Content generation method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a content generation method and device, equipment and a storage medium. The method provided by the invention comprises the following steps: presenting a first interactive interface associated with an intelligent agent, wherein the first interactive interface comprises a content display area and an input component; in the content display area, a media generation history is presented, the media generation history is associated with multiple media generation modes, and the multiple media generation modes at least comprise a first generation mode associated with the intelligent agent and a second generation mode independent of the intelligent agent; and in response to receiving the generation request via the input component, providing, in the content presentation area, at least one item of media content generated by the agent based on the generation request, the at least one item of media content being generated based on at least a portion of the media generation history. In this way, the embodiment of the invention can effectively improve the generation quality of the media content.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and more particularly to methods, apparatus, devices and computer-readable storage media for content generation. Background Technology

[0002] With the development of computer technology, more and more content sharing and media editing applications have integrated media content generation functions, allowing users to generate media content within them. Media content generation technology enables users to create multi-dimensional creative works based on single image or video materials, greatly lowering the barrier to entry for media content creation. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for content generation is provided. The method includes: presenting a first interactive interface associated with an agent, the first interactive interface including a content display area and an input component; presenting a media generation history in the content display area, the media generation history being associated with multiple media generation modes, the multiple media generation modes including at least a first generation mode associated with the agent and a second generation mode independent of the agent; and in response to receiving a generation request via the input component, providing in the content display area at least one piece of media content generated by the agent based on the generation request, the at least one piece of media content being generated based on at least a portion of the media generation history.

[0004] In a second aspect of this disclosure, an apparatus for content generation is provided. The apparatus includes: a first presentation module configured to present a first interactive interface associated with an agent, the first interactive interface including a content display area and an input component; a second presentation module configured to present a media generation history in the content display area, the media generation history being associated with multiple media generation modes, the multiple media generation modes including at least a first generation mode associated with the agent and a second generation mode independent of the agent; and a providing module configured to, in response to receiving a generation request via the input component, provide in the content display area at least one piece of media content generated by the agent based on the generation request, the at least one piece of media content being generated based on at least a portion of the media generation history.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0008] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0010] Figures 2A to 2G Example interfaces according to some embodiments of this disclosure are shown;

[0011] Figure 3 A flowchart illustrating an example process for generating content according to some embodiments of this disclosure is shown;

[0012] Figure 4 A schematic structural block diagram of an example apparatus for content generation according to some embodiments of the present disclosure is shown; and

[0013] Figure 5 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0016] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0017] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0018] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0019] As mentioned above, with the development of computer technology, more and more content sharing or media content editing applications have integrated media content generation functions, allowing users to generate media content within them. Media content generation technology enables users to generate multi-dimensional creative works based on single image or video materials, which greatly lowers the barrier to entry for media content creation.

[0020] Embodiments of this disclosure propose a content generation scheme. The scheme includes: presenting a first interactive interface associated with an agent, the first interactive interface including a content display area and an input component; presenting a media generation history in the content display area, the media generation history being associated with multiple media generation modes, the multiple media generation modes including at least a first generation mode associated with the agent and a second generation mode independent of the agent; and in response to receiving a generation request via the input component, providing at least one piece of media content generated by the agent based on the generation request in the content display area, the at least one piece of media content being generated based on at least a portion of the media generation history.

[0021] In this way, embodiments of the present disclosure, upon receiving a generation request via an input component, can generate media content based on at least a portion of a media generation history associated with multiple generation modes, thereby effectively improving the quality of generated media content.

[0022] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0023] Example Environment

[0024] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, example environment 100 may include electronic device 110.

[0025] In this example environment 100, electronic device 110 may run an application 120 that supports content generation. Application 120 may be any suitable type of application for content generation, examples of which may include, but are not limited to, content generation applications, content editing applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0026] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting content generation.

[0027] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0028] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support content generation in electronic devices 110.

[0029] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0030] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0031] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0032] Example Interaction

[0033] Figures 2A to 2G Example interfaces 200A to 200G according to some embodiments of the present disclosure are shown. Interfaces 200A to 200G may, for example, be provided by... Figure 1 The electronic device 110 shown is provided.

[0034] In some embodiments, the electronic device 110 presents an interactive interface associated with the intelligent agent. The interactive interface includes a content display area and input components. For example, such as... Figure 2AAs shown, electronic device 110 can present an interactive interface associated with an agent. Such an interactive interface could be, for example, interface 200A, which includes an input component 205. Electronic device 110 can support interaction between user 140 and the agent through the input component 205 in interface 200A. Such interaction could be, for example, a conversation with the agent. For instance, electronic device 110 can receive prompts input by user 140 via the input component 205 in interface 200A. Furthermore, electronic device 110 can provide corresponding content to user 140 via interface 200A. Such content could include, for example, media content, text content, audio content, etc. Here, the agent is also called an agent. The agent can utilize one or more models (e.g., a language model or a multimodal model) to drive its interaction with the user. As an example, the agent can utilize a language model or a multimodal model to generate corresponding response content (e.g., at least one piece of media content) based on the user's input request.

[0035] In some embodiments, the electronic device 110 presents a media generation history in a content display area. The media generation history is associated with multiple media generation modes. The multiple media generation modes include at least a first generation mode associated with the agent and a second generation mode independent of the agent.

[0036] As an example, such as Figure 2A As shown, the electronic device 110 can present a media generation history 215 in the content display area 210 of an interactive interface (e.g., interface 200A). The media generation history 215 is associated with multiple media generation modes, meaning it is associated with multiple content streams. In other words, the media generation history 215 is generated through multiple media generation modes. For example, the media generation history 215 includes content generated by a first generation mode associated with the agent and content generated by a second generation mode independent of the agent. Here, the first generation mode instructs the agent to generate media content based on at least a portion of the media generation history 215. The second generation mode could be, for example, an image generation mode, a video generation mode, and an audio generation mode.

[0037] In some embodiments, the electronic device 110 also supports user 140 referencing content presented in the interactive interface to generate media content or modify the referenced content. Specifically, the electronic device 110 can present reference information associated with the target content in the input component based on the selection of target content in the media generation history. Further, the electronic device 110 can obtain a generation request associated with the target content via the input component. The target content includes first content or second content. The first content is associated with a first generation mode. The second content is associated with a second generation mode.

[0038] As an example, such as Figure 2B As shown, electronic device 110 can receive a selection operation for target content (e.g., content 220) in media generation history 215 via an interactive interface (e.g., interface 200B). The target content can be generated by a first generation mode or a second generation mode. In other words, electronic device 110 supports user 140 referencing content from different generation streams. After the target content (e.g., media content 220) is selected, electronic device 110 can present reference information associated with the target content (e.g., media content 220) in input component 205. Such reference information can be, for example, descriptive information associated with the target content or the target content itself. Furthermore, electronic device 110 can obtain a generation request associated with the target media content via input component 205. This generation request can, for example, include reference information.

[0039] In some scenarios, after the target content is referenced, the electronic device 110 can also receive an editing request for the target content via the input component 205. After the editing request is received, the electronic device 110 can trigger an editing event for the target content. After the target content is edited, the electronic device 110 can display the edited target content in the media generation history 215.

[0040] In this way, embodiments of this disclosure can reference target content in the media generation history, thereby enabling the subsequent generation of media content based on the target content, which can improve the quality of media content generation.

[0041] In some embodiments, the electronic device 110 may present a first reference control in response to the selection of historical media content in the media generation history. Further, the electronic device 110 may present reference information associated with the historical media content in an input component in response to the triggering of the first reference control.

[0042] As an example, such as Figure 2BAs shown, electronic device 110 can present historical media content in media generation history 215. Such historical media content could be, for example, content 220. When historical media content (e.g., media content 220) is selected, electronic device 110 can present a first reference control 225 in the area where the historical media content (e.g., media content 220) is located. The first reference control 225 is associated with the historical media content (e.g., content 220) and is configured to trigger the presentation of reference information associated with the historical media content (e.g., media content 220) in input component 205. When the first application control 225 is triggered (e.g., by clicking or double-clicking), electronic device 110 can present the reference information associated with the historical media content (e.g., media content 220) in input component 205 to construct a generation request based on the reference information. Here, the reference information can be, for example, historical media content (e.g., media content 220).

[0043] In some scenarios, electronic device 110 also supports user 140 referencing multiple pieces of content. For example, when a reference control associated with media content 230 is triggered, electronic device 110 can also present reference information associated with media content 230 in input component 205. For example, electronic device 110 can present media content 230 in input component 205.

[0044] In this way, embodiments of this disclosure support users in referencing media content, thereby referencing the referenced media content during the subsequent generation of media content, and thus providing users with higher quality media content.

[0045] In some embodiments, the electronic device 110 may acquire input content via an input component. The input content indicates a reference dimension associated with historical media content. Further, the electronic device 110 may construct a generation request based on the input content and the historical media content.

[0046] As an example, such as Figure 2B As shown, electronic device 110 can acquire input content via input component 205. This input content can, for example, indicate the reference dimensions of the referenced historical media content (e.g., media content 220). These reference dimensions can include, for example, style, character, outline, etc. For instance, the input content could be "Generate another image with the same style, referencing the style of the referenced image." Upon receiving the input content, electronic device 110 can construct a generation request based on the input content and the referenced historical media content (e.g., media content 220) to generate at least one piece of media content.

[0047] In this way, embodiments of the present disclosure can indicate the reference dimension of the referenced content by inputting information, thereby making it more convenient to indicate the reference dimension used to generate media content, thereby improving the efficiency of generating media content.

[0048] In some embodiments, the electronic device 110 can determine a reference dimension corresponding to at least one of the multiple historical media contents based on the order of these contents in the input component. As an example, when multiple historical media contents are referenced, the electronic device 110 can present the referenced multiple historical media contents in the input component 205. For example, the electronic device 110 can present media content 220 and media content 230 in the input component 205. Media content 220 and media content 230 can be ordered based on the order in which they are referenced. For example, if media content 220 is referenced first and media content 230 is referenced later, then media content 220 is in the first position and media content 230 is in the second position. After receiving the input content, the electronic device 110 can determine the historical media content to be referenced based on the input content. For example, if the input content is "reference",... Figure 1 The electronic device 110 can determine the historical media content to be referenced as media content 220 based on the input content, and the style dimension of the media content 220 to be referenced.

[0049] In this way, the embodiments of this disclosure can more flexibly determine the media content to be referenced and the reference dimensions to be referenced, thereby improving the efficiency of media content generation.

[0050] In some embodiments, the electronic device 110 also supports user 140 in referencing text content. Specifically, the electronic device 110 may present a second reference control in response to the selection of text content in the media generation history. Further, the electronic device 110 may present reference information associated with the text content in an input component in response to the triggering of the second reference control.

[0051] As an example, such as Figure 2CAs shown, when text content (e.g., text content 235) in media generation history 215 is selected, electronic device 110 can present a second reference control 240 in an interactive interface (e.g., interface 200C). The second reference control 240 is associated with the selected text content (e.g., text content 235). When the second reference control 240 is triggered, electronic device 110 can present reference information associated with the text content (e.g., text content 235) in input component 205. For example, when the second reference control 240 is triggered, electronic device 110 can present a reference label 245 in input component 205. Electronic device 110 can present reference information associated with text content 235 in reference label 245. This reference information may, for example, indicate at least a portion of text content 235. In other words, electronic device 110 can present at least a portion of text content 235 in reference label 245.

[0052] In this way, embodiments of this disclosure allow user 140 to reference text content in the media generation history, thereby enabling the construction of richer generation requests and improving the quality of media content generation.

[0053] In some embodiments, in response to receiving a generation request via an input component, the electronic device 110 provides at least one piece of media content generated by the agent based on the generation request in a content display area. The at least one piece of media content is generated based on at least a portion of the media generation history.

[0054] As an example, such as Figure 2D As shown, electronic device 110 can receive a generation request via input component 205. Such a generation request can be constructed, for example, based on input information and / or reference information received by electronic device 110 via input component 205. Upon receiving the generation request, electronic device 110 can provide at least one piece of media content 250 in content display area 210. This at least one piece of media content 250 is generated by the agent based on at least a portion of the media generation history 215. At least a portion of the media generation history 215 can be determined, for example, based on a prompt used to construct the generation request. For example, upon receiving a prompt, server 130 can determine, based on the prompt, target content from the media generation history with a matching degree greater than a threshold, to determine the content used to generate at least one piece of media content 250. For example, the prompt is "Generate a kitten playing guitar." Upon receiving the prompt, server 130 can determine content associated with "guitar" and "kitten" from the media generation history 215 to generate at least one piece of media content 250.

[0055] In some scenarios, after receiving a generation request, the electronic device 110 can not only provide at least one piece of media content 250 in the content display area 210, but also provide descriptive information associated with the at least one piece of media content 250 in the content display area 210. Such descriptive information may include, for example, prompts for generating the at least one piece of media content 250, descriptions of the images of the at least one piece of media content 250, etc.

[0056] In some embodiments, to make the interface more concise and allow users to focus more on the generated media content, the electronic device 110 may collapse a portion of the text in the response content. Specifically, the electronic device 110 may display the response content generated by the agent based on the generation request in the content display area. Further, the electronic device 110 may stop displaying a portion of the text content of the response content in the content display area in response to at least one piece of media content being presented in the response content.

[0057] As an example, such as Figure 2D As shown, the electronic device 110 can display response content 255 generated by the intelligent agent based on the generation request in the content display area 210. The response content 255 includes at least one piece of media content 250 and multiple pieces of text content. The multiple pieces of text content here may include, for example, text content 255-1. Text content 255-1 may be, for example, descriptive information associated with at least one piece of media content 250.

[0058] Upon receiving a generation request, the agent can output different parts of the response content 255 in a preset order. For example, the agent can first output text content 255-1, and after text content 255-1 is fully rendered, the agent will then output at least one piece of media content 250. Once at least one piece of media content 250 is rendered in the response content 255, as... Figure 2E As shown, electronic device 110 can stop displaying a portion of the text content in response content 255. For example, electronic device 110 can hide text content 255-1 in response content 255.

[0059] In this way, the embodiments of this disclosure can stop presenting redundant text content after the media content is presented, thereby allowing users to focus more on the generated media content and thus enabling users to view the generated media content more efficiently.

[0060] In some embodiments, the electronic device 110 can also re-present hidden text content. Specifically, the electronic device 110 can present a viewing control associated with a portion of the text content within the response content. Further, the electronic device 110 can present a portion of the text content of the response content in the content display area in response to a triggering of the viewing control.

[0061] As an example, such as Figure 2E As shown, when a portion of the text content in response content 255 (e.g., text content 255-1) is stopped from being displayed, electronic device 110 can display a viewing control 260 associated with the portion of the text content (e.g., text content 255-1) in response content 255. When the viewing control 260 is triggered (e.g., by clicking or double-clicking), electronic device 110 can re-represent the portion of the text content in response content 255 (e.g., text content 255-1) in content display area 210.

[0062] In this way, embodiments of the present disclosure can re-present hidden text content by triggering the viewing control, thereby making it easier for users to view the text content and improving the efficiency of users obtaining information.

[0063] In some embodiments, the electronic device 110 may also support the user 140 in switching media generation modes. Specifically, the electronic device 110 may switch the interactive interface from a first generation mode to a second generation mode in response to receiving a switching request via the interactive interface.

[0064] As an example, such as Figure 2E As shown, electronic device 110 can receive a switching request via an interactive interface (e.g., interface 200D). The switching request is configured to trigger a switch in media generation mode. Upon receiving the switching request via the interactive interface (e.g., interface 200E), electronic device 110 can switch the interactive interface from a first generation mode to a second generation mode. For example, electronic device 110 can receive the switching request via appropriate interactive controls in interface 200E. After receiving the switching request, electronic device 110 can switch the interactive interface from the first generation mode to the second generation mode.

[0065] In this way, the embodiments of this disclosure can more conveniently switch between generation modes, thereby improving the efficiency of media generation mode switching.

[0066] In some embodiments, the electronic device 110 may present multiple switching entry points in the interactive interface, the multiple switching entry points corresponding to various media generation modes. Further, the electronic device 110 may switch the interactive interface from a first generation mode to a second generation mode in response to the selection of a target switching entry point among the multiple switching entry points associated with a second generation mode.

[0067] As an example, such as Figure 2EAs shown, the electronic device 110 can present multiple switching entry points in an interactive interface (e.g., interface 200E). These multiple switching entry points may include, for example, switching entry point 265 and switching entry point 266. These multiple switching entry points correspond to various media generation modes. For example, switching entry point 265 may correspond to a first generation mode, and switching entry point 266 may correspond to a second generation mode. When a target switching entry point (e.g., switching entry point 266) associated with the second generation mode is selected, the electronic device 110 can switch the interactive interface (e.g., interface 200E) from the first generation mode to the second generation mode. For example, the electronic device 110 can switch interface 200E from a generation mode associated with an intelligent agent to a generation mode independent of the intelligent agent (e.g., image generation mode, text generation mode, video generation mode, etc.).

[0068] In this way, the embodiments of this disclosure can switch the media generation mode of the interactive interface through multiple switching entry points, thereby enabling more flexible switching of the media generation mode.

[0069] In some embodiments, the electronic device 110 may present a switching control for switching media generation modes in the input component. Further, the electronic device 110 may switch the input component to a second generation mode via the switching control.

[0070] As an example, such as Figure 2E As shown, the electronic device 110 can display a switching control 270 in the input component 205. When the switching control 270 is clicked, the electronic device 110 can display a mode selection panel 270-1. The selection panel 270-1 includes multiple candidate options, each associated with a different media generation mode. For example, candidate option 270-2 is associated with a second generation mode. When candidate option 270-2 is selected, the electronic device 110 can switch the input component 205 to the mode associated with the second generation mode.

[0071] In this way, embodiments of the present disclosure can switch the media generation mode of the input component through a switching control in the input component, thereby making it more convenient for users to switch the media generation mode.

[0072] In some embodiments, at least one media content includes at least a first media content and a second media content. The electronic device 110 may, in response to the selection of the first media content, present a generation control corresponding to the first media content in the content display area. Further, the electronic device 110 may, in response to the triggering of the generation control, update the first media content to a third media content while maintaining the presentation of the second media content. The third media content is generated based on a first prompt message associated with the first media content.

[0073] As an example, such as Figure 2E and 2F As shown, once at least one media content is generated, the electronic device 110 can display a first media content (e.g., media content 275-1) and a second media content (e.g., media content 275-2) from the at least one media content in the content display area 210. The first media content (e.g., media content 275-1) and the second media content (e.g., media content 275-2) can, for example, correspond to different prompt messages. These different prompt messages are used to generate the first media content (e.g., media content 275-1) and the second media content (e.g., media content 275-2).

[0074] When a first media content (e.g., media content 275-1) is selected, the electronic device 110 can display a generation control 280 associated with the first media content (e.g., media content 275-1) in the content display area 210. The generation control 280 is configured to regenerate the first media content (e.g., media content 275-1) based on a first prompt message associated with it. This first prompt message could be, for example, "Generate an astronaut." When the generation control 280 is triggered (e.g., by clicking or double-clicking), the electronic device 110 updates the first media content (e.g., media content 275-1) to a third media content (e.g., media content 275-3). The third media content (e.g., media content 275-3) is generated based on the first prompt message associated with the first media content (e.g., media content 275-1). During the regeneration of the first media content (e.g., media content 275-1), the second media content (e.g., media content 275-2) does not change accordingly.

[0075] In this way, embodiments of the present disclosure can individually adjust any media content in at least one generated media content, thereby allowing for more flexible adjustment of at least one media content.

[0076] In some embodiments, the electronic device 110 may also present a viewing window in response to a triggering of a fourth media content within at least one media content. The viewing window presents the fourth media content and a second prompt message for generating the fourth media content.

[0077] Let's take media content 275-2 as an example of fourth-generation media content for illustration. For example... Figure 2F As shown, after at least one media content is generated, the electronic device 110 can display a fourth media content (e.g., media content 275-2) in the content display area 210. When the fourth media content (e.g., media content 275-2) is triggered (e.g., by clicking or double-clicking), as... Figure 2GAs shown, the electronic device 110 can present a viewing window 285. The viewing window 285 is configured to present at least one piece of media content. The electronic device 110 can present a fourth piece of media content (e.g., media content 275-2) and a second prompt message 290 for generating the fourth piece of media content in the viewing window 285. In some scenarios, the electronic device 110 can receive a content switching operation from the user 140 via the viewing window 285 to switch the media content presented in the viewing window 285. The second prompt message 290 here could be, for example, "Generate a bright moon". In this way, embodiments of this disclosure can provide the user with fourth media content and a second prompt message for generating the fourth piece of media content through a viewing window, thereby making it easier for the user to obtain the fourth media content and the second prompt message, thus improving the efficiency of the user's information acquisition.

[0078] In this way, embodiments of the present disclosure, upon receiving a generation request via an input component, can generate media content based on at least a portion of a media generation history associated with multiple generation modes, thereby effectively improving the quality of generated media content.

[0079] Example process

[0080] Figure 3 A flowchart of an example process 300 generated according to some embodiments of the present disclosure is shown. Process 300 can be implemented at electronic device 110. Reference is made below. Figure 1 To describe process 300.

[0081] like Figure 3 As shown, in box 310, electronic device 110 presents an interactive interface associated with the intelligent agent, which includes a content display area and input components.

[0082] In frame 320, electronic device 110 presents a media generation history in the content display area. The media generation history is associated with multiple media generation modes, which include at least a first generation mode associated with the intelligent agent and a second generation mode independent of the intelligent agent.

[0083] In box 330, electronic device 110, in response to receiving a generation request via an input component, provides at least one piece of media content generated by the agent based on the generation request in the content display area, wherein the at least one piece of media content is generated based on at least a portion of the media generation history.

[0084] In some embodiments, process 300 further includes: presenting reference information associated with the target content in an input component based on the selection of target content in the media generation history; and obtaining a generation request associated with the target content via the input component.

[0085] In this way, embodiments of this disclosure can reference target content in the media generation history, thereby enabling the subsequent generation of media content based on the target content, which can improve the quality of media content generation.

[0086] In some embodiments, presenting reference information associated with the target content in the input component based on the selection of target content in the media generation history includes: presenting a first reference control in response to the selection of historical media content in the media generation history; and presenting reference information associated with the historical media content in the input component in response to the triggering of the first reference control.

[0087] In this way, embodiments of this disclosure support users in referencing media content, thereby referencing the referenced media content during the subsequent generation of media content, and thus providing users with higher quality media content.

[0088] In some embodiments, obtaining a generation request associated with target content via an input component includes: obtaining input content via the input component, the input content indicating a reference dimension associated with historical media content; and constructing a generation request based on the input content and the historical media content.

[0089] In this way, embodiments of the present disclosure can indicate the reference dimension of the referenced content by inputting information, thereby making it more convenient to indicate the reference dimension used to generate media content, thereby improving the efficiency of generating media content.

[0090] In some embodiments, the historical media content includes multiple historical media content items, and process 300 further includes: determining a reference dimension corresponding to at least one of the multiple historical media content items from the input content based on the order of the multiple historical media content items in the input component.

[0091] In this way, the embodiments of this disclosure can more flexibly determine the media content to be referenced and the reference dimensions to be referenced, thereby improving the efficiency of media content generation.

[0092] In some embodiments, presenting reference information associated with the target content in the input component based on the selection of target content in the media generation history includes: presenting a second reference control in response to the selection of text content in the media generation history; and presenting reference information associated with the text content in the input component in response to the triggering of the second reference control.

[0093] In this way, embodiments of this disclosure allow user 140 to reference text content in the media generation history, thereby enabling the construction of richer generation requests and improving the quality of media content generation.

[0094] In some embodiments, the target content includes: first content associated with a first generation mode; or second content associated with a second generation mode.

[0095] In this way, embodiments of this disclosure can reference target content in different content streams, thereby allowing for more flexible addition of references and improving the efficiency of content referencing.

[0096] In some embodiments, at least one media content includes at least a first media content and a second media content, and process 300 further includes: in response to the selection of the first media content, presenting a generation control corresponding to the first media content in a content display area; and in response to the triggering of the generation control, updating the first media content to a third media content while maintaining the presentation of the second media content, the third media content being generated based on a first prompt message associated with the first media content.

[0097] In this way, embodiments of the present disclosure can individually adjust any media content in at least one generated media content, thereby allowing for more flexible adjustment of at least one media content.

[0098] In some embodiments, process 300 further includes: in response to a triggering of a fourth media content in at least one media content, presenting a viewing window, the viewing window presenting the fourth media content and a second prompt message for generating the fourth media content.

[0099] In this way, embodiments of the present disclosure can provide users with fourth media content and second prompt information for generating the fourth media content through a viewing window, thereby making it easier for users to obtain the fourth media content and the second prompt information, thus improving the efficiency of users obtaining information.

[0100] In some embodiments, process 300 further includes: in response to receiving a switching request via the interactive interface, switching the interactive interface from a first generation mode to a second generation mode.

[0101] In this way, the embodiments of this disclosure can more conveniently switch between generation modes, thereby improving the efficiency of media generation mode switching.

[0102] In some embodiments, switching the interactive interface from a first generation mode to a second generation mode includes: presenting multiple switching entry points in the interactive interface, the multiple switching entry points corresponding to multiple media generation modes; and switching the interactive interface from the first generation mode to the second generation mode in response to the selection of a target switching entry point associated with the second generation mode among the multiple switching entry points.

[0103] In this way, the embodiments of this disclosure can switch the media generation mode of the interactive interface through multiple switching entry points, thereby enabling more flexible switching of the media generation mode.

[0104] In some embodiments, switching the interactive interface from a first generation mode to a second generation mode includes: presenting a switching control for switching media generation modes in the input component; and switching the input component to the second generation mode via the switching control.

[0105] In this way, embodiments of the present disclosure can switch the media generation mode of the input component through a switching control in the input component, thereby making it more convenient for users to switch the media generation mode.

[0106] In some embodiments, providing at least one piece of media content generated by an agent based on a generation request in a content display area includes: presenting response content generated by the agent based on the generation request in the content display area; and stopping the presentation of a portion of the text content of the response content in the content display area in response to at least one piece of media content being presented in the response content.

[0107] In this way, the embodiments of this disclosure can stop presenting redundant text content after the media content is presented, thereby allowing users to focus more on the generated media content and thus enabling users to view the generated media content more efficiently.

[0108] In some embodiments, process 300 further includes: presenting a viewing control associated with a portion of the text content in the response content; and presenting a portion of the text content of the response content in a content display area in response to triggering the viewing control.

[0109] In this way, embodiments of the present disclosure can re-present hidden text content by triggering the viewing control, thereby making it easier for users to view the text content and improving the efficiency of users obtaining information.

[0110] Example devices and equipment

[0111] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 4 A schematic structural block diagram of an example device 400 for content generation according to certain embodiments of the present disclosure is shown. Device 400 may be implemented as or included in electronic device 110. Various modules / components in device 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0112] like Figure 4As shown, the device 400 includes: a first presentation module 410 configured to present a first interactive interface associated with an agent, the first interactive interface including a content display area and an input component; a second presentation module 420 configured to present a media generation history in the content display area, the media generation history being associated with multiple media generation modes, the multiple media generation modes including at least a first generation mode associated with the agent and a second generation mode independent of the agent; and a providing module 430 configured to, in response to receiving a generation request via the input component, provide at least one piece of media content generated by the agent based on the generation request in the content display area, the at least one piece of media content being generated based on at least a portion of the media generation history.

[0113] In some embodiments, the apparatus 400 further includes an acquisition module configured to present reference information associated with the target content in an input component based on the selection of target content in the media generation history; and to acquire a generation request associated with the target content via the input component.

[0114] In some embodiments, the acquisition module is further configured to: present a first reference control in response to the selection of historical media content in the media generation history; and present reference information associated with the historical media content in the input component in response to the triggering of the first reference control.

[0115] In some embodiments, the acquisition module is further configured to: acquire input content via an input component, the input content indicating a reference dimension associated with historical media content; and construct a generation request based on the input content and the historical media content.

[0116] In some embodiments, the historical media content includes multiple historical media content items, and the apparatus 400 further includes a determining module configured to determine a reference dimension corresponding to at least one of the multiple historical media content items from the input content based on the order of the multiple historical media content items in the input component.

[0117] In some embodiments, the acquisition module is further configured to: present a second reference control in response to selection of text content in the media generation history; and present reference information associated with the text content in the input component in response to triggering of the second reference control.

[0118] In some embodiments, the target content includes: first content associated with a first generation mode; or second content associated with a second generation mode.

[0119] In some embodiments, at least one media content includes at least a first media content and a second media content. The device 400 also includes a generation module configured to, in response to the selection of the first media content, present a generation control corresponding to the first media content in a content display area; and in response to the triggering of the generation control, update the first media content to a third media content while maintaining the presentation of the second media content, wherein the third media content is generated based on a first prompt message associated with the first media content.

[0120] In some embodiments, the device 400 further includes a third presentation module configured to present a viewing window in response to a triggering of a fourth media content in at least one media content, the viewing window presenting the fourth media content and a second prompt message for generating the fourth media content.

[0121] In some embodiments, the device 400 further includes a switching module configured to switch the interactive interface from a first generation mode to a second generation mode in response to receiving a switching request via the interactive interface.

[0122] In some embodiments, the switching module is further configured to: present multiple switching entrances in the interactive interface, the multiple switching entrances corresponding to multiple media generation modes; and, in response to the selection of a target switching entrance among the multiple switching entrances associated with a second generation mode, switch the interactive interface from a first generation mode to a second generation mode.

[0123] In some embodiments, the switching module is further configured to: present a switching control for switching media generation modes in the input component; and switch the input component to a second generation mode via the switching control.

[0124] In some embodiments, the providing module 430 is further configured to: present response content generated by the agent based on the generation request in the content display area; and stop presenting a portion of the text content of the response content in the content display area in response to at least one piece of media content being presented in the response content.

[0125] In some embodiments, the device 400 further includes a viewing module configured to present a viewing control associated with a portion of the text content in the response content; and to present a portion of the text content of the response content in a content display area in response to triggering the viewing control.

[0126] The modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 400 may be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0127] Figure 5 A block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to implement the electronic device 110 discussed above.

[0128] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processing units or processors 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processor 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0129] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0130] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0131] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0132] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0133] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0134] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should 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-readable program instructions.

[0135] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0136] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0137] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0138] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A content generation method, comprising: An interactive interface associated with the intelligent agent is presented, the interactive interface including a content display area and input components; In the content display area, a media generation history is presented, which is associated with multiple media generation modes. The multiple media generation modes include at least a first generation mode associated with the agent and a second generation mode independent of the agent. as well as In response to receiving a generation request via the input component, at least one piece of media content generated by the agent based on the generation request is provided in the content display area, the at least one piece of media content being generated based on at least a portion of the media generation history.

2. The method according to claim 1, further comprising: Based on the selection of target content in the media generation history, reference information associated with the target content is presented in the input component; as well as The generation request associated with the target content is obtained via the input component.

3. The method of claim 2, wherein presenting reference information associated with the target content in the input component based on the selection of target content in the media generation history includes: In response to the selection of historical media content in the media generation history, a first reference control is presented; as well as In response to the triggering of the first reference control, the reference information associated with the historical media content is presented in the input component.

4. The method of claim 3, wherein obtaining the generation request associated with the target content via the input component comprises: Input content is obtained via the input component, and the input content indicates a reference dimension associated with the historical media content; as well as The generation request is constructed based on the input content and the historical media content.

5. The method according to claim 4, wherein the historical media content includes multiple types of historical media content, and the method further includes: Based on the order of the multiple historical media contents in the input component, the reference dimension corresponding to at least one of the multiple historical media contents is determined from the input content.

6. The method of claim 2, wherein presenting reference information associated with the target content in the input component based on the selection of target content in the media generation history includes: In response to the selection of text content in the media generation history, a second reference control is presented; as well as In response to a triggering of the second reference control, the reference information associated with the text content is presented in the input component.

7. The method according to claim 2, wherein the target content includes: The first content associated with the first generation mode; or The second content associated with the second generation mode.

8. The method according to claim 1, wherein the at least one media content includes at least first media content and second media content, and the method further includes: In response to the selection of the first media content, a generation control corresponding to the first media content is presented in the content display area; as well as In response to the triggering of the generation control, the first media content is updated to the third media content while the second media content is still presented, the third media content being generated based on the first prompt information associated with the first media content.

9. The method according to claim 1, further comprising: In response to a triggering of a fourth media content among the at least one media content, a viewing window is presented, the viewing window presenting the fourth media content and a second prompt message for generating the fourth media content.

10. The method according to claim 1, further comprising: In response to receiving a switching request via the interactive interface, the interactive interface is switched from the first generation mode to the second generation mode.

11. The method of claim 10, wherein switching the interactive interface from the first generation mode to the second generation mode comprises: The interactive interface presents multiple switching entry points, which correspond to the various media generation modes. as well as In response to the selection of a target switching entry associated with the second generation mode among the plurality of switching entries, the interactive interface is switched from the first generation mode to the second generation mode.

12. The method of claim 10, wherein switching the interactive interface from the first generation mode to the second generation mode comprises: The input component includes a toggle control for switching media generation modes; as well as The input component is switched to the second generation mode via the switching control.

13. The method of claim 1, wherein providing at least one piece of media content generated by the agent based on the generation request in the content display area comprises: In the content display area, the response content generated by the intelligent agent based on the generation request is presented; as well as In response to the presentation of at least one piece of media content in the response content, the presentation of a portion of the text content of the response content in the content display area is stopped.

14. The method of claim 13, further comprising: The response content includes a view control associated with the specified text content. as well as In response to a triggering of the viewing control, a portion of the text content of the response content is presented in the content display area.

15. An apparatus for content generation, comprising: The first presentation module is configured to present an interactive interface associated with the intelligent agent, the interactive interface including a content display area and input components; The second presentation module is configured to present a media generation history in the content display area. The media generation history is associated with multiple media generation modes, which include at least a first generation mode associated with the agent and a second generation mode independent of the agent. as well as A providing module is configured to, in response to receiving a generation request via the input component, provide in the content display area at least one piece of media content generated by the agent based on the generation request, the at least one piece of media content being generated based on at least a portion of the media generation history.

16. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processor.

17. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 14.

Images