Cover image generation method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention discloses a cover image generation method and device, electronic equipment, a storage medium and a program product. The cover image generation method comprises the following steps: in response to a request for generating a cover image of a story text, analyzing the story text, and determining a cover type corresponding to the story text according to an analysis result; the cover type comprises a story image type, a role image type or a third-person perspective description type; and generating a cover image of the story text according to the cover type. According to the method and device, the intelligent generation effect of the cover image of the story text is achieved, it can be ensured that the generated cover image accurately reflects the content features of the story text, the accuracy of cover image generation is improved, and the generation result of the cover image is more flexible and richer.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device, storage medium and program product for generating a cover image. Background Art

[0002] In the related art, in generating the cover image of the story text, the user usually manually selects the background image and the text content, and then synthesizes the background image and the text content selected by the user into the cover image. This method relies on the manual operation of the user and lacks intelligence. In addition, the background image and the text content selected by the user are highly subjective, resulting in an inaccurate cover image of the story text, which is difficult to reflect the content characteristics of the story text. Therefore, it is necessary to provide a method for generating the cover image of the story text intelligently and accurately. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, device, electronic device, storage medium and program product for generating a cover image, so as to solve the problem that the cover image generation effect of the story text is poor and it is difficult to accurately reflect the content characteristics of the story text.

[0004] To solve the above technical problems, the embodiments of the present application are implemented as follows: On the one hand, an embodiment of the present application provides a method for generating a cover image, comprising: In response to a request for generating a cover image of a story text, analyzing the story text, and determining a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A cover image of the story text is generated according to the cover type.

[0005] On the other hand, an embodiment of the present application provides a cover image generation device, including: An analysis module, configured to analyze the story text in response to a request for generating a cover image of the story text, and determine a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A generating module is used to generate a cover image of the story text according to the cover type.

[0006] On the other hand, an embodiment of the present application provides an electronic device, including a processor and a memory electrically connected to the processor, the memory storing a computer program, and the processor being used to call and execute the computer program from the memory to implement the above-mentioned cover image generation method.

[0007] On the other hand, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program can be executed by a processor to implement the above-mentioned method for generating a cover image.

[0008] On the other hand, an embodiment of the present application provides a computer program product, including a computer program, which is executed by a processor to implement the above-mentioned method for generating a cover image.

[0009] The technical solution of the embodiment of the present application is adopted, by analyzing the story text, and determining the cover type corresponding to the story text according to the analysis results, the cover type includes a story image type, a character image type or a third-person perspective narrative type, and then generating a cover image of the story text according to the cover type. It can be seen that the generation process of the cover image does not involve manual operation of the user, and can intelligently determine the cover type that matches the story text, and automatically generate a cover image that matches the cover type, which not only achieves the intelligent generation effect of the cover image, but also can ensure that the generated cover image accurately reflects the content characteristics of the story text, thereby improving the accuracy of the cover image generation. In addition, in the process of intelligently generating the cover image, by dividing the cover type of the story text into a story image type, a character image type or a third-person perspective narrative type, the story text can be expressed through a variety of types of cover images, thereby making the generation result of the cover image more flexible and rich. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate one or more embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in one or more embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 is a schematic flow chart of a method for generating a cover image according to an embodiment of the present application; Figure 2 is a schematic interface diagram of a cover image of a character image type according to an embodiment of the present application; Figure 3 is a schematic interface diagram of a cover image of a character image type according to another embodiment of the present application; Figure 4 This is a schematic interface diagram of a cover image of a third-person perspective narrative type according to an embodiment of the present application; Figure 5 is a schematic interface diagram of a cover image of a third-person perspective narrative type according to another embodiment of the present application; Figure 6 is a schematic interface diagram of a method for generating a cover image according to an embodiment of the present application; Figure 7 is a schematic interface diagram of a method for generating a cover image according to another embodiment of the present application; Figure 8 is a schematic interface diagram of a method for generating a cover image according to yet another embodiment of the present application; Fig. 9 is a schematic interface diagram of a method for generating a cover image according to yet another embodiment of the present application; Fig.10 is a schematic interface diagram of a method for generating a cover image according to yet another embodiment of the present application; Fig.11 is a schematic interface diagram of a method for generating a cover image according to yet another embodiment of the present application; Fig.12 is a schematic block diagram of a cover image generating device according to an embodiment of the present application; Fig.13 is a schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a method, device, electronic device, storage medium and program product for generating a cover image, so as to solve the problem that the cover image generation effect of a story text is poor and it is difficult to accurately reflect the content characteristics of the story text.

[0013] In order to enable the technical solution in the present application to be better understood by the personnel in the technical field, the technical solution in the embodiment of the present application will be clearly and completely described below in combination with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should belong to the scope of protection of the present application. For example, in response to receiving the active request of the user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require the acquisition and use of the user's personal information. Thus, the user can autonomously choose whether to provide personal information to the electronic device, application, server or storage medium and other software or hardware that performs the operation of the technical solution of the present disclosure according to the prompt information. As an optional but non-limiting implementation method, in response to receiving the active request of the user, the method of sending the prompt information to the user can be, for example, a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0014] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein.

[0015] The method for generating a cover image provided in the embodiment of the present application can be executed by an electronic device, or by software installed in the electronic device. Specifically, the electronic device can be a terminal device or a server device. The terminal device can include a smart phone, a laptop computer, a smart wearable device, a vehicle terminal, etc. The server device can include an independent physical server, a server cluster composed of multiple servers, or a cloud server capable of cloud computing.

[0016] Figure 1 is a schematic flow chart of a method for generating a cover image according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps S102-S104: Step S102, in response to a request to generate a cover image for a story text, analyze the story text, and determine a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type.

[0017] Optionally, when analyzing a story text and determining a cover type corresponding to the story text based on the analysis results, the following steps can be performed: analyzing the story type of the story text; and selecting a cover type that matches the story type from multiple cover types to be selected as the cover type of the story text.

[0018] The story type of the story text can be determined by analyzing at least one of the following content features of the story text: the story introduction of the story text, the story atmosphere of the story text and / or the story tone. The story atmosphere of the story text refers to the overall atmosphere and mood of the story text. The story tone of the story text refers to the overall style and main emotions of the story text. Common story types may include apocalyptic, fantasy, competitive, detective, romantic, urban emotional, workplace, etc.

[0019] Step S104, generating a cover image of the story text according to the cover type.

[0020] Optionally, when generating a cover image of a story text according to a cover type, the following steps may be performed: acquiring text feature information of the story text according to cover attribute information of the cover type; and generating a cover image according to the text feature information.

[0021] The cover attribute information may include at least one of the following: image elements on the cover image, image element types, and display information of image elements. The cover attribute information is used to determine which text feature information of the story text is analyzed. Image elements may include images and / or text. Image element types may include at least one of the following: atmosphere images, character images, wonderful dialogue text (i.e., wonderful dialogue content), etc. The display information of image elements may include at least one of the following: the display position and display mode (such as font, color, etc.) of the image elements on the cover image.

[0022] Optionally, the cover attribute information corresponding to the story image type may include an atmosphere image, and the cover attribute information corresponding to the character image type may include at least one of a character image, character information, and a character's wonderful dialogue content. The cover attribute information corresponding to the third-person perspective narrative type may include at least one of wonderful dialogue content and a story introduction.

[0023] The text feature information may include at least one of the following: the story atmosphere of the story text, the story tone of the story text, the highlight text in the story text, the text atmosphere of the highlight text, the text tone of the highlight text, the role information of the story characters in the story text, the wonderful dialogue content, the role information of the dialogue characters corresponding to the wonderful dialogue content, the story summary of the story text, etc.

[0024] The highlight text in the story text refers to the wonderful fragments in the story text, such as the fragments where the plot turns, the fragments with more intense plots, etc. The text atmosphere of the highlight text refers to the atmosphere and mood of the highlight text, and the text tone of the highlight text refers to the style and main emotion of the highlight fragment corresponding to the highlight text. The wonderful dialogue content refers to the dialogue fragments that are more prominent and very eye-catching in the story text. The highlight text may include the wonderful dialogue content. The role information may include at least one of the following: role attribute information, role relationship information, and role behavior information. The role attribute information includes the personal information of the role, such as the role name, gender, age, hobbies, personality, etc. The role relationship information refers to the relationship between multiple roles, such as husband-wife relationship, colleague relationship, friend relationship, etc. The role behavior information refers to the actions taken by the role (or multiple roles), such as "role A patted the table".

[0025] Among the several cover types, the cover image of the story image type uses images to represent the text feature information of the story text, such as representing the story tone of the story text, the text atmosphere of the highlight text, etc. The cover image of the character image type uses images and / or texts to represent the text feature information related to the characters of the story text, such as representing the character attribute information, character relationship information, and the wonderful dialogue content between the characters, etc. The cover image of the third-person perspective narrative type uses texts to represent the text feature information of the story text, such as representing the wonderful dialogue content by telling the story from a third-person perspective outside the story.

[0026] For story texts that emphasize atmosphere, such as apocalyptic and suspense stories, it is expected that the overall atmosphere and tone of the story text can be conveyed through the cover image, so the cover type corresponding to such story text can be determined as the story image type. For story texts with more conflict plots, such as sports and investigation stories, it is expected that the highlight text in the story text can be visualized and visualized through the cover image, so the cover type corresponding to such story text can be determined as the story image type.

[0027] For story texts with obvious protagonists, multiple protagonists or group portraits, such as romance, urban emotional, and workplace story texts, it is expected that the cover image conveys the relationship between the protagonist or all the characters, so the cover type corresponding to such story texts can be determined as the character image type. For story texts that advance the plot through dialogue, such as urban and love story texts, it is expected that the cover image conveys the wonderful dialogue in the story text and the character information involved in the wonderful dialogue, so the cover type corresponding to such story text can be determined as the character image type.

[0028] For story texts that highlight online chats, such as online novels and workplace stories, it is expected that the cover image will convey the story content or exciting chat content of the story text. Therefore, it can be determined that the cover type corresponding to this type of story text is the third-person perspective narrative type.

[0029] For different cover types, the generation methods of the cover images are different. The following embodiments will describe in detail the generation method of the cover image of each cover type.

[0030] In this embodiment, the request for generating the cover image may be an AI (Artificial Intelligence) generation request. Based on this, the AI ​​big model may analyze the story text and determine the cover type corresponding to the story text according to the analysis result. Then, the AI ​​big model generates a cover image of the story text according to the cover type. The AI ​​big model may use any open source artificial intelligence model with text analysis capabilities.

[0031] The technical solution of the embodiment of the present application is adopted, by analyzing the story text, and determining the cover type corresponding to the story text according to the analysis results, the cover type includes a story image type, a character image type or a third-person perspective narrative type, and then generating a cover image of the story text according to the cover type. It can be seen that the generation process of the cover image does not involve manual operation of the user, and can intelligently determine the cover type that matches the story text, and automatically generate a cover image that matches the cover type, which not only achieves the intelligent generation effect of the cover image, but also can ensure that the generated cover image accurately reflects the content characteristics of the story text, thereby improving the accuracy of the cover image generation. In addition, in the process of intelligently generating the cover image, by dividing the cover type of the story text into a story image type, a character image type or a third-person perspective narrative type, the story text can be expressed through a variety of types of cover images, thereby making the generation result of the cover image more flexible and rich.

[0032] In one embodiment, the cover type is a story image type, and the text feature information includes at least one of the following: the story atmosphere and / or story tone of the story text, the text atmosphere and / or text tone of the highlight text in the story text. The story atmosphere of the story text refers to the overall atmosphere and mood of the story text, and the story tone of the story text refers to the overall style and main emotion of the story text. The highlight text in the story text refers to the wonderful fragments in the story text, such as fragments where the plot turns, fragments with more intense plots, and so on. The text atmosphere of the highlight text refers to the atmosphere and mood of the highlight text, and the text tone of the highlight text refers to the style and main emotion of the highlight fragment corresponding to the highlight text.

[0033] In this embodiment, when generating a cover image according to text feature information, at least one of the following steps A1 to A2 may be performed: Step A1, generating an image that matches the atmosphere and / or tone of the story as a cover image.

[0034] Step A2: Generate an image that matches the atmosphere and / or tone of the text as a cover image.

[0035] For story texts that emphasize atmosphere, such as apocalyptic and suspense story texts, it is expected that the overall atmosphere and tone of the story text can be conveyed through the cover image, so the text feature information includes the story atmosphere and / or story tone of the story text, so that the generated cover image can convey the story atmosphere and / or story tone of the story text. For story texts with more conflict plots, such as sports and investigation story texts, it is expected that the highlight text in the story text can be visualized and visualized through the cover image, so the text feature information can include the text atmosphere and / or text tone of the highlight text, so that the cover image can convey the text atmosphere and / or text tone of the highlight text.

[0036] It can be seen that the cover image of the story image type can convey the overall atmosphere and tone of the story text, or visualize and visualize the highlight text in the story text. Therefore, for story texts that emphasize atmosphere (such as apocalyptic and suspense story texts) and story texts with more conflict plots (such as sports and investigation story texts), story image type cover images can be generated for the story text.

[0037] In one embodiment, the cover type includes a character image class, and the text feature information includes at least one of the following: character information of the story characters in the story text, wonderful dialogue content, and character information of the dialogue characters corresponding to the wonderful dialogue content. The character information includes at least one of the following: character attribute information, character relationship information, and character behavior information. The character attribute information includes the character's personal information, such as the character's name, gender, age, hobbies, personality, etc. The character relationship information refers to the relationship between multiple characters, such as husband and wife relationships, colleague relationships, friend relationships, etc. The character behavior information refers to the actions taken by the character (or multiple characters), such as "character A patted the table." The wonderful dialogue content refers to the more prominent and very eye-catching dialogue fragments in the story text.

[0038] In this embodiment, when generating a cover image according to text feature information, the following steps may be performed: an image matching the character information is generated as a cover image. Since the character may be the protagonist, all characters, or a dialogue character corresponding to the wonderful dialogue content in the story text, for a cover image of the character image type, the cover image may convey one of the protagonist information, all character information, or the character information of the dialogue character corresponding to the wonderful dialogue content. If the protagonist line of the story text is very obvious, the protagonist information may be conveyed through the cover image. If the story text involves multiple characters or a group story, the character information of all characters may be conveyed through the cover image. If the story text uses dialogue to advance the plot, the character information of the dialogue character corresponding to the wonderful dialogue content may be conveyed through the cover image.

[0039] Figure 2 is a schematic interface diagram of a cover image of a character image type according to an embodiment of the present application. Figure 2 As shown, the cover type includes a character image class, and the text feature information includes the character information of the story characters in the story text. Assuming that the protagonists in the story text include character 1 and character 2, the images of character 1 and character 2 in the cover image are matched with the character information of character 1 and character 2 respectively, so that the character information of the protagonist is accurately conveyed through the cover image. For example, the gender of character 1 is male and the age is 30 years old, and the gender of character 2 is female and the age is 28 years old. Then an image that meets the characteristics of "gender male, age 30 years old" can be generated as the image of character 1, and an image that meets the characteristics of "gender female, age 28 years old" can be generated as the image of character 2.

[0040] Optionally, when generating an image matching the character information as a cover image, an image matching the character information may be generated, and wonderful dialogue content may be added to the image matching the character information to obtain a cover image. For example, the cover type includes a character image class, and the text feature information includes wonderful dialogue content and character information of the dialogue character. By analyzing the wonderful dialogue content in the story text and the character information of the dialogue character of the wonderful dialogue content, a character image matching the character information of the dialogue character is generated, and the wonderful dialogue content is added to the character image.

[0041] Figure 3 FIG. 1 is a schematic interface diagram of a cover image of a character image type according to another embodiment of the present application. Figure 3 As shown, suppose the following wonderful dialogue content is extracted from the story text: “Character 1 (male): I’m from a neighboring country, and I came here to steal your cooking secrets! Character 2 (female): Are you okay? It can be determined that the dialogue characters corresponding to the above-mentioned wonderful dialogue content include character 1 and character 2. Then the images of character 1 and character 2 in the cover image are matched with the character information of character 1 and character 2 respectively, and the dialogue content of each character is added next to the image of character 1 and the image of character 2 respectively, so that the cover image can simultaneously represent the relevant information of the scene, characters and wonderful dialogue, thereby accurately conveying the wonderful dialogue content and the character information of the dialogue characters (such as the gender of the characters) through the cover image.

[0042] In one embodiment, the cover type includes a third-person perspective narrative type, and the text feature information includes at least one of the following: a story summary, wonderful dialogue content, and highlight text of the story text.

[0043] In this embodiment, when generating a cover image based on text feature information, the following steps can be performed: first, a story narrative text narrated from a third-person perspective is generated based on the text feature information; second, a cover image is generated based on the story narrative text. The story narration text may be a story synopsis, wonderful dialogue content or highlight text of the story text, or may be text content with the same meaning extracted from the story synopsis, wonderful dialogue content or highlight text.

[0044] In one embodiment, the text feature information includes a story introduction and / or a highlight text. When generating a story narrative text narrated from a third-person perspective based on the text feature information, the following steps B1 to B2 may be performed: Step B1, determine the story element information corresponding to the story introduction and / or highlight text; the story element information includes at least one of the following: story theme, story keywords, story scene.

[0045] The theme of a story refers to the central idea or concept that runs through the entire story text. It can be understood as the core information that the story text wants to convey to the reader. The theme of a story can be determined through the story introduction. The story introduction can accurately express the main plot or main plot of the story text through concise and general words. Therefore, the theme of the story can be determined through the story introduction. The theme of a story can be broad, such as "freedom", or specific, such as "growing pains".

[0046] The story keywords can be extracted from the story introduction and / or the highlight text. Optionally, the words in the story introduction and / or the highlight text that meet at least one of the following conditions are extracted as the story keywords: the frequency of occurrence is higher than or equal to a preset frequency, the number of occurrences is higher than or equal to a preset number of times, the part of speech belongs to a specified part of speech, etc.

[0047] A story scene can be a specific location and / or time period, such as a hotel lobby, a battlefield, or a family living room. At a specific location and / or time period, the story characters will perform a series of actions, and this series of actions combined with the specific location and / or time period can be considered a story scene of the story text. In other words, a story scene usually includes at least one or a combination of specific environments, characters, dialogues, and activity ranges.

[0048] Step B2, generating a story narrative text that conforms to the story element information.

[0049] In this step, generating a story narration text that conforms to the story element information means generating a text that satisfies at least one of the following as the story narration text based on the text feature information: the text conforms to the story theme, the text contains story keywords, and the text scene conforms to the story scene. In this embodiment, the third-person perspective refers to the perspective of a person outside the story text, and the person outside the story text is not a story character.

[0050] Figure 4 This is a schematic interface diagram of a cover image of a third-person perspective narrative type according to an embodiment of the present application. Figure 4 In the illustrated embodiment, the story summary and / or highlight text of the story text are analyzed to determine the story element information corresponding to the story summary and / or highlight text, generate a story narration text that conforms to the story element information, and then generate a cover image based on the story narration text. Assume that the generated story narration text includes the following content: “User A: I’m going to stop working and listen to the big news first!!! User B: What’s next?” It can be seen that the cover image displays a story narrative text, that is, the story text is narrated in a third-person perspective. Figure 4 User A and User B on the interface shown are people outside the story text, that is, User A and User B are not story characters. User A and User B narrate the story text in a third-person perspective, so that people outside the story text present the story text in the form of discussing the story. Since different users usually have different feelings about the same story, when discussing the story from a third-person perspective, it is possible to discuss from multiple aspects, thereby breaking away from the story framework of the story text and recommending the story text from various angles.

[0051] In this embodiment, a story narrative text is generated by discussing the story from a third-person perspective, and the interface of the story narrative text is used as a cover image, so that the cover image can convey the feelings of people outside the story about the story text, thereby recommending the story text from multiple aspects and angles.

[0052] In one embodiment, the text feature information includes wonderful dialogue content. When generating a story narrative text narrated from a third-person perspective based on the text feature information, the following steps C1 to C2 may be performed: Step C1, extracting the dialogue text of each dialogue character in the wonderful dialogue content.

[0053] Among them, the wonderful dialogue content refers to the more prominent and eye-catching dialogue fragments in the story text.

[0054] Step C2, filling the dialogue text of each dialogue character into the chat item of the instant messaging chat structure to obtain the story narration text corresponding to the wonderful dialogue content.

[0055] The chat items in the instant messaging chat structure have the same meaning as the chat items on the chat interface of the instant messaging chat software. The cover image shows the chat items and the dialogue characters corresponding to the chat items, which are extracted from the wonderful dialogue content of the story text. In this embodiment, the third-person perspective refers to the perspective of the story characters in the story text.

[0056] Figure 5 This is a schematic interface diagram of a cover image of a third-person perspective narrative type according to another embodiment of the present application. Figure 5 In the illustrated embodiment, by analyzing the wonderful dialogue content of the story text, the dialogue text of each dialogue character in the wonderful dialogue content is filled into the chat item of the instant messaging chat structure, and the story narrative text corresponding to the wonderful dialogue content can be obtained. Then, a cover image is generated according to the story narrative text. For example, the following wonderful dialogue content in the story text is extracted: "Role A: Yanyan, believe me. I didn't cheat. We must be in sync. Yanyan, don't you believe me? Role B: How could that be? We are best friends. Role A: Oh, that's good. Let's go buy a dress for the prom~ Role B: I have something to do so I can't go." It can be seen that Figure 5 The cover image shows the above story narration text, and the text content of the story narration text is the same as the wonderful dialogue content, the difference is that the two are presented in different forms. Figure 5 The cover image shown clearly shows the wonderful dialogue content in the story text.

[0057] In this embodiment, a story narrative text is generated by narrating the story from a third-person perspective, and the interface of the story narrative text is used as a cover image, so that the cover image can convey the wonderful dialogue content in the story text, thereby recommending the story text with the wonderful dialogue content as an attraction point.

[0058] In one embodiment, the method for generating a cover image further includes the following steps D1 to D3: Step D1, in response to a request for generating a cover image, display multiple cover templates; the cover template includes at least one of the following: a graphic template, a text template.

[0059] Among them, the graphic template refers to a cover image template that includes both images and text, and the text template refers to a cover image template that only includes text content. The graphic template includes at least one of the following template information: image display method (such as image size, image rendering method, etc.), the display position of the text on the image, and the text display method (such as text size, text direction, etc.). The text template may include at least one of the following template information: the display position of the text on the image, and the text display method (such as text size, text direction, etc.).

[0060] Step D2, in response to the user's selection operation of a target cover template from multiple cover templates, obtain the highlight text in the story text.

[0061] Step D3, generating a cover image according to the highlight text and the target cover template.

[0062] In this embodiment, if the user selects a graphic template, after extracting the highlighted text, an image matching the text features of the highlighted text can be generated as the background image of the cover image, and the text content of the highlighted text is added to the background image to generate the cover image. If the user selects a text template, after extracting the highlighted text, the highlighted text is processed according to the template information of the text template, and the resulting text interface is the cover image.

[0063] In addition to automatically generating a background image and / or text content that matches the template information of the cover template, the background image and / or text content of the cover image can also be customized by the user. Two customization methods are exemplified below.

[0064] Optionally, after responding to the request for generating a cover image, multiple cover templates are displayed, and the user selects one of the cover templates. Then, according to the cover template selected by the user, an information input portal matching the cover template is provided to the user. For example, after determining that the user has selected a graphic template, an image input portal and a text input portal are provided to the user, so that the user can provide an image through the image input portal and provide text through the text input portal. Then, a cover image is synthesized based on the image and text input by the user.

[0065] Optionally, after responding to the request for generating the cover image, an image input entry is first displayed, for example, multiple images are displayed to the user for selection, and the multiple images may include images stored in a local photo album. The user can select one of the images, or choose to skip (i.e., not select). Afterwards, a text input entry is displayed to the user, and the user can enter text content through the text input entry, for example, pasting a highlighted text in a story text through the text input entry. The user can also choose to skip, i.e., not enter text. Afterwards, a cover template is displayed to the user according to the image and / or text content entered by the user. If the user only enters an image, an image template is displayed to the user. If the user enters an image and text content, a text template is displayed to the user. If the user only enters text content, a text template is displayed to the user. Since the user has entered the image and / or text content in advance, the image and / or text content on the cover template displayed at this time may be the image and / or text content entered in advance by the user. Afterwards, the user can select one of the cover templates from the displayed multiple cover templates as the cover image.

[0066] The following is a specific example to illustrate the method of generating the cover image provided in this application by using an AI big model.

[0067] In one embodiment, the user first edits the story text through the electronic device. Figure 6 As shown, the user edits the story text through the "write story" function in a certain editing tool on the electronic device. After editing the text content of the story text, the user clicks the virtual button "next" in the lower right corner of the interface, and the electronic device enters the following Figure 7 The publishing settings interface shown in FIG. 1 shows a cover image generation entry on the publishing settings interface. The dotted box indicates that the cover image has not been generated yet. The user clicks the virtual button “Go to Add” on the interface, and the electronic device enters the following Figure 8 The cover adding interface shown. There are two areas displayed on the cover adding interface, where area 100 displays multiple images such as image 1, image 2, etc., which can be images stored in the local album. Area 200 displays a virtual trigger button "AI Generate" for AI-generated cover images.

[0068] If the user selects an image in area 100, the electronic device enters the image editing interface so that the user can edit the image selected. Fig. 9The cover editing interface shown in the figure displays an image 1 selected by the user on the cover adding interface and multiple cover templates, including graphic templates and text templates. If the user selects a graphic template, the cover editing interface displays multiple graphic templates for selection; if the user selects a text template, the cover editing interface displays multiple text templates for selection. After the user selects one of the cover templates, the electronic device automatically generates a cover image based on the image selected by the user and the template information of the cover template, such as Fig.10 When automatically generating a cover image, the AI ​​model extracts the highlight text in the story text and adds the highlight text to the image to obtain the cover image. Optionally, after the cover image is generated, a virtual button for returning to the previous interface is displayed on the interface. If the user is not satisfied with the generated cover image, the user can click the virtual button to return to the previous interface and reselect the cover template.

[0069] Electronic equipment enters Figure 8 After the cover adding interface is shown, if the user clicks the virtual trigger button "AI Generate" in area 200, an AI generation request for the cover image is issued. After receiving the AI ​​generation request, the electronic device analyzes the story text and determines the cover type corresponding to the story text based on the analysis results of the story text.

[0070] Among them, the cover type includes story image type, character image type or third-person perspective narrative type. More finely granularly, the story image type can be subdivided into full-text image type and highlight image type; the character image type can be subdivided into protagonist image type, all-character image type and wonderful dialogue image type. The full-text image type is suitable for story texts that emphasize atmosphere, such as apocalyptic and suspense story texts. It is expected that the overall atmosphere and tone of the story text can be conveyed through the cover image. Therefore, when analyzing the story text, the story atmosphere and / or story tone of the story text are mainly analyzed. The highlight image type is suitable for story texts with more conflict plots, such as competitive and detective story texts. It is expected that the highlight text in the story text can be visualized and visualized through the cover image. Therefore, when analyzing the story text, the text atmosphere and / or text tone of the highlight text in the story text are mainly analyzed. The protagonist image type is suitable for story texts with obvious protagonist lines, such as romance and urban emotional story texts. It is expected that the relationship between the protagonists can be conveyed through the cover image. Therefore, when analyzing the story text, the character information of the protagonist of the story is mainly analyzed. The overall character map type is suitable for story texts with multiple protagonists or group portraits, such as workplace story texts. It is expected that the relationship between all the characters can be conveyed through the cover image. Therefore, when analyzing the story text, the character information of all the characters in the story text is mainly analyzed. The wonderful dialogue map type is suitable for story texts that advance the plot through dialogue, such as urban and love story texts. It is expected that the cover image can convey the wonderful dialogue in the story text and the character information involved in the wonderful dialogue. Therefore, when analyzing the story text, the wonderful dialogue content in the story text and the character information of the dialogue characters involved in the wonderful dialogue content are mainly analyzed.

[0071] like Fig.11 As shown, the electronic device displays a plurality of cover templates corresponding to the cover types to the user, and the display order of the cover templates corresponding to the plurality of cover types can be arranged according to the matching degree between each cover type and the story type of the story text. Fig.11 Among the multiple cover types displayed, the full text image type has the highest matching degree with the story type. The user clicks the virtual button "Generate Now" below the cover template of the full text image type to trigger the electronic device to automatically generate a cover image of the full text image type.

[0072] It can be seen that by adopting the technical solution provided in this embodiment, a cover image of a story text can be generated for the user in two ways. One of the ways is: analyzing the story text through an AI big model, intelligently determining the cover type corresponding to the story text, and then intelligently generating a cover image of the story text according to the cover type. Another way is: providing users with a variety of cover templates, including graphic templates and text templates, and generating a cover image for the user through the user's selection of the cover template. Regardless of which method is used to generate the cover image of the story text, it can ensure that the generated cover image accurately reflects the content characteristics of the story text, thereby improving the accuracy of the cover image generation. In addition, in the process of intelligently generating the cover image, by dividing the cover type of the story text into a story image type, a character image type, or a third-person perspective narrative type, the story text can be expressed through a variety of types of cover images, thereby making the generation result of the cover image more flexible and rich.

[0073] In summary, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recorded in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing can be advantageous.

[0074] The above is a method for generating a cover image provided in an embodiment of the present application. Based on the same idea, an embodiment of the present application also provides a device for generating a cover image.

[0075] Fig.12 is a schematic block diagram of a cover image generation device according to an embodiment of the present application, such as Fig.12 As shown, the device comprises: The analysis module 121 is used to analyze the story text in response to a request for generating a cover image of the story text, and determine the cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type or a third-person perspective narrative type; The generating module 122 is used to generate a cover image of the story text according to the cover type.

[0076] In one embodiment, when the analysis module 121 analyzes the story text and determines the cover type corresponding to the story text according to the analysis result, the following steps are performed: Analyze the story type of the story text; From a plurality of cover types to be selected, a cover type to be selected that matches the story type is selected as the cover type of the story text.

[0077] In one embodiment, when generating the cover image of the story text according to the cover type, the generating module 122 performs the following steps: Acquiring text feature information of the story text according to the cover attribute information of the cover type; The cover image is generated according to the text feature information.

[0078] In one embodiment, the cover type is the story image type; the text feature information includes at least one of the following: the story atmosphere and / or story tone of the story text, the text atmosphere and / or text tone of the highlight text in the story text; When generating the cover image according to the text feature information, the generating module 122 performs at least one of the following steps: generating an image that matches the atmosphere and / or tone of the story as the cover image; An image that matches the atmosphere and / or tone of the text is generated as the cover image.

[0079] In one embodiment, the cover type includes a character image type; the text feature information includes at least one of the following: character information of the story character of the story text, the wonderful dialogue content, and character information of the dialogue character corresponding to the wonderful dialogue content; the character information includes at least one of the following: character attribute information, character relationship information, and character behavior information; When generating the cover image according to the text feature information, the generating module 122 performs the following steps: An image matching the character information is generated as the cover image.

[0080] In one embodiment, when generating an image matching the character information as the cover image, the generating module 122 performs the following steps: generating an image matching the character information; The wonderful dialogue content is added to the image matching the character information to obtain the cover image.

[0081] In one embodiment, the cover type includes a third-person perspective narrative type; the text feature information includes at least one of the following: a story summary, wonderful dialogue content, and highlight text of the story text; When generating the cover image according to the text feature information, the generating module 122 performs the following steps: Generating a story narrative text narrated from a third-person perspective according to the text feature information; The cover image is generated according to the story narrative text. In one embodiment, the text feature information includes the story introduction and / or the highlight text; When the generating module 122 generates a story narrative text narrated in a third-person perspective according to the text feature information, the generating module 122 performs the following steps: Determine the story element information corresponding to the story introduction and / or the highlight text; the story element information includes at least one of the following: story theme, story keywords, story scene; Generate the story narration text that conforms to the story element information.

[0082] In one embodiment, the text feature information includes the wonderful conversation content; When the generating module 122 generates a story narrative text narrated in a third-person perspective according to the text feature information, the generating module 122 performs the following steps: Extracting the dialogue text of each dialogue character in the wonderful dialogue content; The dialogue texts of the dialogue characters are filled into the chat items of the instant messaging chat structure to obtain the story narration text corresponding to the wonderful dialogue content.

[0083] In one embodiment, the method further comprises: A display module, for displaying a plurality of cover templates in response to a request for generating the cover image; the cover templates include at least one of the following: a graphic template and a text template; An acquisition module, configured to acquire the highlight text in the story text in response to a user selecting a target cover template from the plurality of cover templates; The second generating module is used to generate the cover image according to the highlighted text and the target cover template.

[0084] Those skilled in the art should understand that Fig.12 The cover image generation device in the invention can be used to implement the cover image generation method described above, and the detailed description thereof should be similar to that described in the method part above. To avoid redundancy, it will not be further described here.

[0085] Based on the same idea, the embodiment of the present application also provides an electronic device, such as Fig.13As shown. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors 1301 and memory 1302, and the memory 1302 may store one or more storage applications or data. Among them, the memory 1302 may be a short-term storage or a permanent storage. The application stored in the memory 1302 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the electronic device. Furthermore, the processor 1301 can be configured to communicate with the memory 1302 to execute a series of computer executable instructions in the memory 1302 on the electronic device. The electronic device may also include one or more power supplies 1303, one or more wired or wireless network interfaces 1304, one or more input and output interfaces 1305, and one or more keyboards 1306.

[0086] Specifically in this embodiment, the electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the electronic device, and the one or more programs are configured to be executed by one or more processors, including the following computer executable instructions: In response to a request for generating a cover image of a story text, analyzing the story text, and determining a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A cover image of the story text is generated according to the cover type.

[0087] The technical solution of the embodiment of the present application is adopted, by analyzing the story text, and determining the cover type corresponding to the story text according to the analysis results, the cover type includes a story image type, a character image type or a third-person perspective narrative type, and then generating a cover image of the story text according to the cover type. It can be seen that the generation process of the cover image does not involve manual operation of the user, and can intelligently determine the cover type that matches the story text, and automatically generate a cover image that matches the cover type, which not only achieves the intelligent generation effect of the cover image, but also can ensure that the generated cover image accurately reflects the content characteristics of the story text, thereby improving the accuracy of the cover image generation. In addition, in the process of intelligently generating the cover image, by dividing the cover type of the story text into a story image type, a character image type or a third-person perspective narrative type, the story text can be expressed through a variety of types of cover images, thereby making the generation result of the cover image more flexible and rich.

[0088] The embodiment of the present application further proposes a computer-readable storage medium, which stores one or more computer programs. The one or more computer programs include instructions. When the instructions are executed by an electronic device including multiple application programs, the electronic device can execute each process of the embodiment of the method for generating a cover image, and are specifically used to execute: In response to a request for generating a cover image of a story text, analyzing the story text, and determining a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A cover image of the story text is generated according to the cover type.

[0089] The technical solution of the embodiment of the present application is adopted, by analyzing the story text, and determining the cover type corresponding to the story text according to the analysis results, the cover type includes a story image type, a character image type or a third-person perspective narrative type, and then generating a cover image of the story text according to the cover type. It can be seen that the generation process of the cover image does not involve manual operation of the user, and can intelligently determine the cover type that matches the story text, and automatically generate a cover image that matches the cover type, which not only achieves the intelligent generation effect of the cover image, but also can ensure that the generated cover image accurately reflects the content characteristics of the story text, thereby improving the accuracy of the cover image generation. In addition, in the process of intelligently generating the cover image, by dividing the cover type of the story text into a story image type, a character image type or a third-person perspective narrative type, the story text can be expressed through a variety of types of cover images, thereby making the generation result of the cover image more flexible and rich.

[0090] An embodiment of the present application provides a computer program product, including a computer program, which is executed by a processor to implement the various processes of the cover image generation method embodiment as described above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0091] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0092] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0093] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0098] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0099] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0100] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0101] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0102] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0103] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for generating a cover image, characterized in that: include: In response to a request for generating a cover image of a story text, analyzing the story text, and determining a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A cover image of the story text is generated according to the cover type.

2. The method according to claim 1, characterized in that The step of analyzing the story text and determining the cover type corresponding to the story text according to the analysis result includes: Analyze the story type of the story text; From a plurality of cover types to be selected, a cover type to be selected that matches the story type is selected as the cover type of the story text.

3. The method according to claim 2, characterized in that Generating a cover image of the story text according to the cover type includes: Acquiring text feature information of the story text according to the cover attribute information of the cover type; The cover image is generated according to the text feature information.

4. The method according to claim 3, characterized in that The cover type is the story image type; the text feature information includes at least one of the following: the story atmosphere and / or story tone of the story text, the text atmosphere and / or text tone of the highlight text in the story text; Generating the cover image according to the text feature information includes at least one of the following: generating an image that matches the atmosphere and / or tone of the story as the cover image; An image that matches the atmosphere and / or tone of the text is generated as the cover image.

5. The method according to claim 3, characterized in that: The cover type includes a character image type; the text feature information includes at least one of the following: character information of the story character of the story text, the wonderful dialogue content, and character information of the dialogue character corresponding to the wonderful dialogue content; the character information includes at least one of the following: character attribute information, character relationship information, and character behavior information; The step of generating the cover image according to the text feature information includes: An image matching the character information is generated as the cover image.

6. The method according to claim 5, characterized in that The step of generating an image matching the character information as the cover image comprises: generating an image matching the character information; The wonderful dialogue content is added to the image matching the character information to obtain the cover image.

7. The method according to claim 3, characterized in that The cover type includes a third-person perspective narrative type; the text feature information includes at least one of the following: a story summary, wonderful dialogue content, and highlight text of the story text; The step of generating the cover image according to the text feature information includes: Generating a story narrative text narrated from a third-person perspective according to the text feature information; The cover image is generated according to the story narrative text.

8. The method according to claim 7, characterized in that The text feature information includes the story introduction and / or the highlight text; The step of generating a story narrative text narrated from a third-person perspective according to the text feature information includes: Determine the story element information corresponding to the story introduction and / or the highlight text; the story element information includes at least one of the following: story theme, story keywords, story scene; Generate the story narration text that conforms to the story element information.

9. The method according to claim 7, characterized in that: The text feature information includes the wonderful conversation content; The step of generating a story narrative text narrated from a third-person perspective according to the text feature information includes: Extracting the dialogue text of each dialogue character in the wonderful dialogue content; The dialogue texts of the dialogue characters are filled into the chat items of the instant messaging chat structure to obtain the story narration text corresponding to the wonderful dialogue content.

10. The method according to claim 1, characterized in that The method further comprises: In response to a request for generating the cover image, a plurality of cover templates are displayed; the cover templates include at least one of the following: a graphic template and a text template; In response to a user selecting a target cover template from the plurality of cover templates, acquiring highlight text in the story text; The cover image is generated according to the highlighted text and the target cover template.

11. A device for generating a cover image, characterized in that: include: An analysis module, configured to analyze the story text in response to a request for generating a cover image of the story text, and determine a cover type corresponding to the story text according to the analysis result; the cover type includes a story image type, a character image type, or a third-person perspective narrative type; A generating module is used to generate a cover image of the story text according to the cover type.

12. An electronic device, characterized in that: It comprises a processor and a memory electrically connected to the processor, the memory stores a computer program, and the processor is used to call and execute the computer program from the memory to implement the method for generating a cover image as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The storage medium is used to store a computer program, and the computer program can be executed by a processor to implement the method for generating a cover image as described in any one of claims 1-10.

14. A computer program product, characterized in that It comprises a computer program, which is executed by a processor to implement the method for generating a cover image as described in any one of claims 1-10.

Images