Content generation method and device, equipment and storage medium
By combining structured input with multi-style generation strategies, the problems of cumbersome and homogenized content generation in the digital content generation process are solved, achieving an efficient and personalized content generation process and improving user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-29
- Publication Date
- 2026-04-03
AI Technical Summary
In existing technologies, the process of generating digital content is cumbersome and highly homogenized, failing to flexibly adapt to user needs, resulting in low generation efficiency and poor user experience.
By providing a structured input area for content requirements and pre-configured style generation strategies, a diverse range of candidate content can be generated, and confirmation, preview, and editing controls can be set up to achieve a user-friendly content generation process.
It improves the flexibility and diversity of content generation, meets personalized needs, enhances generation efficiency and user interaction experience, and reduces the risk of homogenization.
Smart Images
Figure CN121786286A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of Internet application technology, and in particular to a content generation method, apparatus, device and storage medium. Background Technology
[0002] In scenarios involving the automated generation of digital content, online content is typically presented as event pages. The generation process generally involves selecting a theme template from a pre-set template library, manually writing the copy, choosing suitable images from a resource library, and finally packaging and publishing. This method is not only cumbersome and time-consuming, but also severely limited by the existing content in the resource and template libraries, resulting in highly homogenized and inflexible content that negatively impacts user experience. Summary of the Invention
[0003] In view of this, this application provides a content generation method, apparatus, device, and storage medium.
[0004] This application provides the following solution: Firstly, a content generation method is provided, which includes: The content generation page includes an input area, which includes at least one preset field and an input control corresponding to the preset field. The preset field is used to guide the user to input structured content requirement information. In response to the structured content requirement information input by the user through the input control, at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents are displayed on the content generation page. The at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles. In response to the user's triggering operation on the first confirmation control associated with the target content among the at least two candidate contents, the target content is output.
[0005] Optionally, the content generation page further includes preview controls associated with the at least two candidate contents respectively; The method further includes: In response to the user's triggering operation on the preview control associated with the target content among the at least two candidate contents, an extended panel is displayed on the content generation page, in which the target content, a second confirmation control associated with the target content, and an edit control are displayed; In response to the user's adjustment operation on the target content through the editing control, update the target content displayed in the extended panel; In response to the user's triggering operation on the second confirmation control, the updated target content is output.
[0006] Optionally, the extended panel further includes a content switching control; the method further includes: In response to a triggering operation of the content switching control, other candidate content that is different from the target content is switched and displayed in the extended panel.
[0007] Optionally, the content switching control is an identifier switching control that corresponds one-to-one with each candidate content; then, responding to the triggering operation of the content switching control, switching and displaying other candidate content different from the target content in the extended panel includes: In response to a trigger operation on any identifier switching control, the extended panel switches the display to the candidate content corresponding to the triggered identifier switching control.
[0008] Optionally, the content switching control is a sequential switching control that cycles through content in a preset order; then, responding to a trigger operation on the content switching control by displaying other candidate content different from the target content in the extended panel includes: In response to a trigger operation of the sequence switching control, the extended panel switches to display the next candidate content adjacent to the target content in a preset order of the at least two candidate contents.
[0009] Optionally, the extended panel further includes a restore control; the method further includes: Save the user's adjustment operations on the target content through the editing controls in a time sequence; In response to the triggering operation of the restore control, the target content displayed in the extended panel is restored to the corresponding historical adjustment version.
[0010] Optionally, the step of saving the user's adjustment operation records of the target content through the editing control in a time sequence includes: Assign a corresponding version identifier to each adjustment operation, generate corresponding adjustment summary information based on each adjustment operation, and save the version identifier and the corresponding adjustment summary information together. The step of restoring the target content displayed in the extended panel to the corresponding historical adjustment version in response to the triggering operation of the restore control includes: In response to the triggering operation of the recovery control, a historical version list pops up in the extended panel, and the historical version list displays the version identifier and corresponding adjustment summary information; In response to the user's selection of a target version identifier in the historical version list, the target content is restored to the historical adjustment version corresponding to the target version identifier.
[0011] Optionally, the extended panel further includes a recommendation control; the method further includes: In response to the user's first adjustment operation initiated through the editing control, the intent characteristics of the first adjustment operation are identified, and based on the intent characteristics, at least one adjustment recommendation is generated and displayed in the extended panel through the recommendation control; In response to the user's confirmation of the adjusted recommendation information, the corresponding adjustment operation is performed based on the adjusted recommendation information, and the target content in the extended panel is updated.
[0012] Optionally, the at least two candidate contents are generated in the following manner: A content generation request is sent to the server, the content generation request carrying the structured content requirement information. The server generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies. Based on the content generation model and the at least two prompt word sequences, the at least two candidate contents are generated.
[0013] Optionally, the candidate content includes text content and image content, and the content generation model includes a text content generation model and an image content generation model; The server then generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies, and generates at least two candidate contents based on the content generation model and the at least two prompt word sequences, including: The server generates at least two text prompt word sequences and at least two image prompt word sequences based on the structured content requirement information and the at least two style generation strategies, wherein the intents of the at least two text prompt word sequences and the at least two image prompt word sequences are matched. At least two text contents are generated based on the text content generation model and the at least two text prompt words, and at least two image contents are generated based on the image content model and the at least two image prompt word sequences; The at least two text contents and the at least two image contents are combined to obtain the at least two candidate contents.
[0014] Optionally, the editing control includes at least one of the following: theme style adjustment control, text adjustment control, and element layout control.
[0015] Secondly, a content generation apparatus is provided, the apparatus comprising: A page display unit is configured to display a content generation page, the content generation page including an input area, the input area including at least one preset field and an input control corresponding to the preset field, the preset field being used to guide the user to input structured content requirement information; An operation monitoring unit is configured to monitor operations in the content generation page; The page display unit is further configured to: in response to the structured content requirement information input by the user through the input control, display at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents on the content generation page, wherein the at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles; and in response to the user's triggering operation on the first confirmation control associated with the target content among the at least two candidate contents, output the target content.
[0016] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed, implements the steps of the method described in the first aspect.
[0017] Fourthly, an electronic device is provided, comprising: one or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in the first aspect.
[0018] Fifthly, a computer program product is provided, including a computer program that, when executed, implements the steps of the method described in the first aspect.
[0019] According to the specific embodiments provided in this application, the following technical effects are disclosed: 1) This application guides users to input structured content requirements by providing a structured input area with preset fields and corresponding input controls. It then generates at least two candidate contents with different visual styles using at least two pre-configured style generation strategies. A first confirmation control associated with the candidate contents is set up for the user to trigger the output of the target content. Compared with existing technologies, this solution offers several advantages: First, the structured input method enables precise collection of user content requirements, avoiding the ambiguity in requirement capture caused by traditional unstructured input. Second, generating candidate contents with differentiated visual styles based on multi-style generation strategies improves the flexibility and diversity of content generation, better matching the personalized needs of different users while significantly increasing content generation efficiency and differentiation, effectively reducing the risk of content homogenization. Third, the associated triggering of candidate contents through the first confirmation control simplifies the user operation process, ensuring the accuracy and convenience of the target content output, and enhancing the user experience.
[0020] 2) This application can ensure that the server accurately identifies user intent through structured content requirement information, and at the same time, it can generate candidate content with differentiated visual styles by combining at least two style generation strategies, thereby improving the flexibility and diversity of content generation and better matching the personalized needs of different users.
[0021] 3) This application further refines the candidate content into a combination of text and images, enabling the server to generate text prompt word sequences and image prompt word sequences for intent matching, call the corresponding model to generate text content and image content, and then combine them into candidate content. This achieves collaborative generation of text content and image content, ensuring that the two are highly consistent in theme and style, avoiding the problem of misalignment between text and images. Furthermore, the combination of text content and image content enriches the presentation of candidate content, meets the needs of different business scenarios for integrated text and image content, and improves the visual appeal and information transmission efficiency of the content.
[0022] 4) This application adds a preview control associated with the candidate content and an extended panel containing the target content, a second confirmation control, and an editing control. This allows users to view, adjust, and confirm the target content on the current page after triggering the preview. This avoids interruptions in the interaction flow caused by page jumps, ensuring a seamless experience of previewing, editing, and confirming. Furthermore, the editing control meets users' personalized adjustment needs, solving the problem of difficulty in real-time modification after generating multiple solutions in the traditional way, and further improving the flexibility of content generation and user interaction experience.
[0023] 5) This application adds a content switching control to the extended panel. After the user triggers the control, they can directly switch to display other candidate content in the extended panel without having to close the extended panel and re-trigger the preview. This simplifies the comparison and switching of multiple candidate content, shortens the user's operation path, and allows the extended panel to have the comprehensive functions of previewing, editing and switching. This avoids the distraction caused by frequent operations and improves the efficiency of filtering and adjusting multiple options.
[0024] 6) This application adds a recovery control to the extended panel, which not only solves the problem of difficulty in reverting when users make mistakes or the adjustment effect is not satisfactory, ensuring the security and flexibility of content adjustment, but also allows users to accurately locate and restore to a satisfactory version through the time sequence management of operation records, further optimizing the editing interaction experience.
[0025] 7) This application adds a recommendation control to the extended panel, which allows users to automatically perform adjustments based on the displayed adjustment recommendations after the first adjustment operation. This reduces the editing decision-making cost for users (especially for non-professional users), makes the adjustment operation more in line with the user's potential needs, and improves the accuracy and efficiency of content adjustment through intent recognition and recommendation mechanisms.
[0026] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 This is a schematic diagram of the system architecture applicable to the embodiments of this application.
[0029] Figure 2 A flowchart illustrating the content generation method provided in this application embodiment.
[0030] Figure 3 This is a schematic diagram of the input area in the content generation page provided in the embodiments of this application.
[0031] Figure 4 This is a schematic diagram of candidate content in the content generation page provided in the embodiments of this application.
[0032] Figure 5 A schematic block diagram of a content generation apparatus provided in an embodiment of this application.
[0033] Figure 6A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0035] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.
[0036] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.
[0037] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."
[0038] In scenarios where digital content is automatically generated, online content is usually presented in the form of an event page. The process of generating such an event page is generally as follows: select a theme template from a preset template library, then write the copy manually, select suitable images from a material library, and finally package and publish it.
[0039] The implementation of this technology has significant technical limitations: on the one hand, the manual process of template selection, text writing, and material screening is cumbersome, resulting in low efficiency and long processing time for generating event pages; on the other hand, the limited capacity and types of the material library restrict the scope of material access to existing resources within the library, which not only makes the visual presentation and content design of event pages prone to homogenization, but also makes it impossible to dynamically adapt and flexibly adjust materials according to real-time operational needs and user preferences, resulting in poor display flexibility of event pages and affecting the user experience.
[0040] In view of this, this application provides a new approach. To facilitate understanding of this application, the system architecture on which this application is based will first be described. Figure 1 This is a schematic diagram of the system architecture applicable to the embodiments of this application, such as... Figure 1 As shown, the system architecture may include: user terminal, terminal device and server terminal.
[0041] In this embodiment, the user terminal is set on the terminal device. The user terminal involved in this application can be a client running on the terminal device, a mini-program, or a web application running through a browser.
[0042] Terminal devices can include, but are not limited to, smart mobile terminals, wearable devices, PCs (Personal Computers), and smart home devices. Smart mobile devices can include devices such as mobile phones, tablets, laptops, PDAs (Personal Digital Assistants), and connected car terminals. Wearable devices can include devices such as smartwatches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality) devices, and mixed reality devices (devices that support both virtual and augmented reality). Smart home devices can include devices such as smart TVs and smart refrigerators with displays.
[0043] The user client can interact with the server through the network, request and retrieve at least two candidate contents from the server, and then display them.
[0044] The server side can be a platform that provides content generation services, a single server, a server cluster consisting of multiple servers, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) services, such as high management difficulty and weak service scalability.
[0045] As one possible approach, after receiving structured content requirement information, the user sends a candidate content generation request to the server. The server generates at least two candidate contents with different visual styles based on the structured content requirement information and at least two pre-configured style generation strategies, and transmits them to the user. The user then displays these at least two candidate contents on the content generation page.
[0046] It should be understood that Figure 1The number of client terminals, terminal devices, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of client terminals, terminal devices, and servers.
[0047] It should be noted that the terms "first" and "second" used in this disclosure do not have any limitations on size, order, or quantity; they are merely used to distinguish between the two types of confirmation controls, such as "first confirmation control" and "second confirmation control" to distinguish between them.
[0048] Figure 2 This is a flowchart of a content generation method provided in an embodiment of this application. This method can be... Figure 1 The user-side execution in the system shown is as follows. Figure 2 As shown, the method may include the following steps: Step 201: Display the content generation page. The content generation page includes an input area, which includes at least one preset field and an input control corresponding to the preset field. The preset field is used to guide the user to input structured content requirement information.
[0049] Step 202: In response to the structured content requirement information input by the user through the input control, display at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents on the content generation page. The at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles.
[0050] Step 203: In response to the user's triggering action on the first confirmation control associated with the target content among at least two candidate contents, output the target content.
[0051] As can be seen from the above process, this application guides users to input structured content requirements by providing a structured input area containing preset fields and corresponding input controls. It then generates at least two candidate contents with different visual styles by combining at least two pre-configured style generation strategies, and sets a first confirmation control associated with the candidate contents for the user to trigger the output of the target content. Compared with existing technologies, this solution offers several advantages: First, the structured input method enables precise collection of user content requirements, avoiding the problem of vague requirement capture caused by traditional unstructured input. Second, generating candidate contents with differentiated visual styles based on multi-style generation strategies improves the flexibility and diversity of content generation, better matching the personalized needs of different users, while significantly improving content generation efficiency and differentiation, effectively reducing the risk of content homogenization. Third, the associated triggering of candidate contents through the first confirmation control simplifies the user operation process, ensures the accuracy and convenience of the target content output, and enhances the user interaction experience.
[0052] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments.
[0053] First, the above step 201, namely "displaying a content generation page, the content generation page including an input area, the input area including at least one preset field and an input control corresponding to the preset field, the preset field being used to guide the user to input structured content requirement information", will be described in detail with reference to the embodiments.
[0054] In this embodiment, the content generation page can be a page integrating an intelligent agent, where users can interact with the intelligent agent to generate content. An intelligent agent is a software entity possessing autonomous perception, decision-making, and execution capabilities. In the field of artificial intelligence, intelligent agents are also translated as intelligent agents, proxies, agents, intelligent subjects, etc.
[0055] In this embodiment, the generated content can be an item display image, with the item image as the visual core, and simultaneously overlaid with item-related text information. It can be directly rendered in the product display area, discount recommendation area, and theme promotion area of various stores (such as local life promotion venues, brand promotion venues, access event venues, etc.).
[0056] In practical applications, when a user triggers the content generation function, such as by clicking the "Create Meeting Room" button on the user's device, the device responds to the trigger by loading and displaying the content generation page on the user's screen. This content generation page is presented as a visual interactive interface, which includes at least an input area. This input area includes at least one preset field and corresponding input controls. The preset field guides the user to input structured content requirements.
[0057] The preset fields can be determined based on the actual business scenario of content generation. For example... Figure 3 As shown, it can include at least the associated activity field, the theme description field, and the image description field (including the selling point field and the material field).
[0058] The associated activity field is mainly used to establish a connection between the venue and existing activity data in the backend, ensuring that the generated content matches the basic attributes of the activity (such as activity time, participating products, discount rules, etc.). The corresponding input control can be a drop-down selector, which can preload a list of activities already created in the backend (such as a special activity for the Winter Hot Pot Festival). Users can directly select the target activity without manually entering activity information, thus avoiding data association errors.
[0059] The theme description field is mainly used to input the theme of the event and clarify the purpose of the event. The corresponding input control can be a text box. The theme example can also be provided in the text box (such as [Example: Winter Hot Pot Festival]) to guide users to describe accurately and ensure that the theme is clear and meets the actual needs of the theme.
[0060] The selling point field is mainly used to input the selling points of the event theme. The corresponding input control can be a preset selling point checkbox. Common marketing phrases (such as super low price, limited time discount, full reduction benefits, new product launch) can be built into the checkbox. Users can select one or more selling points according to the needs of the event, which reduces the user's input cost and ensures the standardization of selling point expression, avoiding the omission of selling points caused by unstructured input.
[0061] The material field is mainly used to describe the main content of the event material image. The corresponding input control can be a material prompt input box. The input box allows users to describe the main visual elements they want to include, such as a boiling hot pot surrounded by couple's tableware.
[0062] The following describes step 202, namely, "in response to the structured content requirement information input by the user through the input control, display at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents on the content generation page," in conjunction with an embodiment.
[0063] In this embodiment, after a user inputs structured content requirement information via an input control, at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents are displayed on the content generation page. The at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles.
[0064] Different visual styles refer to at least two candidate contents that differ significantly in at least one of several dimensions, such as color scheme, visual element density, typography, font style, and graphic design. The aim is to provide users with diverse visual choices to suit the personalized needs of different business scenarios and target audiences.
[0065] At least two candidate contents can be generated in the following manner: A content generation request is sent to the server, carrying structured content requirement information. The server generates at least two prompt word sequences based on the structured content requirement information and at least two style generation strategies. Based on the content generation model and the at least two prompt word sequences, at least two candidate contents are generated.
[0066] Specifically, after receiving a content generation request, the server can analyze the structured content requirement information and extract the information it contains, such as "Winter Hot Pot Festival Special Event" in the associated activity field, "Winter, Hot Pot" in the theme description field, "Super Low Price" in the selling point field, and "Boiling Hot Pot" in the material field. At the same time, it can retrieve at least two pre-configured style generation strategies from the strategy library, and then generate at least two prompt word sequences based on the extracted information and at least two style generation strategies. Based on these prompt word sequences and the pre-built content generation model, at least two candidate contents are generated.
[0067] Structured content requirements information ensures that the server accurately identifies user intent. At the same time, combining at least two style generation strategies can generate candidate content with differentiated visual styles, thereby improving the flexibility and diversity of content generation and better matching the personalized needs of different users.
[0068] It should be noted that the strategy library can be pre-configured with various style generation strategies, which can be dynamically adjusted based on actual business scenarios and business needs.
[0069] Optionally, the candidate content may include text content and image content, and the content generation model may include a text content generation model and an image content generation model.
[0070] The server generates at least two text cue word sequences and at least two image cue word sequences based on structured content requirement information and at least two style generation strategies, wherein the intents of at least two text cue word sequences and at least two image cue word sequences are matched. Generate at least two text contents based on a text content generation model and at least two text cue words, and generate at least two image contents based on an image content model and at least two image cue word sequences; Combine at least two text contents and at least two image contents to obtain at least two candidate contents.
[0071] In this embodiment, the candidate content is further refined into a combination of text and images. The server generates text prompt sequences and image prompt sequences for intent matching, respectively. The corresponding model is then called to generate text content and image content, which are then combined into candidate content. This achieves collaborative generation of text content and image content, ensuring that the two are highly consistent in theme and style, avoiding the problem of misalignment between text and images. Furthermore, the combination of text content and image content enriches the presentation of candidate content, meets the needs of different business scenarios for integrated text and image content, and improves the visual appeal and information transmission efficiency of the content.
[0072] The following describes step 203, namely "in response to the user's triggering operation on the first confirmation control associated with the target content among at least two candidate contents, output the target content", in detail with reference to the embodiments.
[0073] The content generation page displays candidate content along with a first confirmation control associated with each candidate. When the user performs a trigger action (such as clicking or touching) on the first confirmation control associated with the target content from at least two candidate content groups, the target content is output. In practical applications, the target content can be directly deployed to the corresponding business scenario or stored locally.
[0074] Optionally, the content generation page may also display preview controls associated with at least two candidate content items, which can preview the candidate content. Furthermore, after step 202, the following may be included: In response to a user's triggering action on the preview control associated with the target content among at least two candidate contents, such as clicking the preview button associated with the target content, an extended panel is displayed on the content generation page, and the target content, a second confirmation control associated with the target content, and an edit control are displayed in the extended panel; In response to user adjustments to the target content via editing controls, update the target content displayed in the extended panel; In response to the user's triggering action on the second confirmation control, the updated target content is output.
[0075] In this embodiment, by adding a preview control associated with the candidate content and an extended panel containing the target content, a second confirmation control, and an editing control, the user can view, adjust, and confirm the target content on the current page after triggering the preview. This avoids interruptions in the interaction flow caused by page jumps, ensuring a seamless experience of previewing, editing, and confirming. Furthermore, the editing control meets the user's personalized adjustment needs, solving the problem of difficulty in real-time modification after generating multiple solutions in traditional methods, and further improving the flexibility of content generation and the user interaction experience.
[0076] In addition, the aforementioned editing controls may include at least one of theme style adjustment controls, text adjustment controls, and element layout controls.
[0077] When the theme style adjustment control is triggered, it is used to adjust the visual theme style of the target content in response to the user's style selection operation. For example, after being triggered, a color swatch will pop up (containing 10 preset theme colors, such as Chinese red, tech blue, and minimalist white). After the user selects a theme color, the main color of the target content in the extended panel will be updated based on the theme color selected by the user, including background color, text color, border color, etc.
[0078] When the text adjustment control is triggered, it is used to update the text information in the target content in response to the user's text modification operation. For example, after being triggered, a text editing box pops up in the target content of the extended panel, where the user can modify the text content, adjust the font, font size, alignment, etc.
[0079] When the element layout control is triggered, it is used to adjust the arrangement of elements in the target content in response to the user's layout modification operation. For example, after being triggered, the user can drag the elements in the target content (such as product cards and discount tags) to adjust their positions.
[0080] The aforementioned editing controls allow users to optimize the details of candidate content in a targeted manner, making the generated content better suited to actual application scenarios.
[0081] Furthermore, the extended panel can also include a content switching control. When the user clicks the content switching control, other candidate content that is different from the target content can be switched and displayed in the extended panel.
[0082] By adding a content switching control to the extended panel, users can directly switch between displaying other candidate content within the extended panel after triggering the control, without having to close the extended panel and re-trigger the preview. This simplifies the comparison and switching of multiple candidate content, shortens the user's operation path, and gives the extended panel a comprehensive function of previewing, editing, and switching, avoiding the distraction caused by frequent operations and improving the efficiency of filtering and adjusting multiple options.
[0083] The content switching control can be either an identifier switching control that corresponds one-to-one with each candidate content, or a sequential switching control that cycles through the content in a preset order.
[0084] When the content switching control is an identifier switching control that corresponds one-to-one with each candidate content, the user can select any identifier switching control from it. At this time, the extended panel will directly switch to the candidate content corresponding to the triggered identifier switching control.
[0085] When the content switching control is a sequential switching control that cycles through content in a preset order, when the user triggers the sequential switching control, the next candidate content adjacent to the target content will be displayed in the extended panel according to the preset order of the generated candidate content.
[0086] The different switching methods described above ensure that users with different usage habits (such as those who prefer to directly select specific content or those who prefer to browse in order) can easily switch between candidate content.
[0087] As an example, such as Figure 4 The image shown is a schematic diagram of the content generation page. (Refer to...) Figure 4As shown in (a), after the user inputs structured content requirements through the input controls, candidate content with different visual styles, namely candidate content a and candidate content b, are displayed on the content generation page. A first confirmation control 41 corresponding to each candidate content is also displayed on the content generation page. A preview control 42 associated with each candidate content is also displayed on the content generation page.
[0088] refer to Figure 4 As shown in (b), when the user clicks one of the preview controls 42, an extended panel 43 is displayed on the content generation page. The extended panel 43 allows for previewing, editing, and outputting the target content. The extended panel 43 displays an editing control 44, a second confirmation control 45, and a content switching control 46.
[0089] When the user clicks the edit control 44, a color picker 47 is displayed in the extended panel. The user can adjust the theme color of the target content displayed in the extended panel by selecting a theme color in the color picker, and complete the output of the target content by using the second confirmation control 45. When the user wants to preview other candidate content, there is no need to exit the extended panel; they can directly switch between other candidate content by clicking the content switching control 46.
[0090] This application integrates multiple steps such as previewing, comparing, editing, and confirming into a single interactive process, shortening the user's operation path, avoiding process interruptions and attention distractions caused by page jumps, and achieving a seamless and efficient user experience.
[0091] To avoid the problem of unreversible actions after user misoperation, the extended panel in this embodiment may further include a restore control. The method may also include: Saves a time-series record of user adjustments to the target content using editing controls; In response to the user's triggering of the restore control, the target content displayed in the extended panel is restored to the corresponding historical adjustment version.
[0092] Specifically, each adjustment operation can be assigned a corresponding version identifier, such as a timestamp or version number, and a corresponding adjustment summary can be generated based on each adjustment operation, such as changing font size or adjusting color scheme. Finally, the version identifier and the corresponding adjustment summary information are associated and saved. When the user triggers the restore control, a historical version list pops up in the extended panel. This historical list displays each version identifier and its corresponding adjustment summary information. The user can select the historical adjustment version they want to restore based on the adjustment summary information. When the user clicks on the target version identifier displayed in the historical version list, the currently displayed target content will be restored to the historical adjustment version corresponding to the target version identifier.
[0093] As one feasible approach, the restore control can be implemented using a combination of an icon and a drop-down menu. When the user clicks the icon, the drop-down menu is displayed, which sorts the historical adjustment versions in reverse chronological order. Each version can include information such as a timestamp, adjustment summary information, and a preview thumbnail. The user can select one of the historical adjustment versions to restore.
[0094] This method not only solves the problem of difficulty in reverting to the previous version when users make mistakes or the adjustment is not satisfactory, ensuring the safety and flexibility of content adjustment, but also allows users to accurately locate and restore the satisfactory version through the time sequence management of operation records, further optimizing the editing interaction experience.
[0095] Furthermore, the extended panel can also include recommendation controls. The method can also include: In response to the user's first adjustment operation initiated through the editing control, the intent characteristics of the first adjustment operation are identified, and based on the intent characteristics, at least one adjustment recommendation is generated and displayed in the extended panel through the recommendation control; In response to the user's confirmation of the adjustment of the recommendation information, the corresponding adjustment operation is performed based on the adjusted recommendation information, and the target content in the extended panel is updated.
[0096] Specifically, once a user performs the first adjustment operation through the editing control, such as adjusting the theme style of the target content and changing the main color (e.g., changing the default Chinese red main color of the Winter Hot Pot Festival and Guochao Style venue to warm orange through the theme style adjustment control), the system will immediately start the intent feature recognition process: first, collect the data of this adjustment (adjustment type is "main color change", color before adjustment and color after adjustment), then associate it with the structured requirement information of the target content (event theme "Winter Hot Pot Festival", basic style "Guochao Style", core selling point "ultra-low price"), and finally extract the intent tag "strengthen the warm winter atmosphere with warm colors, while adapting to the color tone of Guochao Style". Based on this intent tag, the system will match and generate at least one adjustment recommendation from the recommendation rule library. For example, it may prioritize recommending "Simultaneously change the auxiliary color (text border, decorative lines) to light yellow, and add the reason that 'warm orange + light yellow matches the warm scene of hot pot in winter and conforms to the color blocking design logic of the national trend'"; at the same time, it may generate a secondary recommendation "Optimize the lighting effect of the main visual of hot pot, and change it to warm orange soft light to match the new main color". These adjustment recommendations can be automatically displayed in a pop-up window through the recommendation control in the extended panel. Each recommendation in the pop-up window is equipped with a "color palette / layer" icon, a recommendation title and an "Apply Recommendation" button. After the user clicks "Apply Recommendation", the system will update the target content in the extended panel in real time (such as simultaneously changing the auxiliary color to light yellow and completing the soft light optimization of the main visual lighting), and pop up a prompt "Recommendation has been applied, content has been updated". This not only helps users quickly complete the detailed optimization needs after the main color change, but also avoids content inconsistency caused by non-professional users ignoring design details such as color matching and lighting adaptation, ensuring that the adjusted target content is more in line with the business scenario needs in terms of style consistency and visual refinement.
[0097] By adding a recommendation control to the extended panel, users can automatically make adjustments based on the displayed adjustment recommendations after the first adjustment. This reduces the editing decision-making cost for users (especially for non-professional users), makes the adjustment operations more in line with the user's potential needs, and improves the accuracy and efficiency of content adjustment through intent recognition and recommendation mechanisms.
[0098] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0099] According to another embodiment, a content generation apparatus is provided. Figure 5This is a schematic block diagram of a content generation apparatus provided in an embodiment of this application. The apparatus is disposed in... Figure 1 The user end in the illustrated architecture. For example... Figure 5 As shown, the device 500 mainly includes a page display unit 501 and an operation monitoring unit 502. The main functions of each component are as follows: The page display unit 501 is configured to display a content generation page, which includes an input area. The input area includes at least one preset field and an input control corresponding to the preset field. The preset field is used to guide the user to input structured content requirement information.
[0100] Operation monitoring unit 502 is configured to monitor operations in the content generation page.
[0101] The page display unit 501 is further configured to, in response to the structured content requirement information input by the user through the input control, display at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents on the content generation page, wherein the at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles; and to, in response to the user's triggering operation on the first confirmation control associated with the target content among the at least two candidate contents, output the target content.
[0102] As one possible implementation, the content generation page further includes preview controls associated with each of the at least two candidate contents; the page display unit 501 is also configured to: In response to the user's triggering operation on the preview control associated with the target content among the at least two candidate contents, an extended panel is displayed on the content generation page, in which the target content, a second confirmation control associated with the target content, and an edit control are displayed; In response to the user's adjustment operation on the target content through the editing control, update the target content displayed in the extended panel; In response to the user's triggering operation on the second confirmation control, the updated target content is output.
[0103] As one possible implementation, the extended panel also includes content switching controls; the page display unit 501 is further configured to: In response to a triggering operation of the content switching control, other candidate content that is different from the target content is switched and displayed in the extended panel.
[0104] Optionally, the content switching control is an identifier switching control that corresponds one-to-one with each candidate content; then the page display unit 501 is specifically configured as follows: In response to a trigger operation on any identifier switching control, the extended panel switches the display to the candidate content corresponding to the triggered identifier switching control.
[0105] Optionally, the content switching control is a sequential switching control that cycles through content in a preset order; then the page display unit 501 is specifically configured as follows: In response to a trigger operation of the sequence switching control, the extended panel switches to display the next candidate content adjacent to the target content in a preset order of the at least two candidate contents.
[0106] As one possible implementation, the extended panel also includes a restore control; the page display unit 501 is further configured to: Save the user's adjustment operations on the target content through the editing controls in a time sequence; In response to the triggering operation of the restore control, the target content displayed in the extended panel is restored to the corresponding historical adjustment version.
[0107] Optionally, the page display unit 501 is specifically configured as follows: Assign a corresponding version identifier to each adjustment operation, generate corresponding adjustment summary information based on each adjustment operation, and save the version identifier and the corresponding adjustment summary information together. In response to the triggering operation of the recovery control, a historical version list pops up in the extended panel, and the historical version list displays the version identifier and corresponding adjustment summary information; In response to the user's selection of a target version identifier in the historical version list, the target content is restored to the historical adjustment version corresponding to the target version identifier.
[0108] As one possible implementation, the extended panel also includes a recommendation control; the page display unit 501 is further configured to: In response to the user's first adjustment operation initiated through the editing control, the intent characteristics of the first adjustment operation are identified, and based on the intent characteristics, at least one adjustment recommendation is generated and displayed in the extended panel through the recommendation control; In response to the user's confirmation of the adjusted recommendation information, the corresponding adjustment operation is performed based on the adjusted recommendation information, and the target content in the extended panel is updated.
[0109] Optionally, the at least two candidate contents are generated in the following manner: A content generation request is sent to the server, the content generation request carrying the structured content requirement information. The server generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies. Based on the content generation model and the at least two prompt word sequences, the at least two candidate contents are generated.
[0110] Furthermore, the candidate content includes text content and image content, and the content generation model includes a text content generation model and an image content generation model; The server then generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies, and generates at least two candidate contents based on the content generation model and the at least two prompt word sequences, including: The server generates at least two text prompt word sequences and at least two image prompt word sequences based on the structured content requirement information and the at least two style generation strategies, wherein the intents of the at least two text prompt word sequences and the at least two image prompt word sequences are matched. At least two text contents are generated based on the text content generation model and the at least two text prompt words, and at least two image contents are generated based on the image content model and the at least two image prompt word sequences; The at least two text contents and the at least two image contents are combined to obtain the at least two candidate contents.
[0111] Optionally, the editing control includes at least one of the following: theme style adjustment control, text adjustment control, and element layout control. The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The system and device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0112] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.
[0113] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed, implements the steps of the method described in any of the foregoing method embodiments.
[0114] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.
[0115] This application also provides a computer program product, including a computer program that, when executed, implements the steps of the method described in any of the foregoing method embodiments.
[0116] in, Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Specifically, it may include a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, and a memory 620. The processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, and memory 620 can be communicatively connected via a communication bus 630. The input / output interface 613 can also be referred to as an I / O interface 613.
[0117] The processor 610 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.
[0118] The memory 620 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 620 can store the operating system 621 for controlling the operation of the electronic device 600, and the basic input / output system (BIOS) 622 for controlling the low-level operations of the electronic device 600. Additionally, it can store a web browser 623, a data storage management system 624, and a content generation device 500, etc. The aforementioned content generation device 500 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 620 and is called and executed by the processor 610.
[0119] Input / output interface 613 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.
[0120] Network interface 614 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0121] Bus 630 includes a pathway for transmitting information between various components of the device, such as processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, and memory 620.
[0122] It should be noted that although the above-described device only shows the processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, memory 620, bus 630, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.
[0123] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.
[0124] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A content generation method, characterized in that, The method includes: The content generation page includes an input area, which includes at least one preset field and an input control corresponding to the preset field. The preset field is used to guide the user to input structured content requirement information. In response to the structured content requirement information input by the user through the input control, at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents are displayed on the content generation page. The at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles. In response to the user's triggering operation on the first confirmation control associated with the target content among the at least two candidate contents, the target content is output.
2. The method according to claim 1, characterized in that, The content generation page also includes preview controls associated with each of the at least two candidate contents; The method further includes: In response to the user's triggering operation on the preview control associated with the target content among the at least two candidate contents, an extended panel is displayed on the content generation page, in which the target content, a second confirmation control associated with the target content, and an edit control are displayed; In response to the user's adjustment operation on the target content through the editing control, update the target content displayed in the extended panel; In response to the user's triggering operation on the second confirmation control, the updated target content is output.
3. The method according to claim 2, characterized in that, The extended panel also includes content switching controls; the method further includes: In response to a triggering operation of the content switching control, other candidate content that is different from the target content is switched and displayed in the extended panel.
4. The method according to claim 3, characterized in that, The content switching control is an identifier switching control that corresponds one-to-one with each candidate content; then, in response to the triggering operation of the content switching control, switching the display of other candidate content different from the target content in the extended panel includes: In response to a trigger operation on any identifier switching control, the extended panel switches the display to the candidate content corresponding to the triggered identifier switching control.
5. The method according to claim 4, characterized in that, The content switching control is a sequential switching control that cycles through content in a preset order; therefore, the step of responding to a trigger operation on the content switching control by switching and displaying other candidate content different from the target content in the extended panel includes: In response to a trigger operation of the sequence switching control, the extended panel switches to display the next candidate content adjacent to the target content in a preset order of the at least two candidate contents.
6. The method according to claim 2, characterized in that, The extended panel also includes a recovery control; the method further includes: Save the user's adjustment operations on the target content through the editing controls in a time sequence; In response to the triggering operation of the restore control, the target content displayed in the extended panel is restored to the corresponding historical adjustment version.
7. The method according to claim 6, characterized in that, The step of saving the user's adjustment operations on the target content through the editing control in a time-series manner includes: Assign a corresponding version identifier to each adjustment operation, generate corresponding adjustment summary information based on each adjustment operation, and save the version identifier and the corresponding adjustment summary information together. The step of restoring the target content displayed in the extended panel to the corresponding historical adjustment version in response to the triggering operation of the restore control includes: In response to the triggering operation of the recovery control, a historical version list pops up in the extended panel, and the historical version list displays the version identifier and corresponding adjustment summary information; In response to the user's selection of a target version identifier in the historical version list, the target content is restored to the historical adjustment version corresponding to the target version identifier.
8. The method according to claim 2, characterized in that, The extended panel also includes a recommendation control; the method further includes: In response to the user's first adjustment operation initiated through the editing control, the intent characteristics of the first adjustment operation are identified, and based on the intent characteristics, at least one adjustment recommendation is generated and displayed in the extended panel through the recommendation control; In response to the user's confirmation of the adjusted recommendation information, the corresponding adjustment operation is performed based on the adjusted recommendation information, and the target content in the extended panel is updated.
9. The method according to claim 1, characterized in that, The at least two candidate contents are generated in the following manner: A content generation request is sent to the server, the content generation request carrying the structured content requirement information. The server generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies. Based on the content generation model and the at least two prompt word sequences, the at least two candidate contents are generated.
10. The method according to claim 9, characterized in that, The candidate content includes text content and image content, and the content generation model includes a text content generation model and an image content generation model; The server then generates at least two prompt word sequences based on the structured content requirement information and the at least two style generation strategies, and generates at least two candidate contents based on the content generation model and the at least two prompt word sequences, including: The server generates at least two text prompt word sequences and at least two image prompt word sequences based on the structured content requirement information and the at least two style generation strategies, wherein the intents of the at least two text prompt word sequences and the at least two image prompt word sequences are matched. At least two text contents are generated based on the text content generation model and the at least two text prompt words, and at least two image contents are generated based on the image content model and the at least two image prompt word sequences; The at least two text contents and the at least two image contents are combined to obtain the at least two candidate contents.
11. The method according to any one of claims 1 to 10, characterized in that, The editing controls include at least one of the following: theme style adjustment controls, text adjustment controls, and element layout controls.
12. A content generation apparatus, characterized in that, The device includes: A page display unit is configured to display a content generation page, the content generation page including an input area, the input area including at least one preset field and an input control corresponding to the preset field, the preset field being used to guide the user to input structured content requirement information; An operation monitoring unit is configured to monitor operations in the content generation page; The page display unit is further configured to: in response to the structured content requirement information input by the user through the input control, display at least two candidate contents and a first confirmation control associated with each of the at least two candidate contents on the content generation page, wherein the at least two candidate contents are generated based on the structured content requirement information and at least two pre-configured style generation strategies, and the at least two candidate contents have different visual styles; and in response to the user's triggering operation on the first confirmation control associated with the target content among the at least two candidate contents, output the target content.
13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program performs the steps of the method described in any one of claims 1 to 11.
14. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 11.
15. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program performs the steps of the method described in any one of claims 1 to 11.