 is configured to determine the information on the character attribute variables of the second dimension based on the dialogue information and the information on factors affecting the ability of the first virtual character, using a machine learning model.
  • the determination module 730 is further configured to parse the dialogue information to determine whether the dialogue information is associated with the plot of the interactive multimedia content; when the dialogue information is associated with the plot of the interactive multimedia content, a machine learning model is used to determine information of the character attribute variable of at least one dimension based on the dialogue information, prompt information corresponding to the character attribute variable of at least one dimension, and summary information of the historical plot experienced by the first virtual character.
  • the determination module 730 is further configured to determine the plot development information of the interactive multimedia content based on information of the character attribute variable of at least one dimension; the display module 710 is further configured to display the plot page corresponding to the plot development information.
  • the determination module 730 is configured to determine the plot after the first preset plot node in response to the interactive multimedia content reaching the first preset plot node based on information of the character attribute variable of at least one dimension, wherein the plot development information of the interactive multimedia content includes the plot after the first preset plot node; and the display module 710 is configured to display the screen corresponding to the plot after the first preset plot node.
  • the interactive device 70 further includes: a generating module 740 configured to generate reply information of the second virtual character according to the dialogue information and the character setting information of the second virtual character.
  • the display module 710 is further configured to display the reply information of the second virtual character.
  • the generation module 740 is configured to parse the dialogue information to determine whether the dialogue information is associated with the plot of the interactive multimedia content; when the dialogue information is associated with the plot of the interactive multimedia content, the reply information of the second virtual character is generated based on the dialogue information, the character setting information of the second virtual character, and the summary information of the historical plot experienced by the first virtual character.
  • the display module 710 is also configured to display a first control for adding the second virtual character to a preset group in response to the interactive multimedia content reaching a second preset plot node and/or the first virtual character completing a preset task, wherein adding the second virtual character to the preset group indicates that the first virtual character and the second virtual character form a preset relationship;
  • the receiving module 720 is also configured to receive a user's trigger operation on the first control;
  • the display module 710 is also configured to display a prompt message for adding the second virtual character to the preset group.
  • the receiving module 720 is further configured to receive a user's operation on a second control of a preset group; the display module 710 is further configured to display information of one or more virtual characters in the preset group; Block 720 is further configured to receive a user's selection operation on the second virtual character; and display module 710 is further configured to display a dialogue interface between the first virtual character and the second virtual character.
  • the display module 710 is further configured to display initial dialogue information of the second virtual character in the dialogue interface, wherein the initial dialogue information of the second virtual character is generated according to character setting information of the second virtual character.
  • the display module 710 is further configured to display guidance information for the second virtual character to reply in response to the dialogue information including information indicating that the user wants to terminate the interactive multimedia content, wherein the guidance information is used to guide the user to return to the interactive multimedia content.
  • the interactive device of the above embodiment displays a dialogue interface between the first virtual character and the second virtual character, and in response to receiving dialogue information with the second virtual character input by the user, can determine information of at least one dimension of character attribute variables based on the dialogue information, thereby affecting the development of the plot of the interactive multimedia content.
  • the user can affect the character attribute variables through the interactive mode of dialogue with the second virtual character, thereby affecting the development of the plot of the interactive multimedia content. Closely linking the interactive process with the plot of the interactive multimedia content makes it easier to attract users to interact, expands the interactive form of the interactive multimedia content, and improves the effectiveness and effect of the interactive process.
  • modules are only logical modules divided according to the specific functions implemented by them, and are not used to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above modules 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 modules are shown with dotted lines in the drawings to indicate that these modules may not actually exist, and the operations/functions implemented by them can be implemented by the processing circuit itself.
  • the device may also include a memory, which can store various information generated by the device, various modules contained in the device during operation, programs and data used for operation, data to be sent by the communication module, etc.
  • the memory may be a volatile memory and/or a non-volatile memory.
  • the memory may include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), and a flash memory.
  • the memory may also be located outside the device.
  • the device may also include a communication module, which can be used to communicate with other devices.
  • the communication module can be implemented in an appropriate manner known in the art, such as including communication components such as an antenna array and/or a radio frequency link, various types of interfaces, communication modules, etc. It will not be described in detail here.
  • the device may also include other components not shown, such as a radio frequency link, a baseband processing module, and/or a baseband processing module. Blocks, network interfaces, processors, controllers, etc. will not be described in detail here.
  • FIG8 shows a block diagram of some embodiments of the electronic device of the present disclosure.
  • the electronic device 8 can be various types of devices, for example, can include but not limited to mobile terminals such as mobile phones, laptop computers, 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.
  • the electronic device 8 can include a display panel for displaying data and/or execution results used in the scheme of the present disclosure.
  • the display panel can be in various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel.
  • the display panel can be not only a flat panel, but also a curved panel or even a spherical panel.
  • the electronic device 8 of this embodiment includes: a memory 81 and a processor 82 coupled to the memory 81. It should be noted that the components of the electronic device 8 shown in FIG8 are only exemplary and non-restrictive. According to actual application requirements, the electronic device 8 may also have other components. The processor 82 may control other components in the electronic device 8 to perform desired functions.
  • the memory 81 is used to store one or more computer-readable instructions.
  • the processor 82 is used to execute the computer-readable instructions, the computer-readable instructions are executed by the processor 82 to implement the method according to any of the above embodiments.
  • the specific implementation of each step of the method and the related explanation content please refer to the above embodiments, and the repetition will not be repeated here.
  • the processor 82 and the memory 81 may communicate with each other directly or indirectly.
  • the processor 82 and the memory 81 may communicate with each other through a network.
  • the network may include a wireless network, a wired network, and/or any combination of a wireless network and a wired network.
  • the processor 82 and the memory 81 may also communicate with each other through a system bus, which is not limited by the present disclosure.
  • the processor 82 may 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 may 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 gates or transistor logic devices, discrete hardware components.
  • the central processing unit (CPU) may be an X86 or ARM architecture, etc.
  • the memory 81 may include any combination of various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the memory 81 may include, for example, a system memory, which may store, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs. Various applications and various data may also be stored in the storage medium.
  • a system memory which may store, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs.
  • Various applications and various data may also be stored in the storage medium.
  • various operations/processes according to the present disclosure are performed by software and/or firmware.
  • the program constituting the software can be installed from a storage medium or a network to a computer system with a dedicated hardware structure, such as a computer system (or electronic device) 900 shown in FIG9 .
  • the computer system can perform various functions, including functions such as those described above.
  • FIG9 is a block diagram showing an example structure of a computer system that can be used in an embodiment of the present disclosure.
  • a central processing unit (CPU) 901 performs various processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903.
  • ROM read-only memory
  • RAM random access memory
  • the central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above.
  • ROM 902, RAM 903, and storage part 908 may be various forms of computer-readable storage media, as described below. It should be noted that although ROM 902, RAM 903, and storage device 908 are shown separately in FIG. 9 , one or more of them may be combined or located in the same or different memory or storage modules.
  • the CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904.
  • An input/output interface 905 is also connected to the bus 904.
  • an input portion 906 such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.
  • an output portion 907 including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.
  • a storage portion 908 including a hard disk, a magnetic tape, etc.
  • a communication portion 909 including a network interface card such as a LAN card, a modem, etc.
  • the communication portion 909 allows communication processing to be performed via a network such as the Internet.
  • the various devices or modules in the computer system 900 shown in FIG. 9 communicate through the bus 904, they can also communicate through a network or other means, wherein the network can include a wireless network, a wired network, and/or any combination of a wireless network and a wired network.
  • a drive 910 is also connected to the input/output interface 905 as needed.
  • a removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.
  • a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 911 .
  • 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 contains program code for executing the method shown in the flowchart.
  • the computer program can be downloaded and installed from the network through the communication part 909, or downloaded from the storage part 909.
  • the computer program is installed by the component 908, or is installed from the ROM 902.
  • a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment.
  • a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above.
  • 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 of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by an instruction execution system, device or device or used in combination with it.
  • a computer-readable signal medium may include a data signal propagated in a 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 of the above.
  • 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, device, 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 of the above.
  • the computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
  • a computer program comprising: instructions, which, when executed by a processor, cause the processor to execute any of the methods of the above embodiments.
  • the instructions may be embodied as computer program codes.
  • computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, the programming languages including but not limited to object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages.
  • the program code 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.
  • 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)).
  • the computer alternatively, can be connected to an external computer (eg, via the Internet using an Internet service provider).
  • each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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.
  • each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
  • modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.
  • exemplary hardware logic components 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.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOCs systems on chip
  • CPLDs complex programmable logic devices
  • an interaction method comprising: displaying a dialogue interface between a first virtual character and a second virtual character, wherein the first virtual character and the second virtual character are virtual characters in interactive multimedia content, and the first virtual character is a virtual character controlled by a user; receiving dialogue information with the second virtual character input by the user; and determining information of a character attribute variable of at least one dimension based on the dialogue information, wherein the character attribute variable of at least one dimension affects the development of the plot of the interactive multimedia content.
  • determining information of the role attribute variable of at least one dimension based on the conversation information includes: parsing the conversation information to determine whether the conversation information is associated with the role attribute variable of at least one dimension; and, in a case where the conversation information is associated with the role attribute variable of at least one dimension, using a machine learning model to determine information of the role attribute variable of at least one dimension based on the conversation information and prompt information corresponding to the role attribute variable of at least one dimension.
  • the at least one dimension of the role attribute variable includes a first dimension of the role attribute variable
  • the first dimension is used to represent the relationship between the first virtual character and the second virtual character
  • the prompt information includes the emotion influencing factor information of ...
  • the prompt information includes the emotion influencing factor information of the second virtual character according to the dialogue information
  • the at least The prompt information corresponding to the character attribute variable of at least one dimension is determined by using a machine learning model.
  • the information includes: determining the information of the character attribute variable of the first dimension by using a machine learning model according to the dialogue information and the emotional influencing factor information of the second virtual character.
  • the prompt information also includes: character setting information of the second virtual character, and the information of determining the character attribute variables of the first dimension by using a machine learning model based on the dialogue information and the emotional influencing factor information of the second virtual character includes: information of determining the character attribute variables of the first dimension by using a machine learning model based on the dialogue information, the emotional influencing factor information of the second virtual character and the character setting information of the second virtual character.
  • the role attribute variables of at least one dimension include role attribute variables of a second dimension
  • the second dimension is used to represent the ability of the first virtual character
  • the prompt information includes: information on factors affecting the ability of the first virtual character
  • the prompt information corresponding to the role attribute variables of at least one dimension includes: determining the information on the role attribute variables of the second dimension using a machine learning model based on the dialogue information and the information on factors affecting the ability of the first virtual character.
  • determining information of character attribute variables of at least one dimension based on the dialogue information also includes: parsing the dialogue information to determine whether the dialogue information is associated with the plot of the interactive multimedia content; and, when the dialogue information is associated with the plot of the interactive multimedia content, using a machine learning model to determine information of the character attribute variables of at least one dimension based on the dialogue information, prompt information corresponding to the character attribute variables of at least one dimension, and summary information of the historical plot experienced by the first virtual character.
  • the method further includes: determining plot development information of the interactive multimedia content based on information of the character attribute variables of the at least one dimension; and displaying a plot page corresponding to the plot development information.
  • determining the plot development information of the interactive multimedia content based on the information of the character attribute variables of the at least one dimension includes: in response to the interactive multimedia content reaching a first preset plot node, determining the plot after the first preset plot node based on the information of the character attribute variables of the at least one dimension, wherein the plot development information of the interactive multimedia content includes the plot after the first preset plot node; and displaying the plot page corresponding to the plot development information includes: displaying the screen corresponding to the plot after the first preset plot node.
  • the method further comprises: Setting information, generating reply information of the second virtual character; and displaying the reply information of the second virtual character.
  • generating the reply information of the second virtual character based on the dialogue information and the character setting information of the second virtual character includes: parsing the dialogue information to determine whether the dialogue information is associated with the plot of the interactive multimedia content; if the dialogue information is associated with the plot of the interactive multimedia content, generating the reply information of the second virtual character based on the dialogue information, the character setting information of the second virtual character and the summary information of the historical plot experienced by the first virtual character.
  • the method further includes: in response to the interactive multimedia content reaching a second preset plot node and/or the first virtual character completing a preset task, displaying a first control for adding the second virtual character to a preset group, wherein adding the second virtual character to the preset group indicates that the first virtual character and the second virtual character form a preset relationship; receiving a trigger operation of the user on the first control; and displaying a prompt message for adding the second virtual character to the preset group.
  • the display of the dialogue interface between the first virtual character and the second virtual character includes: receiving the user's operation on the second control of the preset group; displaying information of one or more virtual characters in the preset group; receiving the user's selection operation on the second virtual character; and displaying the dialogue interface between the first virtual character and the second virtual character.
  • the displaying of the dialogue interface between the first virtual character and the second virtual character includes: displaying initial dialogue information of the second virtual character in the dialogue interface, wherein the initial dialogue information of the second virtual character is generated according to the character setting information of the second virtual character.
  • the method further includes: in response to the dialogue information including information indicating that the user wants to terminate the interactive multimedia content, displaying guidance information for the second virtual character to reply, wherein the guidance information is used to guide the user to return to the interactive multimedia content.
  • an interactive device comprising: a display module, configured to display a dialogue interface between a first virtual character and a second virtual character, wherein the first virtual character and the second virtual character are virtual characters in interactive multimedia content, and the first virtual character is a virtual character controlled by a user; a receiving module, configured to receive dialogue information with the second virtual character input by the user; and a determining module, configured to determine information of a character attribute variable of at least one dimension based on the dialogue information, wherein the character attribute variable of at least one dimension affects the development of the plot of the interactive multimedia content.
  • an electronic device comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the interaction method of any embodiment of the present disclosure based on instructions stored in the memory.
  • a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the interactive method of any embodiment of the present disclosure is performed.
  • a computer program comprising: instructions, which, when executed by a processor, cause the processor to execute the interactive method of any embodiment described in the present disclosure.
  • a computer program product comprising instructions, which, when executed by a processor, implement the interactive method of any embodiment described in the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Human Computer Interaction (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开涉及一种交互方法、装置、电子设备以及计算机可读存储介质，涉及计算机技术领域。本公开的交互方法包括：显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色；接收用户输入的与第二虚拟角色的对话信息；根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。

Description

交互方法、装置、电子设备以及计算机可读存储介质
相关申请的交叉引用
本申请是以CN申请号为202311598857.3，申请日为2023年11月27日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及计算机技术领域，特别涉及一种交互方法、装置、电子设备以及计算机可读存储介质。
背景技术
互动多媒体内容。例如，游戏、互动电视剧、互动电影等，用户在体验过程中可以控制其中的虚拟角色与非玩家角色进行交互。目前，这种交互的内容往往是设定好。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
根据本公开的一些实施例，提供的一种交互方法，包括：显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色；接收用户输入的与第二虚拟角色的对话信息；根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。
根据本公开的一些实施例，提供的一种交互装置，包括：显示模块，被配置为显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色；接收模块，被配置为接收用户输入的与第二虚拟角色的对话信息；确定模块，被配置为根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。
根据本公开的又一些实施例，提供一种电子设备，包括：存储器；和耦接至存储器的处理器，处理器被配置为基于存储在存储器中的指令，执行本公开中的任一实施 例的交互方法。
根据本公开的再一些实施例，提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时执行本公开中的任一实施例的交互方法。
根据本公开的又一些实施例，提供一种计算机程序，包括指令，当所述指令被处理器执行时，使所述处理器实现本公开中的任一实施例的交互方法。
根据本公开的再一些实施例，提供一种计算机程序产品，包括指令，当所述指令被处理器执行时，使所述处理器实现本公开中的任一实施例的交互方法。
通过以下参照附图对本公开的示例性实施例的详细描述，本公开的其它特征及其优点将会变得清楚。
附图说明
下面参照附图说明本公开的优选实施例。此处所说明的附图用来提供对本公开的进一步理解，各附图连同下面的具体描述一起包含在本说明书中并形成说明书的一部分，用于解释本公开。应当理解的是，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开构成限制。在附图中：
图1示出本公开的一些实施例的交互方法的流程示意图；
图2示出本公开的一些实施例的界面的示意图；
图3示出本公开的另一些实施例的界面的示意图；
图4示出本公开的又一些实施例的界面的示意图；
图5示出本公开的另一些实施例的交互方法的流程示意图。
图6示出本公开的又一些实施例的交互方法的流程示意图。
图7示出本公开的一些实施例的交互装置的结构示意图；
图8示出本公开的一些实施例的电子设备的结构示意图；
图9示出本公开的一些实施例的计算机系统的结构示意图。
应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不一定是按照实际的比例关系绘制的。在各附图中使用了相同或相似的附图标记来表示相同或者相似的部件。因此，一旦某一项在一个附图中被定义，则在随后的附图中可能不再对其进行进一步讨论。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完 整地描述，但是显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。以下对实施例的描述实际上也仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值应被解释为仅仅是示例性的，不限制本公开的范围。
本公开中使用的术语“包括”及其变型意指至少包括后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包括但不限于”。此外，本公开使用的术语“包含”及其变型意指至少包含后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包含但不限于”。因此，包括与包含是同义的。术语“基于”意指“至少部分地基于”。
整个说明书中所称“一个实施例”、“一些实施例”或“实施例”意味着与实施例结合描述的特定的特征、结构或特性被包括在本发明的至少一个实施例中。例如，术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。而且，短语“在一个实施例中”、“在一些实施例中”或“在实施例中”在整个说明书中各个地方的出现不一定全都指的是同一个实施例，但是也可以指同一个实施例。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。除非另有指定，否则“第一”、“第二”等概念并非意图暗示如此描述的对象必须按时间上、空间上、排名上的给定顺序或任何其他方式的给定顺序。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图对本公开的实施例进行详细说明，但是本公开并不限于这些具体的 实施例。下面这些具体实施例可以相互结合，对于相同或者相似的概念或过程可能在某些实施例不再赘述。此外，在一个或多个实施例中，特定的特征、结构或特性可以由本领域的普通技术人员从本公开将清楚的任何合适的方式组合。
发明人发现：现有的用户在互动多媒体内容中控制虚拟角色与非玩家角色的交互方式单一。例如，用户控制虚拟角色与非玩家角色对话的内容是设定好的，比较固定和机械化，并且互动多媒体的剧情也是设定好的，剧情与对话部分是完全割裂的。目前的交互方式导致交互的效率和效果都比较低。
有鉴于此，本公开提出一种交互方法，提高交互的效率和效果。
图1为本公开交互方法一些实施例的流程图。如图1所示，该实施例的方法包括：步骤S102～S106。
在步骤S102中，显示第一虚拟角色与第二虚拟角色的对话界面。
例如，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色。第二虚拟角色可以为非玩家角色(Non-Player Character，NPC)。例如，互动多媒体内容为游戏、互动电视剧、互动电影等，不限于所举示例。
本公开中显示相关步骤都可以通过图形用户界面(Graphical User Interface，GUI)实现。
在一些实施例中，响应于用户的触发操作，显示对话界面。用户的触发操作可以是打开互动多媒体内容的操作，触发对话控件的操作，或是语音唤醒等操作，不限于所举示例。
在步骤S104中，接收用户输入的与第二虚拟角色的对话信息。
对话界面中还可以显示对话输入区域，用于接收输入的对话信息。对话信息可以通过文本、语音等任何形式输入。用户可以就任意感兴趣的话题与第二虚拟角色进行对话，可以与互动多媒体内容的剧情、人物等相关，也可以与互动多媒体内容的剧情、人物等无关。
在步骤S106中，根据对话信息，确定至少一个维度的角色属性变量的信息。
至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。例如，在至少一个维度的角色属性变量的信息不同的情况下，互动多媒体内容的剧情走向不同的分支。
在一些实施例中，至少一个维度的角色属性变量包括：第一维度的角色属性变量、第二维度的角色属性变量中至少一项。第一维度用于表示第一虚拟角色与第二虚拟角 色之间的关系，第二维度用于表示第一虚拟角色的能力。第一虚拟角色和第二虚拟角色的对话可以影响两者之间的关系，也可以影响第一虚拟角色的能力。
第一维度的角色属性变量可以包括一个或多个第一变量。例如，一个或多个第一变量可以包括一个或多个正面情感的变量和/或一个或多个负面情感的变量。例如，正面情感的变量包括好感度、亲密度、信赖度等，负面情感包括疏离度、仇恨值等，不限于所举示例。
第二维度的角色属性变量可以包括一个或多个第二变量。例如，一个或多个第二变量包括：武力值、生命值、智力值、体力值等用于表示第一虚拟角色的能力的一项或多项变量。
第一维度的角色属性变量的信息可以是一个或多个第一变量的值、等级、变化值、变化等级中至少一项。第二维度的角色属性变量的信息可以是一个或多个第二变量的值、等级、变化值、变化等级中至少一项。可以采用数值或等级等方式对一个或多个第一变量和一个或多个第二变量进行量化，不限于所举示例。
上述实施例的方法，用户控制的第一虚拟角色可以和第二虚拟角色进行对话，显示第一虚拟角色与第二虚拟角色的对话界面，响应于接收到用户输入的与第二虚拟角色的对话信息，根据对话信息，可以确定至少一个维度的角色属性变量的信息，从而影响互动多媒体内容的剧情的发展。通过上述实施例的方法，用户通过与第二虚拟角色对话的交互方式，可以影响角色属性变量，进而影响互动多媒体内容的剧情的发展。将交互过程与互动多媒体内容的剧情紧密联系，更加容易吸引用户进行交互，扩展互动多媒体内容的互动形式，提高了交互过程的有效性和效果。
在一些实施例中，第二虚拟角色为与第一虚拟角色具有预设关系的角色，响应于用户对第二虚拟角色的唤出操作，显示第一虚拟角色与第二虚拟角色的对话界面。
第一虚拟角色和第二虚拟角色之间的预设关系可以是正面关系也可以是负面关系。例如，第一虚拟角色和第二虚拟角色之间可以是伙伴、情侣、盟友等正面关系，也可以是敌人、对手等负面关系。
在一些实施例中，第一虚拟角色和第二虚拟角色之间的预设关系是响应于用户的对第一虚拟角色和第二虚拟角色之间的关系建立操作而生成的。可以接收用户对第二虚拟角色的选择和预设关系的类型的选择，确定第一虚拟角色和第二虚拟角色之间的预设关系，还可以显示该预设关系。
可以设置不同类型的预设关系供用户进行选择。用户可以灵活选择不同的虚拟角 色作为第二虚拟角色，并配置第一虚拟角色和第二虚拟角色之间的预设关系。例如，显示关系配置界面，显示可以配置的一个或多个虚拟角色，接收用户将虚拟角色A设置为第一虚拟角色的伙伴，将虚拟角色B设置为第一虚拟角色的敌人的操作等。
与第一虚拟角色形成不同类型的预设关系的第二虚拟角色，可以被配置到不同的预设分组中。例如，接收用户将第二虚拟角色加入选择的预设分组的触发操作，显示将第二虚拟角色加入预设分组的提示信息。例如，第二虚拟角色加入预设分组的提示信息为“A成为你的伙伴”。还可以显示预设分组中的一个或多个虚拟角色的信息，例如，显示一个或多个虚拟角色的名称、简介和/或图像等，不限于所举示例。
在一些实施例中，接收用户对预设分组的选择操作，显示预设分组中一个或多个虚拟角色的信息，接收用户对第二虚拟角色的选择操作；显示第一虚拟角色与第二虚拟角色的对话界面。
随着互动多媒体内容中剧情的发展，可以出现不同的虚拟角色，剧情走向影响解锁的虚拟角色。用户可以选择出现的虚拟角色作为第二虚拟角色，并配置第一虚拟角色与第二虚拟角色的预设关系。
在一些实施例中，响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，显示将第二虚拟角色加入预设分组的第一控件，其中，将第二虚拟角色加入预设分组表示第一虚拟角色与第二虚拟角色形成预设关系；接收用户对第一控件的触发操作；显示将第二虚拟角色加入预设分组的提示信息。
在一些实施例中，响应于用户控制第一虚拟角色在互动多媒体内容中完成预设任务和/或剧情发展到第二预设剧情节点，解锁并显示第二虚拟角色。第二虚拟角色可以通过用户对第一控件的触发被加入预设分组，也可以通过用户的提前配置，自动加入预设分组。例如，接收用户提前配置的加入不同的预设分组的虚拟角色的目标特征，在解锁的第二虚拟角色符合目标特征的情况下，自动被加入相对应的预设分组。例如，用户配置称为伙伴的虚拟角色为X阵营的领导角色，在解锁的虚拟角色符合该特征时，将解锁的虚拟角色加入伙伴分组。
例如，响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，可以显示关系配置界面，在关系配置界面中显示将第二虚拟角色加入预设分组的第一控件。例如，关系配置界面中显示一个或多个虚拟角色，每个虚拟角色后可以设置第一控件。或者，响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，可以显示第二虚拟角色的显示界面，在第二虚拟角色的显示界面显 示第一控件。或者，响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，在当前界面中显示第一控件。
第一控件可以以任何形式显示和触发，在此不作限制。例如，互动多媒体内容的显示界面中出现的第二虚拟角色的图像可以直接作为第一控件，用户对第二虚拟角色的图像的点击可以作为对第一控件的触发。在只配置了一种预设关系(或分组)的情况下，响应于用户对第一控件的触发，直接将第二虚拟角色加入预设分组，并显示提示信息。在配置了多种预设关系的情况下，响应于用户对第一控件的触发，显示多种候选预设关系(或候选预设分组)，接收用户对候选预设关系(或候选预设分组)的选择，显示将第二虚拟角色加入选择的候选预设分组的提示信息。
如图2所示，可以在第二虚拟角色的显示界面中显示提示信息“A成为了你的伙伴”。
在一些实施例中，接收用户对预设分组的第二控件的操作；显示预设分组中的一个或多个虚拟角色的信息；接收用户对第二虚拟角色的选择操作；显示第一虚拟角色与第二虚拟角色的对话界面。
在存在多个的预设分组的情况下，可以显示多个预设分组的第二控件，接收用户对任意预设分组的第二控件的触发操作，显示选择的预设分组中一个或多个虚拟角色的信息。每个虚拟角色的信息可以包括：名称、图像中至少一项，但不限于所举示例。如图3所示，在多媒体内容的显示界面中，可以显示第二控件，可以以预设分组的名称显示，例如“伙伴”。用户可以点击“伙伴”控件，显示与第一虚拟角色成为伙伴关系的一个或多个虚拟角色。如图4所示，点击“伙伴”控件后可以显示多个虚拟角色的头像。
如图4所示，在预设分组中的虚拟角色超出阈值的情况下，可以显示部分虚拟角色，例如，显示与阈值相等数量的虚拟角色。显示的虚拟角色可以按照加入预设分组的顺序，或者按照与第一虚拟角色的关系程度，或者按照与第一虚拟角色的交互次数等进行排序。剩余的部分虚拟角色可以隐藏。可以设置第三控件，如图4中所示的“全部”控件，响应于用户触发第三控件显示隐藏的部分虚拟角色的信息。
如图4所示，响应于用户选择一个虚拟角色C作为第二虚拟角色，显示第一虚拟角色与第二虚拟角色C的对话界面。
在一些实施例中，在对话界面中显示第二虚拟角色的初始对话信息，其中，第二虚拟角色的初始对话信息是根据第二虚拟角色的人物设定信息生成的。
如图4所示，对话界面中还可以显示第二虚拟角色的立绘(或动态形象)、背景等，显示第二虚拟角色的初始对话信息。不同第二虚拟角色的初始对话信息是不同的，可以根据第二虚拟角色的人物设定信息，采用生成。例如，将第二虚拟角色的人物设定信息输入机器学习模型，生成第二虚拟角色的对话信息。例如，人物设定信息可以包括：角色的出身背景信息、性别、性格、年龄、语言风格中至少一项的描述信息，不限于所举示例。还可以将第二虚拟角色的人物设定信息输入机器学习模型生成第二虚拟角色的立绘或动态形象，将背景信息输入机器学习模型，生成背景等。
本公开中的机器学习模型可以是AI(Artificial Intelligence，人工智能)模型、大模型等，具体的可以是神经网络模型、深度学习模型、大语言模型(Large Language Model，LLM)、生成式模型等。生成式模型例如为AIGC(Artificial Intelligence Generated Content，人工智能生成内容)，可以是文本生成模型、图像生成模型、视频生成模型、语音生成模型或多模态生成模型等，不限于所举示例。
如图4所示，对话界面中可以显示语音输入控件，也可以显示文本输入区，用于接收用户输入的对话信息，不限于所举示例。
在一些实施例中，在对话信息为语音的情况下，可以首先进行语音识别，将语音转换为文本，根据对话信息对应的文本，确定至少一个维度的角色属性变量的信息。
在一些实施例中，根据对话信息，确定至少一个维度的角色属性变量的信息包括：根据对话信息以及第一虚拟角色与第二虚拟角色的一条或多条历史对话信息，确定至少一个维度的角色属性变量的信息。
在第一虚拟角色与第二虚拟角色已经产生对话的情况下，可以根据用户当前输入的对话信息和一条或多条历史对话信息，确定至少一个维度的角色属性变量的信息。一条或多条历史对话信息可以是预设时间内的历史对话信息，或者预设数量的历史对话信息，或者进入对话界面后第一条对话信息到当前输入的对话信息之前的历史对话信息，不限于所举示例。结合当前输入的对话信息和历史对话信息，可以更加准确理解对话的含义，从而更加准确的确定至少一个维度的角色属性变量的信息。
图5为本公开交互方法的另一些实施例的流程图。如图5所示，根据所述对话信息，确定至少一个维度的角色属性变量的信息包括：包括：步骤S502～S504。
在步骤S502中，对对话信息进行解析，确定对话信息是否与至少一个维度的角色属性变量相关联。
例如，可以采用机器学习模型对对话信息(以及一条或多条历史对话信息)进行 理解，确定对话信息是否与第一维度的角色属性变量相关联和/或对话信息是否与第二维度的角色属性变量相关联。
在步骤S504中，在对话信息与至少一个维度的角色属性变量相关联的情况下，根据对话信息以及至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定至少一个维度的角色属性变量的信息。
至少一个维度的角色属性变量对应的提示信息用于辅助机器学习模型理解对话信息与至少一个维度的角色属性变量的关系，以及对至少一个维度的角色属性变量产生的影响。
在一些实施例中，在至少一个维度的角色属性变量包括第一维度的角色属性变量的情况下，提示信息包括第二虚拟角色的情感影响因素信息和/或人物设定信息；在至少一个维度的角色属性变量包括第二维度的角色属性变量的情况下，提示信息包括第一虚拟角色的能力影响因素信息。
例如，第二虚拟角色的情感影响因素信息包括好感度示例、亲密度示例、信赖度示例、疏离度示例、仇恨值示例中至少一项。例如，好感度示例可以是用于描述影响第二虚拟角色对其他虚拟角色的好感度的语句、情形和/或事件等的文本，不限于所举示例。其他示例与好感度示例类似，在此不再赘述。
例如，第一虚拟角色的能力影响因素信息包括武力值示例、生命值示例、智力值示例、体力值示例中至少一项。例如，武力值示例可以是用于描述影响第二虚拟角色的武力值的语句、情形和/或事件等的文本，不限于所举示例。其他示例与武力值示例类似，在此不再赘述。
在一些实施例中，在至少一个维度的角色属性变量包括第一维度的角色属性变量，提示信息包括第二虚拟角色的情感影响因素信息的情况下，根据对话信息以及第二虚拟角色的情感影响因素信息，采用机器学习模型，确定第一维度的角色属性变量的信息。
可以将对话信息(以及一条或多条历史对话信息)和第二虚拟角色的情感影响因素信息输入机器学习模型，得到输出的第一维度的角色属性变量的信息。
在一些实施例中，在至少一个维度的角色属性变量包括第一维度的角色属性变量，提示信息包括第二虚拟角色的情感影响因素信息和人物设定信息的情况下，根据对话信息、第二虚拟角色的情感影响因素信息以及第二虚拟角色的人物设定信息，采用机器学习模型，确定第一维度的角色属性变量的信息。
可以将对话信息(以及一条或多条历史对话信息)、第二虚拟角色的情感影响因素信息和第二虚拟角色的人物设定信息输入机器学习模型，得到输出的第一维度的角色属性变量的信息。
结合对话信息、第二虚拟角色的情感影响因素信息和第二虚拟角色的人物设定信息，确定表示第一虚拟角色与第二虚拟角色之间的关系的第一维度的角色属性变量的信息，提高了准确性，并有助于提高后续确定互动多媒体内容的剧情发展的准确性。
在一些实施例中，在至少一个维度的角色属性变量包括第二维度的角色属性变量，提示信息包括第一虚拟角色的能力影响因素信息的情况下，根据对话信息以及第一虚拟角色的能力影响因素信息，采用机器学习模型，确定第二维度的角色属性变量的信息。
可以将对话信息(以及一条或多条历史对话信息)以及第一虚拟角色的能力影响因素信息输入机器学习模型，确定第二维度的角色属性变量的信息。
结合对话信息与第一虚拟角色的能力影响因素信息，确定表示第二虚拟角色的能力的第二维度的角色属性变量的信息，提高了准确性，并有助于提高后续确定互动多媒体内容的剧情发展的准确性。
上述实施例中，根据用户输入的对话信息，影响第一虚拟角色和第二虚拟角色的之间的关系和/或第二虚拟角色的能力，进而影响互动多媒体内容的剧情发展，有利于提高用户进行交互的兴趣和动力，提高了互动交互的频率、有效性和效果。
用户可以与第二虚拟角色进行与剧情相关联的对话，这种情况下，也可以相应的进行处理。
在一些实施例中，对对话信息进行解析，确定对话信息是否与互动多媒体内容的剧情相关联；在对话信息与互动多媒体内容的剧情相关联的情况下，根据对话信息、至少一个维度的角色属性变量对应的提示信息以及第一虚拟角色所经历的历史剧情的摘要信息，采用机器学习模型，确定至少一个维度的角色属性变量的信息。
例如，可以采用机器学习模型对对话信息(以及一条或多条历史对话信息)进行理解，确定对话信息是否与互动多媒体内容的剧情相关联。例如，对话信息中涉及历史剧情、互动多媒体内容中的人物(角色)等，可以认为对话信息互动多媒体内容的剧情相关联。
历史剧情的摘要信息，可以是根据第一虚拟角色所经历的所有历史剧情提取的。例如，历史剧情的摘要包括第一虚拟角色所经历的各个章节的事件描述信息。
可以将对话信息(以及一条或多条历史对话信息)、至少一个维度的角色属性变量对应的提示信息以及第一虚拟角色所经历的历史剧情的摘要信息输入机器学习模型，得到输出的至少一个维度的角色属性变量的信息。
结合对话信息、历史剧情以及至少一个维度的角色属性变量对应的提示信息，可以将交互行为与剧情更加紧密的结合在一起，更加准确的确定至少一个维度的角色属性变量的信息，从而更加准确的影响互动多媒体内容的剧情的发展。
至少一个维度的角色属性变量对应的提示信息的具体内容，以及至少一个维度的角色属性变量的确定方法，可以参考上述一个或多个实施例的结合，在此不再赘述。
在一些实施例中，显示至少一个维度的角色属性变量的信息。
可以在对话界面中显示至少一个维度的角色属性变量的信息。如图4所示，对话界面中可以显示第二虚拟角色对第一虚拟角色的好感度，还可以显示对话后好感度的变化信息。对话界面中还可以显示第一虚拟角色的武力值的变化信息等，不限于所举示例。
下面结合图6描述本公开交互方法的又一些实施例。
图6为本公开交互方法又一些实施例的流程图。如图6所示，该实施例的方法包括：步骤S602～S622。
在步骤S602中，响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，解锁并显示第二虚拟角色。
在步骤S604中，显示将第二虚拟角色加入预设分组的第一控件。
在步骤S606中，响应于用户对第一控件的触发操作，显示将第二虚拟角色加入预设分组的提示信息。
在步骤S608中，响应于用户对预设分组的第二控件的操作，显示预设分组中的一个或多个虚拟角色的信息。
在步骤S610中，响应于用户对第二虚拟角色的选择操作，显示第一虚拟角色与第二虚拟角色的对话界面。
在步骤S612中，接收用户输入的与第二虚拟角色的对话信息。
步骤S602～S612可以参考前述实施例，在此不再赘述。
在步骤S614中，根据对话信息和第二虚拟角色的人物设定信息，生成第二虚拟角色的回复信息。
在一些实施例中，对对话信息进行解析，确定对话信息是否与互动多媒体内容的 剧情相关联；在对话信息与互动多媒体内容的剧情相关联的情况下，根据对话信息、第二虚拟角色的人物设定信息以及第一虚拟角色所经历的历史剧情的摘要信息，生成第二虚拟角色的回复信息。
例如，可以采用机器学习模型对对话信息(以及一条或多条历史对话信息)进行理解，确定对话信息是否与互动多媒体内容的剧情相关联。历史剧情的摘要信息，可以是根据第一虚拟角色所经历的所有历史剧情提取的。第二虚拟角色的人物设定信息可以反映第二虚拟角色的人物性格、语言风格等特征。生成的回复信息中会针对用户输入的对话信息涉及的剧情相关内容进行回复，并体现出第二虚拟角色的语言风格。
不同的第二虚拟角色可以对应机器学习模型的不同的代理端(Agent)或者不同的机器学习模型，不同的代理端或者不同的机器学习模型可以对应的存储第一虚拟角色所经历的剧情。
存储用户在互动多媒体内容中的进度(所经历的剧情)等历史数据之后，用户可以根据剧情或经历等与第二虚拟角色对话。将对话信息、第二虚拟角色的人物设定信息和历史剧情的摘要信息结合，生成第二虚拟角色的回复信息，可以使第二虚拟角色与第一虚拟角色针对剧情进行对话和聊天，提高了交互的趣味性、有效性和效果。
在一些实施例中，在对话信息与互动多媒体内容的剧情相关联的情况下，根据对话信息、第二虚拟角色的人物设定信息，生成第二虚拟角色的回复信息。
用户也可以与第二虚拟角色进行与剧情无关的对话，第二虚拟角色也可以生成相应的回复，并且不同的第一虚拟角色的回复会因人物设定信息的不同而体现出不同的语言风格。
在步骤S616中，显示第二虚拟角色的回复信息。
如图4所示，可以在第二虚拟角色对应的回复区域显示回复信息，也可以采用语音的形式播放回复信息，不限于所举示例。
在步骤S618中，根据对话信息，确定至少一个维度的角色属性变量的信息。
步骤S618可以参考前述实施例，在此不再赘述。步骤S618与步骤S614可以并列执行或者调整先后顺序。
在步骤S620中，根据至少一个维度的角色属性变量的信息，确定互动多媒体内容的剧情发展信息。
至少一个维度的角色属性变量的信息可以影响互动多媒体内容的剧情的发展。在一些实施例中，响应于互动多媒体内容到达第一预设剧情节点，根据至少一个维度的 角色属性变量的信息，确定第一预设剧情节点之后的剧情。互动多媒体内容的剧情发展信息包括第一预设剧情节点之后的剧情。
互动多媒体内容中可以设置一个或多个第一预设剧情节点，每个第一预设剧情节点可以配置对应的剧情确定条件，将至少一个维度的角色属性变量的信息与第一预设剧情节点对应的剧情确定条件进行比对，从而确定在第一预设剧情节点之后剧情走向的剧情分支。例如，剧情确定条件包括至少一个维度的角色属性变量对应的一个或多个阈值。例如，不同的剧情分支对应不同的阈值，根据至少一个维度的角色属性变量的信息与每个剧情分支对应的阈值的比对，可以确定剧情的发展。例如，好感度的上升或下降可以影响结局的走向，可以影响第二虚拟角色是否成为第一虚拟角色的最终的伴侣等。例如，第二虚拟角色对第一虚拟角色的好感度为第一值的情况下，剧情走向第一分支，第二虚拟角色对第一虚拟角色的好感度为第二值的情况下，剧情走向第二分支。
在一些实施例中，根据至少一个维度的角色属性变量的信息和第一虚拟角色所经历的历史剧情的信息，采用机器学习模型，生成互动多媒体内容的剧情发展信息。
可以根据至少一个维度的角色属性变量的信息和历史剧情，实时生成剧情。用户的对话信息和所经历的历史剧情，可以反映用户的个性以及对互动多媒体内容的体验感受，因此，可以为用户生成并提高个性化的剧情，以进一步提高交互的效果以及互动多媒体内容的效果。
在步骤S622中，显示与剧情发展信息相对应的剧情页面。
例如，在第一预设剧情节点之后，显示确定的第一预设剧情节点之后的剧情对应的画面。
在用户控制第一虚拟角色处于第一预设剧情节点的情况下，响应于退出对话界面，显示根据至少一个维度的角色属性变量的信息，确定的第一预设剧情节点之后的剧情的画面。
在一些实施例中，响应于对话信息包括表示用户欲中止互动多媒体内容的信息，显示第二虚拟角色回复的引导信息，其中，引导信息用于引导用户返回互动多媒体内容。
例如，对对话信息进行解析确定是否包括表示用户欲中止互动多媒体内容的信息，可以根据对话信息和第二虚拟角色的人物设定信息生成引导信息，引导用户返回互动多媒体内容。例如，用户的对话信息为“这一关太难了，不玩了”，引导信息包括关 卡的提示信息或者对用户的安慰信息等，以使用户继续体验互动多媒体内容。
每个第二虚拟角色可以对应一个Bot(机器人或自动化程序)，可以与用户进行对话、影响剧情的发展以及对用户的行为进行引导。使用户与第二虚拟角色的交互和互动多媒体内容可以相互作用，相互促进，提升互动多媒体内容的整体可操作性和互动体验。
本公开中确定初始对话信息的机器学习模型、对对话信息进行理解的机器学习模型、确定至少一个维度的角色属性变量的信息的机器学习模型、生成回复信息的机器学习模型、生成剧情信息的机器学习模型等各个机器学习模型可以是相同的模型，也可以是不同的模型。
本公开的方案可以通过实现剧情走向影响用户能够解锁的虚拟角色，用户可以针对剧情与虚拟角色交互，与虚拟角色的交互内容反之影响剧情走向。使得互动多媒体内容中交互的部分与剧情相互影响，紧密关联，扩展了互动多媒体内容的交互和互动方式，提高了交互效率和交互的有效性和效果。
本公开还提供一种交互装置，下面结合图7进行描述。
图7为本公开交互装置的一些实施例的结构图。如图7所示，该实施例的交互装置70包括：显示模块710，接收模块720，确定模块730。
显示模块710被配置为显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色。
接收模块720被配置为接收用户输入的与第二虚拟角色的对话信息。
确定模块730被配置为根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。
在一些实施例中，确定模块730被配置为对对话信息进行解析，确定对话信息是否与至少一个维度的角色属性变量相关联；在对话信息与至少一个维度的角色属性变量相关联的情况下，根据对话信息以及至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定至少一个维度的角色属性变量的信息。
在一些实施例中，至少一个维度的角色属性变量包括第一维度的角色属性变量，第一维度用于表示第一虚拟角色与第二虚拟角色之间的关系，提示信息包括第二虚拟角色的情感影响因素信息，确定模块730被配置为根据对话信息以及第二虚拟角色的情感影响因素信息，采用机器学习模型，确定第一维度的角色属性变量的信息。
在一些实施例中，至少一个维度的角色属性变量包括第二维度的角色属性变量，第二维度用于表示第一虚拟角色的能力，提示信息包括：第一虚拟角色的能力影响因素信息，确定模块730被配置为根据对话信息以及第一虚拟角色的能力影响因素信息，采用机器学习模型，确定第二维度的角色属性变量的信息。
在一些实施例中，确定模块730还被配置为对对话信息进行解析，确定对话信息是否与互动多媒体内容的剧情相关联；在对话信息与互动多媒体内容的剧情相关联的情况下，根据对话信息、至少一个维度的角色属性变量对应的提示信息以及第一虚拟角色所经历的历史剧情的摘要信息，采用机器学习模型，确定至少一个维度的角色属性变量的信息。
在一些实施例中，确定模块730还被配置为根据至少一个维度的角色属性变量的信息，确定互动多媒体内容的剧情发展信息；显示模块710还被配置为显示与剧情发展信息相对应的剧情页面。
在一些实施例中，确定模块730被配置为响应于互动多媒体内容到达第一预设剧情节点，根据至少一个维度的角色属性变量的信息，确定第一预设剧情节点之后的剧情，其中，互动多媒体内容的剧情发展信息包括第一预设剧情节点之后的剧情；显示模块710被配置为显示第一预设剧情节点之后的剧情对应的画面。
在一些实施例中，交互装置70还包括：生成模块740，被配置为根据对话信息和第二虚拟角色的人物设定信息，生成第二虚拟角色的回复信息。显示模块710还被配置为显示第二虚拟角色的回复信息。
在一些实施例中，生成模块740被配置为对对话信息进行解析，确定对话信息是否与互动多媒体内容的剧情相关联；在对话信息与互动多媒体内容的剧情相关联的情况下，根据对话信息、第二虚拟角色的人物设定信息以及第一虚拟角色所经历的历史剧情的摘要信息，生成第二虚拟角色的回复信息。
在一些实施例中，显示模块710还被配置为响应于互动多媒体内容到达第二预设剧情节点和/或第一虚拟角色完成预设任务，显示将第二虚拟角色加入预设分组的第一控件，其中，将第二虚拟角色加入预设分组表示第一虚拟角色与第二虚拟角色形成预设关系；接收模块720还被配置为接收用户对第一控件的触发操作；显示模块710还被配置为显示将第二虚拟角色加入预设分组的提示信息。
在一些实施例中，接收模块720还被配置为接收用户对预设分组的第二控件的操作；显示模块710还被配置为显示预设分组中的一个或多个虚拟角色的信息；接收模 块720还被配置为接收用户对第二虚拟角色的选择操作；显示模块710还被配置为显示第一虚拟角色与第二虚拟角色的对话界面。
在一些实施例中，显示模块710还被配置为在对话界面中显示第二虚拟角色的初始对话信息，其中，第二虚拟角色的初始对话信息是根据第二虚拟角色的人物设定信息生成的。
在一些实施例中，显示模块710还被配置为响应于对话信息包括表示用户欲中止互动多媒体内容的信息，显示第二虚拟角色回复的引导信息，其中，引导信息用于引导用户返回互动多媒体内容。
上述实施例的交互装置，显示第一虚拟角色与第二虚拟角色的对话界面，响应于接收到用户输入的与第二虚拟角色的对话信息，根据对话信息，可以确定至少一个维度的角色属性变量的信息，从而影响互动多媒体内容的剧情的发展。通过上述实施例的装置，用户通过与第二虚拟角色对话的交互方式，可以影响角色属性变量，进而影响互动多媒体内容的剧情的发展。将交互过程与互动多媒体内容的剧情紧密联系，更加容易吸引用户进行交互，扩展互动多媒体内容的互动形式，提高了交互过程的有效性和效果。
应注意，上述各个模块仅是根据其所实现的具体功能划分的逻辑模块，而不是用于限制具体的实现方式，例如可以以软件、硬件或者软硬件结合的方式来实现。在实际实现时，上述各个模块可被实现为独立的物理实体，或者也可由单个实体(例如，处理器(CPU或DSP等)、集成电路等)来实现。此外，上述各个模块在附图中用虚线示出指示这些模块可以并不实际存在，而它们所实现的操作/功能可由处理电路本身来实现。
此外，尽管未示出，该设备也可以包括存储器，其可以存储由设备、设备所包含的各个模块在操作中产生的各种信息、用于操作的程序和数据、将由通信模块发送的数据等。存储器可以是易失性存储器和/或非易失性存储器。例如，存储器可以包括但不限于随机存储存储器(RAM)、动态随机存储存储器(DRAM)、静态随机存取存储器(SRAM)、只读存储器(ROM)、闪存存储器。当然，存储器可也位于该设备之外。可选地，尽管未示出，但是该设备也可以包括通信模块，其可用于与其它装置进行通信。在一个示例中，通信模块可以被按照本领域已知的适当方式来实现，例如包括天线阵列和/或射频链路等通信部件，各种类型的接口、通信模块等等。这里将不再详细描述。此外，设备还可以包括未示出的其它部件，诸如射频链路、基带处理模 块、网络接口、处理器、控制器等。这里将不再详细描述。
本公开的一些实施例还提供一种电子设备。图8示出本公开的电子设备的一些实施例的框图。例如，在一些实施例中，电子设备8可以为各种类型的设备，例如可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。例如，电子设备8可以包括显示面板，以用于显示根据本公开的方案中所利用的数据和/或执行结果。例如，显示面板可以为各种形状，例如矩形面板、椭圆形面板或多边形面板等。另外，显示面板不仅可以为平面面板，也可以为曲面面板，甚至球面面板。
如图8所示，该实施例的电子设备8包括：存储器81以及耦接至该存储器81的处理器82。应当注意，图8所示的电子设备8的组件只是示例性的，而非限制性的，根据实际应用需要，该电子设备8还可以具有其他组件。处理器82可以控制电子设备8中的其它组件以执行期望的功能。
在一些实施例中，存储器81用于存储一个或多个计算机可读指令。处理器82用于运行计算机可读指令时，计算机可读指令被处理器82运行时实现根据上述任一实施例所述的方法。关于该方法的各个步骤的具体实现以及相关解释内容可以参见上述的实施例，重复之处在此不作赘述。
例如，处理器82和存储器81之间可以直接或间接地互相通信。例如，处理器82和存储器81可以通过网络进行通信。网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。处理器82和存储器81之间也可以通过系统总线实现相互通信，本公开对此不作限制。
例如，处理器82可以体现为各种适当的处理器、处理装置等，诸如中央处理器(CPU)、图形处理器(Graphics Processing Unit，GPU)、网络处理器(NP)等；还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。中央处理元(CPU)可以为X86或ARM架构等。例如，存储器81可以包括各种形式的计算机可读存储介质的任意组合，例如易失性存储器和/或非易失性存储器。存储器81例如可以包括系统存储器，系统存储器例如存储有操作系统、应用程序、引导装载程序(Boot Loader)、数据库以及其他程序等。在存储介质中还可以存储各种应用程序和各种数据等。
另外，根据本公开的一些实施例，根据本公开的各种操作/处理在通过软件和/或固 件实现的情况下，可从存储介质或网络向具有专用硬件结构的计算机系统，例如图9所示的计算机系统(或电子设备)900安装构成该软件的程序，该计算机系统在安装有各种程序时，能够执行各种功能，包括诸如前文所述的功能等等。图9是示出根据本公开的实施例的中可采用的计算机系统的示例结构的框图。
在图9中，中央处理单元(CPU)901根据只读存储器(ROM)902中存储的程序或从存储部分908加载到随机存取存储器(RAM)903的程序执行各种处理。在RAM 903中，也根据需要存储当CPU 901执行各种处理等时所需的数据。中央处理单元仅仅是示例性的，其也可以是其它类型的处理器，诸如前文所述的各种处理器。ROM 902、RAM 903和存储部分908可以是各种形式的计算机可读存储介质，如下文所述。需要注意的是，虽然图9中分别示出了ROM 902、RAM 903和存储装置908，但是它们中的一个或多个可以合并或者位于相同或不同的存储器或存储模块中。
CPU 901、ROM 902和RAM 903经由总线904彼此连接。输入/输出接口905也连接到总线904。
下述部件连接到输入/输出接口905：输入部分906，诸如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等；输出部分907，包括显示器，比如阴极射线管(CRT)、液晶显示器(LCD)，扬声器，振动器等；存储部分908，包括硬盘，磁带等；和通信部分909，包括网络接口卡比如LAN卡、调制解调器等。通信部分909允许经由网络比如因特网执行通信处理。容易理解的是，虽然图9中示出计算机系统900中的各个装置或模块是通过总线904来通信的，但它们也可以通过网络或其它方式进行通信，其中，网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。
根据需要，驱动器910也连接到输入/输出接口905。可拆卸介质911比如磁盘、光盘、磁光盘、半导体存储器等等根据需要被安装在驱动器910上，使得从中读出的计算机程序根据需要被安装到存储部分908中。
在通过软件实现上述系列处理的情况下，可以从网络比如因特网或存储介质比如可拆卸介质911安装构成软件的程序。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分909从网络上被下载和安装，或者从存储部 分908被安装，或者从ROM 902被安装。在该计算机程序被CPU 901执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，在本公开的上下文中，计算机可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是，但不限于：电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
在一些实施例中，还提供了一种计算机程序，包括：指令，指令当由处理器执行时使处理器执行上述任一个实施例的方法。例如，指令可以体现为计算机程序代码。
在本公开的实施例中，可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络(，包括局域网(LAN)或广域网(WAN))连接到用户 计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块、部件或单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块、部件或单元的名称在某种情况下并不构成对该模块、部件或单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示例性的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
根据本公开的一些实施例，提供的一种交互方法，包括：显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色；接收用户输入的与第二虚拟角色的对话信息；根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。
在一些实施例中，根据所述对话信息，确定至少一个维度的角色属性变量的信息包括：对所述对话信息进行解析，确定所述对话信息是否与所述至少一个维度的角色属性变量相关联；在所述对话信息与所述至少一个维度的角色属性变量相关联的情况下，根据所述对话信息以及所述至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息。
在一些实施例中，至少一个维度的角色属性变量包括第一维度的角色属性变量，所述第一维度用于表示所述第一虚拟角色与所述第二虚拟角色之间的关系，所述提示信息包括所述第二虚拟角色的情感影响因素信息，所述根据所述对话信息以及所述至 少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息包括：根据所述对话信息以及所述第二虚拟角色的情感影响因素信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息。
在一些实施例中，所述提示信息还包括：所述第二虚拟角色的人物设定信息，所述根据所述对话信息以及所述第二虚拟角色的情感影响因素信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息包括：根据所述对话信息、所述第二虚拟角色的情感影响因素信息以及所述第二虚拟角色的人物设定信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息。
在一些实施例中，所述至少一个维度的角色属性变量包括第二维度的角色属性变量，所述第二维度用于表示所述第一虚拟角色的能力，所述提示信息包括：所述第一虚拟角色的能力影响因素信息，所述根据所述对话信息以及所述至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息包括：根据所述对话信息以及所述第一虚拟角色的能力影响因素信息，采用机器学习模型，确定所述第二维度的角色属性变量的信息。
在一些实施例中，所述根据所述对话信息，确定至少一个维度的角色属性变量的信息还包括：对所述对话信息进行解析，确定所述对话信息是否与所述互动多媒体内容的剧情相关联；在所述对话信息与所述互动多媒体内容的剧情相关联的情况下，根据所述对话信息、所述至少一个维度的角色属性变量对应的提示信息以及所述第一虚拟角色所经历的历史剧情的摘要信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息。
在一些实施例中，该方法还包括：根据所述至少一个维度的角色属性变量的信息，确定所述互动多媒体内容的剧情发展信息；显示与所述剧情发展信息相对应的剧情页面。
在一些实施例中，所述根据所述至少一个维度的角色属性变量的信息，确定所述互动多媒体内容的剧情发展信息包括：响应于所述互动多媒体内容到达第一预设剧情节点，根据所述至少一个维度的角色属性变量的信息，确定所述第一预设剧情节点之后的剧情，其中，所述互动多媒体内容的剧情发展信息包括所述第一预设剧情节点之后的剧情；所述显示与所述剧情发展信息相对应的剧情页面包括：显示所述第一预设剧情节点之后的剧情对应的画面。
在一些实施例中，该方法还包括：根据所述对话信息和所述第二虚拟角色的人物 设定信息，生成所述第二虚拟角色的回复信息；显示所述第二虚拟角色的回复信息。
在一些实施例中，所述根据所述对话信息和所述第二虚拟角色的人物设定信息，生成所述第二虚拟角色的回复信息包括：对所述对话信息进行解析，确定所述对话信息是否与所述互动多媒体内容的剧情相关联；在所述对话信息与所述互动多媒体内容的剧情相关联的情况下，根据所述对话信息、所述第二虚拟角色的人物设定信息以及所述第一虚拟角色所经历的历史剧情的摘要信息，生成所述第二虚拟角色的回复信息。
在一些实施例中，该方法还包括：响应于所述互动多媒体内容到达第二预设剧情节点和/或所述第一虚拟角色完成预设任务，显示将所述第二虚拟角色加入预设分组的第一控件，其中，将所述第二虚拟角色加入预设分组表示所述第一虚拟角色与所述第二虚拟角色形成预设关系；接收所述用户对所述第一控件的触发操作；显示将所述第二虚拟角色加入预设分组的提示信息。
在一些实施例中，所述显示第一虚拟角色与第二虚拟角色的对话界面包括：接收所述用户对预设分组的第二控件的操作；显示所述预设分组中的一个或多个虚拟角色的信息；接收所述用户对所述第二虚拟角色的选择操作；显示所述第一虚拟角色与所述第二虚拟角色的对话界面。
在一些实施例中，所述显示第一虚拟角色与第二虚拟角色的对话界面包括：在所述对话界面中显示所述第二虚拟角色的初始对话信息，其中，所述第二虚拟角色的初始对话信息是根据所述第二虚拟角色的人物设定信息生成的。
在一些实施例中，该方法还包括：响应于所述对话信息包括表示所述用户欲中止所述互动多媒体内容的信息，显示所述第二虚拟角色回复的引导信息，其中，所述引导信息用于引导所述用户返回所述互动多媒体内容。
根据本公开的一些实施例，提供的一种交互装置，包括：显示模块，被配置为显示第一虚拟角色与第二虚拟角色的对话界面，其中，第一虚拟角色和第二虚拟角色为互动多媒体内容中的虚拟角色，第一虚拟角色为用户控制的虚拟角色；接收模块，被配置为接收用户输入的与第二虚拟角色的对话信息；确定模块，被配置为根据对话信息，确定至少一个维度的角色属性变量的信息，其中，至少一个维度的角色属性变量影响互动多媒体内容的剧情的发展。
根据本公开的又一些实施例，提供一种电子设备，包括：存储器；和耦接至存储器的处理器，处理器被配置为基于存储在存储器中的指令，执行本公开中的任一实施例的交互方法。
根据本公开的再一些实施例，提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时执行本公开中的任一实施例的交互方法。
根据本公开的又一些实施例，提供计算机程序，包括：指令，指令当由处理器执行时使处理器执行本公开中所述的任一实施例的交互方法。
根据本公开的一些实施例，提供一种计算机程序产品，包括指令，所述指令当由处理器执行时实现本公开中所述的任一实施例的交互方法。
以上描述仅为本公开的一些实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
在本文提供的描述中，阐述了许多特定细节。然而，理解的是，可以在没有这些特定细节的情况下实施本发明的实施例。在其他情况下，为了不模糊该描述的理解，没有对众所周知的方法、结构和技术进行详细展示。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上示例仅是为了进行说明，而不是为了限制本公开的范围。本领域的技术人员应该理解，可在不脱离本公开的范围和精神的情况下，对以上实施例进行修改。本公开的范围由所附权利要求来限定。

Claims (19)

  1. 一种交互方法，包括：
    显示第一虚拟角色与第二虚拟角色的对话界面，其中，所述第一虚拟角色和所述第二虚拟角色为互动多媒体内容中的虚拟角色，所述第一虚拟角色为用户控制的虚拟角色；
    接收所述用户输入的与所述第二虚拟角色的对话信息；
    根据所述对话信息，确定至少一个维度的角色属性变量的信息，其中，所述至少一个维度的角色属性变量影响所述互动多媒体内容的剧情的发展。
  2. 根据权利要求1所述的交互方法，其中，所述根据所述对话信息，确定至少一个维度的角色属性变量的信息包括：
    对所述对话信息进行解析，确定所述对话信息是否与所述至少一个维度的角色属性变量相关联；
    在所述对话信息与所述至少一个维度的角色属性变量相关联的情况下，根据所述对话信息以及所述至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息。
  3. 根据权利要求2所述的交互方法，其中，所述至少一个维度的角色属性变量包括第一维度的角色属性变量，所述第一维度用于表示所述第一虚拟角色与所述第二虚拟角色之间的关系，所述提示信息包括所述第二虚拟角色的情感影响因素信息，所述根据所述对话信息以及所述至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息包括：
    根据所述对话信息以及所述第二虚拟角色的情感影响因素信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息。
  4. 根据权利要求3所述的交互方法，其中，所述提示信息还包括：所述第二虚拟角色的人物设定信息，所述根据所述对话信息以及所述第二虚拟角色的情感影响因素信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息包括：
    根据所述对话信息、所述第二虚拟角色的情感影响因素信息以及所述第二虚拟角色的人物设定信息，采用机器学习模型，确定所述第一维度的角色属性变量的信息。
  5. 根据权利要求2-4任一项所述的交互方法，其中，所述至少一个维度的角色属性变量包括第二维度的角色属性变量，所述第二维度用于表示所述第一虚拟角色的能 力，所述提示信息包括所述第一虚拟角色的能力影响因素信息，所述根据所述对话信息以及所述至少一个维度的角色属性变量对应的提示信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息包括：
    根据所述对话信息以及所述第一虚拟角色的能力影响因素信息，采用机器学习模型，确定所述第二维度的角色属性变量的信息。
  6. 根据权利要求2-5任一项所述的交互方法，其中，所述根据所述对话信息，确定至少一个维度的角色属性变量的信息还包括：
    对所述对话信息进行解析，确定所述对话信息是否与所述互动多媒体内容的剧情相关联；
    在所述对话信息与所述互动多媒体内容的剧情相关联的情况下，根据所述对话信息、所述至少一个维度的角色属性变量对应的提示信息以及所述第一虚拟角色所经历的历史剧情的摘要信息，采用机器学习模型，确定所述至少一个维度的角色属性变量的信息。
  7. 根据权利要求1-6任一项所述的交互方法，还包括：
    根据所述至少一个维度的角色属性变量的信息，确定所述互动多媒体内容的剧情发展信息；
    显示与所述剧情发展信息相对应的剧情页面。
  8. 根据权利要求7所述的交互方法，其中：
    所述根据所述至少一个维度的角色属性变量的信息，确定所述互动多媒体内容的剧情发展信息包括：
    响应于所述互动多媒体内容到达第一预设剧情节点，根据所述至少一个维度的角色属性变量的信息，确定所述第一预设剧情节点之后的剧情，其中，所述互动多媒体内容的剧情发展信息包括所述第一预设剧情节点之后的剧情；
    所述显示与所述剧情发展信息相对应的剧情页面包括：
    显示所述第一预设剧情节点之后的剧情对应的画面。
  9. 根据权利要求1-8任一项所述的交互方法，还包括：
    根据所述对话信息和所述第二虚拟角色的人物设定信息，生成所述第二虚拟角色的回复信息；
    显示所述第二虚拟角色的回复信息。
  10. 根据权利要求9所述的交互方法，其中，所述根据所述对话信息和所述第二 虚拟角色的人物设定信息，生成所述第二虚拟角色的回复信息包括：
    对所述对话信息进行解析，确定所述对话信息是否与所述互动多媒体内容的剧情相关联；
    在所述对话信息与所述互动多媒体内容的剧情相关联的情况下，根据所述对话信息、所述第二虚拟角色的人物设定信息以及所述第一虚拟角色所经历的历史剧情的摘要信息，生成所述第二虚拟角色的回复信息。
  11. 根据权利要求1-10任一项所述的交互方法，还包括：
    响应于所述互动多媒体内容到达第二预设剧情节点和/或所述第一虚拟角色完成预设任务，显示将所述第二虚拟角色加入预设分组的第一控件，其中，将所述第二虚拟角色加入所述预设分组表示所述第一虚拟角色与所述第二虚拟角色形成预设关系；
    接收所述用户对所述第一控件的触发操作；
    显示将所述第二虚拟角色加入所述预设分组的提示信息。
  12. 根据权利要求11所述的交互方法，其中，所述显示第一虚拟角色与第二虚拟角色的对话界面包括：
    接收所述用户对所述预设分组的第二控件的操作；
    显示所述预设分组中的一个或多个虚拟角色的信息；
    接收所述用户对所述第二虚拟角色的选择操作；
    显示所述第一虚拟角色与所述第二虚拟角色的对话界面。
  13. 根据权利要求1-12任一项所述的交互方法，其中，所述显示第一虚拟角色与第二虚拟角色的对话界面包括：
    在所述对话界面中显示所述第二虚拟角色的初始对话信息，其中，所述第二虚拟角色的初始对话信息是根据所述第二虚拟角色的人物设定信息生成的。
  14. 根据权利要求1-13任一项所述的交互方法，还包括：
    响应于所述对话信息包括表示所述用户欲中止所述互动多媒体内容的信息，显示所述第二虚拟角色回复的引导信息，其中，所述引导信息用于引导所述用户返回所述互动多媒体内容。
  15. 一种交互装置，包括：接收模块和显示模块，其中：
    显示模块，被配置为显示第一虚拟角色与第二虚拟角色的对话界面，其中，所述第一虚拟角色和所述第二虚拟角色为互动多媒体内容中的虚拟角色，所述第一虚拟角色为用户控制的虚拟角色；
    接收模块，被配置为接收所述用户输入的与所述第二虚拟角色的对话信息；
    确定模块，被配置为根据所述对话信息，确定至少一个维度的角色属性变量的信息，其中，所述至少一个维度的角色属性变量影响所述互动多媒体内容的剧情的发展。
  16. 一种电子设备，包括：
    处理器；以及
    耦接至所述处理器的存储器，用于存储指令，所述指令被所述处理器执行时，使所述处理器执行如权利要求1-14任一项所述的交互方法。
  17. 一种计算机可读存储介质，其上存储有计算机程序，其中，该程序被处理器执行时实现权利要求1-14任一项所述交互方法的步骤。
  18. 一种计算机程序，包括指令，当所述指令被处理器执行时，使所述处理器实现权利要求1-14任一项所述的交互方法。
  19. 一种计算机程序产品，包括指令，当所述指令被处理器执行时，使所述处理器实现权利要求1-14任一项所述的交互方法。
PCT/CN2024/133258 2023-11-27 2024-11-20 交互方法、装置、电子设备以及计算机可读存储介质 Pending WO2025113282A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202311598857.3 2023-11-27
CN202311598857.3A CN117618890A (zh) 2023-11-27 2023-11-27 交互方法、装置、电子设备以及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2025113282A1 true WO2025113282A1 (zh) 2025-06-05

Family

ID=90028129

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/133258 Pending WO2025113282A1 (zh) 2023-11-27 2024-11-20 交互方法、装置、电子设备以及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN117618890A (zh)
WO (1) WO2025113282A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117618890A (zh) * 2023-11-27 2024-03-01 北京字跳网络技术有限公司 交互方法、装置、电子设备以及计算机可读存储介质
JP2025147374A (ja) * 2024-03-25 2025-10-07 Kddi株式会社 情報処理装置、情報処理方法及びプログラム
CN118153529A (zh) * 2024-03-25 2024-06-07 北京字跳网络技术有限公司 交互内容生成和显示方法、装置及电子设备
CN118509669A (zh) * 2024-05-10 2024-08-16 北京字跳网络技术有限公司 互动多媒体内容的创建方法、交互方法、系统和相关设备
WO2025245739A1 (zh) * 2024-05-29 2025-12-04 抖音视界有限公司 用于多智能体的处理方法及装置、存储介质、程序产品
CN121816569A (zh) * 2024-08-06 2026-04-07 北京字跳网络技术有限公司 交互方法、装置、存储介质和计算机程序产品

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180336794A1 (en) * 2017-05-16 2018-11-22 Fujitsu Limited Interactive stories
CN111309886A (zh) * 2020-02-18 2020-06-19 腾讯科技（深圳）有限公司 一种信息交互方法、装置和计算机可读存储介质
CN112827167A (zh) * 2021-02-25 2021-05-25 腾讯科技（深圳）有限公司 虚拟关系养成应用中的剧情触发方法、装置、终端及介质
CN113987148A (zh) * 2021-10-28 2022-01-28 上海嬉燃科技有限公司 基于虚拟聊天角色的聊天方法以及相关装置
CN114461775A (zh) * 2022-02-09 2022-05-10 网易（杭州）网络有限公司 人机交互方法、装置、电子设备及存储介质
JP2022180282A (ja) * 2021-05-24 2022-12-06 ネイバー コーポレーション ペルソナチャットボット制御方法及びシステム
CN115577081A (zh) * 2022-09-30 2023-01-06 北京百度网讯科技有限公司 对话方法及装置、设备和介质
CN117618890A (zh) * 2023-11-27 2024-03-01 北京字跳网络技术有限公司 交互方法、装置、电子设备以及计算机可读存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6691351B2 (ja) * 2015-03-31 2020-04-28 株式会社バンダイナムコエンターテインメント プログラム及びゲームシステム
US11562267B2 (en) * 2019-09-14 2023-01-24 Oracle International Corporation Chatbot for defining a machine learning (ML) solution
CN112825559B (zh) * 2019-11-20 2022-11-08 腾讯科技（深圳）有限公司 互动视频播放方法及装置、互动视频生成方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180336794A1 (en) * 2017-05-16 2018-11-22 Fujitsu Limited Interactive stories
CN111309886A (zh) * 2020-02-18 2020-06-19 腾讯科技（深圳）有限公司 一种信息交互方法、装置和计算机可读存储介质
CN112827167A (zh) * 2021-02-25 2021-05-25 腾讯科技（深圳）有限公司 虚拟关系养成应用中的剧情触发方法、装置、终端及介质
JP2022180282A (ja) * 2021-05-24 2022-12-06 ネイバー コーポレーション ペルソナチャットボット制御方法及びシステム
CN113987148A (zh) * 2021-10-28 2022-01-28 上海嬉燃科技有限公司 基于虚拟聊天角色的聊天方法以及相关装置
CN114461775A (zh) * 2022-02-09 2022-05-10 网易（杭州）网络有限公司 人机交互方法、装置、电子设备及存储介质
CN115577081A (zh) * 2022-09-30 2023-01-06 北京百度网讯科技有限公司 对话方法及装置、设备和介质
CN117618890A (zh) * 2023-11-27 2024-03-01 北京字跳网络技术有限公司 交互方法、装置、电子设备以及计算机可读存储介质

Also Published As

Publication number Publication date
CN117618890A (zh) 2024-03-01

Similar Documents

Publication Publication Date Title
WO2025113282A1 (zh) 交互方法、装置、电子设备以及计算机可读存储介质
WO2025124093A1 (zh) 交互方法、装置、计算机可读存储介质和计算机程序产品
CN107301213A (zh) 智能问答方法及装置
WO2025200203A1 (zh) 交互内容生成方法和交互内容显示方法、装置及电子设备
WO2025113271A1 (zh) 互动多媒体内容的生成方法、装置、电子设备和存储介质
US20230122202A1 (en) Grounded multimodal agent interactions
WO2024036899A1 (zh) 信息交互方法、装置、设备及介质
CN116637375A (zh) 智能剧情生成方法及装置
US20250249363A1 (en) Interaction method, medium, and electronic device
CN118898256A (zh) 内容生成方法、装置、电子设备、存储介质和程序产品
US20250384881A1 (en) Communication method, electronic device, storage media, and products
US20260099520A1 (en) Conversation methods, electronic devices, storage media, and products
US20250337706A1 (en) Multimedia content recommendation method and device, electronic device and storage medium
US20250148216A1 (en) Method and apparatus for training large model, electronic device and storage medium
WO2025232305A1 (zh) 互动多媒体内容的创建方法、交互方法、系统和相关设备
CN115245682A (zh) 游戏互动方法、设备、系统及计算机可读存储介质
CN118714397A (zh) 生成视频的方法、装置、设备和介质
EP4415839A1 (en) Grounded multimodal agent interactions
WO2025112922A1 (zh) 交互方法、交互装置和计算机可读存储介质
WO2026000343A1 (zh) 智能体的测试方法、装置、电子设备、介质和程序产品
US12613627B2 (en) Interaction method, device, electronic apparatus, storage medium and program product
WO2025112912A1 (zh) 交互方法、交互装置和计算机可读存储介质
US20250184290A1 (en) Determining the intended recipient of undirected utterances in a multi-bot context
WO2025112594A1 (zh) 交互方法、装置、计算机可读存储介质和计算机程序产品
WO2025199945A1 (zh) 对话方法、装置、电子设备、存储介质和产品

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24896373

Country of ref document: EP

Kind code of ref document: A1