Search

CN-121981083-A - Content generation method, device, electronic equipment and storage medium

CN121981083ACN 121981083 ACN121981083 ACN 121981083ACN-121981083-A

Abstract

The disclosure provides a content generation method, a content generation device, electronic equipment and a storage medium, and relates to the technical field of content creation and multimedia generation, in particular to the technical field of multi-mode content generation and editing. The method comprises the steps of obtaining an authoring instruction input by a user, analyzing the authoring instruction to identify an authoring intention and an authoring material contained in the authoring instruction, processing the authoring material according to the authoring intention to construct a visualized node diagram, updating the content of a designated node according to the editing instruction if the editing instruction of the user on the designated node in the node diagram is received, synchronizing the updated content into the designated node, and keeping the diagram structure of the node diagram unchanged. According to the method and the device, through accurate analysis and efficient processing of the authoring instructions, structural management and consistency maintenance of the authoring content are improved, so that consistency and consistency of content generated in the authoring process are improved, operation complexity of a user is reduced, and user experience is further improved.

Inventors

  • ZHANG JIFENG

Assignees

  • 北京百度网讯科技有限公司

Dates

Publication Date
20260505
Application Date
20251226

Claims (14)

  1. 1. A content generation method, wherein the method comprises: Acquiring an authoring instruction input by a user; Analyzing the authoring instruction to identify an authoring intention and authoring materials contained in the authoring instruction; processing the authoring material according to the authoring intention to construct a visualized node diagram; if an edit instruction of a user to a designated node in the node diagram is received, updating the content of the designated node according to the edit instruction, synchronizing the updated content to the designated node, and keeping the diagram structure of the node diagram unchanged.
  2. 2. The method of claim 1, wherein the processing the authoring material according to the authoring intent to construct a visualized node diagram comprises: if the creation intention is new content, generating a content text according to the initial text description contained in the creation material; And decomposing the content text into a plurality of independent nodes, identifying the logic relationship among the nodes, and generating a visualized node diagram according to the logic relationship among the nodes.
  3. 3. The method of claim 1, wherein the processing the authoring material according to the authoring intent to construct a visualized node diagram comprises: If the authoring intention is to edit the existing content, analyzing the existing content contained in the authored material, and constructing an initial node diagram according to an analysis result, wherein the initial node diagram contains specific text description and a relation between nodes; editing or expanding on the initial node diagram to update the content of the node diagram, thereby obtaining a visualized node diagram.
  4. 4. The method of claim 2, wherein the parsing the content text into a plurality of independent nodes and identifying logical relationships between nodes, generating a visualized node graph from the logical relationships between nodes, comprises: carrying out node splitting on the content text according to semantics by adopting a large model, and identifying logical relations among nodes; Constructing a graph structure according to the logic relationship among the nodes to obtain a node graph; and rendering the node map into a visual interface to be presented to a user, so as to obtain a visual node map.
  5. 5. The method according to claim 1, wherein, if an edit instruction of a user to a designated node in the node map is received, updating the content of the designated node according to the edit instruction, synchronizing the updated content to the designated node, and keeping the map structure of the node map unchanged, including: receiving an editing instruction of a user for a designated node in the node diagram; adjusting text description contents of the designated nodes according to the editing instruction to obtain modified text contents; Reorganizing and format-standardizing the modified text content to obtain standardized text content; Writing the standardized text content back to the designated node of the node map, wherein the node identification and map structure remain unchanged during the modification process.
  6. 6. The method of any one of claims 1 to 5, wherein the method further comprises: collecting and integrating text contents of all nodes in the node diagram to obtain a context information base; identifying core elements in the context information base, wherein the core elements refer to key elements which keep consistent in graph nodes; consistency information is generated based on the core element and previously generated visual information such that the overall content remains consistent.
  7. 7. The method of claim 6, wherein the method further comprises: receiving a media type corresponding to generated content selected by a user, wherein the media type comprises pictures, videos or audios; and generating media content corresponding to the media type according to the specific text description, the consistency information and the style instruction of the current node, and carrying out association operation on the media content and the current node.
  8. 8. The method of claim 7, wherein the method further comprises: And after the media content is generated, updating the media content of the corresponding node, and recording the version number of the media content update, wherein the structural relation of the whole node diagram is kept unchanged during the update.
  9. 9. The method of claim 8, wherein the method further comprises: receiving a generated content export selection input by a user; if the export selection is a single path, splicing the video segments of each node, and synchronizing the audio and the subtitles to obtain a complete video file; if the export selection is branching scenario export, generating independent video files for each branch, and exporting the files of each branch in parallel; if the export is selected as the export storyboard, exporting the content of each node as the storyboard in the form of a picture; If the user selects to export the complete video, synthesizing the audio, the subtitle and the video clip into a complete video file; If the user chooses to export the data exchange format graph, the topology and content of the node graph are exported as the data exchange format.
  10. 10. The method of claim 9, wherein the method further comprises: when the generated content is exported, ordering the nodes according to the topological structure of the node diagram; and splicing the contents of each node according to the ordered node sequence to generate continuous contents.
  11. 11. A content generation apparatus, wherein the apparatus comprises: The acquisition module is used for acquiring an authoring instruction input by a user; the analysis module is used for analyzing the authoring instruction to identify the authoring intention and the authoring material contained in the authoring instruction; The processing module is used for processing the authoring material according to the authoring intention so as to construct a visualized node diagram; and the updating module is used for updating the content of the appointed node according to the editing instruction if receiving the editing instruction of the user on the appointed node in the node diagram, synchronizing the updated content into the appointed node and keeping the diagram structure of the node diagram unchanged.
  12. 12. An electronic device, comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.
  13. 13. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-10.
  14. 14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-10.

Description

Content generation method, device, electronic equipment and storage medium Technical Field The present disclosure relates to the field of content creation and multimedia generation technologies, and in particular, to the field of multi-modal content creation and editing technologies, and in particular, to a content creation method, a device, an electronic apparatus, and a storage medium. Background With the development of multi-mode generation technology, content creators increasingly rely on AI (ARTIFICIAL INTELLIGENCE ) assisted creation, but the existing generation type AI tool generally adopts a single-time generation mode triggered by a single Prompt, so that the problems of uncontrollable generation process, difficult management of complex structures, lack of consistency control mechanism, insufficient node-level editability and the like exist, which results in low creation efficiency, high cost and poor content consistency. Disclosure of Invention The disclosure provides a content generation method, a content generation device, electronic equipment and a storage medium. According to an aspect of the present disclosure, there is provided a content generation method including: Acquiring an authoring instruction input by a user; Analyzing the authoring instruction to identify an authoring intention and authoring materials contained in the authoring instruction; processing the authoring material according to the authoring intention to construct a visualized node diagram; if an edit instruction of a user to a designated node in the node diagram is received, updating the content of the designated node according to the edit instruction, synchronizing the updated content to the designated node, and keeping the diagram structure of the node diagram unchanged. According to another aspect of the present disclosure, there is provided a content generating apparatus including: The acquisition module is used for acquiring an authoring instruction input by a user; the analysis module is used for analyzing the authoring instruction to identify the authoring intention and the authoring material contained in the authoring instruction; The processing module is used for processing the authoring material according to the authoring intention so as to construct a visualized node diagram; and the updating module is used for updating the content of the appointed node according to the editing instruction if receiving the editing instruction of the user on the appointed node in the node diagram, synchronizing the updated content into the appointed node and keeping the diagram structure of the node diagram unchanged. According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the above claims. According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of the above-mentioned technical solutions. According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the above technical solutions. The present disclosure provides a content generation method, apparatus, device, and storage medium, which can flexibly construct a visualized node map by acquiring an authoring instruction input by a user and parsing authoring intent and authoring material therein. By presenting the constructed node diagram to the user in a visual mode, the complexity of the user in understanding and operating the authored content is reduced, so that the user can more efficiently author and edit, the operation complexity of the user is obviously reduced, and the user experience is further improved. Further, by allowing the user to independently edit the designated nodes in the node diagram, the content is updated and then synchronized to the node diagram, and meanwhile, the stability of the overall diagram structure is improved. The independent editing capability of the node level greatly improves the flexibility and efficiency of creation, and enables a user to freely modify and update the content of a specific node on the premise of not affecting other nodes and the overall structure. In addition, the consistency and consistency of the authoring process are improved by keeping the graph structure unchanged, so that the authored content always keeps clear logic relation in the editing process. Therefore, the method and the device have the advantages that through constructing the visual node diagram and the node-level independent editing function, the structural management and consistency main