Content generation method, apparatus, electronic device, and computer readable storage medium

Abstract

The present invention relates to a content generation method, an apparatus, an electronic device, and a computer readable storage medium. The method comprises: displaying a first interface, wherein the first interface displays an input box, a content generation control, and a plurality of dimension labels, and the plurality of dimension labels are respectively used for prompting a user to input, from different feature dimensions, prompt information describing content to be generated; in response to a trigger operation on the first interface, displaying at least one piece of target prompt information in the input box; and in response to a trigger operation on the content generation control, displaying a second interface, wherein the second interface displays at least one piece of target content and the at least one piece of target prompt information, and the at least one piece of target content is generated on the basis of the at least one piece of target prompt information.

Description

Content generation methods, apparatus, electronic devices, and computer-readable storage media

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202410508641.1, filed on April 25, 2024, entitled "Content Generation Method, Apparatus, Electronic Device and Computer-Readable Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of image editing technology, and in particular to a content generation method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0004] Artificial Intelligence Generated Content (AIGC) is a rapidly developing industry that has a profound impact on the editing of video, audio, images, and text content. Currently, some content editing software incorporates features that generate content based on prompts, producing images that match the user's expectations based on user-input prompts. Summary of the Invention

[0005] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a content generation method, apparatus, electronic device, storage medium and program product.

[0006] A first aspect of this disclosure provides a content generation method, the method comprising: displaying a first interface, the first interface displaying an input box, a content generation control, and multiple dimension labels; the multiple dimension labels being used to prompt a user to input prompt information describing the content to be generated from different feature dimensions; in response to a triggering operation on the first interface, displaying at least one target prompt information in the input box; and in response to a triggering operation on the content generation control, displaying a second interface, the second interface displaying at least one target content and the at least one target prompt information, the at least one target content being generated based on the at least one target prompt information.

[0007] In some embodiments of this disclosure, before displaying at least one target prompt message in the input box in response to a triggering operation on the first interface, the method further includes:

[0008] In response to a triggering operation on a target dimension label among the multiple dimension labels, at least one recommended prompt message is displayed on a first interface. The at least one recommended prompt message is used to indicate a prompt message that matches the target feature dimension indicated by the target dimension label. The display of at least one target prompt message in the input box in response to a triggering operation on the first interface includes: in response to a triggering operation on a target recommended prompt message among the at least one recommended prompt messages, displaying the target recommended prompt message in the input box. The at least one target prompt message includes the target recommended prompt message.

[0009] In some embodiments of this disclosure, the first interface further displays a reference content control associated with the target dimension label. The display of at least one target prompt message in the input box in response to a trigger operation on the first interface includes: displaying at least one reference content in the first interface in response to a trigger operation on the reference content control; displaying at least one reference prompt message in the first interface in response to a selection operation on the target reference content, wherein the at least one reference prompt message is used to indicate a prompt message identified from the target reference content that matches the target feature dimension; displaying the target reference prompt message in the input box in response to a trigger operation on the target reference prompt message, wherein the at least one target prompt message includes the target reference prompt message; or, displaying the target reference content in the input box in response to a selection operation on the target reference content of at least one reference content, wherein the at least one target prompt message includes the target reference content.

[0010] In some embodiments of this disclosure, the multiple dimension labels are located in different input areas of the input box, and the display state of the multiple dimension labels is different from the display state of the at least one prompt message.

[0011] In some embodiments of this disclosure, the display of at least one recommended prompt in the first interface in response to a trigger operation for a target dimension label among the plurality of dimension labels includes: displaying the at least one recommended prompt in the first interface in response to a trigger operation for displaying an input cursor in the input area corresponding to the target dimension label.

[0012] In some embodiments of this disclosure, a progress bar control is also displayed in the first interface. The progress bar control is used to indicate the sum of the descriptive degree corresponding to the feature dimensions matched by the at least one target prompt information. The descriptive degree is used to indicate the completeness of the description of the content to be generated by the corresponding feature dimension.

[0013] In some embodiments of this disclosure, the second interface also displays recommended adjustment information, which is generated based on the at least one target content and the at least one target prompt information; the recommended adjustment information is used to indicate the adjustment direction of the at least one target prompt information.

[0014] In some embodiments of this disclosure, the recommended adjustment information includes first prompt information; when the at least one target prompt information does not include the first prompt information, the adjustment direction includes any one of the following: adding the first prompt information, replacing the second prompt information in the at least one target prompt information with the first prompt information; when the at least one target prompt information includes the first prompt information, the adjustment direction includes any one of the following: deleting the first prompt information, adjusting the image detail information corresponding to the first prompt information.

[0015] In some embodiments of this disclosure, the second interface also displays the content generation control. In response to a trigger operation on the content generation control, after displaying the second interface, the method further includes: in response to a trigger operation on the second interface, updating the at least one target prompt information; in response to a trigger operation on the content generation control, updating the at least one target content, wherein the updated at least one target content is generated based on the updated at least one target prompt information.

[0016] A second aspect of this disclosure provides a content generation apparatus, comprising: a display module for displaying a first interface, the first interface displaying an input box, a content generation control, and multiple dimension labels; the multiple dimension labels being used to prompt a user to input prompt information describing the content to be generated from different feature dimensions; in response to a triggering operation on the first interface, displaying at least one target prompt information in the input box; and in response to a triggering operation on the content generation control, displaying a second interface, the second interface displaying at least one target content and the at least one target prompt information, the at least one target content being generated based on the at least one target prompt information.

[0017] In some embodiments of this disclosure, the display module is further configured to, in response to a triggering operation on a target dimension label among the plurality of dimension labels, display at least one recommended prompt in the first interface before displaying at least one target prompt in the input box in response to a triggering operation on the first interface. The at least one recommended prompt is used to indicate a prompt that matches the target feature dimension indicated by the target dimension label. Specifically, the display module is configured to, in response to a triggering operation on the target recommended prompt among the at least one recommended prompt, display the target recommended prompt in the input box. The at least one target prompt includes the target recommended prompt.

[0018] In some embodiments of this disclosure, the first interface further displays a reference content control associated with the target dimension label. Specifically, the display module is configured to: display at least one reference content in the first interface in response to a trigger operation on the reference content control; display at least one reference prompt in the first interface in response to a selection operation on a target reference content among the at least one reference content, wherein the at least one reference prompt is used to indicate a prompt identified from the target reference content that matches the target feature dimension; display the target reference prompt in an input box in response to a trigger operation on a target reference prompt in the at least one reference prompt, wherein the at least one target prompt includes the target reference prompt; or, display the target reference in an input box in response to a selection operation on a target reference content among at least one reference content, wherein the at least one target prompt includes the target reference content.

[0019] In some embodiments of this disclosure, the multiple dimension labels are located in different input areas of the input box, and the display state of the multiple dimension labels is different from the display state of the at least one prompt message.

[0020] In some embodiments of this disclosure, the display module 601 is specifically used to display the at least one recommendation prompt in the first interface in response to a trigger operation that displays an input cursor in the input area corresponding to the target dimension label.

[0021] In some embodiments of this disclosure, a progress bar control is also displayed in the first interface. The progress bar control is used to indicate the sum of the descriptive degree corresponding to the feature dimensions matched by the at least one target prompt information. The descriptive degree is used to indicate the completeness of the description of the content to be generated by the corresponding feature dimension.

[0022] In some embodiments of this disclosure, the second interface also displays recommended adjustment information, which is generated based on the at least one target content and the at least one target prompt information; the recommended adjustment information is used to indicate the adjustment direction of the at least one target prompt information.

[0023] In some embodiments of this disclosure, the recommended adjustment information includes first prompt information; when the at least one target prompt information does not include the first prompt information, the adjustment direction includes any one of the following: adding the first prompt information, replacing the second prompt information in the at least one target prompt information with the first prompt information; when the at least one target prompt information includes the first prompt information, the adjustment direction includes any one of the following: deleting the first prompt information, adjusting the image detail information corresponding to the first prompt information.

[0024] In some embodiments of this disclosure, the second interface also displays the content generation control. The display module is further configured to, after displaying the second interface in response to a trigger operation on the content generation control, update the at least one target prompt information in response to a trigger operation on the second interface; and update the at least one target content in response to a trigger operation on the content generation control, wherein the updated at least one target content is generated based on the updated at least one target prompt information.

[0025] A third aspect of this disclosure provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the content generation method as described in the first aspect.

[0026] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the content generation method as described in the first aspect.

[0027] A fifth aspect of this disclosure provides a computer program product, wherein the computer program product includes a computer program that, when the computer program product is run on a processor, causes the processor to execute the computer program to implement the content generation method as described in the first aspect.

[0028] A sixth aspect of this disclosure provides a chip including a processor and a communication interface coupled to the processor, the processor being used to execute program instructions to implement the content generation method as described in the first aspect. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0030] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 is a flowchart illustrating a content generation method provided in an embodiment of this disclosure;

[0032] Figure 2 is one of the interface diagrams of the content generation method provided in the embodiments of this disclosure;

[0033] Figure 3 is a second schematic diagram of the interface of the content generation method provided in the embodiments of this disclosure;

[0034] Figure 4 is a third schematic diagram of the interface of the content generation method provided in this embodiment of the present disclosure;

[0035] Figure 5 is a fourth schematic diagram of the interface of the content generation method provided in this embodiment of the present disclosure;

[0036] Figure 6 is a structural block diagram of a content generation device provided in an embodiment of this disclosure;

[0037] Figure 7 is a structural block diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0038] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0039] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0040] The terms "first," "second," etc., used in this disclosure and in the claims are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this disclosure can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0041] The electronic devices in this disclosure can be mobile electronic devices or non-mobile electronic devices. Mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc.; non-mobile electronic devices can be personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc.; this disclosure does not impose specific limitations.

[0042] Currently, in the text-to-image functionality of most AIGC products, the input cost for prompts is very high, and the descriptions are difficult. Faced with the inability to write prompts, users typically try to find words used by other users, modify and adjust them, and then attempt to generate new material. However, both searching for words used by other users and modifying and adjusting those words are time-consuming and complex, often leading many users to give up at the outset.

[0043] As the application of text-to-image (TPO) functionality becomes more widespread, more and more users are using it. However, for users without much experience, it's difficult to accurately describe the expected content. They struggle to write prompts, or their input prompts are often inaccurate, resulting in the inability to quickly and accurately generate content that meets their expectations. For example, editing prompts is costly and difficult for most users. They lack a clear concept of image description, unsure of what prompts to use or how to describe the desired image style. Furthermore, the high randomness and uncontrollability of TPO's generated results, coupled with users' incomplete understanding of image features, leads to limited input prompts that easily overlook professional details such as lighting, lens, camera position, and movement. Additionally, users are unfamiliar with the completeness of prompts and lack a concept of high-quality prompts, consistently failing to generate satisfactory content.

[0044] Based on the aforementioned technical problems, this disclosure provides a content generation method. The method involves displaying a first interface with an input box, a content generation control, and multiple dimension labels. These dimension labels prompt the user to input descriptive information from different feature dimensions to describe the content to be generated. In response to a trigger operation on the first interface, at least one target prompt is displayed in the input box. In response to a trigger operation on the content generation control, a second interface is displayed, showing at least one target content and the at least one target prompt, where the at least one target content is generated based on the at least one target prompt. In this solution, by displaying multiple dimension labels on the first interface, the user is prompted to describe the expected image from which feature dimensions, resulting in more complete image descriptions. Thus, for users with limited experience using the text-to-image function, the prompts from multiple dimension labels allow for accurate descriptions of the expected image from different feature dimensions, improving the accuracy and completeness of the user-input prompts and enabling the rapid and accurate generation of images that meet the user's expectations.

[0045] The execution subject of the content generation method provided in this disclosure can be the aforementioned electronic device (including mobile electronic devices and non-mobile electronic devices), or it can be a functional module and / or functional entity in the electronic device that can implement the content generation method. The specific implementation subject can be determined according to actual usage requirements, and this disclosure does not limit it.

[0046] The content generation method provided by the present disclosure will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0047] As shown in Figure 1, this disclosure provides a content generation method, which may include the following steps 100 to 102.

[0048] 100. Display the first interface.

[0049] The first interface displays an input box, a content generation control, and multiple dimension labels; these multiple dimension labels are used to prompt the user to input prompts describing the content to be generated from different feature dimensions.

[0050] These multiple dimension labels are used to indicate different feature dimensions of the content to be generated. The content to be generated is automatically generated based on the prompts entered by the user on the first interface.

[0051] In this embodiment of the application, the content to be generated can be video, audio, image, text, etc., and there is no limitation here.

[0052] In this embodiment of the application, the prompt information may include information in the form of words, phrases, images, audio, etc., used to describe the content to be generated.

[0053] In this context, the feature dimension of an image can be understood as the descriptive elements or the descriptive subject of the image.

[0054] For example, the feature dimensions of an image may include at least one of the following: the subject of the image, the style of the image, the lens of the image, the color of the image, the light sensitivity of the image, the camera position of the image, and the action of the image. The feature dimensions of an image may also include other aspects, which can be determined according to the actual situation and are not limited here.

[0055] In some embodiments of this disclosure, the multiple dimension labels can be located at any feasible position in the first interface, and the specific location can be determined according to the actual situation, without limitation here.

[0056] In some embodiments of this disclosure, the multiple dimension labels may be located in the input box, and the display state of the multiple dimension labels is different from the display state of the at least one prompt message.

[0057] For example, the multiple dimension labels are displayed in a grayed-out state. Users cannot modify the multiple dimension labels displayed in the input box by triggering the input box. After the user triggers the input box and enters the target prompt information corresponding to a dimension label in the input box, the dimension label can continue to be displayed in the input box in a grayed-out state, or the dimension label can be canceled from being displayed in the input box. The specific method can be determined according to the actual situation, and is not limited here.

[0058] For example, the multiple dimension labels are displayed in an uneditable state, meaning they cannot be modified. In other words, the multiple dimension labels displayed in the input box cannot be modified, and users cannot modify the multiple dimension labels displayed in the input box by triggering the input box. In this way, the dimension labels can be prevented from being modified during the user's input of prompt information, thus preventing them from serving their purpose of prompting the user.

[0059] In this embodiment of the disclosure, the user can see the at least one dimension note while inputting prompt information in the input box. This can promptly prompt the user on which feature dimensions to input prompt information from, and also promptly prompt the user on which feature dimensions have not yet been inputted. By prompting the user to input prompt information from different feature dimensions, complete prompt information describing the image can be obtained, making the generated image more in line with the user's needs and improving the user experience.

[0060] In some embodiments of this disclosure, the first interface may also display other content or other controls, which can be determined according to the actual situation and is not limited here.

[0061] For example, the first interface may also display a keyboard, which allows users to input prompts in the input box using the keyboard. The keyboard may display an input method input area and / or a voice control. In this embodiment of the disclosure, users can input prompts using the input method input area or the voice control.

[0062] 101. In response to a trigger operation on the first interface, display at least one target prompt message in the input box.

[0063] In some embodiments of this disclosure, at least one target prompt can be obtained by the user through input operations on the input box while referring to multiple dimension labels; at least one target prompt can also be obtained by the user through input operations on the input box without referring to multiple dimension labels; at least one target prompt can also be a recommended prompt selected by the user from at least one recommended prompt displayed on the first interface. The specific details can be determined according to the actual situation and are not limited here.

[0064] In some embodiments of this disclosure, the triggering operation on the first interface may include the user's text input operation in the keyboard area, the user's voice input operation, the user's input operation that triggers the display of the input cursor in the input box (a certain area), the user's selection input operation for any recommended prompt information, and other feasible input operations. The specific operation can be determined according to the actual situation and is not limited here.

[0065] In some embodiments of this disclosure, at least one target prompt may correspond to multiple dimension labels, meaning that at least one target prompt may include prompts corresponding to each dimension label among the multiple dimension labels; alternatively, at least one target prompt may correspond to a portion of the multiple dimension labels, meaning that at least one target prompt may only include prompts corresponding to each dimension label among the partial dimension labels; furthermore, a portion of the prompts in at least one target may correspond to all or some of the multiple dimension labels, while another portion of the prompts does not correspond to any of the multiple dimension labels; the specific details can be determined according to the actual situation and are not limited here.

[0066] In some embodiments of this disclosure, when a target marker is displayed on the target dimension label among the multiple dimension labels, the first interface also displays at least one recommendation prompt, which is used to indicate a prompt that matches the target feature dimension indicated by the target dimension label.

[0067] The target dimension label can be any one of the multiple dimension labels, or any part of the multiple dimension labels; the specific choice can be determined based on the actual situation and is not limited here. Different dimension labels correspond to recommendation suggestions belonging to different feature dimensions.

[0068] For example, if the content to be generated is an image, and the target dimension label is the dimension label corresponding to the style of the image, then the at least one recommended prompt is a prompt for indicating the style of the image; if the target dimension label is the dimension label corresponding to the color of the image, then the at least one recommended prompt is a prompt for indicating the color of the image.

[0069] The recommended prompt can be a prompt that is frequently used by the current user within a preset time period, or a prompt that is popular among users of the material editing software. The specific prompt can be determined according to the actual situation and is not limited here.

[0070] In this embodiment of the disclosure, by displaying a target marker on the target dimension label among the multiple dimension labels, at least one recommended prompt message matching the target feature dimension indicated by the target dimension label is triggered to be displayed on the first interface. In this way, at least one recommended prompt message for the target feature dimension is displayed to the user, so that the user can select the required prompt message from it and input it into the input box to generate an image. This can solve the problem that the user is not clear on how to describe what the prompt message matching the target feature dimension in the expected image is, and the user does not need to think about what the prompt message matching the target feature dimension in the expected image is. This can reduce the difficulty for the user to input prompt message and improve the user experience.

[0071] In some embodiments of this disclosure, the target marker can be a selection marker, a text bolding marker, an underline marker, or an input cursor, etc. The specific marker can be determined according to the actual situation and is not limited here.

[0072] In some embodiments of this disclosure, when the multiple dimension labels can be located within the input box, the target marker can be the input cursor of the input box. Thus, when the input cursor is located in the area of ​​a dimension label, at least one recommendation prompt corresponding to that dimension label is displayed on the first interface.

[0073] For example, when the input cursor is located at the dimension label corresponding to the lens of the image (hereinafter referred to as the lens dimension label), at least one recommendation prompt corresponding to the lens dimension label is displayed in the first interface.

[0074] In some embodiments of this disclosure, the multiple dimension labels divide the input box into different input areas, that is, the input box is a segmented input box, and different dimension labels correspond to different input box segments. When the input cursor is located at a dimension label, the input prompt information is located in the input box segment where that dimension label is located.

[0075] For example, when the input cursor is located at the dimension label corresponding to the subject of the image (hereinafter referred to as the subject dimension label), the prompt information entered in the input box is located in the input box segment corresponding to that subject dimension label.

[0076] In this embodiment of the disclosure, when the multiple dimension labels can be located in the input box, the target mark can be the input cursor of the input box, which can promptly prompt the user which feature dimension is currently being input, thereby making the prompt information input by the user more consistent with the feature dimension, and allowing the user to input prompt information from different feature dimensions, thereby making the generated image more in line with the user's needs and improving the user experience.

[0077] In some embodiments of this disclosure, before step 101 above, the content generation method provided in this application may further include step 103 below; step 101 above can be specifically implemented through step 101a below.

[0078] 103. In response to a trigger operation targeting a target dimension label among the plurality of dimension labels, at least one recommendation prompt message is displayed on the first interface.

[0079] The at least one recommendation prompt is used to indicate a prompt that matches the target feature dimension indicated by the target dimension label.

[0080] For example, step 103 above can be implemented by step 103a below.

[0081] 103a. In response to a triggering operation that displays the input cursor in the input area corresponding to the target dimension label, the at least one recommendation prompt is displayed in the first interface.

[0082] 101a. In response to a triggering operation on the target recommendation message in the at least one recommendation message, display the target recommendation message in the input box.

[0083] The at least one target prompt information includes the target recommendation prompt information.

[0084] It can be understood that the triggering operation on the first interface in step 101 above includes the triggering operation on the target recommendation prompt information in the at least one recommendation prompt information, and the target recommendation prompt information is one of the at least one target prompt information.

[0085] In this embodiment of the disclosure, when a target marker is displayed on the target dimension label, at least one selectable suggestion is provided to the user. Therefore, the user can select one or more of the at least one suggestion from the suggestions as suggestions for generating the image. This reduces the difficulty of inputting suggestions for the user, improves the accuracy and speed of inputting suggestions, and increases the efficiency of inputting suggestions, thereby improving the user experience.

[0086] In some embodiments of this disclosure, the user may not select any of the recommended prompts from at least one of the recommended prompts that match the target dimension label. If the user determines that at least one of the recommended prompts does not include prompts that can accurately describe the expected image, and the user has already determined the prompts that can accurately describe the expected image, the user can input the prompts in the input box by text input or voice input.

[0087] In some embodiments of this disclosure, the first interface also displays a reference content control associated with the target dimension label, and the above step 101 can be specifically implemented through the following steps 101b to 101d.

[0088] 101b. In response to a triggering operation on the reference content control, display at least one reference content in the first interface.

[0089] The reference content can be reference videos, reference audio, reference images, reference text, etc., and the specifics can be determined according to the actual situation. No restrictions are imposed here.

[0090] In some embodiments of this disclosure, at least one reference content may be imported locally from an electronic device, or imported from a conversation in an instant social application, or may be preset content related to a target dimension tag. The specific content can be determined according to the actual situation and is not limited here.

[0091] 101c. In response to the selection operation of the target reference content in the at least one reference content, at least one reference prompt message is displayed in the first interface.

[0092] The at least one reference prompt information is used to indicate the prompt information identified from the target reference content that matches the target feature dimension.

[0093] In this embodiment of the disclosure, different dimension labels correspond to different reference content controls. When target markers are displayed on different dimension labels, the at least one reference content triggered by the corresponding reference content control may be the same or different. However, in response to the selection operation of the same target reference content, the feature dimensions corresponding to the at least one reference prompt information triggered are different.

[0094] 101d. In response to a triggering operation of the target reference information in the at least one reference prompt information, the target reference prompt information is displayed in the input box.

[0095] The at least one target prompt information includes the target reference prompt information.

[0096] It can be understood that the triggering operation of the first interface in step 101 above includes the triggering operation of the target reference prompt information in the at least one reference prompt information, and the target reference prompt information is one of the at least one target prompt information.

[0097] In this embodiment of the disclosure, by responding to a trigger operation on the reference content control, at least one reference content is displayed on the first interface. In response to a selection operation on the target reference content, at least one selectable reference prompt information recommended to the user is displayed on the first interface. Therefore, the user can select one or more of the at least one reference prompt information as prompt information for generating the content to be generated, thereby reducing the difficulty of inputting prompt information for the user, improving the accuracy and speed of inputting prompt information, improving the efficiency of inputting prompt information, and improving the user experience.

[0098] In some embodiments of this disclosure, the user may not select any of the reference prompts among at least one reference prompts that match the target dimension label. If the user determines that at least one reference prompt does not include a prompt that can accurately describe the expected content (content to be generated), and the user has already determined the prompt for accurately describing the expected content, the user can input the prompt in the input box by text input or voice input.

[0099] In some embodiments of this disclosure, the reference content control is a reference image control. Step 101b can be implemented by step 101b1, step 101c can be implemented by step 101c1, and step 101d can be implemented by step 101d1.

[0100] 101b1. In response to a trigger operation on the reference image control, display at least one reference image in the first interface.

[0101] In some embodiments of this disclosure, at least one reference image may be imported from the local photo album of an electronic device, or from a conversation of a real-time social application, or may be a preset image related to a target dimension tag. The specific image can be determined according to the actual situation and is not limited here.

[0102] In some embodiments of this disclosure, if at least one reference image is imported from a local photo album, the material editing software needs to obtain permission to access the local photo album when the reference image control is used for the first time. Then, the software determines whether it has permission to access the local photo album based on the user's selection. If the user allows the material editing software to access the local photo album, at least one reference image can be displayed on the first interface; otherwise, at least one reference image is prohibited from being displayed on the first interface.

[0103] In some embodiments of this disclosure, if at least one reference image is imported from a local photo album, then the at least one reference image can be all or part of the images in the local photo album, which can be determined according to the actual situation and is not limited here.

[0104] 101c1. In response to a selection operation of a target reference image in the at least one reference image, at least one reference prompt message is displayed in a first interface.

[0105] The at least one reference prompt information is used to indicate prompt information that is identified from the target reference image and matches the feature dimension of the target.

[0106] In this embodiment of the disclosure, different dimension labels correspond to different reference image controls. When target marks are displayed on different dimension labels, the at least one reference image triggered by the corresponding reference image control may be the same or different. However, in response to the selection operation of the same target reference image, the feature dimensions corresponding to at least one reference prompt information triggered for display are different.

[0107] For example, if the input cursor is located on the subject dimension label corresponding to the subject of the image, by selecting the target reference image, at least one reference prompt information matching the subject dimension label is identified from the target reference image, and the at least one reference prompt information belongs to the feature dimension of the subject of the image; if the input cursor is located on the color dimension label corresponding to the color of the image, by selecting the target reference image, at least one reference prompt information matching the color dimension label is identified from the target reference image, and the at least one reference prompt information belongs to the feature dimension of the color of the image.

[0108] 101d1. In response to a triggering operation on the target reference information in the at least one reference prompt information, the target reference prompt information is displayed in the input box.

[0109] The at least one target prompt information includes the target reference prompt information.

[0110] In this embodiment of the disclosure, when a target marker is displayed on the target dimension label, in response to the selection operation of the target reference image, at least one selectable reference prompt information recommended to the user is displayed on the first interface. Therefore, the user can select one or more of the at least one reference prompt information as prompt information for generating the image according to their needs. In this way, the difficulty of inputting prompt information for the user can be reduced, the accuracy and speed of input prompt information can be improved, the input efficiency of prompt information can be improved, and the user experience can be improved.

[0111] In some embodiments of this disclosure, the user may not select any of the reference prompts among at least one reference prompts that match the target dimension label. If the user determines that at least one reference prompt does not include prompts that can accurately describe the expected image, and the user has already determined the prompts used to accurately describe the expected image, the user can input the prompts in the input box via text input or voice input.

[0112] In some embodiments of this application, the first interface also displays a reference content control associated with the target dimension label, and the above step 101 can be specifically implemented through the following step 101e.

[0113] 101e. In response to a selection operation of a target reference content in the at least one reference content, the target reference content is displayed in the input box, and the at least one target prompt message includes the target reference content.

[0114] It is understandable that, in response to the selection of target reference content, the target reference content is displayed as a target prompt message in the input box. In this way, using the target reference content as the target prompt message can make the description of the content to be generated more detailed and accurate, thereby making the generated content more in line with the user's expectations.

[0115] In some embodiments of this disclosure, after the target recommendation prompt (or target reference prompt) is displayed in the input box, the user can also delete or modify the triggering operation of the target recommendation prompt (or target reference prompt) so that at least one target prompt does not include the target recommendation prompt (or target reference prompt). The specific details can be determined according to the actual situation and are not limited here.

[0116] In some embodiments of this disclosure, a progress bar control is also displayed in the first interface. The progress bar control is used to indicate the sum of the descriptive degree corresponding to the feature dimensions matched by the at least one target prompt information. The descriptive degree is used to indicate the completeness of the description of the content to be generated by the corresponding feature dimension.

[0117] In some embodiments of this application, the degree of description corresponding to different feature dimensions may be the same or different, and the specific degree may be determined according to the actual situation, which is not limited here.

[0118] In some embodiments of this application, if the degree of description corresponding to different feature dimensions is the same, then the degree of description corresponding to each feature dimension is the reciprocal of the number of multiple dimension labels; if the degree of description corresponding to different feature dimensions is not the same, then the degree of description corresponding to different feature dimensions can be determined according to the importance of the description of the content to be generated by different feature dimensions. Specifically, it can be determined according to the actual situation, and is not limited here.

[0119] For example, if different feature dimensions correspond to the same level of description, then the progress bar control is used to indicate the ratio of the number of feature dimensions to which the prompt information (at least one target prompt information) included in the input box belongs to the number of the multiple dimension labels.

[0120] In this embodiment, a progress bar control is associated with an input box. The progress bar control is used to indicate the completeness of the input prompt information. Since the number of multiple dimension labels is fixed, the greater the number of feature dimensions to which the input prompt information belongs, the greater the completeness of the input prompt information. The greater the completeness of the input prompt information, the more complete the description of the desired image, and the closer the image can be to the desired image based on the input prompt information, thus generating an image that meets the user's expectations.

[0121] In this embodiment of the disclosure, the user can determine the completeness of the prompt information entered in the input box based on the progress information displayed by the progress bar control, and then determine how close the image generated based on the currently entered prompt information is to the image expected by the user. This can encourage the user to input prompt information from more feature dimensions in order to generate an image that is closer to the user's expectations.

[0122] In this embodiment, the first interface is not limited to one interface or multiple interfaces; the specific interface can be determined according to the actual situation, and no limitation is made here.

[0123] For example, if the first interface is a single interface, an input box and a progress bar control can always be displayed on the first interface. When at least one recommended prompt and reference content control are displayed on the first interface, at least one reference content and at least one reference prompt are not displayed on the first interface. If the first interface is multiple interfaces, one interface is used to display an input box, a progress bar control, at least one recommended prompt and reference content control, and another interface is used to display an input box, a progress bar control, at least one reference content and at least one reference prompt.

[0124] 102. In response to the triggering operation of the content generation control, display the second interface.

[0125] The second interface displays at least one target content and at least one target prompt information, wherein the at least one target content is generated based on the at least one target prompt information.

[0126] It is understood that, in response to a triggering operation on the content generation control, at least one target prompt message is obtained, then the at least one target prompt message is input into the content generation model to generate at least one target content, and then the at least one target content is displayed. The content generation model can be determined with reference to relevant technologies, and is not limited here.

[0127] In some embodiments of this application, at least one target prompt can be displayed at any location on the second interface. For example, if an input box is displayed on the second interface, at least one target prompt can be displayed in the input box.

[0128] In this embodiment of the disclosure, at least one target content and at least one target prompt information are displayed on the second interface, so that the user can compare the image effect of the at least one target content and at least one target prompt information, determine how to modify at least one target prompt information, and generate an image that is closer to the expected image.

[0129] In some embodiments of this disclosure, the second interface also displays recommended adjustment information, which is generated based on the at least one target content and the at least one target prompt information; the recommended adjustment information is used to indicate the adjustment direction of the at least one target prompt information.

[0130] The second interface can display one or more recommended adjustment messages, depending on the actual situation; no limit is set here.

[0131] In some embodiments of this disclosure, the recommended adjustment information may be directly the adjustment direction of the prompt information for the at least one target, or it may be indirectly an indication of the adjustment direction of the prompt information for the at least one target. The specific direction can be determined according to the actual situation, and is not limited here.

[0132] In some embodiments of this disclosure, the recommended adjustment information is further used to indicate that the image generated after adjusting the at least one target prompt information according to the adjustment direction is more closely matched with the prompt information of the generated image. That is, the image generated after adjusting the at least one target prompt information according to the adjustment direction is more closely matched with the image expected by the user, and the generated image is closer to the image expected by the user.

[0133] The specific content of the recommended adjustment information is not limited in the embodiments disclosed herein, and can be determined according to the actual situation. No limitation is made here.

[0134] In this embodiment of the disclosure, recommended adjustment information is provided to the user in the second interface. The user can refer to the recommended adjustment information to determine how to adjust at least one target prompt information to obtain an image that better meets the user's expectations. Alternatively, the user can choose not to refer to the recommended adjustment information and determine how to adjust at least one target prompt information on their own to obtain an image that better meets the user's expectations.

[0135] In this embodiment of the disclosure, by displaying recommended adjustment information on the second interface, the user can be provided with feasible adjustment directions for at least one target prompt information, thereby reducing the difficulty for the user to analyze how to adjust at least one target prompt information. This allows the user to adjust at least one target prompt information according to the recommended adjustment information, so that the generated image better meets the user's expectations.

[0136] In some embodiments of this disclosure, the recommended adjustment information includes first prompt information; when the at least one target prompt information does not include the first prompt information, the adjustment direction includes any one of the following: adding the first prompt information, replacing the second prompt information in the at least one target prompt information with the first prompt information; when the at least one target prompt information includes the first prompt information, the adjustment direction includes any one of the following: deleting the first prompt information, adjusting the image detail information corresponding to the first prompt information.

[0137] For example, when the first prompt information includes weight information, the image detail information corresponding to the first prompt information can be adjusted to include the weight information; when the first prompt information includes proportion information, the image detail information corresponding to the first prompt information can be adjusted to include the proportion information; when the first prompt information includes aspect ratio information, the image detail information corresponding to the first prompt information can be adjusted to include the aspect ratio information.

[0138] In this embodiment of the disclosure, the adjustment direction may also include other situations, which can be determined according to the actual situation and are not limited here.

[0139] In this embodiment of the disclosure, since the output result of the image generation technology based on prompt information is random, by summarizing and learning the at least one target content generated and the at least one target prompt information used in the generated image, recommended adjustment information is output. This allows for precise control of variables, so that after adjusting the prompt information based on the recommended adjustment information, the generation result is no longer random. This speeds up the generation of images that meet user expectations, and can quickly generate images that meet expectations for both users with and without experience using the text-to-image function.

[0140] Currently, in related image generation technologies, users adjust the prompts on the generated image based on the effect of the generated image and their expected image effect, so that the generated image based on the adjusted prompts is closer to the user's expected image. In this embodiment, after generating the image based on the prompts, the generated image and its prompts are analyzed. The analysis results are summarized and analyzed to predict which results are recommended for the user (adjusting the prompts based on these results will quickly produce an image that meets the user's expectations) and which results are discarded (adjusting the prompts based on these results will make the generated image deviate more from the user's expectations). Finally, recommended adjustment information is generated and displayed to the user to guide them in adjusting the prompts based on the recommended adjustment information, and then generating an image closer to the user's expectations based on the adjusted prompts.

[0141] In some embodiments of this disclosure, the recommended adjustment information may be obtained by analyzing the common features of at least one target content to obtain common image features, then analyzing the common features of at least one target prompt information to obtain common prompt information features, then combining the common features of the prompt information and the common features of the image to predict the features of the image expected by the user, and then determining the recommended adjustment information for adjusting at least one target prompt information based on the predicted features of the image expected by the user and at least one target prompt information.

[0142] In some embodiments of this disclosure, the recommended adjustment information also has a certain degree of randomness. The recommended adjustment information is usually the adjustment information that predicts the highest probability of making the image meet the user's expectations from the analyzed adjustment information. Even if at least one target content and at least one target prompt information are the same, the recommended adjustment information obtained by summarizing and analyzing the at least one target content and at least one target prompt information at different times may be different.

[0143] In some embodiments of this disclosure, at least one target content and at least one target prompt information can be input into a prompt information optimization model to output the recommended adjustment information. The prompt information optimization model is trained using model training data. Each sample data in the large amount of sample data in the model training data includes prompt information, an image generated based on the prompt information, and adjusted prompt information obtained by the user adjusting the prompt information based on the generated image. The specific training process can be referred to in related technologies and is not limited here.

[0144] In this embodiment of the disclosure, the second interface and the first interface can be the same interface, only the displayed content is different. The second interface can also be a different interface from the first interface. The specific interface can be determined according to the actual situation, and no limitation is made here.

[0145] In this embodiment of the disclosure, by displaying multiple dimension labels on the first interface, users are prompted to describe the expected generated image from which feature dimensions, thus obtaining relatively complete prompts for image description. In this way, users without much experience using the text-to-image function can accurately describe the expected image from different feature dimensions based on the prompts from the multiple dimension labels, improving the accuracy and completeness of the user-input prompts for describing the expected image, thereby quickly and accurately generating an image that meets the user's expectations.

[0146] In some embodiments of this disclosure, the second interface also displays the content generation control. After step 102 above, the content generation method provided by the embodiments of this disclosure may further include the following steps 104 and 105.

[0147] 104. In response to a trigger operation on the second interface, update the at least one target prompt information.

[0148] In some embodiments of this application, an input box is displayed in the second interface, and the input box displays at least one target prompt message. The triggering operation of the second interface can be the triggering operation of the input box displayed in the second interface.

[0149] In some embodiments of this application, the second interface displays multiple first recommendation prompts for the user. These multiple first recommendation prompts may be preset recommendation prompts or recommendation prompts generated by an effect adjustment model based on the display effect of at least one target content to adjust at least one target content (through these recommendation prompts, the adjusted at least one target content can better meet the user's needs and the display effect can be more satisfactory to the user). The specifics can be determined according to the actual situation and are not limited here.

[0150] Updating the at least one target prompt information may include deleting one or more prompt information from the at least one target prompt information, adding one or more prompt information, or modifying one or more prompt information. The specifics can be determined according to the actual situation and are not limited here.

[0151] 105. In response to a triggering operation on the content generation control, update the at least one target content.

[0152] The updated target content is generated based on the updated target prompt information.

[0153] It is understandable that, in response to the triggering operation of the content generation control, at least one updated target prompt information is obtained, then the updated at least one target prompt information is input into the content generation model to generate at least one updated target content, and then the updated at least one target content is displayed.

[0154] It is understood that if at least one target content includes an image that meets the user's expectations, then steps 104 and 105 do not need to be executed. If at least one target content does not include an image that meets the user's expectations, then steps 104 and 105 need to be executed to obtain an updated target content. If the updated target content includes an image that meets the user's expectations, then steps 104 and 105 do not need to be executed again to update the generated target content. If the updated target content does not include an image that meets the user's expectations, then steps 104 and 105 need to be executed again to update the generated target content. This process continues until the latest updated target content includes an image that meets the user's expectations.

[0155] In this embodiment of the disclosure, an input box including at least one target prompt information and a content generation control are displayed on the second interface, which makes it convenient for the user to adjust at least one target prompt information on the second interface and generate a new image based on the adjusted prompt information.

[0156] In some embodiments of this disclosure, the prompt information entry interface corresponding to the content generation method provided in this embodiment may also display inspiration images recommended to the user. The user can directly use a recommended inspiration image, or trigger the recognition of a recommended inspiration image to obtain prompt information describing the inspiration image, and then adjust the prompt information to generate an image that meets the user's needs based on the adjusted prompt information. The specific details can be determined according to the actual situation and are not limited here.

[0157] For example, as shown in Figure 2, the content to be generated is an image, and the prompt information is a prompt word. This is an optional text-based image entry interface. The text-based image entry interface displays multiple recommended inspiration images and a text-based image entry control marked "201". The text-based image entry control includes the prompt content "Please enter the prompt word you are thinking of". Clicking the text-based image entry control displays the first interface, as shown in Figure 3. The user has already entered "prompt word 1" in the area corresponding to dimension label 1 in the input box marked "302". The current input cursor marked "302" is located in the area corresponding to dimension label 2. The first interface displays multiple recommended prompt words corresponding to dimension label 2. If the user selects one from the multiple recommended prompt words, the selected recommended prompt word is displayed in the input box. The first interface also displays a progress bar control marked "303". The progress bar control currently indicates that the input completeness of the prompt word is "x%" (x>0). The first interface also displays a reference image control. In response to a trigger operation on the reference image control, a first interface including multiple recommended images is displayed. In response to a user's trigger operation on recommended image 2, multiple reference prompts corresponding to recommended image 2 are displayed. In response to a trigger operation on reference prompt 3, reference prompt 3 is displayed in the area corresponding to dimension label 2 in the input box, and the progress bar control indicates the input completeness of the prompt 'y%' (y>x). After the user inputs multiple prompts, in response to a trigger operation on the content generation control, a second interface as shown in Figure 5 is displayed. The second interface includes four generated target content images, recommendation adjustment information, and six prompts for the generated images. For example, if the six prompts are "girl portrait, Japanese style, low contrast, blue background, star effect," then the recommendation adjustment information could be "Summary: The keyword 'sparkling stars' makes it easier to generate accurate results."

[0158] In this embodiment, interactive capabilities are extended based on existing algorithms. This allows for low-cost guidance of users to perfectly input prompts, provides reasonable recommendations and adjustments by predicting the effect of images that meet user expectations, and ultimately achieves rapid generation of images that meet the desired results.

[0159] Currently, various content editing software's entry and distribution portals all integrate AIGC capabilities. Therefore, the interactive scheme corresponding to the content generation method provided in this disclosure can be integrated as an SDK into various terminals and entry points for reuse. Whether it is a user's image editing needs or video generation or editing needs, the content generation method provided in this disclosure can be used to quickly achieve them.

[0160] Figure 6 is a structural block diagram of a content generation device according to an embodiment of this disclosure. As shown in Figure 6, it includes: a display module 601, used to display a first interface, which displays an input box, a content generation control, and multiple dimension labels; the multiple dimension labels are used to prompt the user to input prompt information describing the content to be generated from different feature dimensions; in response to a trigger operation on the first interface, at least one target prompt information is displayed in the input box; in response to a trigger operation on the content generation control, a second interface is displayed, which displays at least one target content and the at least one target prompt information, the at least one target content being generated based on the at least one target prompt information.

[0161] In some embodiments of this disclosure, the display module is further configured to, in response to a triggering operation on a target dimension label among the plurality of dimension labels, display at least one recommended prompt in the first interface before displaying at least one target prompt in the input box in response to a triggering operation on the first interface. The at least one recommended prompt is used to indicate a prompt that matches the target feature dimension indicated by the target dimension label. The display module 601 is specifically configured to, in response to a triggering operation on the target recommended prompt among the at least one recommended prompt, display the target recommended prompt in the input box. The at least one target prompt includes the target recommended prompt.

[0162] In some embodiments of this disclosure, the first interface further displays a reference content control associated with the target dimension label. The display module 601 is specifically configured to, in response to a trigger operation on the reference content control, display at least one reference content in the first interface; in response to a selection operation on the target reference content among the at least one reference content, display at least one reference prompt message in the first interface, the at least one reference prompt message being used to indicate prompt messages identified from the target reference content that match the target feature dimension; in response to a trigger operation on the target reference prompt message among the at least one reference prompt message, display the target reference prompt message in the input box, the at least one target prompt message including the target reference prompt message; or, in response to a selection operation on the target reference content among the at least one reference content, display the target reference content in the input box, the at least one target prompt message including the target reference content.

[0163] In some embodiments of this disclosure, the multiple dimension labels are located in different input areas of the input box, and the display state of the multiple dimension labels is different from the display state of the at least one prompt message.

[0164] In some embodiments of this disclosure, the display module 601 is specifically used to display the at least one recommendation prompt in the first interface in response to a trigger operation that displays an input cursor in the input area corresponding to the target dimension label.

[0165] In some embodiments of this disclosure, a progress bar control is also displayed in the first interface. The progress bar control is used to indicate the sum of the descriptive degree corresponding to the feature dimensions matched by the at least one target prompt information. The descriptive degree is used to indicate the completeness of the description of the content to be generated by the corresponding feature dimension.

[0166] In some embodiments of this disclosure, the second interface also displays recommended adjustment information, which is generated based on the at least one target content and the at least one target prompt information; the recommended adjustment information is used to indicate the adjustment direction of the at least one target prompt information.

[0167] In some embodiments of this disclosure, the recommended adjustment information includes first prompt information; when the at least one target prompt information does not include the first prompt information, the adjustment direction includes any one of the following: adding the first prompt information, replacing the second prompt information in the at least one target prompt information with the first prompt information; when the at least one target prompt information includes the first prompt information, the adjustment direction includes any one of the following: deleting the first prompt information, adjusting the image detail information corresponding to the first prompt information.

[0168] In some embodiments of this disclosure, the second interface also displays the content generation control. The display module 601 is further configured to, after displaying the second interface in response to a trigger operation on the content generation control, update the at least one target prompt information in response to a trigger operation on the second interface; and update the at least one target content in response to a trigger operation on the content generation control, wherein the updated at least one target content is generated based on the updated at least one target prompt information.

[0169] In this embodiment, each module can implement the content generation method provided in the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0170] Figure 7 is a schematic diagram of an electronic device provided in an embodiment of this disclosure. It is used to illustrate an electronic device that implements any content generation method in the embodiments of this disclosure and should not be construed as a specific limitation on the embodiments of this disclosure.

[0171] As shown in Figure 7, the electronic device 700 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0172] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 700 with various devices is shown, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0173] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processor 701, it can perform the functions defined in any content generation method provided in embodiments of this disclosure.

[0174] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0175] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0176] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0177] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: display a first interface, the first interface displaying an input box, a content generation control, and multiple dimension labels; the multiple dimension labels are respectively used to prompt the user to input prompt information describing the content to be generated from different feature dimensions; in response to a triggering operation on the first interface, display at least one target prompt information in the input box; and in response to a triggering operation on the content generation control, display a second interface, the second interface displaying at least one target content and the at least one target prompt information, the at least one target content being generated based on the at least one target prompt information.

[0178] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0179] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0180] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0181] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0182] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0183] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0184] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0185] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A content generation method, comprising: The first interface is displayed, which includes an input box, a content generation control, and multiple dimension labels. The multiple dimension labels are used to prompt the user to input prompt information describing the content to be generated from different feature dimensions. In response to a trigger operation on the first interface, at least one target prompt message is displayed in the input box; In response to a triggering operation on the content generation control, a second interface is displayed. The second interface displays at least one target content and at least one target prompt message, wherein the at least one target content is generated based on the at least one target prompt message.

2. The method according to claim 1, wherein, In response to a triggering operation on the first interface, before displaying at least one target prompt message in the input box, the method further includes: In response to a trigger operation targeting a target dimension label among the plurality of dimension labels, at least one recommendation prompt is displayed on the first interface, wherein the at least one recommendation prompt is used to indicate a prompt that matches the target feature dimension indicated by the target dimension label; In response to a triggering operation on the first interface, displaying at least one target prompt message in the input box includes: In response to a triggering operation on a target recommendation message in the at least one recommendation message, the target recommendation message is displayed in the input box, wherein the at least one target message includes the target recommendation message.

3. The method according to claim 2, wherein, The first interface also displays reference content controls associated with the target dimension label. In response to a trigger operation on the first interface, at least one target prompt message is displayed in the input box, including: In response to a triggering operation on the reference content control, at least one reference content is displayed in the first interface; In response to the selection operation of the target reference content in the at least one reference content, at least one reference prompt information is displayed in the first interface, the at least one reference prompt information being used to indicate the prompt information identified from the target reference content that matches the target feature dimension; In response to a triggering operation on a target reference prompt in the at least one reference prompt, the target reference prompt is displayed in the input box, wherein the at least one target prompt includes the target reference prompt. or, In response to a selection operation of a target reference content among the at least one reference content, the target reference content is displayed in the input box, and the at least one target prompt information includes the target reference content.

4. The method according to claim 2, wherein, The multiple dimension labels are located in different input areas of the input box, and the display state of the multiple dimension labels is different from the display state of the at least one prompt message.

5. The method according to claim 4, wherein, In response to a trigger operation targeting a target dimension label among the plurality of dimension labels, at least one recommendation prompt is displayed on the first interface, including: In response to a trigger operation that displays an input cursor in the input area corresponding to the target dimension label, at least one recommendation prompt is displayed in the first interface.

6. The method according to claim 1, wherein, The first interface also displays a progress bar control, which is used to indicate the sum of the descriptive degree corresponding to the feature dimensions matched by the at least one target prompt information, and the descriptive degree is used to indicate the completeness of the description of the content to be generated by the corresponding feature dimension.

7. The method according to claim 1, wherein, The second interface also displays recommended adjustment information, which is generated based on the at least one target content and the at least one target prompt information; the recommended adjustment information is used to indicate the direction of adjustment for the at least one target prompt information.

8. The method according to claim 7, wherein, The recommended adjustment information includes a first prompt message; If the first prompt information is not included in the at least one target prompt information, the adjustment direction includes any one of the following: adding the first prompt information, or replacing the second prompt information in the at least one target prompt information with the first prompt information; When the at least one target prompt information includes the first prompt information, the adjustment direction includes any one of the following: deleting the first prompt information, or adjusting the image detail information corresponding to the first prompt information.

9. The method according to any one of claims 1 to 8, wherein, The second interface also displays the content generation control. In response to a trigger operation on the content generation control, after displaying the second interface, the method further includes: In response to a trigger operation on the second interface, update the at least one target prompt information; In response to a triggering operation on the content generation control, the at least one target content is updated, and the updated at least one target content is generated based on the updated at least one target prompt information.

10. A content generation apparatus, comprising: The display module is used to display the first interface, which displays an input box, a content generation control, and multiple dimension labels; the multiple dimension labels are used to prompt the user to input prompt information describing the content to be generated from different feature dimensions; In response to a trigger operation on the first interface, at least one target prompt message is displayed in the input box; In response to a triggering operation on the content generation control, a second interface is displayed. The second interface displays at least one target content and at least one target prompt message, wherein the at least one target content is generated based on the at least one target prompt message.

11. An electronic device, comprising: Memory and processor; memory is used to store computer programs. The processor is used to execute the content generation method of any one of claims 1 to 9 when a computer program is invoked.

12. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the content generation method of any one of claims 1 to 9.

Images