Interaction method for multimedia content, and device, medium and program product

Abstract

Provided in the embodiments of the present disclosure are an interaction method for multimedia content, and a device, a storage medium and a computer program product. The method comprises: in response to a trigger operation, displaying a dialog interface for generating multimedia content; in response to receiving a request for generating multimedia content, displaying in the dialog interface a multimedia content outline associated with multimedia content to be generated; and on the basis of a multimedia generation instruction, displaying generated multimedia content, wherein the multimedia generation instruction indicates confirmation of the multimedia content outline or confirmation of an edited multimedia content outline in the dialog interface. On the basis of the method in the embodiments of the present disclosure, a multimedia content outline can be provided to a user before multimedia content is generated, and by means of a user-friendly interaction interface, the user can perform an editing operation on the multimedia content outline, so as to obtain multimedia content meeting his / her personalized requirements, thereby improving the user experience.

Description

Interaction method, device, medium and program product for multimedia content TECHNICAL FIELD

[0001] The present disclosure relates generally to the field of computers, and more particularly to an interaction method, an electronic device, a computer-readable storage medium, and a computer program product for multimedia content. BACKGROUND

[0002] With the continuous development of artificial intelligence (AI) technology, its application scenarios are also expanding, and gradually covering various fields. For example, from smart home to agriculture, from retail to manufacturing, the application of AI technology is affecting people's life and work. In addition, AI technology is also widely used in finance, education, transportation, medical treatment and other fields, and has brought great impetus to the development of society and economy.

[0003] SUMMARY

[0004] According to an example embodiment of the present disclosure, an interaction method, an electronic device, a computer storage medium, and a computer program product for multimedia content are provided.

[0005] In a first aspect of the present disclosure, an interaction method for multimedia content is provided, comprising: in response to a trigger operation, displaying a dialogue interface for generating multimedia content; in response to receiving a request for generating multimedia content, displaying a multimedia content outline associated with the multimedia content to be generated in the dialogue interface; and based on a multimedia generation instruction, displaying the generated multimedia content, wherein the multimedia generation instruction indicates confirmation of the multimedia content outline or confirmation of the edited multimedia content outline in the dialogue interface.

[0006] In a second aspect of the present disclosure, an electronic device is provided, comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which when executed by the at least one processing unit causes the electronic device to perform the method described in the first aspect of the present disclosure.

[0007] In a third aspect of the present disclosure, a computer-readable storage medium is provided, having machine-executable instructions stored thereon, which when executed by a device cause the device to perform the method described in the first aspect of the present disclosure.

[0008] In a fourth aspect of the present disclosure, a computer program product is provided, comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method described in the first aspect of the present disclosure.

[0009] The summary section is provided to introduce a series of concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or essential features of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] 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:

[0011] Figure 1 shows a schematic diagram of an example system in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 shows a flowchart of an interactive method for multimedia content according to an embodiment of the present disclosure;

[0013] Figures 3A-3F illustrate schematic diagrams of exemplary processes for multimedia content interaction according to embodiments of the present disclosure;

[0014] Figures 4A-4D illustrate exemplary processes for editing multimedia content in an editing interface for displaying text-type multimedia content according to embodiments of the present disclosure;

[0015] Figures 5A-5D illustrate exemplary processes for editing multimedia content in an editing interface for displaying multimedia content of image type according to embodiments of the present disclosure;

[0016] Figures 6A-6E illustrate schematic diagrams of a process for associating a portion of multimedia content with data information according to an embodiment of the present disclosure.

[0017] Figure 7 shows a schematic block diagram of an example apparatus according to some embodiments of the present disclosure; and

[0018] Figure 8 shows a block diagram of an example device that can be used to implement embodiments of the present disclosure. Detailed Implementation

[0019] 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.

[0020] Currently, artificial intelligence technology is applied to various application scenarios. With the continuous development of intelligent models and the continuous emergence of large-scale data sets, artificial intelligence technology has also made great progress and innovation in generating multimedia content (e.g., text, images, audio, etc.), and has brought much convenience and innovation to people's work and life. In generating multimedia content that meets the requirements, using interactive operations to maximize the satisfaction of users' personalized needs and improve user experience is also a hot research topic. Therefore, a technical solution is needed that can maximize the satisfaction of users' personalized needs and improve user experience in the process of multimedia content generation through interactive operations.

[0021] Therefore, embodiments of the present disclosure provide an interactive method for multimedia content. The method can include: in response to a trigger operation, displaying a dialogue interface for generating multimedia content; in response to receiving a request for generating multimedia content, displaying a multimedia content outline associated with the multimedia content to be generated in the dialogue interface; and displaying the generated multimedia content based on multimedia generation instructions, wherein the multimedia generation instructions indicate confirmation of the multimedia content outline or confirmation of the edited multimedia content outline in the dialogue interface. By adopting the method according to the embodiments of the present disclosure, the user can be provided with a multimedia content outline before generating the multimedia content, and through a user-friendly interactive interface, the user can perform editing operations on the multimedia content outline to obtain multimedia content that meets their personalized requirements, and further improve the user experience.

[0022] Embodiments of the present disclosure will be described in detail below with further reference to the accompanying drawings, in which FIG. 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. The example environment 100 includes computing devices 110 and 120. The computing device 110 can be deployed with an intelligent model 112 (e.g., a generative intelligent model or other artificial intelligence model) that can be trained to generate various content, such as but not limited to multimedia content. The computing device 120 is also shown in FIG. 1. In some embodiments, the computing device 120 communicates with the computing device 110 through a network 130. The network 130 can include a wired network, a wireless network, or a combination thereof, for providing communication between the computing device 120 and the computing device 110. In some embodiments, the computing device 120 can be connected to the computing device 110 through a data line, and the present disclosure does not limit the connection manner between the computing device 110 and the computing device 120.

[0023] Computing devices 110 and 120 can include, but are not limited to, personal computers, server computers, handheld or laptop devices, mobile devices (such as mobile telephones, personal digital assistants (PDAs), media players, and the like), multiprocessor systems, consumer electronics, wearable electronic devices, smart home devices, minicomputers, mainframe computers, edge computing devices, distributed computing systems including any of the above systems or devices, and the like.

[0024] An application (e.g., a client program) for invoking the intelligent model 112 to generate multimedia content can be installed in the computing device 120. For example, in the system 100 in FIG. 1, the computing device 120 can communicate with the computing device 110 through the network 130, and send a request to the intelligent model 112 in the computing device 110 to generate multimedia content. The intelligent model 112 in the computing device 110 can generate multimedia content in response to the request from the computing device 120 and provide the generated multimedia content to the computing device 120.

[0025] In some embodiments, the computing device 120 can display a dialogue interface for generating multimedia content in response to a triggering operation in an interface (e.g., a main interface) of the application. The computing device 120 can display a multimedia content outline associated with the multimedia content to be generated in the dialogue interface in response to receiving the request to generate multimedia content. In some embodiments, the computing device 120 can send the request to generate multimedia content to the computing device 110 to generate the multimedia content outline associated with the multimedia content based on the request to generate multimedia content by the intelligent model 112 in the computing device 110. The computing device 110 can send the generated multimedia content outline to the computing device 120 for display in the dialogue interface of the computing device 120. The computing device 120 can also obtain and display the generated multimedia content based on multimedia generation instructions, where the multimedia generation instructions indicate a confirmation of the multimedia content outline displayed in the current dialogue interface or a confirmation of the edited multimedia content outline in the current dialogue interface.

[0026] In some embodiments, a user of the computing device 120 can browse the multimedia content outline displayed in the dialogue interface and decide whether to perform an editing operation on the multimedia content outline in the current dialogue interface. If it is decided not to perform the editing operation, i.e., the user thinks that the current generated multimedia content outline meets the requirements, the multimedia generation instructions can be triggered to generate the multimedia content. In addition, the user can also perform an editing operation on the multimedia content outline, and after the editing operation ends and the desired multimedia content outline is obtained, the multimedia generation instructions can be triggered to trigger the generation of the multimedia content.

[0027] The computing device 120 can respond to the multimedia generation instruction, and send an instruction to generate multimedia content to the computing device 110, so as to generate the multimedia content based on the multimedia outline confirmed by the user (the multimedia outline after the editing operation or the multimedia outline without the editing operation) by the intelligent model 112. The computing device 110 can send the generated multimedia content to the computing device 120, and display in the interface of the computing device 120, for example, the multimedia content editing interface.

[0028] It can be understood that although the intelligent model 112 is deployed in the computing device 110 in FIG. 1, according to actual needs, the intelligent model 112 can be split into multiple sub-models, and each sub-model can be deployed in a corresponding computing device, achieving distributed deployment, for example, to support large-scale models. Accordingly, the corresponding computing device can send the generated information to the computing device 120 and display in response to the request or instruction from the computing device 120.

[0029] In addition, although the intelligent model 112 is shown as being deployed separately from the computing device 120 in FIG. 1, it can be understood that as the intelligent model 112 is lightened, the intelligent model 112 can also be deployed locally on the computing device 120, so as to be able to respond to the request of the user more quickly and generate the corresponding information. When the intelligent model 112 is deployed locally on the computing device 120, the interaction method of the corresponding multimedia content is similar to the process described in combination with FIG. 1, and those skilled in the art can understand the description above, and for the sake of brevity, the description is not repeated here.

[0030] According to the interaction method for multimedia content according to the embodiments of the present disclosure, the user can be provided with the multimedia outline before the multimedia content is generated, and through the user-friendly interaction interface, the user can perform the editing operation on the multimedia outline, so as to obtain the multimedia content meeting the individual requirements of the user, and further improve the user experience.

[0031] The block diagram of the example environment 100 in which the embodiments of the present disclosure can be implemented is described above in combination with FIG. 1. The interaction method for multimedia content according to the embodiments of the present disclosure is described below in combination with FIG. 2. FIG. 2 shows a flowchart of the interaction method 200 for multimedia content according to the embodiments of the present disclosure. The method 200 can be executed at the computing device 120 in FIG. 1 and any suitable computing device. It should be understood that the numbering in the flowchart of the method 200 does not represent the execution order of the steps, some or all of the steps can be executed in parallel, or the execution order can be interchanged, and the present disclosure does not limit this. In addition, the method 200 in FIG. 2 can also include additional steps not shown and / or the steps shown can be omitted, and the scope of the present disclosure is not limited in this respect.

[0032] In block 202, the computing device 120 can display a dialogue interface for generating multimedia content in response to a triggering operation. In some embodiments, an application (e.g., a client program) that invokes the intelligent model 112 to generate multimedia content can be installed in the computing device 120, so that the interaction method for multimedia content according to embodiments of the present disclosure can be performed.

[0033] In some embodiments, the computing device 120 can start the application, and display a triggering control in an interface after the application is started (e.g., a start interface or a main interface of the application). The user can start the triggering operation by clicking or touching the triggering control. For example, the triggering control can be a button control displayed in the current interface. Alternatively, the user can also start the triggering operation by means such as voice. The specific implementation of the triggering operation is not limited in the present disclosure.

[0034] The computing device 120 can display a dialogue interface for generating multimedia content in response to the triggering operation from the user. In the dialogue interface, an input area and an information display area can be included. The input area can receive the input information of the user, and transmit the input information to the intelligent model 112 in the computing device 110, so that the model 112 generates a corresponding result according to the input information of the user and sends the result to the computing device 120. The computing device 120 can display the received result in the information display area to facilitate the user to browse.

[0035] In block 204, the computing device 120 can display a multimedia content outline associated with the multimedia content to be generated in the dialogue interface in response to receiving a request for generating the multimedia content.

[0036] In some embodiments, the computing device 120 can receive a request for generating multimedia content input into the input area in the dialogue interface. In some embodiments, the request can include prompt information associated with the multimedia content to be generated. The prompt information can represent the relevant content (e.g., theme, etc.) of the multimedia content to be generated, the information size (e.g., word count in the case of text information, resolution size in the case of image information, etc.), the keywords in the generated content, the application field, and the like.

[0037] The computing device 120 can display, in the conversation interface, a multimedia content outline associated with the multimedia content to be generated, in response to receiving the request to generate the multimedia content. In some embodiments, the computing device 120 can send the received request to generate the multimedia content to the intelligent model 112, to generate, by the model 112, the multimedia content outline associated with the multimedia content based on the request. The computing device 120 can obtain the multimedia content outline generated by the model 112, and display the obtained multimedia content outline in the current conversation interface, e.g., the multimedia content outline can be displayed in an information display area in the conversation interface for the user to browse.

[0038] In some embodiments, the multimedia content outline can represent the structure of the multimedia content to be generated in the form of multiple levels, and each level includes at least one section. For example, a multimedia content outline including two levels, a first level including two sections and a second level including three sections, represents that the structure of the multimedia content is divided into two sections, and there are two sub-sections in the first section and three sub-sections in the second section. In addition, a brief introduction is provided for each level and each section in the corresponding level in the multimedia content outline, indicating the main content of the generated multimedia content in the corresponding section.

[0039] By displaying the multimedia content outline for the user in the conversation interface, the user can understand the outline of the multimedia content to be generated before obtaining the generated multimedia content, so as to facilitate the user to determine whether to adjust the multimedia content outline in the later step to obtain a more required or demanded multimedia content.

[0040] In block 206, the computing device 120 can display the generated multimedia content based on the multimedia generation instruction. In some embodiments, the multimedia generation instruction indicates the confirmation of the multimedia content outline or the confirmation of the edited multimedia content outline in the conversation interface.

[0041] In some embodiments, the computing device 120 displays the multimedia content outline in, for example, an information display area in the conversation interface. The displayed multimedia content outline can be editable. In other words, the computing device 120 can receive an editing operation of the multimedia content outline by the user in the information display area in the conversation interface, and display the edited or adjusted multimedia content outline based on the received editing operation.

[0042] In some embodiments, the computing device 120 can send the received editing operation for the multimedia content outline to the intelligent model 112 to adjust the multimedia content outline based on the user’s editing operation by the intelligent model 112. The computing device 120 can obtain the multimedia content outline adjusted by the intelligent model 112 and display the adjusted multimedia content outline in the information display area in the conversation interface. In some embodiments, the user can perform the editing operation for the multimedia content outline multiple times to obtain a multimedia outline that meets the requirements.

[0043] In some embodiments, the intelligent model 112 can further adjust its parameters based on the user’s editing operation to provide the user with generated content that meets the user’s requirements in the subsequent multimedia content generation process for the user.

[0044] In addition, in some embodiments, after the computing device 120 displays the generated multimedia content outline in block 204, the user can determine that the multimedia content outline currently displayed in the conversation interface meets the requirements by browsing the generated multimedia content outline and can not edit the multimedia content outline.

[0045] In some embodiments, when the user determines that the multimedia content outline after the editing operation or the multimedia content outline without the editing operation meets the requirements, the user can issue a multimedia generation instruction to the computing device 120 by clicking or touching the control for generating multimedia. The computing device 120 can send the instruction to the intelligent model 112 to generate corresponding multimedia content based on the multimedia content outline after the editing operation or without the editing operation by the intelligent model 112. The computing device 120 (for example, an application installed in the computing device 120) can obtain the generated multimedia content from the intelligent model 112 and display the multimedia content.

[0046] In some embodiments, the hierarchy of the generated multimedia content corresponds to the hierarchy of the outline, and the content in each hierarchy in the multimedia content is generated based on the introduction in the corresponding hierarchy in the outline. For example, taking the case that the generated multimedia content is text content, each part in each hierarchy in the text corresponds to each part in each hierarchy in the outline respectively, and the content of each part in each hierarchy in the text is generated based on the introduction of each part in each hierarchy in the outline. Taking the case that the generated multimedia content is video image content, the video image can be divided into multiple hierarchies according to the content dimension, each part in each hierarchy in the video image corresponds to each part in each hierarchy in the outline respectively, and the content of each part in each hierarchy in the video image is generated based on the introduction of each part in each hierarchy in the outline. Taking the case that the generated multimedia content is audio content, the audio content can be similarly divided into multiple hierarchies according to the content dimension, each part in each hierarchy in the audio corresponds to each part in each hierarchy in the outline respectively, and the content of each part in each hierarchy in the audio is generated based on the introduction of each part in each hierarchy in the outline. In addition, the generated multimedia content can also be corresponded to the multimedia content outline according to other dimensions, which is not limited in the present disclosure.

[0047] In some embodiments, in response to the received multimedia generation instruction, the computing device 120 can jump from the dialogue interface to the multimedia content editing interface, and display the obtained multimedia content in the multimedia content editing interface, so as to facilitate the user to perform editing operation on the multimedia content. In some embodiments, the generated multimedia content can include one or more of the following types: text, image or audio, and different types of multimedia content can be displayed in the multimedia content editing page of the corresponding type. For example, the multimedia content can include a document with text information, accordingly, the generated document can be displayed in the document editing interface. The multimedia content can also include image content (for example, static image or video image, etc.) with image information, accordingly, the generated image content can be displayed in the image editing interface. The multimedia content can include multimedia content with audio information, accordingly, the generated audio content can be displayed in the audio editing interface.

[0048] Thus, according to the interaction method for multimedia content provided by the embodiments of the present disclosure, the user can be provided with a multimedia content outline before the multimedia content is generated, and through the user-friendly interaction interface, the user can perform editing operations on the multimedia content outline, so as to obtain the multimedia content meeting the personalized requirements of the user, and further improve the user experience. For example, the user can perform editing operations on the displayed multimedia content outline in the dialogue interface, and can also perform editing operations on the generated multimedia content in the multimedia content editing page. By providing the user with a friendly interface that can be edited, the processing capability of the intelligent model 112 can be fully utilized through the interaction operation, so that the content meeting the user's requirements and personalized requirements can be provided in the content generation process, thereby further improving the user experience.

[0049] The interaction process for multimedia content will be described below in conjunction with FIGS. 3A-3F. FIGS. 3A-3F show schematic diagrams of an exemplary process for multimedia content interaction according to an embodiment of the present disclosure. FIGS. 3A-3F show schematic diagrams of an interaction interface 300 in the generation process of multimedia content of an application program installed on the computing device 120 for invoking the intelligent model 112 according to an embodiment of the present disclosure. It can be understood that the interaction interface in FIGS. 3A-3F is only schematic, and the interaction interface 300 can be displayed accordingly according to the different types of the computing device 120.

[0050] FIG. 3A shows a schematic diagram 300 of an interface of a dialogue interface displayed by the computing device 120 for generating multimedia content based on a trigger operation. The schematic diagram 300 in FIG. 3A can include a control area 310 and a dialogue interface 320. The control area 310 displays a plurality of controls associated with the application program “XXXX”, such as a first control 3111, a second control 3112, and a third control 3112. Each control can be used to trigger a corresponding function in the application program. For example, the first control 3111 can trigger the generation of multimedia content, the second control 3112 can trigger a search function, and the third control 3113 can trigger a translation function, and the like. Although three controls are shown in FIG. 3A, this is only exemplary. According to the types of functions that can be supported by the application program, the number of controls can be different. In some embodiments, a plurality of controls can be displayed in the control area 310 by triggering the “new dialogue” control 311 in the control area 310.

[0051] In addition, the control area 310 can also include a “recent dialogue” control 313 for displaying historical dialogue information and a favorites control 315. It can be understood that other types of controls can also be provided in the control area 310 according to requirements, which are not limited in the present disclosure.

[0052] In response to the triggering of the first control 3111 (e.g., the first control 3111 corresponds to a function for generating multimedia content), the computing device 120 displays a dialog interface 320 in the interface 300. The dialog interface 320 can include an information display region 340 and an input region 360. Various information associated with the generation of the multimedia content can be displayed in the information display region 340. The input region 360 includes a dialog box 362 for receiving information input by the user to further implement the interaction with the user.

[0053] As shown in FIG. 3A, in response to the triggering operation of the first control 3111, the computing device 120 can determine that the function for generating multimedia content is initiated. Accordingly, the computing device 120 displays the dialog interface 320 in the interface 300. The computing device 120 can display prompt information for the user in the information display region 340 in the dialog interface 320, which in some embodiments can include the type or style of the multimedia content to be generated for the user to select. Based on the selection of the type by the user, the application can utilize the intelligent model 112 to generate and display the multimedia content corresponding to the selected type for the user.

[0054] FIG. 3B is a schematic diagram of receiving a request for generating multimedia content in the input region 360 in the dialog interface 320. In the example of FIG. 3B, the user selects the first type displayed in the information display region 340 and inputs a request for generating multimedia content in the input region 360. In some embodiments, the request can include prompt information associated with the multimedia content to be generated. The prompt information can indicate the relevant content (e.g., theme, etc.), information size (e.g., word count in the case of text information, resolution size in the case of image information, etc.), keyword, application field, etc. of the multimedia content to be generated. For example, the request information in FIG. 3B can be “Please generate multimedia content about field A, including keyword B, with size C”.

[0055] In response to receiving the request for generating multimedia content input in FIG. 3B, the computing device 120 displays a multimedia content outline associated with the multimedia content to be generated in the dialog interface 320. In some embodiments, the multimedia content outline is editable. That is, the computing device 120 can receive an editing operation of the multimedia content outline by the user in the dialog interface 320 and display the edited multimedia content outline.

[0056] Figures 3C and 3D show a schematic diagram of displaying the editable multimedia content outline in the conversation interface 320 in response to receiving the request of generating the multimedia content according to an embodiment of the present disclosure. Figure 3C shows a first schematic diagram of displaying the multimedia content outline in the interface 300. As can be seen from Figure 3C, due to the limitation of the interface length, the conversation interface 320 does not display the multimedia content outline completely, and thus the user can continuously display the multimedia content outline in the interface 320 by operating the input device such as a mouse, and the remaining part of the multimedia outline is displayed in the conversation interface 320 as shown in Figure 3D.

[0057] In some embodiments, the multimedia content outline can include a plurality of levels, each level can include a plurality of sections, and each section in each level includes at least one corresponding sub-section. Taking the multimedia content outline shown in Figures 3C and 3D as an example, the multimedia content outline includes two levels, and the first level includes three sections: the first section 351, the second section 352, and the third section 353. The second level includes: the first sub-section and the second sub-section in the first section 351, the third sub-section, the fourth sub-section, and the fifth sub-section in the second section 352, and the sixth sub-section in the third section 353. Figure 3C only displays the third sub-section in the second section 352, and Figure 3D displays the remaining part of the multimedia content outline. It can be understood that the multimedia content outline in Figures 3C and 3D is only schematic, and the intelligent model 112 can generate a multimedia content outline with different numbers of levels and corresponding sections and divided sub-sections in each level according to the prompt information of the multimedia content to be generated.

[0058] In some embodiments, the multimedia content outline is editable. Accordingly, the computing device 120 can display the edited multimedia content outline according to the editing operation of the user on the multimedia content outline in the conversation interface 320. In some embodiments, the editing operation can include: adjusting at least one section in the corresponding level (for example, adding one or more new sections in the corresponding level; deleting one or more sections in the corresponding level; regenerating one or more new sections in the corresponding level); adjusting at least one sub-section in the corresponding section (for example, including: adding one or more new sub-sections in the corresponding section in the corresponding level; deleting one or more sub-sections in the corresponding section to which the editing operation is directed; regenerating one or more new sub-sections in the corresponding section); adjusting the order of a plurality of sub-sections in the corresponding section to which the editing operation is directed; setting the content size of the corresponding section; instructing to generate an image in the corresponding section, and displaying the attribute of the image to be generated in the corresponding section, etc.

[0059] An exemplary implementation of editing operations on a multimedia outline will be described below in conjunction with the accompanying drawings. FIG. 3E shows a schematic interface diagram 300 of adding a new section in a corresponding hierarchy, according to an embodiment of the present disclosure. In response to receiving a click or touch operation of a user on the control of "Add Section" in section 354 in FIG. 3D, the computing device 120 displays the dialogue interface 320 after adding a new section 355, as shown in FIG. 3E. In the new section 355, a prompt information is displayed, prompting the user to input a title of the section. In some embodiments, the computing device 120 sorts the subsections (e.g., the seventh subsection) in the new section according to the multimedia content outline that has been generated, and prompts the user to input a title and introduction for the subsection. In addition, the added section 355 can also be provided with a control for setting the content size of the section.

[0060] In addition, by setting a corresponding control, the computing device 120 can also delete one or more sections in a corresponding hierarchy in response to a triggering operation of a user on the control. In some embodiments, by setting a corresponding control, the computing device 120 can also regenerate a new one or more sections in a corresponding hierarchy in response to a triggering operation of a user on the control.

[0061] In some embodiments, the editing operations on the multimedia content outline can also include adjusting at least one subsection in a corresponding section, for example, adding a new subsection in a corresponding section in a corresponding hierarchy. Each section shown in FIGS. 3C and 3D is provided with a control for adding a subsection in the section, as indicated by "+" in FIGS. 3C and 3D. In response to a click or triggering of the adding subsection control, the computing device 120 can add a subsection in the corresponding section, and display a prompt information for setting the subsection. The present disclosure does not limit the specific implementation.

[0062] In some embodiments, adjusting at least one subsection in a corresponding section can also include deleting a subsection in the corresponding section that the editing operation is directed to. For example, each section shown in FIGS. 3C and 3D is provided with a control for deleting a subsection in the section, as indicated by "X" in FIGS. 3C and 3D. In response to a click or triggering of the deleting subsection control, the computing device 120 can delete a pre-selected subsection in the corresponding section.

[0063] In some embodiments, adjusting at least one sub-section in the corresponding section can further include regenerating one or more updated sub-sections in the section to which the editing operation is directed. For example, as illustrated in FIGS. 3C and 3D, each section is provided with a control for regenerating a sub-section in the section, as illustrated by the “R” in FIGS. 3C and 3D. In response to a click or a trigger of the regenerating sub-section control “R”, the computing device 120 can regenerate an updated sub-section in the corresponding section. In some embodiments, in response to a trigger of the regenerating sub-section control “R”, the computing device 120 can send a request to regenerate a sub-section in the section to the intelligent model 112 to regenerate the sub-section in the section by the model 112, and display the regenerated sub-section to the user via the computing device 120. In some embodiments, the regenerated sub-section can have a different number, title, introduction, etc. than the previous sub-section.

[0064] In some embodiments, the editing operation on the multimedia content outline can further include sequentially adjusting a plurality of sub-sections in the section to which the editing operation is directed. For example, as illustrated in FIGS. 3C and 3D, each section is provided with a control for sequentially adjusting the sub-sections in the section, as illustrated by the “O” in FIGS. 3C and 3D. In response to a click or a trigger of the sequentially adjusting sub-section control “O”, the computing device 120 can reorder all the sub-sections in the corresponding section, and display the reordered sub-sections in the current section.

[0065] In some embodiments, the editing operation on the multimedia content outline can further include setting a content size in the corresponding section. The content size can have different metrics depending on the type of the multimedia content. For example, for text, the content size can include the number of words in the text. For example, for images, the content size can include the resolution of the images, etc. In some embodiments, the computing device 120 can provide a control for setting the corresponding content size to the user in each section. The computing device 120 can set the size of the multimedia content in the corresponding section in response to the user's control of the control. For example, taking a control of a sliding type as an example, in response to the user sliding the control in a first direction, the content size can be increased based on the currently set content size; in response to the user sliding the control in a second direction opposite to the first direction, the content size can be decreased based on the currently set content size. Other ways of adjusting the content size in the corresponding section are not limited by the present disclosure.

[0066] In some embodiments, the editing operation on the multimedia content outline can further include an instruction to generate an image in the corresponding section, and further display attributes of the image to be generated in the corresponding section. In some embodiments, the corresponding section is further provided with a control to generate the image in the section. In response to receiving a triggering operation of the control by the user, the computing device 120 can display the attributes of the image to be generated in the corresponding section. The attributes can include, but are not limited to, a description of the image, image size, etc. In some embodiments, the image can be generated by the intelligent model 112 based on the displayed attribute information. FIG. 3F shows a schematic diagram of an interface 300 for instructing to generate an image in the corresponding section according to an embodiment of the present disclosure. As shown in FIG. 3F, in response to receiving a triggering operation of the image generation control (not shown) in the first section 351 by the user, the computing device 120 can display the attributes of the image (e.g., an AI image) to be generated in the image attribute information display area 3511 in the first section 351, as shown as “one black and white image with design sense” in FIG. 3F.

[0067] The editing operation on the multimedia content outline according to an embodiment of the present disclosure described above in combination with the drawings can be understood that the above editing operation is only illustrative, and the corresponding editing operation can be set according to the requirements, and the present disclosure does not limit this.

[0068] Returning to FIG. 3E, FIG. 3E shows a control 380 for generating multimedia content. In some embodiments, when the user completes the editing operation on the multimedia content outline, the user can issue a multimedia generation instruction by triggering the control 380 to start the generation of the multimedia content. In some embodiments, the computing device 120 can obtain the multimedia content generated based on the edited multimedia content outline in response to the received multimedia generation instruction, and display the generated multimedia content. For example, the computing device 120 can send the received multimedia generation instruction to the intelligent model 112, obtain the multimedia content generated by the intelligent model 112 based on the edited multimedia content outline, and display the obtained multimedia content.

[0069] In some embodiments, when the multimedia content outline generated by the intelligent model 112 meets the user's requirements, the user can not edit the multimedia content outline, but directly obtain the generated multimedia content based on the generated multimedia content outline. As shown in FIG. 3D, the user can click or touch the generated multimedia content control 380 displayed in FIG. 3D without editing the multimedia content outline to start the generation of the multimedia content. The intelligent model 112 can generate the multimedia content based on the unedited multimedia content outline. Accordingly, the computing device 120 can obtain the multimedia content generated from the intelligent model 112, and display the multimedia content.

[0070] In some embodiments, in addition to generating the multimedia content outline, a title recommendation 340 for the multimedia content to be generated can also be provided in the conversation interface 320 (as shown in FIGS. 3C and 3F). In some embodiments, the title can also be edited.

[0071] As shown in FIGS. 3D and 3E, a modification control 374 can also be provided in the conversation interface 320. The modification control 374 can be used to indicate further modification to the outline and / or title. For example, the modification control 374 can include a control to indicate further expansion of the outline, replacement of the title recommendation, further search and update of the multimedia content outline, etc.

[0072] In some embodiments, the intelligent model 112 can search, according to the request for generating the multimedia content, the profile information set for the prompt information in the request for generating the multimedia content, and generate the multimedia content outline based on the searched profile information. The intelligent model 112 can also generate the multimedia content outline based on the request for generating the multimedia content. The computing device 120 can obtain the multimedia content outline generated based on the request or the searched profile information.

[0073] In some embodiments, in the case that the intelligent model 112 searches the profile information, the intelligent model 112 can also provide the searched profile information to the computing device 120, so that the computing device 120 can obtain the profile information related to the multimedia content to be generated. In some embodiments, the computing device 120 can display the title information of the obtained profile information in a reference profile area 370 of the conversation interface 320. As shown in FIG. 3E, the reference profile area 370 can be displayed adjacent to the multimedia content outline. The reference profile area 370 displays the titles of the profile information obtained by the computing device 120 and associated with the multimedia content to be generated, as indicated by the “title of first reference profile information”, “title of second reference profile information”, and “title of third reference profile information” in the area 370 in FIG. 3E. In addition, the computing device 120 can also display various other information related to the corresponding reference profile in the reference profile area 370, so as to facilitate the user to browse.

[0074] In some embodiments, the reference information displayed in the reference area 370 can also include user-uploaded information. In some embodiments, the reference area 370 can also be provided with controls for updating the display of reference information, such as a control for adding reference information and a control for deleting reference information. The computing device 120 can update the display of the reference area 370 in response to receiving an update operation for the reference area 370. For example, in response to an add operation for reference information, the computing device 120 can display the title of the added reference information in the reference area 370; and in response to a delete operation for reference information, the computing device 120 can display the titles of the remaining reference information after the corresponding reference information is deleted in the reference area 370.

[0075] In some embodiments, the computing device 120 can display the updated reference area 370. Further, the computing device 120 can also send the updated reference information to the intelligent model 112 for updating the multimedia content outline based on the updated reference information by the model 112. Accordingly, the computing device 120 can display the updated multimedia content outline.

[0076] In some embodiments, in response to the received multimedia generation instruction, the computing device 120 can jump from the conversation interface 320 to a multimedia content editing interface, and the generated multimedia content is displayed in the multimedia content editing interface. In some embodiments, the type of the generated multimedia content can include one or more of the following types: text, image, or audio, and accordingly, different types of multimedia content are displayed in the corresponding type of multimedia content editing interface.

[0077] FIGS. 4A-4D illustrate schematic diagrams of an exemplary process of editing multimedia content in an editing interface for displaying text type of multimedia content, according to embodiments of the present disclosure. FIG. 4A illustrates a schematic diagram 400 after jumping from the conversation interface 320 in FIG. 3E or FIG. 3D to a text content editing interface 410 in response to a multimedia generation instruction. The interface 400 shown in FIG. 4A can include a multimedia content editing interface area 410 and a control area 420. The generated text content, for example, the text content generated according to the multimedia content outline in FIG. 3E or FIG. 3D, can be displayed in the multimedia content editing interface area 410. Accordingly, the multimedia content title, the first section title, the first sub-section title, the second sub-section title, the second section title, the third sub-section title, etc. are displayed in the multimedia content editing interface 410. And below each sub-title, the corresponding text content is displayed. The structure of the generated text content corresponds to the hierarchy of the previously generated multimedia content outline.

[0078] As shown in FIG. 4A, the interface 400 can further include a control area 420 for displaying various controls for facilitating user operations. Take the example in FIG. 4A for illustration. The control area 420 can include an "add section" control 430 for adding a corresponding section to the generated multimedia content for adjusting the generated content. In addition, the control area 420 can further include controls such as a control 452 for adjusting the size of the multimedia content, a control 454 for changing the title of the multimedia content, and a control 456 for searching for related information, etc. In some embodiments, the control area 420 can further include an input sub-area 462, similar to the input area 362 in FIGS. 3A-3F, for receiving user input information and can initiate a new dialog interface.

[0079] It can be understood that the controls displayed in the control area 420 in FIG. 4A are only illustrative, and those skilled in the art can configure various types of other controls in the control area 420 as needed, which are not limited in the present disclosure.

[0080] In some embodiments, the computing device 120 can display the adjusted multimedia content in response to the editing operation on the multimedia content received in the multimedia content editing interface 410. In some embodiments, the computing device 120 can determine the section to be edited in the multimedia content in response to the selection operation on at least one section of the multimedia content, and can further display the adjusted multimedia content in response to the editing operation on the section to be edited.

[0081] FIG. 4B shows a schematic diagram of selecting the section to be edited in the multimedia content editing interface 410. The user can select the section to be edited 411 by frame selection. The section to be edited can be highlighted to prompt the user. In addition, after determining the section to be edited 411, the computing device 120 can further display an editing operation selection box 421 in the multimedia content editing interface 410 for providing the user with the editing operation to be selected.

[0082] In some embodiments, in response to the triggering operation of the user on the editing operation selection box 421, the editing operation selection box 421 can be expanded into two parts: an instruction input box 422 and an operation selection box 424. The instruction selection box 422 can be used to receive the instruction input by the user or search, inquire, etc. Various types of editing operations are listed in the operation selection box 424 for the user to select.

[0083] FIG. 4C illustrates a schematic diagram of displaying the instruction input box 422 and the operation selection box 424 in response to the user’s triggering operation on the edit operation selection box 421. The operations listed in the operation selection box 424 in FIG. 4C are operations performed on the selected text content, which can include at least one of the following: writing a continuation to the to-be-edited portion; writing an expansion to the to-be-edited portion; writing an abridgment to the to-be-edited portion; polishing (e.g., for text content) the to-be-edited portion; generating a content extract (e.g., a summary) corresponding to the to-be-edited portion based on the to-be-edited portion; adjusting the tone of the to-be-edited portion; translating the to-be-edited portion; correcting the grammar of the to-be-edited portion; or generating an image based on the to-be-edited portion, etc. In addition, the operation selection box 424 can also include search and reference operations, as well as inquiry operations, etc.

[0084] In some embodiments, the computing device 120 can send the user-selected edit operation (e.g., “expansion”) instruction to the intelligent model 112 for editing the to-be-edited portion according to the user’s edit operation instruction by the intelligent model 112. The intelligent model 112 can send the content after the edit operation to the computing device 120 and display it.

[0085] In some embodiments, in response to the edit operation on the to-be-edited portion, the computing device 120 can display the information after the edit operation in a pop-up box. In response to the triggering operation on the first control in the pop-up box, the computing device 120 can insert the information after the edit operation into the multimedia content or replace the to-be-edited portion in the multimedia content.

[0086] Taking FIG. 4C as an example, in response to receiving the user’s selection of the “expansion” operation, the computing device 120 enters the interface in FIG. 4D. FIG. 4D displays the interface 400 after expanding the to-be-edited portion 411. The interface 400 displays a pop-up box 428, which displays the information after the edit operation (e.g., “expansion”). The pop-up box 428 can be provided with various types of controls, such as a “copy” control, a “regenerate” control, an “insert” control, and a “replace” control. In response to the user’s selection of the corresponding control, the computing device 120 can process the information displayed in the pop-up box 428. For example, in response to the triggering operation on the “insert” control in the pop-up box 428, the computing device 120 can insert the information after the edit operation into the multimedia content (e.g., after the to-be-edited portion 411). Alternatively, in response to the triggering operation on the “replace” control in the pop-up box 428, the computing device 120 can replace the to-be-edited portion 411 in the multimedia content with the information after the edit operation.

[0087] In some embodiments, in response to a triggering operation on the second control in the pop-up box, the computing device 120 can re-perform a corresponding editing operation (i.e., the last selected editing operation) on the information displayed in the pop-up box. The computing device 120 can display the updated information after the re-performed editing operation in the pop-up box. Through this operation, the user can be provided with the convenience of re-performing the editing operation to obtain multimedia content that is more in line with requirements.

[0088] Taking FIG. 4D as an example, in response to a triggering operation on the “regenerate” control in the pop-up box 428, the computing device 120 can perform the “expand writing” operation on the to-be-edited part 411 again. For example, the computing device 120 can send the “expand writing” instruction to the intelligent model 112 again, so that the intelligent model 112 performs the editing operation on the to-be-edited part again according to the instruction. The intelligent model 112 sends the content after the re-performed editing operation to the computing device 120 and displays it. Thus, the updated information after the re-performed editing operation is displayed in the pop-up box 428. The user can perform the above operation multiple times until the multimedia content that meets the requirements is obtained.

[0089] The above describes an exemplary process of editing text content in combination with FIGS. 4A-4D. It can be understood that multimedia content can include various types, and accordingly, the method according to the embodiments of the present disclosure can be used for other various types of multimedia content, and the generated multimedia content is edited in the corresponding multimedia content editing interface.

[0090] In the following, a process of editing image content will be described in combination with FIGS. 5A-5D. FIGS. 5A-5D show schematic diagrams of an exemplary process of editing multimedia content in an editing interface for displaying image type multimedia content according to an embodiment of the present disclosure. It can be understood that the principle of editing operation on various types of multimedia content is similar.

[0091] FIG. 5A shows a multimedia content editing interface 510 displaying image type multimedia content. The image type in FIG. 5A includes a video image. FIG. 5A also shows a control region 520, which is similar to the control region 420 in FIGS. 4A-4D, and can be understood in combination with the description of FIGS. 4A-4D above, and for the sake of brevity, will not be described here again.

[0092] In FIG. 5A, the generated image content (e.g., video content) is displayed in the player 512 of the multimedia content editing interface 510. In some embodiments, the video image can be divided into multiple levels in the content dimension, each part in each level of the video image respectively corresponds to each part in each level of the previously generated multimedia content outline, and the content of each part in each level of the video image is generated based on the introduction of each part in each level of the outline. In some embodiments, a timeline associated with the generated video content can also be displayed in the multimedia content editing interface 510 for displaying the playing progress. In addition, the timeline can also be used to select the part to be edited.

[0093] In some embodiments, the selection of the video content can be selected by the operation on the timeline. As illustrated in FIG. 5B, the corresponding time period on the timeline can be selected, and the video segment corresponding to the time period is selected as the part to be edited. For example, in FIG. 5B, the video segment corresponding to the time period between the 20th second and the 30th second 511 is selected as the part to be edited. Similar to FIG. 4B, the part to be edited can be highlighted to prompt the user. In addition, after the part to be edited is determined, the editing operation selection box 521 can be further displayed in the multimedia content editing interface 510 for providing the user with the selectable editing operations.

[0094] In some embodiments, in response to the triggering operation of the user on the editing operation selection box 521, the editing operation selection box 521 can be expanded into two parts: the instruction input box 522 and the operation selection box 524. The instruction selection box 522 is used to receive the instruction or search, inquiry, etc. input by the user. The operation selection box 524 lists various ways of operation for the user to select.

[0095] FIG. 5C illustrates the display of the instruction input box 522 and the operation selection box 524 in response to the triggering operation of the user on the editing operation selection box 521. The editing operations listed in the operation selection box 524 in FIG. 5C are the operations performed on the image content, which can include at least one of the following: adjusting (including adding, modifying or deleting, etc.) the filter of the part to be edited; adjusting (including adding, modifying or deleting, etc.) the special effect of the part to be edited; adjusting the image characteristics (such as resolution, brightness, texture, etc.) of the part to be edited; generating the content extraction (e.g., summarizing the part to be edited) corresponding to the part to be edited based on the part to be edited; adding the corresponding text content or audio content for the part to be edited; adjusting the image style of the part to be edited (e.g., adjusting to the comic style, oil painting style, etc.), etc. In addition, the operation selection box 524 can also include search and reference operations, inquiry operations, etc.

[0096] In some embodiments, the computing device 120 can send the user-selected editing operation (e.g., “adjust filter”) instruction to the intelligent model 112 for editing the to-be-edited portion according to the user’s editing operation instruction by the intelligent model 112. The intelligent model 112 can send the content after the editing operation to the computing device 120 and display.

[0097] In some embodiments, in response to the editing operation on the to-be-edited portion, the computing device 120 can display the information after the editing operation in the pop-up box. In response to the triggering operation on the first control in the pop-up box, the computing device 120 can insert the information after the editing operation into the multimedia content or replace the to-be-edited portion in the multimedia content.

[0098] Taking FIG. 5C as an example, in response to receiving the user’s selection of the “filter” operation, the computing device 120 enters the interface in FIG. 5D. In this interface, the interface after adjusting the filter on the to-be-edited portion is displayed. The pop-up box 528 is displayed in this interface, and the information after the editing operation (e.g., “adjust filter”) is displayed in the pop-up box 528. Various types of controls can be provided in the pop-up box 528, such as the “copy” control, the “regenerate” control, the “insert” control, and the “replace” control. In response to the user’s selection of the corresponding control, the computing device 120 can process the information displayed in the pop-up box 528. For example, in response to the triggering operation on the “insert” control in the pop-up box 528, the computing device 120 can insert the information after the editing operation into the multimedia content (e.g., after the to-be-edited portion). Alternatively, in response to the triggering operation on the “replace” control in the pop-up box 528, the computing device 120 can replace the to-be-edited portion in the multimedia content with the information after the editing operation.

[0099] In some embodiments, in response to the triggering operation on the second control in the pop-up box 528, the computing device 120 can re-execute the corresponding editing operation (i.e., the last selected editing operation) on the information displayed in the pop-up box. The computing device 120 can display the updated information after the re-editing operation in the pop-up box. Through this operation, the user can be provided with the convenience of re-executing the editing operation to obtain the multimedia content after the editing operation that meets the requirements.

[0100] With reference to FIG. 5D, in response to a triggering operation on the "regenerate" control in the pop-up box 528, the computing device 120 can perform the "adjust filter" operation on the to-be-edited portion again. For example, the computing device 120 can send the "adjust filter" instruction to the intelligent model 112 again, so as to edit the to-be-edited portion according to the instruction by the intelligent model 112. The intelligent model 112 sends the content after the re-editing operation to the computing device 120 and displays the content. Thus, the updated information after the re-editing operation is displayed in the pop-up box 528. The user can perform the above operation multiple times until the multimedia content meeting the requirements is obtained.

[0101] The above describes the editing operation performed on the text content and the image content with reference to FIGS. 4A-4D and 5A-5D, respectively. It can be understood that, according to the type of the generated multimedia content, the editing operation can be similarly performed as described above, and the editing operation on the audio content and the multimedia content including one or more of the audio type, the text type and the image type can be similarly understood with reference to the above description. For brevity, the description is not repeated here.

[0102] In some embodiments, the computing device 120 can associate one or more portions in the generated multimedia content with the reference information referred to in the process of generating the multimedia content, and display the associated reference information in a reference information display area in the multimedia content editing interface.

[0103] Specifically, the computing device 120 can determine a to-be-associated portion in the multimedia content based on a first selection operation of the user. The computing device 120 can further display candidate reference information associated with the to-be-associated portion based on the received triggering identifier. In some embodiments, the computing device 120 can determine reference information associated with the to-be-associated portion in the candidate reference information in response to a second selection operation of the user on the candidate reference information, and display title information of the reference information in a reference information display area in the multimedia content editing interface. In some embodiments, the index of the title information of the reference information in the reference information display area is the same as the index of the to-be-associated portion.

[0104] The illustrative process of associating and displaying the to-be-associated portion in the multimedia content with the reference information will be described below with reference to the accompanying drawings. FIGS. 6A-6E show illustrative diagrams of the illustrative process of associating and displaying the to-be-associated portion in the multimedia content with the reference information according to an embodiment of the present disclosure.

[0105] In FIG. 6A, the computing device 120 can determine the portion to be associated in the multimedia content in response to the first selection operation (such as a cursor, etc.) of the user identifying a location in the multimedia content for more than a predetermined time threshold. As illustrated in FIG. 6A, according to the indication of the cursor, the paragraph below the second sub-portion title is the portion to be associated.

[0106] In some embodiments, in response to determining the portion to be associated, the computing device 120 can further display the reference information of the portion to be associated in the information box 640 in the control area 620.

[0107] The computing device 120 can further prompt the user to input a specific identifier to browse the reference information related to the portion to be associated by the prompt information around the portion to be associated. In response to the received trigger identifier, the computing device 120 can display the candidate information associated with the portion to be associated, as shown in FIG. 6B. The reference information related to the portion to be associated and the related description thereof are shown in FIG. 6B.

[0108] In some embodiments, the computing device 120 can determine the reference information in the candidate information to be displayed in association with the portion to be associated in response to the second selection operation of the user on the candidate information. For example, as shown in FIG. 6C, the user selects the first reference information by the box selection operation. Thus, the computing device 120 can determine that the user desires to associate and display the first reference information with the portion to be associated.

[0109] The computing device 120 can display the title information of the reference information in the reference information display area of the multimedia content editing interface 610. In some embodiments, the index of the title information of the reference information in the reference information display area is the same as the index of the portion to be associated. As shown in FIG. 6D, the portion to be associated has the index “[1]”. The information of the first reference information to be displayed in association with the portion to be associated is displayed in the reference information display area in the multimedia content editing interface 610 in FIG. 6E. Exemplarily, the first reference information can be displayed via the title and other related information associated with the information, and the index of the first reference information in the reference information display area is “[1]”, which is the same as the index of the portion to be associated.

[0110] The above describes the information association and display for text content in combination with FIGS. 6A-6E. It can be understood that for multimedia content such as images, audio, etc., the operation mode of associating and displaying the corresponding portion to be associated with the reference information is similar to the process in combination with FIGS. 6A-6E, and those skilled in the art can understand it by referring to the above description, and for the sake of brevity, it is not described here.

[0111] FIG. 7 illustrates a schematic block diagram of an example apparatus 700 according to some embodiments of the present disclosure. The apparatus 700 can be implemented by software, hardware, or a combination of both. As shown in FIG. 7, the apparatus 700 includes a first display module 710, a second display module 720, and a third display module 730.

[0112] In some embodiments, the first display module 710 can display a conversation interface for generating a multimedia content in response to a triggering operation. The second display module 720 can display a multimedia content outline associated with the multimedia content to be generated in the conversation interface in response to receiving a request for generating the multimedia content. The third display module 730 can display the generated multimedia content based on a multimedia generation instruction. In some embodiments, the multimedia generation instruction indicates a confirmation of the multimedia content outline or a confirmation of the edited multimedia content outline in the conversation interface.

[0113] The apparatus 700 of FIG. 7 can be used to implement the processes described above in connection with FIGS. 1-6E, which will not be repeated here for brevity.

[0114] The division of modules or units in the embodiments of the present disclosure is illustrative only, and is merely a logical function division, and another division manner can be used in actual implementation. In addition, each functional unit in the disclosed embodiments can be integrated into one unit, or can be physically separated, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0115] FIG. 8 illustrates a block diagram of an example device 800 that can be used to implement embodiments of the present disclosure. It should be understood that the device 800 illustrated in FIG. 8 is merely an example and should not be construed as limiting the functionality and scope of the implementations described herein. For example, the device 800 can correspond to the computing device 120 described herein in connection with FIG. 1, and can be used to perform the processes described above in connection with FIGS. 1-7.

[0116] As shown in FIG. 8, the device 800 is in the form of a general-purpose computing device. Components of the computing device 800 can include, but are not limited to, one or more processors or processing units 810, a memory 820, a storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. The processing unit 810 can be a real or virtual processor and can execute various processing in accordance with programs stored in the memory 820. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the computing device 800.

[0117] The computing device 800 typically includes a plurality of computer storage media. Such media can be volatile, nonvolatile, removable, and / or non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Storage 820 can be volatile (such as RAM), non-volatile (such as ROM, EEPROM, flash memory, etc.), or some combination of the two. Storage 830 can be removable or non-removable and can include machine readable media such as flash drives, magnetic disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible by the computing device 800.

[0118] The computing device 800 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 8, a disk drive or other computer readable media drive can provide for reading from and writing to a removable, non-removable, or non-volatile media such as a floppy disk, a ZIP® disk, a magnetic tape, or an optical disk, for example. In these instances, the disk drive or other computer readable media drive can connect to the bus (not shown) by one or more data media interfaces. The memory 820 can include a computer program product 825 having one or more program modules configured to carry out the various methods or actions of the various implementations of the present disclosure.

[0119] The communication unit 840 enables communications with other computing devices over a communication media. Additionally, the functionality of the components of the computing device 800 can be implemented in a single computing cluster or multiple computer machines that are capable of communicating over a communication connection. Thus, the computing device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes in the networked environment.

[0120] Input device 850 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. Output device 860 can be one or more output devices, such as a display, a speaker, a printer, etc. Computing device 800 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through communication unit 840, and with one or more devices that enable a user to interact with computing device 800, or any devices (e.g., a network card, a modem, etc.) that enable computing device 800 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface (not shown).

[0121] According to example implementations of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to example implementations of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above. According to example implementations of the present disclosure, a computer program product is provided having a computer program stored thereon, which when executed by a processor implements the method described above.

[0122] Various aspects of the disclosure can be described in the context of flow diagrams and / or block diagrams that illustrate the functions and / or acts performed by the methods, apparatus, devices, and computer program products according to the present disclosure. It is to be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer readable program instructions.

[0123] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, 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 / acts specified in the flow diagrams and / or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flow diagrams and / or block diagrams.

[0124] The computer readable program instructions can also 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 such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0125] The computer readable program instructions can also 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 such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0126] The implementations of the disclosure have been described above with the intent to be illustrative rather than limiting. Although being shown and described in terms of certain implementations and overall functions, the implementations are not intended to exclude other implementations or technologies. Modifications and changes can be made in arrangement, operation, and details of the methods and apparatus described. Many modifications and variations of the described implementations are possible and will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. None, individually or taken in any combination, is to be treated as limiting the described implementations unless otherwise indicated.

Claims

1. A method for interaction of multimedia content, the method comprising: displaying, in response to a triggering operation, a dialogue interface for generating multimedia content; displaying, in the dialogue interface, a multimedia content outline associated with the multimedia content to be generated, in response to receiving a request for generating the multimedia content; and displaying, based on a multimedia generation instruction, the generated multimedia content, wherein the multimedia generation instruction indicates a confirmation of the multimedia content outline or a confirmation of the edited multimedia content outline in the dialogue interface.

2. The method of claim 1, further comprising: displaying, in response to an editing operation in the dialogue interface for the multimedia content outline, the edited multimedia content outline.

3. The method of claim 2, wherein displaying, based on a multimedia generation instruction, the generated multimedia content comprises: retrieving, in response to the received multimedia generation instruction, the multimedia content generated based on the edited multimedia content outline; and displaying the multimedia content.

4. The method of claim 1, wherein the request includes prompt information associated with the multimedia content to be generated.

5. The method of claim 1, wherein the multimedia content outline includes a plurality of levels, each level including at least one section, and wherein each of the at least one section includes a respective at least one sub-section.

6. The method of claim 5, further comprising: displaying, in accordance with an editing operation in the dialogue interface for the multimedia content outline, the edited multimedia content outline, wherein the editing operation includes at least one of: adjusting at least one section in a corresponding level; adjusting at least one sub-section in a corresponding section; sequentially adjusting a plurality of sub-sections in a corresponding section; setting a content size of a corresponding section; or indicating to generate an image in a corresponding section, and displaying, in the corresponding section, an attribute of the image to be generated.

7. The method of claim 1, further comprising: retrieving reference information related to the multimedia content to be generated; and retrieving the multimedia content outline generated based on at least one of the request or the reference information.

8. The method of claim 7, further comprising: displaying, in a reference area of the dialogue interface, title information of the reference information; and updating, in response to receiving an update operation for the reference area, the display of the reference area, wherein the update operation includes one or both of adding reference information or deleting the reference information.

9. The method of claim 1, further comprising: jumping, in response to the received multimedia generation instruction, from the dialogue interface to a multimedia content editing interface, wherein the generated multimedia content is displayed in the multimedia content editing interface. different types of multimedia content are displayed in corresponding types of multimedia content editing interfaces.

11. The method of claim 1, further comprising: ​ ​ ​ 10. The method of claim 9, wherein the type of multimedia content comprises one or more of the following types: text, image, or audio, and wherein, ​ ​ in response to a selection operation on at least a portion of the multimedia content, determining an editing portion in the multimedia content; and in response to an editing operation on the editing portion, displaying the multimedia content after the editing operation.

12. The method of claim 11, wherein the editing portion comprises a text portion, and wherein the editing operation on the editing portion comprises at least one of: continuing the editing portion; expanding the editing portion; abbreviating the editing portion; generating a content extract corresponding to the editing portion based on the editing portion; adjusting a tone of the editing portion; translating the editing portion; correcting a grammar of the editing portion; or generating an image based on the editing portion.

13. The method of claim 11, wherein the editing portion comprises an image portion, and wherein the editing operation on the editing portion comprises at least one of: adjusting a filter of the editing portion; adjusting a special effect of the editing portion; adjusting an image property of the editing portion; generating a content extract corresponding to the editing portion based on the editing portion; adding a corresponding text content or audio content to the editing portion; or adjusting a style of the editing portion.

14. The method of claim 11, further comprising: in response to the editing operation on the editing portion, displaying information after the editing operation in a pop-up box; and in response to a triggering operation on a first control in the pop-up box, inserting the information after the editing operation into the multimedia content or replacing the editing portion in the multimedia content.

15. The method of claim 14, further comprising: in response to a triggering operation on a second control in the pop-up box, re-executing the corresponding editing operation on the information; and displaying updated information after the editing operation in the pop-up box.

16. The method of claim 1, further comprising: in response to a first selection operation of a user, determining an association portion in the multimedia content; and in response to a received triggering identifier, displaying candidate information associated with the association portion.

17. The method of claim 16, wherein the generated multimedia content is displayed in a multimedia content editing interface, the method further comprising: in response to a second selection operation of a user on the candidate information, determining reference information in the candidate information to be associated with the association portion for display; and displaying title information of the reference information in a reference information display area of the multimedia content editing interface, wherein an index of the title information of the reference information in the reference information display area is the same as an index of the association portion.

18. An electronic device, comprising: at least one processing unit; ​ ​ ​ at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 17.

19. A computer readable storage medium having stored thereon a computer program, the computer program, when executed by a processor, implementing the method according to any one of claims 1 to 17.

20. A computer program product having stored thereon a computer program, the computer program, when executed by a processor, implementing the method according to any one of claims 1 to 17.

Images