An advertisement generation method, an electronic device, and a computer readable storage medium

Abstract

The application provides a text generation method, an electronic device and a computer readable storage medium. The text generation method comprises displaying a text generation page, the text generation page comprising a generation button and a target image, the generation button being used to indicate the start of text generation; and in response to a triggering operation on the generation button, generating and displaying a first text corresponding to the target image. The first text can be generated based on the target image and the generation button through the text generation page, the user demand is met, and the user experience is improved.

Description

[Technical Field]

[0001] This application relates to the field of computer technology, and more particularly to a method for generating text, an electronic device, and a computer-readable storage medium. [Background Technology]

[0002] With the rapid development of artificial intelligence technology, copywriting generation has gradually become a focus of attention. Copywriting generation refers to the use of natural language processing technology and machine learning algorithms to automatically generate grammatically correct text content through computers. Currently, copywriting generation technology is widely used in various fields. However, in some areas, the application of existing copywriting generation technology still has certain limitations and cannot fully meet user needs.

[0003] It should be noted that the above description of the technical solutions is only to make it easier for those skilled in the art to understand the present invention. The above technical solutions do not belong to the prior art. For example, the inventors discovered the above technical problems only after they had put in effort on the prior art. [Summary of the Invention]

[0004] This application provides a copywriting generation method that can solve the problem that existing copywriting generation technologies have certain limitations and cannot fully meet user needs.

[0005] In a first aspect, embodiments of this application provide a text generation method, comprising: displaying a text generation page, the text generation page including a generation button and a target image, the generation button being used to indicate the initiation of text generation; and in response to a triggering operation of the generation button, generating and displaying a first text corresponding to the target image.

[0006] In one implementation, the text generation page further includes a content category; the step of generating and displaying the first text corresponding to the target image in response to the triggering operation of the generate button includes: generating and displaying the first text corresponding to the target image that conforms to the content category in response to the triggering operation of the generate button.

[0007] In one implementation, the content categories are multiple; and the method further includes: changing the content category displayed on the copy generation page in response to an operation on the content category.

[0008] In one implementation, the copy generation page further includes a historical data indicator; in response to a triggering operation on the historical data indicator, a historical data indicator page is displayed, the historical data indicator page including at least one piece of historical data.

[0009] In one embodiment, the copy generation page includes an input box for inputting copy generation requirements or inputting at least one image; after generating and displaying first copy corresponding to the target image, in response to the operation of inputting copy generation requirements into the input box, a second copy conforming to the copy generation requirements input into the input box is generated and displayed, the second copy being different from or partially the same as the first copy; or, after generating and displaying the first copy corresponding to the target image, in response to the operation of inputting at least one image into the input box, a third copy corresponding to the at least one image is generated and displayed, wherein the at least one image is different from the target image, and the third copy is different from the first copy.

[0010] In one embodiment, the copy generation page further includes a copy editing indicator; in response to a trigger operation on the copy editing indicator, a copy editing page is displayed, the copy editing page including a first area, a second area, and a third area; wherein, the first area includes at least one copy editing item; the second area includes copy identical to the first copy, and is used to display the copy edited by at least one copy editing item in the second area in response to a trigger operation on the at least one copy editing item in the first area; the third area includes a preview indicator or the third area is a preview area, when the third area includes a preview indicator, in response to a trigger operation on the preview indicator, the preview area is displayed on the copy editing page, the preview area displays all copy content, when the third area is a preview area, the third area is used to display all copy content.

[0011] In one embodiment, before displaying the text generation page, the method further includes: displaying an image acquisition page, the image acquisition page being used to acquire a target image; the image acquisition page including an image acquisition button and / or at least one guide screen; wherein, in response to a triggering operation of the image acquisition button, at least one image is displayed on the image acquisition page; wherein, the guide screen is used to prompt the user to perform the operation steps of text generation, and when there are multiple guide screens, the guide screen is switched in response to the user's operation on the guide screen.

[0012] In one implementation, the first text corresponding to the target image includes at least two, and the contents of the at least two first texts are different or partially the same.

[0013] In one implementation, when generating and displaying the first text corresponding to the target image, a fourth text related to the first text is also generated and displayed, the fourth text indicating a different topic than the first text.

[0014] Secondly, embodiments of this application also provide an electronic device, including: a processor; a memory; the memory storing a computer program, which, when executed, causes the electronic device to perform the method described in the first aspect.

[0015] Thirdly, embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method described in the first aspect.

[0016] The embodiments of this application display a text generation page, which includes a generate button and a target image. The generate button is used to instruct the user to start text generation. In response to triggering the generate button, a first text corresponding to the target image is generated and displayed. Thus, the text generation page allows for one-click text generation based on the target image using the generate button, reducing user operations and meeting user needs to some extent. [Attached Image Description]

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a text generation method provided in an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of a text generation page provided in an embodiment of this application.

[0020] Figure 3 This is an illustration of another text generation page provided in an embodiment of this application;

[0021] Figure 4 A schematic diagram of a historical data indicator page provided in an embodiment of this application;

[0022] Figure 5 A schematic diagram of a text editing page provided for an embodiment of this application;

[0023] Figure 6 Another schematic diagram of a text editing page provided in the embodiments of this application;

[0024] Figure 7 This application provides an illustration of an image acquisition page.

[0025] Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

Detailed Implementation Methods

[0026] To better understand the technical solution of this application, the embodiments of this application will be described more comprehensively below in conjunction with the relevant accompanying drawings.

[0027] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0028] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0029] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0030] With the rapid development of artificial intelligence technology, copywriting generation has gradually become a focus of attention. Copywriting generation refers to the use of natural language processing technology and machine learning algorithms to automatically generate grammatically correct text content through computers. Currently, copywriting generation technology is widely used in various fields. However, some existing copywriting generation technologies require users to perform cumbersome operations, greatly increasing the learning cost and consuming too much unnecessary time. Other existing copywriting generation technologies rely entirely on the generated content and cannot be adapted to user needs, thus failing to fully meet user requirements. Therefore, existing copywriting generation technologies have certain limitations.

[0031] This application provides a document generation method, primarily applied to electronic devices. These electronic devices can be image forming devices, possessing at least one image forming-related function, which may include, but is not limited to, printing, scanning, copying, and faxing functions. For example: a single-function printer: an image forming device with only printing functionality. A multifunction printer: an image forming device with printing, copying, scanning, and / or faxing functions, and the ability to selectively set the number of paper trays. A digital multifunction printer: based on copying functionality, with standard or optional printing, scanning, and faxing functions, employing digital principles and laser printing for document output, allowing for image and text editing as needed, possessing a large-capacity paper tray, high memory, large hard drive, strong network support, and multitasking capabilities. This electronic device can also be a mobile terminal, including but not limited to desktop computers, laptop computers, networked computers, handheld computers, personal digital assistants (PDAs), internet-enabled mobile phones, smartphones, pagers, digital capture devices (e.g., digital cameras and camcorders), internet devices, e-books, information boards, and digital or network boards.

[0032] Please refer to Figure 1 This application provides a flowchart illustrating a text generation method, which includes:

[0033] S101, Display the copy generation page. The copy generation page includes a generate button and a target image. The generate button is used to instruct the user to start copy generation. In one implementation, the generate button can be a button indicating confirmation or initiation. When the user performs copy generation-related operations based on the copy generation page, such as confirming the copy generation requirement by triggering (e.g., clicking, single-clicking, double-clicking, long-pressing, short-pressing, etc.) certain related options, and then triggers (e.g., clicking, single-clicking, double-clicking, long-pressing, short-pressing, etc.) the generate button, a command to start copy generation is issued, thus initiating copy generation. In another implementation, the generate button can also be an option button corresponding to the copy generation requirement. When the user triggers (e.g., clicking, single-clicking, double-clicking, long-pressing, short-pressing, etc.) the corresponding option, a copy generation command is issued, thus initiating copy generation.

[0034] S102, in response to the triggering operation of the generate button, generate and display the first text corresponding to the target image. (See reference) Figure 2 This application provides a schematic diagram of a text generation page, and references... Figure 3 This application provides another illustration of a text generation page.

[0035] In one implementation, the trigger operation for the generate button can be a user-triggered operation on the generate button. Of course, it can also be a trigger operation under other conditions, such as automatically triggering the generate button after a predetermined time under predetermined conditions. There is no specific limitation here, as long as it can trigger an instruction to the generate button. For ease of explanation of the embodiments of this application, the trigger operation described below is preferably a user-executed trigger operation.

[0036] Existing copy generation technology requires users to manually input their copy generation needs. Therefore, when users are unsure how to use the copy generation technology or what form of copy generation needs they should input to obtain copy that meets their requirements, this manual input method can cause confusion for users, hindering their use of the copy generation function and increasing the difficulty and learning cost of using the copy generation function.

[0037] In one implementation, the copy generation page also includes content categories. (See reference) Figure 2The copy generation page also includes a content category indicator area 203, which includes at least one content category. Responding to a user's trigger operation on the generate button, generating and displaying the first copy corresponding to the target image includes: responding to a user's trigger operation on the generate button, generating and displaying the first copy corresponding to the target image that conforms to the content category. Specifically, when the user determines the target image 202, when the user clicks on a content category, the first copy corresponding to the target image 202 is generated based on the content category indicator. In one implementation, when there are multiple content categories (at least two), such as content category 1, content category 2, content category 3…, content category n (n is an integer greater than 3), when the user determines the target image, when the user selects a content category from the content category indicator area 203, the first copy corresponding to the target image 202 is generated based on the selected content category indicator. Furthermore, when there are multiple content categories, the content categories displayed on the copy generation page are changed in response to the user's operation on the content categories. For example, the content category indicator area 203 includes six content categories, but the visible window of the content category indicator area can only display at least two content categories, namely content category 1 and content category 2. Content category 3 and content categories 4-6 cannot be fully displayed. Therefore, when a user needs to use any of the content categories 3-6, the user can slide the content category indicator area 203, such as left-right or up-down, to display other content categories besides the currently displayed content categories 1-2, such as content category 3-4. The user can slide twice to display content categories 5-6. In other words, by sliding the content category indicator area 203, the user can change the content category displayed in the corresponding visible window. The visible window refers to the window corresponding to the range that the user can observe with their naked eye without any operation within the range appropriate for the text generation page. In this way, by providing at least one content category on the copy generation page that indicates the copy generation needs, users only need to select one to generate the corresponding copy. Users can even use the copy generation function without any additional learning, which provides convenience for users, reduces the cost of learning and using the copy generation function, and saves users time in using the copy generation function.

[0038] Some existing copy generation technologies fail to retain the generated copy content after it has been generated, or fail to save it to a predetermined location, such as the local device or another platform within an application. However, this predetermined location may not be on the corresponding copy generation page. This forces users to exit the current copy generation page and perform a cumbersome process to access previously generated copy when they want to access it, which is extremely user-unfriendly. This is especially problematic when previously generated copy includes the desired copy, leading to duplicate generation, redundant copy, and increased strain on the device, ultimately impacting the efficiency of subsequent copy generation.

[0039] In one implementation, refer to Figure 2 The copy generation page also includes a historical data indicator 204. In response to a user's triggering action on the historical data indicator 204, a historical data indicator page is displayed, which includes at least one piece of historical data. (Reference) Figure 4 This application provides a schematic diagram of a historical data indicator page. The diagram includes historical data corresponding to text generation operations performed by the user. This historical data page displays all historical data generated by text according to content category. In response to a user's operation on any content category, the historical data for that content category is displayed. For example, when the user clicks on content category 1, the historical data corresponding to content category 1 is displayed in the visual window of the historical data page. When the historical data corresponding to content category 1 exceeds the range of the visual window, the user can display other historical data of content category 1 in the visual window by operating on any position in the historical data page, such as swiping left or right, or up or down. The visual window refers to the window on the historical data page that corresponds to the range of data that can be observed visually without any user operation. For example, Figure 4In the context of the system, the historical data page can display four historical data points in its visual window. When content category 1 includes six historical data points, users can swipe left or right or up and down to view historical data points 5 and 6. By providing historical data indicators on the copywriting generation page, even after a user has selected a target image but is about to perform the copywriting generation operation, if they are unsure whether the corresponding copywriting generation operation has already been performed, they can directly access the historical data page from the current copywriting generation page without having to perform unnecessary steps such as exiting the current copywriting generation page, returning to the homepage, and then entering the historical data page. This saves user time, promptly resolves user doubts, and avoids users repeatedly performing copywriting generation operations and generating duplicate copy, thus preventing unnecessary consumption of electronic device memory and impacting the efficiency of subsequent copywriting generation methods. In one implementation, historical data is stored in the electronic device. Therefore, to reduce the data storage pressure on the electronic device, ensure the processing efficiency of the electronic device in generating documents, and reduce the number of user operations to clear historical data, or to avoid users forgetting to clear historical data in a timely manner, which could lead to excessive storage pressure on the electronic device and reduced operating efficiency, reference is made to... Figure 4 The historical data page also includes settings for configuring the storage period for historical data. For example, if a user wants historical data to be cleared at predetermined intervals, such as once a week, they can click the settings to set the retention period to one week. In this way, historical data that has been stored for one week will be automatically deleted.

[0040] In one application scenario, after obtaining the first text generated based on a first target image, if the generated text does not meet expectations and further modifications or refinements are desired, existing text generation technology cannot fulfill this requirement. This forces users to exit the current page and regenerate the text from the very beginning when they wish to further modify or refine the text. This creates unnecessary and cumbersome operations, negatively impacting the user experience. Alternatively, in another application scenario, after obtaining the first text generated based on a first target image, if the target image is not the expected image, existing text generation methods require users to exit the current page or return to the initial page to re-execute the text generation. This wastes unnecessary user time.

[0041] In one implementation, the copy generation page further includes an input box 205, which is used to input copy generation requirements or at least one image. After generating and displaying the first copy corresponding to the target image 202, in response to the user's operation of inputting copy generation requirements into the input box 205, a second copy that meets the copy generation requirements input into the input box 205 is generated and displayed, wherein the second copy that meets the copy generation requirements input into the input box 205 is different from the first copy corresponding to the target image 202; or, after generating and displaying the first copy corresponding to the target image 202, in response to the user's operation of inputting at least one image into the input box 205, a third copy corresponding to at least one image is generated and displayed, wherein the at least one image is different from the target image, and the third copy is different from the first copy. For example, when a user confirms that the target image 202 is an image about a snow scene, and enters a text generation requirement such as "describe the snow scene in the image" in the input box 205, then the text describing the snow scene in the target image 202 will be generated and displayed, such as "Snowflakes fall in a flurry, covering the world in silver. Snowflakes are like elves dancing in the air before gently landing, adorning the world as a dreamlike white fairyland." Alternatively, as another example, when the user confirms that the target image 202 is an image about a snow scene, after generating and displaying the first text corresponding to the target image 202, such as "Snowflakes flutter down, covering the world in silver. Snowflakes dance in the air like fairies, then gently land, adorning the world into a dreamlike white wonderland.", if the user enters a text generation request in the input box 205, and this text generation request is based on the first text input, such as "Please regenerate using metaphors," then a new second text corresponding to the request is generated, such as "Snowflakes flutter down like goose feathers, like white flowers sprinkled by celestial maidens. The earth is like a huge white scroll, and the houses are like castles in a fairy tale." Obviously, this second text is different from or partially the same as the first text. In another example, when the user confirms that the target image 202 is image 1 about a snow scene, after generating and displaying the first text corresponding to the target image 202 (the first text is a description of the snow scene image 1), if the user inputs at least one new image (e.g., snow scene image 2) in the input box 205, and this new at least one image (snow scene image 2) is different from the target image (snow scene image 1), then a third text corresponding to the new at least one image is generated and displayed. This third text is different from the first text, or partially the same. Specifically, when the new at least one image and the target image are of the same type, the generated and displayed third text may be different from the first text, or partially the same. When the new at least one image and the target image are not of the same type, for example, the new at least one image is an animal image and the target image is a snow scene image, then the generated and displayed third text is different from the first text.

[0042] In one implementation, refer to Figure 3The copy generation page also includes an editing area 302, which contains at least one copy editing instruction. The copy editing instructions include Edit 1, Edit 2, ..., Edit n. For example, the copy editing instructions include Regenerate, Copy, Modify, Print, etc. In response to a user's trigger action on a copy editing instruction, such as "Modify," the copy editing page is displayed. (See reference) Figure 5 This application provides a schematic diagram of a text editing page, which includes a first area, a second area, and a third area. The first area includes at least one text editing item, such as editing item 1, editing item 2, ..., editing item n. The second area includes text identical to the first text, and is used to display the edited text after being processed by at least one text editing item in response to a user's triggering operation on the first area. The third area includes a preview indicator, or the third area is a preview area. When the third area includes a preview indicator, the preview area is displayed on the text editing page in response to a user's triggering operation on the preview indicator, and the preview area displays all text content. When the third area is a preview area, the third area is used to display all text content. For example, refer to... Figure 6This is a schematic diagram of another text editing page provided in an embodiment of this application. In the diagram, the first area includes at least one text editing item, such as keyboard, insert image, insert background, copy, share, etc., and also includes at least one font adjustment item and a print option. When a user operates based on the first area, such as clicking the keyboard option to activate the keyboard, they can input text or symbols into the second area. The text content displayed in the second area is based on the first text content with the corresponding text or symbols input via the keyboard added. For example, when a user inputs "One winter day, it snowed" before the first text, the text displayed in the second area changes to "One winter day, it snowed. The snow fell thick and fast, covering the world in a silver blanket. Snowflakes danced in the air like fairies before gently landing, adorning the world as a dreamlike white wonderland." Alternatively, when a user operates based on the first area, such as clicking "Insert Image," they are redirected to an image aggregation page. This page includes at least one image. The user selects at least one image from this page, and the selected image is inserted into the first text displayed in the second area. Therefore, the content displayed in the second area includes the first text and the inserted image. Or, when a user operates based on the first area, such as clicking "Insert Background," they are redirected to a background page. This page includes at least one image and / or at least one piece of text. The user selects at least one image and / or at least one piece of text from this page, and the selected image and / or text is inserted into the first text displayed in the second area as a background. Therefore, the content displayed in the second area includes the first text and the inserted background. Or, when a user operates based on the first area, such as clicking "Copy," they copy the first text displayed in the second area. Clicking "Paste" at the beginning, middle, or end of the first text will paste the copied text into the corresponding position. Therefore, the content displayed in the second area includes two parts of the first text. In other words, in response to a user's triggering operation on at least one text editing item in the first area, the text edited by at least one text editing item is displayed in the second area. Alternatively, when a user operates based on the first area, such as clicking share, they are taken to a sharing page. This sharing page includes at least one sharing object, such as at least one application software, at least one contact, etc. The user selects at least one of the sharing objects as the target object, and then shares the content displayed in the second area with the corresponding target object. Obviously, this application embodiment also provides that after the text is generated on the text generation page, if the user needs to manually adjust the generated text, they can trigger an editing instruction item to enter the corresponding text editing page for manual editing.In this way, even if the generated text is insufficient to meet the user's needs, the user can still perform further editing operations based on the generated text. Compared with existing solutions that do not support further editing of the generated text, or that require the user to transfer the text to other editing software for further editing, the text generation method of this application embodiment is more convenient. It does not require the cooperation of other editing software and can achieve rapid editing on the current generation page, which not only satisfies the user experience but also reduces the user's learning cost and saves the user time to obtain satisfactory text based on the text generation technology. For example, if the user is not familiar with the editing operations of other editing software, they still need to further learn how to transfer the generated text to the corresponding editing software, how to use the corresponding editing software for editing, and how to send the text edited by the editing software back to the text generation page.

[0043] In one implementation, when the text displayed in the second area exceeds the corresponding area of ​​the view window, a third area is displayed. In another implementation, the third area includes a preview indicator; when the user clicks the preview indicator, a preview area is displayed. In yet another implementation, the third area is a preview area; when the text displayed in the second area exceeds the corresponding area of ​​the view window, all the text content from the second area is displayed in the third area in a scaled-down format.

[0044] In one implementation, an image acquisition page is displayed before the text generation page, and this image acquisition page is used to acquire the target image. (See reference) Figure 7This application provides a schematic diagram of an image acquisition page, which includes an image acquisition button, an image acquisition area, and / or at least one guide screen. In response to a user's triggering of the image acquisition button, at least one image is displayed. The guide screen prompts the user to perform steps for text generation; when there are multiple guide screens, the screen switches in response to user actions. Furthermore, each guide screen corresponds to at least one content category on the text generation page. Each guide screen and each content category corresponds to a different application scenario, such as image-based writing, image-to-text conversion, meeting material / classroom blackboard organization, marketing copy, image Q&A / image description, etc. For example, image-based writing automatically creates a coherent and logically clear article based on uploaded image content. Image-to-text accurately extracts text information from images and automatically optimizes the format, including paragraph adjustment, table reconstruction, and the addition of chart descriptions. Meeting material / classroom blackboard organization automatically organizes provided images into a well-organized document, including keyword extraction, key point summarization, and supplementary annotations. Marketing copy is used to generate compelling advertising copy for a given image. Image Q&A / image descriptions provide detailed analysis of the information and content within the image, offering complete and accurate descriptions for exam preparation and popular science purposes. Similarly, for example, the onboarding screen includes usage methods for five application scenarios: image-based essay writing, image-to-text conversion, meeting materials / classroom blackboard organization, marketing copy, and image Q&A / image descriptions. When the onboarding screen cannot simultaneously display the usage methods for all five application scenarios, it displays the usage method for each scenario separately. Users can switch between onboarding screens by clicking and interacting with them, such as swiping left or right, or up or down. For instance, if the onboarding screen currently displays the image-based essay writing method, and the user swipes left to write the essay, the image-to-text conversion method will then be displayed on the onboarding screen.

[0045] In addition, refer to Figure 7 The image acquisition page also includes image acquisition indicators, including Import 1 and Import 2. These indicators are used to import images from other software or from the memory of an electronic device. The imported image can be used as the target image. For example, images can be imported from Import 1, such as WeChat, photo albums, or QQ, or from Import 2, such as local image import. Exemplarily, the image acquisition page can be a camera page, where images can be captured; the image acquisition area is the shooting area. In response to a user's triggering of the image acquisition button, displaying at least one image can be: the user clicks the shooting button, captures an image in the shooting area, and displays it on the image acquisition page; or the user clicks the shooting button, captures an image in the shooting area, and displays it on the text generation page.

[0046] In one implementation, the first text corresponding to the target image includes at least two, and the content of the at least two first texts is different or partially the same. Specifically, when a user triggers the generate button based on an image on the text generation page, or when a user selects a content category or enters text requirements in an input box based on an image on the text generation page, at least two first texts are generated, such as generating two texts, first text 1 and first text 2. For example, if a user determines the target image to be a snow scene and selects a content category such as "writing an essay based on a picture," then after triggering the generate button, three essays describing the snow scene image will be generated, such as: Essay 1: "Snowflakes flutter down, covering the world in a silvery white. Snowflakes dance in the air like fairies before gently landing, adorning the world as a dreamlike white wonderland."; Essay 2: "Snowflakes flutter down like goose feathers, like white flowers scattered by celestial maidens. The earth is like a giant white scroll, and the houses are like castles from a fairy tale."; and Essay 3: "Snowflakes flutter down, covering the world in a silvery white. The earth is like a giant white scroll, and the houses are like castles from a fairy tale." The content of Essay 1 and Essay 2 differs. Essay 1 or Essay 2 and Essay 3 share the same content. In this way, users can obtain at least one descriptive text for a target image simply by uploading it. This avoids the situation where only one descriptive text is generated, which may not meet the user's needs, requiring the user to regenerate a new text. This greatly improves the user experience. Furthermore, being able to obtain multiple descriptive texts at once provides users with more options and increases the likelihood of meeting their needs.

[0047] In one implementation, in response to a user's operation on at least one editing instruction, at least one first text is merged and displayed on the text generation page, or at least one first text is displayed on the text editing page. For example, the editing instruction is "merge" or "edit after merging." When at least one first text is generated on the text generation page, the user clicks "merge," which merges the at least one first text into one text and displays it on the current text generation page or the text editing page, allowing the user to edit the merged first text. In this way, multiple different or identical first texts can be merged into one text without manual user operation. Furthermore, after merging multiple first texts, the user can still edit the merged text. This eliminates the need for the user to use their imagination to further edit the text; simple modifications based on the merged text are sufficient, making it more convenient for the user. In another implementation, merging multiple first texts into one text is done automatically, and the merged text does not contain duplicate text content. For example, if some sentences in two initial copy are repeated, one sentence is retained, and the repeated sentences are deleted. In this way, the automatically generated copy after removing duplicate content eliminates the need for manual deletion by the user and better meets the user's needs.

[0048] In one implementation, when generating and displaying the first text corresponding to the target image, a fourth text related to the first text is also generated and displayed, indicating a different topic than the first text. (See reference) Figure 3 The copywriting generation page includes a fourth copywriting display area 301, which includes topics such as Topic 1, Topic 2, and Topic 3. The topics included in the fourth copywriting display area 301 are extended topics related to the target image. For example, if the user determines the target image to be a snow scene, and selects a content category (e.g., writing an essay based on the image) or enters the copywriting requirement as describing the snow scene in the image, an essay describing the snow scene in the image will be generated, along with at least one topic in the fourth copywriting display area, such as Topic 1 "Understanding the Cultural Significance of Snow" or Topic 2 "Poems about Snow." Clearly, the existence of the fourth copywriting provides users with more creative directions and ideas, enriching the content of the first copywriting from different topical perspectives. In other words, after the copywriting is generated, users can obtain more unexpected copywriting that enriches the first copywriting through the fourth copywriting. This better meets user needs.

[0049] In one implementation, refer to Figure 3The text generation page also includes a playback item 303, which plays the first text in response to the user's triggering action. Specifically, the generated and displayed first text includes playback item 303. After the first text is generated and displayed, the user clicks playback item 303, and the electronic device plays the content corresponding to the first text via voice. In this way, even if it is inconvenient for the user to visually observe the first text, they can still listen to it through voice. Even in complex environments or complex work situations, users can still access the content of the first text promptly.

[0050] For ease of understanding, the visible windows mentioned in the embodiments of this application refer to the windows on the corresponding page that allow the user to visually observe the range of data without performing any operation.

[0051] The copywriting generation method described above breaks through the limitations of existing copywriting generation technologies, enabling users to generate copywriting with just one image and one operation. This simplicity reduces the learning curve. Furthermore, it can generate multiple pieces of copy, or simultaneously provide extended copywriting on different topics, making the generated copywriting more closely aligned with user needs. This significantly increases the success rate of copywriting meeting user requirements and reduces unnecessary re-generation. Additionally, after copywriting generation, it provides editing instructions. Even if one or more generated pieces of copywriting do not meet the user's expectations, the user can still edit the copywriting on the spot to obtain the desired result, further enhancing the ease of use of copywriting generation technology.

[0052] In addition, embodiments of this application provide another method for generating text, including:

[0053] S801, Obtain the target image and / or content category.

[0054] Electronic devices acquire target images based on image acquisition pages. For example, if the image acquisition page is a camera page, and the user takes an image using the camera, the electronic device uses that image as the target image. Alternatively, the user can import images from other software or the local device using the image acquisition page, and the imported image is used as the target image. Or, electronic devices can acquire target images based on text generation pages. For example, if the user selects an image using an input box on a text generation page, the image selected using the input box is used as the target image. When the user selects any content category from the content category indicator area on the text generation page, the corresponding content category selected by the user is retrieved.

[0055] S802, in response to the detection of a copy generation instruction, sends a copy generation request to the copy generation model.

[0056] When a user triggers the generate button on the text generation page, the electronic device detects the text generation instruction corresponding to the generate button and sends a text generation request to the text generation model. The text generation request includes the target image and keywords corresponding to the content category. The text generation model is stored in the electronic device or on a server. When the text generation model is stored in the electronic device, the electronic device detects the text generation instruction corresponding to the generate button and sends a text generation request to the text generation model. When the text generation model is stored on a server, the electronic device detects the text generation instruction corresponding to the generate button and sends a text generation request to the text generation model on the server. The large text generation model is used to generate text based on user needs, such as generating text based on an image or the user's text description. For example, this large model supports at least one content category and text generation requirements input in the input box as described in this application embodiment to generate corresponding text.

[0057] S803 receives the first copy sent by the copy generation model and displays the first copy.

[0058] The system receives the first generated copy from the copy generation model and displays it on the electronic device. Specifically, when the copy generation model is stored on the electronic device, the system receives the first generated copy based on the copy generation model interface and displays it on the copy generation page. When the copy generation model is stored on the server, the system receives the first generated copy based on the copy generation model interface on the server and displays it on the copy generation page.

[0059] The copy generation method provided in this application embodiment can generate copy through a large copy generation model, which provides greater convenience for users' copy creation and better meets users' needs for efficient copy creation.

[0060] See Figure 8This is a schematic diagram of the structure of an electronic device 900 provided in an embodiment of this application. The electronic device 900 may include a processor 910, a memory 920, and a communication unit 930. These components communicate through one or more buses. Those skilled in the art will understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiment of this application; it can be a bus topology, a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. The communication unit 930 is used to establish a communication channel, enabling the electronic device to communicate with other devices. It receives user data sent by other devices or sends user data to other devices. The processor 910 is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines. It executes various functions of the electronic device and / or processes data by running or executing software programs, instructions, and / or modules stored in the memory 920, and by calling data stored in the memory. The processor 910 may be composed of integrated circuits (ICs), for example, it may be composed of a single packaged IC, or it may be composed of multiple packaged ICs with the same or different functions connected together. For example, processor 910 may include only a central processing unit (CPU). In this embodiment, the CPU may be a single processing core or may include multiple processing cores. Memory 920 is used to store the execution instructions of processor 910. Memory 920 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in memory 920 are executed by processor 910, the electronic device 900 is able to perform some or all of the steps of the display control method of the image processing apparatus provided in this application as described above.

[0061] In a specific implementation, this application also provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, which, when executed, controls the device where the computer-readable storage medium is located to perform some or all of the steps of the display control method of the image processing apparatus provided in this application. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0062] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the image forming apparatus. In other embodiments of this application, the image forming apparatus may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0063] In the description of this application, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance; unless otherwise specified or explained, the term "multiple" refers to two or more, and the term "various types" refers to two or more; the terms "connection," "fixed," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, an integral connection, or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0064] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for generating copy, characterized in that, include: The text generation page is displayed, which includes a generation button and a target image. The generation button is used to indicate that text generation should be started. In response to the triggering operation of the generate button, a first text corresponding to the target image is generated and displayed.

2. The method according to claim 1, characterized in that, The text generation page also includes content categories; the step of generating and displaying the first text corresponding to the target image in response to the triggering operation of the generate button includes: In response to the triggering operation of the generate button, a first text corresponding to the target image that conforms to the content category is generated and displayed.

3. The method according to claim 2, characterized in that, The content categories are multiple; they also include: In response to the operation on the content category, the content category displayed on the copy generation page is changed.

4. The method according to claim 1, characterized in that, The copy generation page also includes a historical data indicator; in response to a trigger operation on the historical data indicator, a historical data indicator page is displayed, the historical data indicator page including at least one piece of historical data.

5. The method according to claim 1, characterized in that, The copy generation page includes an input box, which is used to input copy generation requirements or input at least one image. After generating and displaying the first text corresponding to the target image, in response to the operation of inputting text generation requirements in the input box, generating and displaying a second text that meets the text generation requirements input in the input box, wherein the second text is different from or partially the same as the first text; or... After generating and displaying the first text corresponding to the target image, in response to the operation of inputting at least one image into the input box, generating and displaying the third text corresponding to the at least one image, wherein the at least one image is different from the target image and the third text is different from the first text.

6. The method according to claim 1, characterized in that, The copy generation page also includes copy editing instructions; in response to the triggering operation of the copy editing instructions, a copy editing page is displayed, which includes a first area, a second area, and a third area; The first area includes at least one text editing item; The second area includes the same text as the first text, and is used to display the text edited by at least one text editing item in the second area in response to a trigger operation on the at least one text editing item in the first area; The third area may include a preview indicator or may be a preview area. When the third area includes a preview indicator, in response to a triggering operation on the preview indicator, the preview area is displayed on the text editing page, and the preview area displays all text content. When the third area is a preview area, the third area is used to display all text content.

7. The method according to claim 1, characterized in that, Before the text generation page, the system further includes: displaying an image acquisition page, which is used to acquire a target image; The image acquisition page includes an image acquisition button and / or at least one guide screen; In response to the triggering operation of the image acquisition button, at least one image is displayed on the image acquisition page; The guide screen is used to prompt the user to perform the operation steps of copy generation. When there are multiple guide screens, the guide screen is switched in response to the user's operation on the guide screen.

8. The method according to claim 1, characterized in that, The first text corresponding to the target image includes at least two, and the content of the at least two first texts is different or partially the same.

9. The method according to claim 1, characterized in that, When generating and displaying the first text corresponding to the target image, a fourth text related to the first text is also generated and displayed, the fourth text indicating a different topic than the first text.

10. An electronic device, characterized in that, include: processor; Memory; The memory stores a computer program that, when executed, causes the electronic device to perform the method described in any one of claims 1-9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1-9.

Images