Object creation method and apparatus, and related product

Abstract

Embodiments of the present disclosure provide an object creation method and apparatus, and a related product. The method comprises: displaying a conversation page for conducting a conversation with a digital assistant; by means of a generative model corresponding to the digital assistant, creating a first object on the basis of at least one round of first conversation content with the digital assistant in the conversation page, and outputting object content of the first object, wherein the first object comprises at least one of a first character, a first chapter-type story, and a first framework-type story, and the object content of the first object is generated on the basis of the first conversation content; and in response to a publishing event for the first object, publishing the first object to a target application according to the object content.

Description

Object creation methods, apparatus and related products

[0001] Cross-references to related applications

[0002] This application claims the benefit of Chinese Patent Application No. 202411441152.5, filed on October 15, 2024. The entire teachings of the above application are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of computer technology, and more particularly to an object creation method, apparatus, and related products. Background Technology

[0004] Currently, some applications offer the ability for users to create and publish characters or stories. Once a character is published, the application's digital assistant can assume the role, allowing users to interact with the character through dialogue. Similarly, once a story is published, the application's digital assistant can assume one or more roles within that story, enabling users to participate in the story's progression through conversations with the assistant.

[0005] In the above scheme, the creation process of characters or stories relies entirely on manual input from users. Users need to input the content of the character they are creating or the content of the story they are creating on a specific page, resulting in low creation efficiency. Summary of the Invention

[0006] This disclosure provides an object creation method, apparatus, and related products that can improve the efficiency of creating content required by users.

[0007] In a first aspect, embodiments of this disclosure provide an object creation method, including:

[0008] Displays a dialog page for interacting with the digital assistant;

[0009] Using the generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0010] In response to a publish event for the first object, the first object is published to the target application according to the object content.

[0011] Secondly, embodiments of this disclosure provide an object creation apparatus, including:

[0012] Page display unit, used to display the dialogue page for interacting with the digital assistant;

[0013] An object creation unit is used to create a first object based on at least one round of first dialogue content with the digital assistant in the dialogue page, using a generative model corresponding to the digital assistant, and to output the object content of the first object; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0014] An object publishing unit is configured to publish the first object to a target application according to the object content in response to a publishing event for the first object.

[0015] Thirdly, embodiments of this disclosure provide an electronic device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the method described in the first aspect above.

[0016] Fourthly, embodiments of this disclosure provide a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the steps of the method described in the first aspect.

[0017] Fifthly, embodiments of this disclosure provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect above. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in one or more embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 is a flowchart illustrating an object creation method provided in an embodiment of this disclosure;

[0020] Figure 2a is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant, according to an embodiment of this disclosure;

[0021] Figure 2b is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant, provided in another embodiment of this disclosure;

[0022] Figure 2c is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant, according to another embodiment of this disclosure;

[0023] Figure 3a is a schematic diagram of a scenario for creating an object according to an embodiment of this disclosure;

[0024] Figure 3b is a schematic diagram of a scenario for creating an object according to another embodiment of this disclosure;

[0025] Figure 3c is a schematic diagram of a scenario for creating an object according to another embodiment of this disclosure;

[0026] Figure 4a is a schematic diagram of a dialog page provided in an embodiment of this disclosure;

[0027] Figure 4b is a schematic diagram of an editing page provided in an embodiment of this disclosure;

[0028] Figure 5 is a schematic diagram of the structure of an object creation apparatus provided in an embodiment of this disclosure;

[0029] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this disclosure, the technical solutions in one or more embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of the embodiments. Based on one or more embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this disclosure.

[0031] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0032] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0033] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0034] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0035] This disclosure provides an object creation method that improves the efficiency of creating user-required content. The object creation method described in this disclosure can be applied to and executed by a terminal device, including but not limited to electronic products such as mobile phones, computers, tablets, laptops, in-vehicle computers, and wearable devices.

[0036] Figure 1 is a flowchart illustrating an object creation method provided in an embodiment of this disclosure. As shown in Figure 1, the method includes:

[0037] Step S102: Display the dialogue page for interacting with the digital assistant;

[0038] Step S104: Using the generative model corresponding to the digital assistant, create a first object based on the content of at least one round of first dialogue with the digital assistant on the dialogue page, and output the object content of the first object; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the content of the first dialogue.

[0039] Step S106: In response to the publish event for the first object, publish the first object to the target application according to the object content described above.

[0040] In this embodiment, firstly, a dialogue page for interacting with a digital assistant is displayed. Then, using a generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output. The first object includes at least one of a first role, a first chapter-type story, and a first architecture-type story. The object content of the first object is generated based on the first dialogue content. Finally, in response to a publication event for the first object, the first object is published to the target application according to the aforementioned object content. Therefore, through this embodiment, it is possible to interact with a digital assistant, and based on the first dialogue content with the digital assistant, combined with the semantic understanding and semantic expansion capabilities of the generative model, a first object can be created and its object content output. The object content of the first object is generated based on the first dialogue content, thereby quickly creating the object required by the user based on the dialogue content with the digital assistant, improving the efficiency of creating the object required by the user.

[0041] In step S102 above, a dialogue page for interacting with the digital assistant is displayed. In this embodiment, the digital assistant, also known as a creative assistant, is an artificial intelligence robot created based on a generative model such as a Large Language Model (LLM). Users can interact with the digital assistant on the dialogue page, for example, by sending voice or text messages.

[0042] In step S104 above, the generative model corresponding to the digital assistant, that is, the generative model for creating the digital assistant, can create a first object for the user and display or play the object content of the first object based on one or more rounds of first dialogue content between the user and the digital assistant. The first object includes at least one of the following: a first character, a first chapter-type story, and a first architecture-type story. The object content of the first object is generated based on the content of each round of first dialogue.

[0043] When the first object includes a first character, the object content of the first object includes the character's character content, specifically including one or more of the first character's character settings, character appearance, character introduction, and character opening remarks. The character settings refer to at least one of the following: the first character's name, age, personality, experience, hobbies, and behavioral habits. The character appearance refers to the first character's physical appearance. The character introduction refers to the relationship between the first character and the user. The character opening remarks may include the first sentence the character sends when conversing with the user and the character's facial expressions during the conversation.

[0044] When the first object includes a first chapter-type story, the object content of the first object includes the story content of the first chapter-type story, specifically including the sequence number of each chapter of the first chapter-type story, the name of each chapter, the plot of each chapter, etc., wherein the first chapter-type story includes at least two chapters.

[0045] In this embodiment, a chapter-based story refers to a story with numerous chapters and plot points. Unlike chapter-based stories, a structure-based story refers to a story without chapters but describing basic story elements. These basic elements include the story title, background, character introductions, etc. In a structure-based story, a user profile is also included, containing the user's identity, experience, and tasks when participating in the story. Therefore, when the first object includes a first structure-based story, the object content of the first object includes the story content of the first structure-based story, specifically including at least one of the following: story title, background description, basic plot, user profile, and opening remarks. The user profile, as described above, refers to the user's identity, experience, and tasks when participating in the story. The opening remarks refer to the first sentence sent by the structure-based story when the user participates in the story, along with the character's facial expressions during the dialogue.

[0046] In step S106 above, the first object can be published to the target application according to the object content of the first object based on the user's publishing operation on the created first object. The target application can be the first application that displays the dialog page and creates the first object, or it can be any second application other than the first application.

[0047] Once the first object is published to the target application, if the first object includes a first role, a digital assistant (also known as a dialogue assistant) created based on a generative model can play the first role within the target application. This digital assistant can be the same as or different from the digital assistant in step S102. The user interacts with the first role in the target application. The first role, played by the digital assistant, can expand its possible dialogue content with the user based on one or more of the first role's character content (character settings, character image, character introduction, character opening lines), combined with the semantic understanding and expansion capabilities of the generative model.

[0048] Once the first object is published to the target application, if the first object includes a first chapter-type story, a digital assistant (also known as a dialogue assistant) created based on a generative model can be used in the target application to play any one or more roles in the first chapter-type story. This digital assistant can be the same as or different from the digital assistant in step S102. The user can then engage in dialogue with these one or more roles in the target application to advance the development of the first chapter-type story. Specifically, the roles played by the digital assistant can expand the possible dialogue content of the characters in the first chapter-type story and engage in dialogue with the user based on the story content of the first chapter-type story (the sequence number of each chapter, the name of each chapter, the plot of each chapter, etc.), combined with the semantic understanding and expansion capabilities of the generative model.

[0049] Once the first object is published to the target application, if the first object includes a first architectural class story, a digital assistant (also known as a dialogue assistant) created based on a generative model can act as the narrator of the first architectural class story within the target application. This digital assistant can be the same as or different from the one used in step S102. Users interact with the narrator in the target application, participating in the story environment provided by the first architectural class story and advancing the story's development. Specifically, the narrator, played by the digital assistant, can expand the possible story progression of the first architectural class story based on its content (at least one of the story's name, background description, basic plot, user introduction, and opening remarks), combined with the semantic understanding and expansion capabilities of the generative model, thereby engaging in dialogue with the user.

[0050] As can be seen, this embodiment enables dialogue with a digital assistant. Based on the first dialogue content with the digital assistant, and combined with the semantic understanding and semantic expansion capabilities of the generative model, a first object is created and its object content is output. The object content of the first object is generated based on the first dialogue content, thereby quickly creating the object required by the user based on the dialogue content with the digital assistant, improving the efficiency of creating the object required by the user.

[0051] In one embodiment, a dialogue page for interacting with a digital assistant is displayed, including:

[0052] Display the homepage of the first application; in response to a trigger event for the first creation entry on the homepage, display a dialogue page for interacting with the digital assistant;

[0053] or,

[0054] Display the homepage of the first application; in response to a trigger event for the first creation entry on the homepage, display the character creation page; in response to a trigger event for the second creation entry on the character creation page, display the dialogue page for interacting with the digital assistant;

[0055] or,

[0056] Display the homepage of the first application; in response to a trigger event for the first creation entry on the homepage, display the creation entry panel; in response to a trigger event for the third creation entry in the creation entry panel, display the dialogue page for interacting with the digital assistant.

[0057] In this embodiment, in one scenario, the user enters the application by triggering the icon of the first application. The terminal device responds to this triggering operation by displaying the homepage of the first application. The homepage can be a dialogue page where the user interacts with a predetermined character. This predetermined character can also be created using a generative model. In one example, the predetermined character can be a character created and published to the first application by the user through the method flow shown in Figure 1. The homepage displays a first creation entry point, such as a "+", which the user can trigger to generate a trigger event. The terminal device responds to this trigger event by displaying a dialogue page for interacting with a digital assistant.

[0058] Figure 2a is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant according to an embodiment of the present disclosure. As shown in Figure 2a, the homepage of the first application is first displayed, and a first creation entry is displayed on the homepage, such as a "+". The user can trigger the first creation entry to enter the dialogue page for interacting with the digital assistant.

[0059] In this embodiment, in another scenario, the terminal device displays the application's homepage using the method described above. The homepage displays a first creation entry point, such as a "+", which the user can trigger to generate a trigger event. Unlike before, in response to this trigger event, the terminal device displays a character creation page. This character creation page can be a form page where the user can fill in relevant information about the character to be created, such as the character name and character experience, thereby creating the character. This character creation page also displays a second creation entry point, such as "AI Creation", which the user can trigger to generate a trigger event. In response to this trigger event, the terminal device displays a dialogue page for interacting with the digital assistant.

[0060] Figure 2b is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant, provided in another embodiment of this disclosure. As shown in Figure 2b, the homepage of a first application is first displayed, which includes a first creation entry point, such as a "+". Users can trigger this first creation entry point to enter a form-style character creation page. The character creation page then displays a second creation entry point, such as "AI Creation". Users can trigger this second creation entry point to enter a dialogue page for interacting with the digital assistant.

[0061] In this embodiment, under another scenario, the terminal device displays the application's homepage using the method described above. The homepage displays a first creation entry point, such as a "+", which the user can trigger to generate a trigger event. Unlike before, the terminal device responds to this trigger event by displaying a creation entry panel. This creation entry panel can integrate multiple functions. Users can access a form page for creating characters, filling in relevant character information to create a character; a form page for creating architectural stories, filling in relevant architectural story information to create an architectural story; and a form page for creating chapter stories, filling in relevant chapter story information to create a chapter story. In this embodiment, the creation entry panel also displays a third creation entry point, such as the prompt "Tell me your ideas, I'll help you create." The user can trigger this third creation entry point to generate a trigger event, and the terminal device responds to this trigger event by displaying a dialogue page for interacting with the digital assistant.

[0062] Figure 2c is a schematic diagram of a scenario showing a dialogue page for interacting with a digital assistant, provided in another embodiment of this disclosure. As shown in Figure 2c, the homepage of a first application is first displayed, which includes a first creation entry point, such as a "+". The user can trigger this first creation entry point to enter the creation entry panel. The creation entry panel displays a third creation entry point, such as the prompt "Tell me your ideas, I'll help you create". The user can trigger this third creation entry point to enter the dialogue page for interacting with the digital assistant.

[0063] As can be seen, this embodiment can display the dialogue page for interacting with the digital assistant in multiple ways, improving the convenience for users to access the dialogue page.

[0064] In one embodiment, a first object is created using a generative model corresponding to the digital assistant, based on at least one round of initial dialogue with the digital assistant on the dialogue page, including:

[0065] Using a generative model, the category of the object to be created is determined based on the content of at least one first-round dialogue with the digital assistant on the dialogue page; the category includes at least one of the following: character, chapter-based story, and architecture-based story.

[0066] Using a generative model, a first object is created based on the first dialogue content and the aforementioned categories; the first object belongs to the aforementioned categories.

[0067] In this embodiment, on the dialogue page, the user can engage in one or more rounds of initial dialogue with the digital assistant, thereby displaying the content of each round of initial dialogue on the dialogue page. The content of the initial dialogue can be in text or voice format. Using the generative model corresponding to the digital assistant, when creating the first object based on the content of each round of initial dialogue displayed on the dialogue page, firstly, the generative model determines the category of the object to be created based on the content of each round of initial dialogue displayed on the dialogue page. This category includes at least one of the following: role, chapter-type story, and architecture-type story. Next, using the generative model, the first object is created based on the content of each round of initial dialogue and the aforementioned category. It can be understood that the first object belongs to the aforementioned category; that is, when the category of the object to be created includes role, the first object includes first role; when the category of the object to be created includes chapter-type story, the first object includes first chapter-type story; and when the category of the object to be created includes architecture-type story, the first object includes first architecture-type story.

[0068] As can be seen, through this embodiment, the generative model can determine the category of the object to be created based on the content of each round of the first dialogue with the digital assistant on the dialogue page, and the generative model can create the first object based on the content of the first dialogue and the above category, thereby achieving the effect of creating a first object that meets the user's needs based on the content of each round of the first dialogue, and improving the accuracy of creating the first object.

[0069] In one embodiment, a generative model is used to determine the category of the object to be created based on at least one round of initial dialogue with the digital assistant on a conversational page, including:

[0070] Generative models extract key content from the first dialogue content, and based on the key content, determine the category of the object to be created; the key content is used to represent the category of the object to be created.

[0071] In the first dialogue, key content includes at least one of the following: statements sent to the digital assistant, inquiry messages and corresponding responses sent by the digital assistant, and guidance messages and corresponding responses sent by the digital assistant.

[0072] In this embodiment, when determining the category of the object to be created based on the content of each round of the first dialogue displayed on the dialogue page using a generative model, the generative model can specifically extract key content from the content of each round of the first dialogue. This key content is used to represent the category of the object to be created, and the category of the object to be created is determined based on this key content.

[0073] In this embodiment, the key content in each round of the first dialogue includes at least one of the following: the statement sent to the digital assistant, the inquiry message and corresponding response sent by the digital assistant, and the guidance message and corresponding response sent by the digital assistant.

[0074] For example, key content in the first dialogue rounds includes the statement sent by the user to the digital assistant, such as the message: "Hello, I want to create a character." Similarly, key content in the first dialogue rounds includes the inquiry message sent by the digital assistant to the user and the user's corresponding response, such as: "Do you need to create a chapter-based story? Yes, I do." Furthermore, key content in the first dialogue rounds includes the guiding message sent by the digital assistant to the user and the user's corresponding response, such as: "Let's create a character. Okay."

[0075] As can be seen, this embodiment can identify key content in various forms in the first dialogue of each round by considering multiple aspects such as user-initiated statements, user inquiries, and user guidance. Based on the key content, the category of the object that the user wants to create can be accurately determined.

[0076] In one embodiment, after determining the above categories, a first object is created using a generative model based on the first dialogue content and the above categories, including:

[0077] Generative models are used to determine at least one content dimension corresponding to the above categories and the content requirements corresponding to the content dimensions.

[0078] Generative models are used to obtain target content corresponding to the content dimension based on the first dialogue content; the target content meets the content requirements corresponding to the content dimension.

[0079] Using a generative model, a first object is created based on the target content; the object content of the first object includes the target content.

[0080] In this embodiment, when creating the first object using a generative model based on the content of each round of the first dialogue and the aforementioned categories, the generative model first determines at least one content dimension corresponding to each category and the corresponding content requirements. The at least one content dimension and the corresponding content requirements for each category can be pre-stored in a database. In this embodiment, each category has its own content dimensions and content requirements. For each category, there is at least one content dimension, and for each content dimension, there are corresponding content requirements.

[0081] For example, in one example, for the character category, there are four content dimensions: character setting, character appearance, character introduction, and character opening remarks. The content requirements for each content dimension are used to indicate the meaning of the content that needs to be recorded in the corresponding content dimension. For example, the content requirements for the character setting dimension are to record the character's name, age, personality, experience, hobbies, behavior habits, etc., while the content requirements for the character appearance dimension are to record the character's physical appearance, etc.

[0082] For example, in one example, for the chapter category, there are several content dimensions such as the chapter number, the chapter name, and the chapter plot. The content requirements for each content dimension are used to indicate the meaning of the content that needs to be recorded in the corresponding content dimension. For example, the content requirement for the chapter name dimension is that the chapter name should be recorded in no more than a certain number of words, and the content requirement for the chapter plot dimension is that the chapter plot should be recorded in no less than a certain number of words.

[0083] For example, in one example, for an architecture-type story, there are several content dimensions: story title, story background description, basic story plot, user introduction, and opening remarks. The content requirements for each content dimension are used to indicate the meaning of the content that needs to be recorded in the corresponding content dimension. For example, the content requirement for the story title dimension is that the title of the story should be recorded in no more than a certain number of words. The content requirement for the story background description dimension is that the background of the story should be recorded in no less than a certain number of words. The content requirement for the user introduction dimension is that the user's identity, experience, tasks, etc., when participating in the architecture-type story should be recorded in no less than a certain number of words.

[0084] Next, in this embodiment, a generative model is used to obtain the target content corresponding to each content dimension belonging to the above categories based on the first dialogue content. The target content for each content dimension satisfies the content requirements corresponding to that content dimension. Finally, a generative model is used to create a first object based on the target content. The object content of the first object includes the target content. In one example, the target content corresponding to each content dimension can be combined to obtain the object content of the first object.

[0085] As can be seen, through this embodiment, at least one content dimension corresponding to the above categories and the content requirements corresponding to the content dimensions can be determined by generative model. Based on the first dialogue content, the target content that meets the content requirements corresponding to the content dimensions can be obtained. Based on the target content, the first object can be created, thereby achieving the effect of efficiently and quickly creating the object required by the user.

[0086] In one embodiment, for each content dimension, a generative model is used to obtain the target content corresponding to that content dimension based on the first dialogue content, including:

[0087] If the first dialogue content contains target content, the target content is obtained from the first dialogue content through a generative model; wherein, the target content includes at least one of the following: statement content sent to the digital assistant, query message and corresponding response content sent by the digital assistant, and guidance message and corresponding response content sent by the digital assistant;

[0088] If the target content is not included in the first dialogue, the generative model is used to expand upon the first dialogue content to obtain the target content.

[0089] In this embodiment, when obtaining the target content that meets the content requirements for each content dimension, firstly, a generative model is used to determine whether the first dialogue content carries the target content that meets the content requirements for that content dimension. When the first dialogue content carries the target content, the target content includes at least one of the following: a statement sent by the user to the digital assistant, an inquiry message and its corresponding response sent by the digital assistant, or a guidance message and its corresponding response sent by the digital assistant. That is, the target content can be a statement sent by the user to the digital assistant, such as the user sending "Create a character named A for me." The target content can also be the user's response after the digital assistant asks a question, such as the digital assistant sending "Is the character you want to create male or female?" and the user replying "Female." The target content can also be the user's response after the digital assistant guides the user, such as the digital assistant sending "Create a female character for you," and the user replying "Okay."

[0090] For each content dimension, if the target content is carried in the first dialogue content of each round, the target content for that content dimension is obtained from the first dialogue content. If the target content is not carried in the first dialogue content of each round, the target content is obtained by expanding the first dialogue content through a generative model based on semantic understanding and semantic expansion capabilities.

[0091] In this embodiment, taking any content dimension as an example, the situation where the target content is not carried in the first dialogue of each round can be either that the first dialogue of each round does not involve any content under that content dimension, or that the first dialogue of each round involves content under that content dimension but the involved content does not meet the content requirements of that content dimension. In both cases, a generative model can be used, based on semantic understanding and semantic expansion capabilities, to expand the first dialogue content to obtain the target content under that content dimension. For example, it can help users conceive or expand storylines, or help users conceive or expand character experiences.

[0092] In one example, for each content dimension, when obtaining the target content corresponding to that content dimension based on the first dialogue content using a generative model, the generative model can send query messages or guidance messages to the user, guiding the user to provide more information related to the target content during the dialogue, thus ensuring that the target content is carried in each round of the first dialogue. When the user still cannot provide complete target content through querying or guidance, the generative model can expand the target content based on the first dialogue content of each round. For example, asking the user "What do you think of this character living in ancient times?" or "What do you think of defining this character as a long-haired woman?" can guide the user to provide more information related to the target content, thus ensuring that the target content is carried in each round of the first dialogue, or expanding the target content based on the first dialogue content of each round when the user still cannot provide complete target content.

[0093] As can be seen, this embodiment can determine whether the target content is carried in the first dialogue of each round, and accurately obtain the target content based on the first dialogue of each round according to different judgment results.

[0094] In one embodiment, for each content dimension, the target content is obtained by expanding upon the first dialogue content using a generative model, including:

[0095] By using a generative model, content elements corresponding to each content dimension are extracted from the first dialogue content, and the content elements corresponding to each content dimension are expanded to obtain the target content corresponding to each content dimension.

[0096] In this embodiment, when the target content is obtained by expanding the first dialogue content, a generative model can be used to extract content elements corresponding to each content dimension from the first dialogue content. These content elements are key information for generating the target content. For example, when the content dimension is a storyline, the content elements could be the basic concept of the storyline; when the content dimension is a character's experience, the content elements could be the character's name, personality, etc. In this embodiment, a generative model can be used to send inquiry messages or guidance messages to the user, guiding the user to provide feedback on the content elements corresponding to each content dimension during the dialogue. Then, based on the semantic understanding and expansion capabilities of the generative model, the content elements corresponding to each content dimension are expanded to obtain the target content corresponding to each content dimension.

[0097] As can be seen from this embodiment, when the user provides feedback on the content elements corresponding to each content dimension, the content elements can be expanded through a generative model to obtain the target content corresponding to each content dimension, thereby achieving the effect of quickly creating the first object based on the user's ideas.

[0098] Furthermore, in one embodiment, when obtaining the target content corresponding to each content dimension based on the first dialogue content using a generative model for each content dimension, it is also possible to directly extract the content elements corresponding to each content dimension from the first dialogue content without determining whether the first dialogue content carries the target content corresponding to each content dimension. The generative model can then expand these content elements to obtain the target content for each content dimension. The specific process of this method can be found in the preceding description. In this approach, the user does not need to provide the target content in the first dialogue content; only the user needs to provide the content elements corresponding to each content dimension. The generative model can then expand these content elements to obtain the target content for each content dimension, simplifying the user's dialogue process and improving the speed and efficiency of generating the first object.

[0099] In one embodiment, before creating the first object based on the target content using a generative model, the following steps are also included:

[0100] Generative models determine whether the target content meets the object creation requirements, or whether the first dialogue content contains an object creation intent.

[0101] In this embodiment, before combining the target content of the first object according to each content dimension using a generative model, it is also necessary to use a generative model to determine whether the target content meets the object creation requirements, or to determine whether the first dialogue content contains the object creation intent.

[0102] If a generative model determines that the target content meets the object creation requirements (e.g., the generative model for a digital assistant), and it is determined that the target content for each content dimension has been obtained, then the target content meets the object creation requirements. In this case, the generative model can be used to combine the target content of each content dimension to obtain the object content of the first object.

[0103] If a generative model determines that the first dialogue content contains an object creation intent—for example, if the user sends text, voice, or instructions indicating that they want to create an object, or if the user sends text or voice indicating that they no longer want to have a conversation—then the generative model can combine the target content of the first object based on the target content of each content dimension to obtain the object content of the first object.

[0104] Figure 3a is a schematic diagram of an object creation scenario provided in an embodiment of this disclosure. As shown in Figure 3a, a user can converse with a digital assistant on a dialogue page and click the "Start Creating" control. The generative model corresponding to the digital assistant takes the user's click operation as an object creation instruction, thereby determining that the first dialogue content carries an object creation intent. Based on the object creation intent, a first object is created, and the object content of the created first object is displayed to the user. In this embodiment, the first object is used as the role for illustration. In Figure 3a, the user can also directly input words like "Help me create it" so that the terminal device can obtain the object creation intent.

[0105] Figure 3b is a schematic diagram of an object creation scenario provided in another embodiment of this disclosure. As shown in Figure 3b, a user can have a conversation with a digital assistant on a dialogue page. When the generative model corresponding to the digital assistant detects that the user does not want to continue the conversation, it determines that the first dialogue content carries an object creation intent. Based on the object creation intent, it creates a first object and displays the object content of the created first object to the user. In this embodiment, the first object is used as a role for illustration.

[0106] Figure 3c is a schematic diagram of an object creation scenario provided in another embodiment of this disclosure. As shown in Figure 3c, when the generative model corresponding to the digital assistant determines that the target content corresponding to each content dimension meets the object creation requirements, it directly creates the first object without requiring user creation instructions and displays the object content of the created first object to the user. In this embodiment, the first object is used as the role for illustration.

[0107] As can be seen, this embodiment can automatically identify whether the user intends to end the conversation and create an object. If so, the first object is created according to the target content, thereby realizing the automated creation of the first object and improving the user's conversational experience during the object creation process.

[0108] In this embodiment, in one scenario, the generative model corresponding to the data counterpart is integrated into the terminal device. The terminal device, through the generative model corresponding to the digital assistant, creates a first object for the user based on one or more rounds of the first dialogue between the user and the digital assistant, and outputs the object content of the first object. In another scenario, the generative model corresponding to the data counterpart is integrated into the server. After the terminal device obtains at least one round of the first dialogue between the user and the digital assistant on the dialogue page, it sends a trigger message and the first dialogue content to the server. The trigger server, through the generative model corresponding to the digital assistant, creates a first object for the user based on one or more rounds of the first dialogue between the user and the digital assistant. That is, the trigger server, through the generative model, determines the category of the object to be created based on at least one round of the first dialogue with the digital assistant on the dialogue page, and creates the first object based on the first dialogue content and category. The specific execution process of the server after being triggered is the same as the previously described process of creating the first object, and will not be repeated here. The server returns the object content of the first object to the terminal device, and the terminal device outputs the object content of the first object.

[0109] In this embodiment, the generative model corresponding to the digital assistant can be trained. During training, manually written user input and the desired generated object content are acquired as sample data. Additionally, prompts are obtained for the generative model, representing the object generation capabilities of the trained model. For example, prompts might include: "You are a screenwriter specializing in characters and stories. You can determine whether the user wants to create a character or a story based on their input, and expand upon the input to obtain a complete character or story. Stories can be either architectural stories or chapter-based stories." The generative model is then trained using the sample data and prompts.

[0110] In step S106 above, in response to a publish event for the first object, the first object is published to the target application according to its content. In one embodiment, publishing the first object to the target application according to its content in response to a publish event for the first object includes:

[0111] In response to a publish event for the first object, the user is redirected to the editing page of the first object. The editing page is filled with object content and first auxiliary content of the first object. The first auxiliary content is generated based on the object content and includes at least one of the first object's image, audio, and timbre.

[0112] In response to the confirmation event for the object content and the first auxiliary content on the editing page, the first object is published to the target application according to the object content and the first auxiliary content.

[0113] In this embodiment, in response to a publish event for the first object, the user can be redirected to the editing page of the first object. The editing page of the first object can be a form-based page that allows editing the content of the first object. When the first object is a first role, the editing page of the first object can be the aforementioned role creation page for the first role. When the first object is a first chapter-type story, the editing page of the first object can be the story creation page for the first chapter-type story. When the first object is a first architecture-type story, the editing page of the first object can be the story creation page for the first architecture-type story.

[0114] The editing page for the first object displays the created object content and the first auxiliary content. The first auxiliary content can be generated based on the object content of the first object using the generative model corresponding to the digital assistant. The generative model corresponding to the digital assistant can generate the first auxiliary content based on the object content of the first object in response to a publishing operation. The first auxiliary content includes at least one of the following: image, audio, and timbre. For example, when the first object is the first character, the first auxiliary content includes any one of the first character's timbre, character image, and audio. Similarly, when the first object is the first chapter of a story, the first auxiliary content includes any one of the main characters' timbre, character image, and audio.

[0115] If the user confirms that the object content and the first auxiliary content of the first object are correct on the editing page, the terminal device responds to the confirmation event for the object content and the first auxiliary content on the editing page and publishes the first object to the target application according to the object content and the first auxiliary content.

[0116] Figure 4a is a schematic diagram of a dialog page provided in an embodiment of the present disclosure, and Figure 4b is a schematic diagram of an editing page provided in an embodiment of the present disclosure. As shown in Figure 4a, if the user views the object content of the first object and confirms that it is correct, the user can trigger the "Publish" control in the dialog page, thereby jumping to the editing page shown in Figure 4b. In this editing page, if the user confirms that the object content of the first object and the first auxiliary content of the first object are correct, the user can trigger the "Publish" control in the editing page, thereby publishing the first object to the target application according to the object content and the first auxiliary content.

[0117] Referring to Figures 4a and 4b, there are multiple entry points at the bottom of the dialogue page and the editing page, such as "AI Creation," "Character," and "Story." Users can trigger these entry points to navigate between the corresponding pages. Specifically, "AI Creation" can lead to the dialogue page, "Character" can lead to the character creation page, and "Story" can lead to the story creation page for chapter-based or structure-based stories.

[0118] As can be seen, this embodiment also provides an editing page for users to further confirm the content of the first object, and automatically provides users with first auxiliary content, thereby enriching the first object, improving the user experience, and improving the efficiency of creating and publishing the first object.

[0119] In one embodiment, before publishing the first object to the target application according to the object content and the first auxiliary content in response to a confirmation event for the object content and the first auxiliary content on the editing page, the method further includes:

[0120] In response to modification events on the editing page concerning the object content and / or primary auxiliary content, display the modified content;

[0121] In response to a confirmation event on the edit page regarding the object content and the first auxiliary content, the first object is published to the target application according to the object content and the first auxiliary content, including:

[0122] In response to the confirmation event for the modified content on the edit page, the first object is published to the target application according to the modified content.

[0123] In this embodiment, the user can also modify the object content and / or the first auxiliary content on the editing page. In response to a modification event on the editing page regarding the object content and / or the first auxiliary content, the modified object content and / or the modified first auxiliary content are displayed on the editing page. Furthermore, the user can also confirm the modified object content and / or the modified first auxiliary content. In response to a confirmation event on the editing page regarding the modified object content and / or the modified first auxiliary content, the first object is published to the target application according to the modified object content and / or the modified first auxiliary content.

[0124] Referring to Figure 4b, users can modify the object content and / or the first auxiliary content in the editing page. The editing page can display the modified content. Based on the modified content, users can trigger the "Publish" control in the editing page to publish the first object to the target application according to the modified object content and / or the modified first auxiliary content.

[0125] As can be seen, through this embodiment, users can also modify the content to be modified on the editing page, thereby achieving the effect of determining the first object and publishing it according to user needs.

[0126] In one embodiment, before publishing the first object to the target application according to the object content and the first auxiliary content in response to a confirmation event for the object content and the first auxiliary content on the editing page, the method further includes:

[0127] In response to the exit event on the editing page, return to the dialog page;

[0128] Based on the content of at least one second round of dialogue with the digital assistant on the dialogue page, modify the object content and output the modified object content;

[0129] In response to a publish event for the first object, the user is redirected to the editing page for the first object; the editing page is populated with the modified object content and the first auxiliary content updated based on the modified object content.

[0130] In response to a confirmation event on the edit page regarding the object content and the first auxiliary content, the first object is published to the target application according to the object content and the first auxiliary content, including:

[0131] In response to the confirmation event on the edit page regarding the modified object content and the updated first auxiliary content, the first object is published to the target application according to the modified object content and the updated first auxiliary content.

[0132] In this embodiment, the user can also return from the editing page to the dialogue page. After returning to the dialogue page, the user can engage in at least one second dialogue with the digital assistant. The generative model corresponding to the digital assistant modifies the object content of the first object based on the content of at least one second dialogue, following the same process as in Figure 1, and outputs the modified object content of the first object. For example, the generative model corresponding to the digital assistant modifies the object content of the first object based on the content of at least one second dialogue, and outputs the modified object content of the first object when it is determined that the user triggers the "Create Object" control, or directly outputs the modified object content of the first object after modifying the object content of the first object.

[0133] If the user confirms that the modified content of the first object is correct, the user can perform a publishing operation. For example, the "Publish" control in the dialog page is triggered. In response to the user's publishing event for the first object, the user is redirected to the editing page of the first object. The editing page is filled with the modified object content and the first auxiliary content updated based on the modified object content. For example, the generative model corresponding to the digital assistant updates the character illustrations on the editing page based on the modified object content.

[0134] If the user confirms that the modified object content and the updated first auxiliary content are correct on the editing page, a publishing operation can be performed. For example, the "Publish" control on the editing page can be triggered, responding to the user's confirmation event on the editing page regarding the modified object content and the updated first auxiliary content, and the first object can be published to the target application according to the modified object content and the updated first auxiliary content.

[0135] As can be seen, this embodiment also enables switching between the editing page and the dialogue page, thereby facilitating users to adjust the content of the first object through dialogue and automatically updating the first auxiliary content based on the modified object content, thereby improving the efficiency of users publishing the first object.

[0136] In summary, through the above embodiments, it is possible to engage in dialogue with a digital assistant. Based on the initial dialogue content with the digital assistant, and combined with the semantic understanding and semantic expansion capabilities of the generative model, a first object can be created and its content output. The object content of the first object is generated based on the initial dialogue content, thereby quickly creating the object required by the user based on the dialogue content with the digital assistant, improving the efficiency of creating the object required by the user.

[0137] Figure 5 is a schematic diagram of the structure of an object creation apparatus provided in an embodiment of this disclosure. As shown in Figure 5, the apparatus includes:

[0138] Page display unit 51 is used to display a dialogue page for interacting with a digital assistant;

[0139] The object creation unit 52 is used to create a first object based on at least one round of first dialogue content with the digital assistant in the dialogue page, using the generative model corresponding to the digital assistant, and output the object content of the first object; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0140] The object publishing unit 53 is configured to publish the first object to the target application according to the object content in response to a publishing event for the first object.

[0141] Optionally, the page display unit 51 is specifically configured to: display the homepage of the first application; in response to a trigger event for a first creation entry point in the homepage, display a dialogue page for interacting with a digital assistant; or, display the homepage of the first application; in response to a trigger event for a first creation entry point in the homepage, display a character creation page; in response to a trigger event for a second creation entry point in the character creation page, display a dialogue page for interacting with a digital assistant; or, display the homepage of the first application; in response to a trigger event for a first creation entry point in the homepage, display a creation entry panel; in response to a trigger event for a third creation entry point in the creation entry panel, display a dialogue page for interacting with a digital assistant.

[0142] Optionally, the object creation unit 52 is specifically used to: determine the category of the object to be created based on at least one round of first dialogue content with the digital assistant in the dialogue page through the generative model; the category includes at least one of character, chapter-type story, and architecture-type story; create a first object based on the first dialogue content and the category through the generative model; the first object belongs to the category.

[0143] Optionally, the object creation unit 52 is further configured to: extract key content from the first dialogue content through the generative model, and determine the category of the object to be created based on the key content; the key content is used to represent the category of the object to be created; wherein, in the first dialogue content, the key content includes at least one of the following: statement content sent to the digital assistant, inquiry messages and corresponding response content sent by the digital assistant, and guidance messages and corresponding response content sent by the digital assistant.

[0144] Optionally, the object creation unit 52 is further configured to: determine at least one content dimension corresponding to the category and the content requirements corresponding to the content dimension through the generative model; obtain the target content corresponding to the content dimension based on the first dialogue content through the generative model; the target content satisfies the content requirements corresponding to the content dimension; and create a first object according to the target content through the generative model; the object content of the first object includes the target content.

[0145] Optionally, the object creation unit 52 is further configured to: if the first dialogue content carries the target content, then obtain the target content from the first dialogue content through the generative model; wherein the target content includes at least one of the statement content sent to the digital assistant, the inquiry message and corresponding response content sent by the digital assistant, and the guidance message and corresponding response content sent by the digital assistant; if the first dialogue content does not carry the target content, then expand the target content by combining it with the first dialogue content through the generative model.

[0146] Optionally, it further includes a determining unit, configured to: determine, via the generative model, that the target content meets the object creation requirements, or determine that the first dialogue content contains an object creation intent, before creating the first object based on the target content through the generative model.

[0147] Optionally, the object publishing unit 53 is specifically configured to: in response to a publishing event for the first object, jump to the editing page of the first object; the editing page is filled with the object content and the first auxiliary content of the first object; the first auxiliary content is generated based on the object content, and the first auxiliary content includes at least one of the first object's image, audio, and timbre; in response to a confirmation event for the object content and the first auxiliary content in the editing page, publish the first object to the target application according to the object content and the first auxiliary content.

[0148] Optionally, it also includes an editing unit, configured to display modified content in response to a modification event on the editing page for the object content and / or the first auxiliary content before publishing the first object to the target application in accordance with the object content and the first auxiliary content in response to a confirmation event on the editing page for the object content and the first auxiliary content;

[0149] The object publishing unit 53 is specifically used to: in response to a confirmation event for the modified content in the editing page, publish the first object to the target application according to the modified content.

[0150] Optionally, it further includes a rollback unit, configured to, in response to an exit event of the editing page, return to the dialogue page before publishing the first object to the target application according to the object content and the first auxiliary content in response to a confirmation event for the object content and the first auxiliary content in the editing page; modify the object content according to at least one round of second dialogue content with the digital assistant in the dialogue page, and output the modified object content; and, in response to a publishing event for the first object, jump to the editing page of the first object; the editing page is filled with the modified object content and the first auxiliary content updated based on the modified object content;

[0151] The object publishing unit 53 is specifically used to: in response to a confirmation event on the editing page for the modified object content and the updated first auxiliary content, publish the first object to the target application according to the modified object content and the updated first auxiliary content.

[0152] The object creation apparatus in this embodiment can implement the various processes of the above-described object creation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0153] This disclosure also provides an electronic device according to an embodiment. Figure 6 is a schematic diagram of the structure of the electronic device provided in an embodiment of this disclosure. As shown in Figure 6, the electronic device can vary considerably due to different configurations or performance. It may include one or more processors 601 and memory 602. The memory 602 may store one or more application programs or data. The memory 602 may be temporary or persistent storage. The application programs stored in the memory 602 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the electronic device. Furthermore, the processor 601 may be configured to communicate with the memory 602 and execute the series of computer-executable instructions in the memory 602 on the electronic device. The electronic device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input or output interfaces 605, one or more keyboards 606, etc.

[0154] In one specific embodiment, the electronic device includes a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following process:

[0155] Displays a dialog page for interacting with the digital assistant;

[0156] Using the generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0157] In response to a publish event for the first object, the first object is published to the target application according to the object content.

[0158] The electronic device in this embodiment can implement the various processes of the above-described object creation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0159] Another embodiment of this disclosure also provides a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the following process:

[0160] Displays a dialog page for interacting with the digital assistant;

[0161] Using the generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0162] In response to a publish event for the first object, the first object is published to the target application according to the object content.

[0163] The computer-readable storage medium in this disclosure embodiment can implement the various processes of the above-described object creation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0164] Another embodiment of this disclosure also provides a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the following process:

[0165] Displays a dialog page for interacting with the digital assistant;

[0166] Using the generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content;

[0167] In response to a publish event for the first object, the first object is published to the target application according to the object content.

[0168] The computer program product in this disclosure embodiment can implement the various processes of the above-described object creation method embodiment and achieve the same effects and functions, which will not be repeated here.

[0169] In various embodiments of this disclosure, the computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0170] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0171] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0172] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0173] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing the embodiments of this disclosure, the functions of each unit can be implemented in one or more software and / or hardware.

[0174] Those skilled in the art will understand that one or more embodiments of this disclosure can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0176] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0178] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0179] One or more embodiments of this disclosure can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this disclosure can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0180] The various embodiments in this disclosure are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0181] The above description is merely an embodiment of this disclosure and is not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. An object creation method, wherein, include: Displays a dialog page for interacting with the digital assistant; Using the generative model corresponding to the digital assistant, a first object is created based on at least one round of first dialogue content with the digital assistant on the dialogue page, and the object content of the first object is output; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content; In response to a publish event for the first object, the first object is published to the target application according to the object content.

2. The method of claim 1, wherein, The dialog page for interacting with the digital assistant includes: Display the homepage of the first application; in response to a trigger event for the first creation entry on the homepage, display a dialogue page for interacting with the digital assistant; or, Display the homepage of the first application; in response to a trigger event for a first creation entry on the homepage, display the character creation page; in response to a trigger event for a second creation entry on the character creation page, display a dialogue page for interacting with the digital assistant; or, Display the homepage of the first application; in response to a trigger event for a first creation entry on the homepage, display the creation entry panel; in response to a trigger event for a third creation entry on the creation entry panel, display a dialogue page for interacting with the digital assistant.

3. The method of claim 1, wherein, The step of creating a first object based on at least one round of first dialogue with the digital assistant through the generative model corresponding to the digital assistant on the dialogue page includes: The generative model determines the category of the object to be created based on at least one round of first dialogue with the digital assistant on the dialogue page; the category includes at least one of character, chapter-based story, and architecture-based story. Using the generative model, a first object is created based on the first dialogue content and the category; the first object belongs to the category.

4. The method of claim 3, wherein, The step of determining the category of the object to be created through the generative model, based on at least one round of first dialogue with the digital assistant on the dialogue page, includes: The generative model extracts key content from the first dialogue content, and determines the category of the object to be created based on the key content; the key content is used to represent the category of the object to be created. In the first dialogue content, the key content includes at least one of the following: statements sent to the digital assistant, inquiry messages and corresponding responses sent by the digital assistant, and guidance messages and corresponding responses sent by the digital assistant.

5. The method of claim 3, wherein, The step of creating a first object based on the first dialogue content and the category using the generative model includes: The generative model is used to determine at least one content dimension corresponding to the category and the content requirements corresponding to the content dimension. The generative model is used to obtain target content corresponding to the content dimension based on the first dialogue content; the target content satisfies the content requirements corresponding to the content dimension. Using the generative model, a first object is created based on the target content; the object content of the first object includes the target content.

6. The method of claim 5, wherein, The step of obtaining the target content corresponding to the content dimension based on the first dialogue content through the generative model includes: If the first dialogue content carries the target content, then the generative model is used to obtain the target content from the first dialogue content; wherein, the target content includes at least one of the following: statement content sent to the digital assistant, inquiry message and corresponding response content sent by the digital assistant, and guidance message and corresponding response content sent by the digital assistant; If the first dialogue content does not contain the target content, the generative model is used to expand the first dialogue content to obtain the target content.

7. The method of claim 5, wherein, Before creating the first object based on the target content using the generative model, the method further includes: The generative model determines whether the target content meets the object creation requirements, or whether the first dialogue content contains an object creation intent.

8. The method of claim 1, wherein, The step of publishing the first object to the target application according to the object content in response to a publication event for the first object includes: In response to a publish event for the first object, the user is redirected to the editing page of the first object; the editing page is filled with the object content and the first auxiliary content of the first object; the first auxiliary content is generated based on the object content, and the first auxiliary content includes at least one of the first object's image, audio, and timbre. In response to a confirmation event on the editing page for the object content and the first auxiliary content, the first object is published to the target application according to the object content and the first auxiliary content.

9. The method of claim 8, wherein, Before publishing the first object to the target application according to the object content and the first auxiliary content in response to a confirmation event for the object content and the first auxiliary content on the editing page, the method further includes: In response to a modification event on the editing page concerning the object content and / or the first auxiliary content, the modified content is displayed; The step of responding to a confirmation event on the editing page for the object content and the first auxiliary content, and publishing the first object to the target application according to the object content and the first auxiliary content, includes: In response to a confirmation event for the modified content on the editing page, the first object is published to the target application according to the modified content.

10. The method of claim 8, wherein, Before publishing the first object to the target application according to the object content and the first auxiliary content in response to a confirmation event for the object content and the first auxiliary content on the editing page, the method further includes: In response to the exit event of the editing page, return to the dialog page; Based on the content of at least one second round of dialogue with the digital assistant on the dialogue page, modify the object content and output the modified object content; In response to a publish event for the first object, the user is redirected to the editing page of the first object; the editing page is filled with the modified content of the object and the first auxiliary content updated based on the modified content of the object. The step of responding to a confirmation event on the editing page for the object content and the first auxiliary content, and publishing the first object to the target application according to the object content and the first auxiliary content, includes: In response to a confirmation event on the editing page regarding the modified object content and the updated first auxiliary content, the first object is published to the target application according to the modified object content and the updated first auxiliary content.

11. An object creation apparatus, wherein, include: Page display unit, used to display the dialogue page for interacting with the digital assistant; An object creation unit is used to create a first object based on at least one round of first dialogue content with the digital assistant in the dialogue page, using a generative model corresponding to the digital assistant, and to output the object content of the first object; the first object includes at least one of a first character, a first chapter-type story, and a first architecture-type story; the object content of the first object is generated based on the first dialogue content; An object publishing unit is configured to publish the first object to a target application according to the object content in response to a publishing event for the first object.

12. An electronic device, comprising: include: processor; as well as, A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the method described in any one of claims 1-10.

13. A computer readable storage medium, wherein, The computer-readable storage medium is used to store computer-executable instructions that, when executed by a processor, implement the steps of the method described in any one of claims 1-10.

14. A computer program product, wherein, The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-10.

Images