Content filling interaction method, commodity information publishing method, and electronic device

Abstract

Disclosed in embodiments of the present disclosure are a content filling interaction method, a commodity information publishing method, and an electronic device. The content filling interaction method comprises: displaying a content filling interface, upon generating artificial intelligence (AI) generated content on the basis of an AI generation request initiated by a user, providing an AI generated content preview area in the content filling interface, and in the preview area, providing an operation option for applying the AI generated content, wherein the content filling interface comprises a plurality of items to be filled; in response to a click operation on the operation option, generating, on the basis of the AI generated content, following content that follows the movement of a mouse pointer; and upon detecting that the mouse pointer is moved to a target item and the click operation is performed, filling the target item with the following content that follows the mouse pointer. By means of the embodiments of the present disclosure, content filling can be completed more efficiently and flexibly.

Description

Content filling interaction, method for publishing commodity information and electronic device

[0001] The present disclosure claims priority to Chinese Patent Application No. 202410842345.5, filed on June 26, 2024 with the Chinese Patent Office and entitled "Content filling interaction, method for publishing commodity information and electronic device", the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates to the technical field of information processing, and particularly relates to a content filling interaction, a method for publishing commodity information and an electronic device. BACKGROUND

[0003] With the continuous development of AI (artificial intelligence) technology, AI technology is increasingly used for content generation in more and more scenarios. Among them, in scenarios that require content filling in some forms, the required content can also be generated by AI generation, and then filled into the form. For example, in a commodity information service system, a merchant needs to fill in the content such as a commodity main picture, a title text, and an attribute into a form provided by a commodity publishing interface in the process of publishing a commodity. In the traditional way, the merchant usually needs to prepare the content such as a picture or a video that can be used as a commodity main picture in advance, save it in a local terminal device, and then upload the picture or the video through a main picture upload option in the commodity publishing interface; in addition, the merchant can also edit the text content that can be used as a title in advance and input it into the title input box of the commodity publishing interface. Among them, the production of related materials such as commodity main pictures may be difficult for some merchants, especially in the case of providing some scene pictures, the merchant needs to spend a lot of time, manpower and material resources to complete the production of high-quality scene pictures. However, after the emergence of AI generation technology, AI generation technology can help users to generate content, for example, in the above-mentioned commodity publishing interface, an operation option for initiating AI generation can be provided, and the user can call an "AI assistant" through the operation option during the process of filling in the form through the above-mentioned commodity publishing interface, and input his own content generation requirements, for example, after inputting two basic white background pictures of a commodity, the AI is asked to help generate multiple scene pictures, and the like, so as to reduce the production cost of commodity main pictures.

[0004] However, after the AI completes the content generation, how to fill in the specific form is also a problem to be considered. The reason for this problem is that, similar to the form in the commodity publishing scenario, there are usually multiple items to be filled in, such as the commodity main picture, the commodity title, and the like. After the AI generates certain content, if automatic filling is performed through the "apply" button, there may be a problem that it is not determined which form item the generated content needs to be filled in. In addition, there may be multiple form items of the same type, for example, multiple commodity main pictures may be required, and the number of pictures generated by the AI may not completely correspond to the number of items to be filled in the form. If the number of generated pictures is more than the number of items to be filled in, the user may still need to select from them. Furthermore, in the case of multiple form items of the same type, the user not only needs to determine which content to use, but also needs to customize the order between the contents, for example, 5 commodity main pictures need to be filled in. At this time, the user may need to customize the order of the commodity main pictures to be displayed to the consumer user in the order, and the like.

[0005] For the above case, if the implementation manner in the prior art is followed, the user may need to select and fill in the corresponding form item in the form in units of each content in sequence. For example, a certain picture is selected from the preview area of the AI generated content and is dragged into a certain form item in the form, and then another picture is selected from the preview area and is dragged into another form item in the form, and the like. This requires the user to repeatedly perform multiple picture dragging operations, which is low in execution efficiency. SUMMARY

[0006] The present disclosure provides a content filling interaction, a method for publishing commodity information, and an electronic device, which can more efficiently and flexibly complete content filling.

[0007] The present disclosure provides the following solutions:

[0008] A content filling interaction method comprises:

[0009] A content filling interface is displayed, an AI generated content preview area is provided in the content filling interface after AI generated content is generated according to a user initiated artificial intelligence (AI) generation request, and an operation option for applying the AI generated content is provided in the preview area, wherein the content filling interface comprises multiple to-be-filled items;

[0010] In response to a click operation on the operation option, follow-up content following the movement of a mouse pointer is generated according to the AI generated content;

[0011] After detecting that the mouse pointer is moved to a target item and a click operation is performed, the follow-up content following the mouse pointer is filled into the target item.

[0012] The AI-generated content is in multiple copies.

[0013] The generating of the follow-up content following the mouse pointer movement according to the AI-generated content comprises:

[0014] In the initial state, the follow-up content following the mouse pointer movement is generated according to one of the multiple AI-generated contents.

[0015] The method further comprises:

[0016] After the current follow-up content is filled in the target item, the follow-up content following the mouse pointer movement is automatically switched to another AI-generated content.

[0017] The AI-generated content is in multiple copies.

[0018] The method further comprises:

[0019] After the follow-up content is generated, if an operation of switching the follow-up content performed by the user through a shortcut key is received, the follow-up content following the mouse pointer movement is switched to another AI-generated content.

[0020] The follow-up content following the mouse pointer movement is switched according to the order of the multiple AI-generated contents displayed in the preview area.

[0021] The method further comprises:

[0022] In the follow-up content, badge information is provided, the badge information is used to express the number of the multiple AI-generated contents, and the display position of the AI-generated content corresponding to the current follow-up content in the preview area.

[0023] A method for publishing commodity information comprises:

[0024] After receiving a commodity publishing request initiated by a user, a commodity information publishing interface is provided, the interface comprises an item display area and a first operation option for initiating an AI generation request, the item display area is used to display multiple to-be-filled items.

[0025] After receiving a request through the first operation option and generating AI-generated content, an AI-generated content preview area is provided in the interface, and a second operation option for applying the AI-generated content is provided in the preview area; wherein the AI-generated content comprises image or text content required in the commodity publishing process, and at least one AI-generated content of the same type is generated each time a request is received.

[0026] in response to a click operation on the second operation option, generating follow-up content following the mouse pointer movement according to the AI-generated content;

[0027] after detecting that the mouse pointer is moved to a target item in the item display area and a click operation is performed, filling the follow-up content following the mouse pointer into the target item, so as to publish the goods after completing the content filling of multiple items.

[0028] wherein the AI-generated content includes multiple AI-generated contents of the same type;

[0029] generating follow-up content following the mouse pointer movement according to the AI-generated content, including:

[0030] in the initial state, generating the follow-up content following the mouse pointer movement according to one of the multiple AI-generated contents;

[0031] The method further comprises:

[0032] after the current follow-up content is filled into the target item, automatically switching the follow-up content following the mouse pointer movement to another AI-generated content.

[0033] A content filling interaction method, comprising:

[0034] displaying a content filling interface, wherein the content filling interface includes multiple items to be filled;

[0035] determining at least one target content;

[0036] generating follow-up content following the mouse pointer movement according to the at least one target content;

[0037] after detecting that the mouse pointer is moved to a target item and a click operation is performed, filling the follow-up content following the mouse pointer into the target item.

[0038] wherein the at least one target content includes:

[0039] after initiating a request through an operation option provided in the content filling interface for initiating an AI generation request, generating at least one AI-generated content.

[0040] wherein the at least one target content includes:

[0041] the content copied to the clipboard, which is from a file or document local to the terminal device, or a page opened through a web browser.

[0042] A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the preceding methods.

[0043] An electronic device comprising:

[0044] one or more processors; and

[0045] a memory associated with the one or more processors, the memory for storing program instructions that, when read and executed by the one or more processors, perform the steps of any of the preceding methods.

[0046] A computer program product comprising computer program / computer executable instructions which, when executed by a processor in an electronic device, implement the steps of any of the preceding methods.

[0047] According to the specific embodiments provided by the present disclosure, the present disclosure discloses the following technical effects:

[0048] According to the embodiments of the present disclosure, in the case where it is necessary to apply AI generated content to a content filling interface, if there are multiple different to-be-filled items in the interface, an operation option for applying the AI generated content can be provided in a preview area, after receiving an application request through the operation option, follow-up content following the movement of a mouse pointer can be generated according to the AI generated content, and after detecting a click operation performed by moving the mouse pointer to a target item in the interface, the follow-up content following the mouse pointer is filled into the target item. In this way, the application of AI generated content to a specific content filling interface can be more efficient and flexible.

[0049] In the initial state after the user clicks the "apply" option, the follow-up content following the mouse pointer movement can be generated according to one of the multiple AI-generated contents. After the user fills the follow-up content into a certain item, the follow-up content of the mouse pointer is automatically switched to another AI-generated content (without the need for the user to perform a click or selection operation in the preview area), and the user directly moves the mouse pointer to another item and performs a click operation again to fill the new follow-up content into the other item. Compared with the traditional way of mouse dragging, this way can more efficiently complete the filling of multiple AI-generated contents into multiple different items. Since which content is filled into which item is determined by the user, and different items have a ranking attribute, after a certain content is filled into a certain item, the ranking attribute of the item can be directly assigned to the content, so that the ranking of the specific content can be automatically determined during the filling process, thereby meeting the user's personalized selection or sorting needs during the filling process.

[0050] Of course, implementing any product of the present disclosure does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0052] FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present disclosure;

[0053] FIG. 2 is a flowchart of a first method provided by an embodiment of the present disclosure;

[0054] FIG. 3 is a schematic diagram of an interface provided by an embodiment of the present disclosure;

[0055] FIG. 4 is a flowchart of a second method provided by an embodiment of the present disclosure;

[0056] FIG. 5 is a flowchart of a third method provided by an embodiment of the present disclosure;

[0057] FIG. 6 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0058] With reference to the drawings and the embodiments of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art are within the scope of the present disclosure.

[0059] In order to facilitate understanding of the scheme provided by the embodiments of the present disclosure, first of all, it needs to be explained that in many applications, filling out a form will be involved. The form described in the embodiments of the present disclosure includes an explicit form, that is, a table line can be drawn in the interface according to the rules of multi-row and multi-column arrangement, for example, the interface provided by some electronic table tools, etc. Or it can also include an implicit form, that is, there is at least one item that needs to be filled in the application interface, but there may be no regular arrangement of table lines. For the latter, it can generally refer to a scenario that needs to complete a certain function on a webpage. For example, in a commodity information service system, a merchant needs to provide a commodity publishing interface to the merchant in the process of publishing a commodity. The commodity publishing interface can include multiple items to be filled, including commodity main picture, title text, attributes, etc. These items can be scattered in multiple locations in the interface, and each item can correspond to an input box or other control. These items and the corresponding input boxes can constitute an implicit form. In summary, whether it is an explicit form or an implicit form, it involves content filling, so the corresponding interface can be collectively referred to as a content filling interface.

[0060] Among them, in the scenario of combining content filling with AI generated content, in some cases, there is only one item to be filled in the interface. At this time, it is possible to realize the automatic filling of AI generated content, or the user only needs to apply the AI generated content to the specific item in the interface through simple operation. For example, assuming that the AI generated content also has only one copy, at this time, the user can directly click the "apply" option in the preview area to fill the AI generated content into the item in the interface. Or if the AI generated content has multiple copies, one of them can be selected in the preview area, and then after clicking the "apply" option, it is filled into the item.

[0061] However, the scenario targeted by the embodiments of the present disclosure is that a specific content filling interface includes multiple different to-be-filled items, and even in some interfaces, multiple to-be-filled items for filling different content types are included. For example, as described in the background section, in a commodity information service system, a merchant user needs to fill in a form in a commodity publishing interface during a commodity publishing process, which includes items for inputting content such as a commodity main image and a commodity title. The commodity main image can be multiple, so the to-be-filled items of the image type are also multiple. The commodity title can be divided into a main title and a subtitle, so the to-be-filled items of the text type can also be multiple, and so on.

[0062] For such a content filling interface, even if the user can be assisted by an AI assistant to generate AI-generated content, in the process of applying such AI-generated content to the above-mentioned content filling interface, automatic filling cannot be achieved, and the user can need to perform multiple-step operations. For example, still taking the form in the above-mentioned commodity publishing interface as an example, assuming that the form includes 6 to-be-filled items of the commodity main image type, after the user uploads two specific commodity white background images, the user generates multiple related scene images through the AI assistant to fill in the remaining 4 items of the commodity main image type. If the user does not specify the specific number of generated images, the AI-generated scene images can be more than 4, and the user needs to select 4 from them to fill in the corresponding items. Even if the user specifies the number of generated images, for example, the AI-generated scene images are 4, but there is still a problem that the AI-generated content cannot be applied to the form in a “one-click” manner.

[0063] This is because, first, the user can still need to customize the order of each piece of AI-generated content when filling multiple pieces of AI-generated content into specific items. For example, for a commodity main image, since multiple different commodity main images can usually share the same commodity main image resource position in a commodity detail page, the images will be displayed in sequence in a carousel. Usually, the merchant can want to display the main image that can better express the characteristics of the commodity to the consumer first. For example, for a clothing commodity, the model upper body image can need to be displayed first, and then various detail images of different perspectives can be displayed, and so on. Obviously, it is difficult to predict how the merchant wants to sort each piece of AI-generated content. Even if each piece of AI-generated content is determined according to a certain rule, there is a high probability that it does not meet the needs of the merchant user. At this time, the merchant user still needs to manually reorder.

[0064] In addition, there is a problem that there can be multiple different types of items in the content filling interface, for example, in the aforementioned example, the form in the commodity publishing interface can have an item for uploading the main commodity image, and also have an item for inputting the commodity title, etc. After the specific content is generated by AI, it is difficult to automatically identify which item needs to be filled with the generated content. That is, it is difficult to realize the correspondence between the content and the item.

[0065] Due to the above problems, after the AI generates the specific content, the process of specifically applying the AI-generated content to the items in the content filling interface still usually needs to be manually operated by the user. Under the method in the prior art, the user can need to perform multiple steps of manual operation. For example, in the aforementioned example, assuming that the AI generates 6 pictures that need to be filled into the items related to the main commodity image in the form, since the picture selection needs to be performed, and the order of each picture needs to be determined, the "mouse dragging" method in the conventional technology is a relatively suitable method. Under this method, the user can need to select four from the six pictures, and sequentially drag them from the preview area to the corresponding items in the form. Each time the mouse is dragged, the mouse pointer needs to be moved to a certain AI-generated content on the preview area, the left mouse button is pressed and not released, and then the mouse pointer is moved to a certain target item in the form, and then the left mouse button is released. Then, the mouse pointer is moved to another AI-generated content on the preview area, and the above process is repeated. In this process, the selection of the AI-generated content and the determination of the order of each AI-generated content can be realized. For example, the first AI-generated picture is dragged to the third item of the main commodity image type, the third AI-generated picture is dragged to the fourth item of the main commodity image type, etc. The user needs to perform at least four dragging operations to apply the AI-generated content to the specific content filling interface.

[0066] The above method can realize the application of the AI-generated content and support the personalized selection or ordering requirements of the user such as the merchant, but the implementation efficiency is relatively low, and the user needs to perform multiple steps of mouse dragging operation to complete the filling of each item.

[0067] In order to improve the operation efficiency of the user, the embodiments of the present disclosure provide a corresponding solution. In this solution, for the case where multiple items exist in the content filling interface, after obtaining the AI generated content, a preview area can be provided to display the AI generated content, and an "apply" operation option can be provided. The user only needs to click on this operation option to generate the follow-up content following the mouse pointer movement according to the AI generated content. That is, after the user clicks "apply" with the mouse, the specific AI generated content (which can exist in the form of a smaller thumbnail, etc.) will be displayed at the lower right side of the mouse pointer, etc. This content will move with the movement of the mouse pointer, so it is called the follow-up content of the mouse pointer. Then, when the user moves the mouse pointer to the position of a certain item in the interface, if the click operation of the mouse is performed again, the current follow-up content can be filled into the item.

[0068] Among them, for the case where there are multiple AI generated contents, in the initial state after the user clicks the "apply" option with the mouse, the follow-up content following the mouse pointer movement can be generated according to one of the multiple AI generated contents. For example, the AI generated content that is arranged at the first position in the preview area can be defaulted as the follow-up content of the mouse pointer. Then, after the user fills this follow-up content into a certain item, the follow-up content of the mouse pointer will automatically switch to another AI generated content (without the user performing the click or selection operation in the preview area again), and the user can directly move the mouse pointer to other items and perform the click operation again to fill the new follow-up content into the other items, and so on.

[0069] For example, in the initial state, the first AI generated content becomes the follow-up content of the mouse pointer, and the user can determine which item is suitable for filling it into through this follow-up content. For example, the first AI generated content is suitable for being placed in the fourth item, the mouse pointer can be moved to the fourth item, and the click operation is performed again to fill the first AI generated content into the fourth item. Then, the second AI generated content will automatically become the new follow-up content, and the mouse pointer can be directly moved to other items to complete the filling. Moreover, since the user selects the items in the filling process, and the items have the arrangement position information in the display interface, when the follow-up content is filled into a certain item, the arrangement position of the item can be determined as the arrangement position of the follow-up content, that is, the custom ordering of the multiple contents can be completed at the same time in the filling process. It can be seen that in the case where there are multiple AI generated contents, the advantages of the content following the mouse pointer provided by the embodiments of the present disclosure will be more prominent.

[0070] Of course, in the case of one AI-generated content, the mouse pointer following mode has an advantage over the mouse dragging mode, mainly manifested as: after generating the following content of the mouse pointer, the mouse pointer can be moved freely, and during this period, the up and down mouse scroll wheel scrolling operation can also be performed in the project filling area to scroll the interface within the visible window, and the operation is more flexible. In the case of mouse dragging, after the user clicks on a certain AI-generated content from the preview area, the left mouse button cannot be released until it is dragged to a certain project, and then the left mouse button can be released. During this period, if the required project is not in the window visible area, it is also difficult to realize the scrolling of the interface in the state that the left mouse button is pressed, so the operation is not flexible enough.

[0071] In addition, in the case of multiple AI-generated contents, there may be a case where the number of AI-generated contents is more than the number of projects. At this time, since the user only needs to click the "apply" option in the preview area, and there is no selection of AI-generated content in the preview area, it may happen that the current following content is not the content the user wants. In view of the above situation, a function of switching the following content by shortcut key can also be provided. For example, in the initial state, the first AI-generated content becomes the following content, but the user thinks that this content does not meet his needs, and then the user can manually switch the following content by pressing the shortcut key. Of course, during the manual switching process, the next following content can also be determined according to the display order of each AI-generated content in the preview area, and so on.

[0072] Of course, since the following content usually exists in the form of a thumbnail, the display area is usually small, and there may be a case where it is not possible to accurately judge the content according to such a thumbnail. In view of this situation, in the preferred embodiment, a superscript information can also be provided in the following content, which can be used to express the number of multiple AI-generated contents and the display position of the AI-generated content corresponding to the current following content in the preview area. For example, assuming that there are 6 AI-generated contents in total, and the current following content is the first one, then "1 / 6" can be displayed in the upper right corner of the following content. In this way, the user can know that the current following content is the first AI-generated content in the preview area. If the specific image details cannot be seen from the following content, the corresponding AI-generated content can be found in the preview area for viewing according to the specific superscript information.

[0073] The above describes the main scheme provided by the embodiments of the present disclosure. It should be noted that in actual application, the implementation scheme of filling the form by generating the follow-up content of the mouse pointer can not be limited to AI-generated content, but can also be other content. For example, it can be content copied from a file or document saved locally by the terminal device, or content copied from a webpage opened by the browser, etc. For example, if a user needs to upload several pictures saved locally by the terminal device as product main pictures, the user can first select and copy the pictures. Or, if a user needs to publish content in a webpage as product main pictures, the user can also select and copy the content in the webpage. Then, after opening the content filling interface, the interface code can detect that the clipboard of the terminal device contains recently copied content. At this time, the user can be asked by a pop-up window or the like whether to fill the currently copied content into the current content filling interface. If so, the follow-up content of the mouse pointer can be generated according to the copied content. The user can fill the follow-up content into a to-be-filled item by moving the mouse pointer to the item and performing a click operation. Then, the follow-up content of the mouse pointer is automatically switched to the next content in the clipboard, and the user can continue to fill the next item by moving the mouse pointer to the position of the item and performing a click operation, without repeatedly switching between different windows (the window where the local folder is located and the window where the content filling interface is located) or performing a mouse drag operation.

[0074] From the perspective of system architecture, referring to FIG. 1, the embodiments of the present disclosure can provide a corresponding solution in a content filling related application or webpage (for example, a product publishing page). In the solution, the specific content (including AI-generated content after initiating a request in the current content filling interface, or content temporarily stored in the clipboard after copying a local folder or document through an online browser, etc.) can be more quickly and efficiently filled into a form by generating follow-up content of a mouse pointer, and the user can easily select and sort the content in the filling process. In specific implementation, if the content is multiple, the content can be grouped into objects, and then the follow-up content of the mouse pointer is generated in units of objects, and the objects are filled into the corresponding items in the form of a queue.

[0075] The specific implementation of the embodiments of the present disclosure is described below.

[0076] Embodiment One

[0077] First, the embodiment one provides a content filling interaction method for the scenario of applying AI-generated content to a form after initiating a request in a content filling interface, as shown in FIG. 2. The method can include:

[0078] S201: display a content filling interface, provide an AI-generated content preview area in the content filling interface after generating AI-generated content according to a user-initiated AI generation request, and provide an operation option for applying the AI-generated content in the preview area, wherein the content filling interface includes a plurality of to-be-filled items.

[0079] The content filling interface can have multiple forms, and different forms can be displayed according to the requirements of different application scenarios, for example, the form for filling in the main picture, title, and other content of the product in the product publishing scenario in the foregoing example, and the like. The specific content filling interface can include a plurality of to-be-filled items. In the embodiments of the present disclosure, an operation option for initiating an AI generation request can also be provided in the content filling interface. The user can invoke an AI assistant or the like through the option and input his or her generation requirements. Then, the AI assistant can generate AI-generated content meeting the user's requirements through an AI model.

[0080] For example, as shown in FIG. 3, which shows a product publishing interface in an example, the left side is a project filling area. After the user invokes an AI assistant, an area for interacting with the AI can be displayed through a sidebar or the like on the right side. In the area, the user can input specific generation requirements. For example, for the plurality of to-be-filled items corresponding to the main picture of the product as shown at 31 in FIG. 3, the user has uploaded two white background pictures. Then, the AI needs to help generate two scene pictures. The user can invoke the AI assistant through a corresponding operation option (not shown in the figure) and input "help me generate two scene pictures" as shown at 32 in FIG. 3. Then, the AI-generated content can be displayed in the preview area as shown at 33 in FIG. 3. In addition, an "apply" operation option as shown at 34 in FIG. 3 can also be provided. If the user thinks that the currently generated scene picture meets his or her requirements, the user can click the "apply" option.

[0081] It should be noted that the specific generation method of the AI-generated content is not the focus of the embodiments of the present disclosure, and therefore will not be described in detail here.

[0082] S202: In response to a click operation on the operation option, generate follow-up content following the movement of a mouse pointer according to the AI-generated content.

[0083] After obtaining the AI-generated content, although there can be a many-to-many relationship between the AI-generated content and the to-be-filled items in the interface, and in the process of applying such AI-generated content, the user still needs to make personalized selection and ordering, etc., in the embodiments of the present disclosure, the user does not need to perform a single selection or multiple selection selection operation on the AI-generated content, and even less involves setting an order in the process of selecting the AI-generated content (in the scenario of a social network system, etc., the user may need to select some pictures from the local album for publishing, in the process of selection, multiple selection can be made, and the order number of each picture is automatically generated and filled into the specific form, but the embodiments of the present disclosure do not adopt this way). Instead, after the user clicks the "apply" option, the following content following the mouse pointer movement can be generated according to the AI-generated content. If the AI-generated content is only one copy, the content can be directly used as the following content, if the AI-generated content is multiple copies, one of them can be used as the following content, for example, the AI-generated content in the first place can be used as the initial following content according to the display order in the preview area, etc.

[0084] Specifically, the following content can be a thumbnail of the AI-generated content, which can be smaller than the thumbnail displayed in the preview area. From the visual effect, after the user clicks the "apply" option, a small thumbnail is displayed at the lower right of the mouse pointer, etc. The thumbnail corresponds to a copy of the AI-generated content, and the small thumbnail moves with the movement of the mouse pointer. For example, as shown in 35 of FIG. 3, it is a mouse pointer, and 36 is the following content.

[0085] It should be noted that since there is only one copy of the following content generated each time, in the case of multiple copies of the AI-generated content, a superscript can be added at the upper right corner of the following content, etc. Such superscript can display the total number of AI-generated content and the display position of the current following content in the preview area. For example, in the example shown in FIG. 3, the current following content is the first scene graph displayed in the preview area, and as shown in 37 of FIG. 3, the prompt information in the superscript of the following content can be "1 / 2", indicating that there are two copies of AI-generated content, and the first copy is currently followed by the mouse pointer.

[0086] S203: After detecting that the mouse pointer is moved to the target item and the click operation is performed, the following content of the following mouse pointer is filled into the target item.

[0087] After the follow-up content of the mouse pointer is generated, the user can move the mouse pointer to a to-be-filled item in the item filling area, perform a click operation, and the follow-up content is filled into the item. For example, as shown in the example in FIG. 3, it is assumed that the mouse pointer is moved to the item shown by 38 and a click operation is performed, and the current follow-up content is filled into the item.

[0088] If the AI-generated content is multiple, in the initial state, the follow-up content following the mouse pointer movement can be generated according to one of the multiple AI-generated content, and after the current follow-up content is filled into the target item, the follow-up content following the mouse pointer movement can be automatically switched to another AI-generated content.

[0089] For example, it is assumed that in the example shown in FIG. 3, after the mouse pointer is moved to the item shown by 38, the follow-up content is filled into the item by clicking the mouse, and the follow-up content of the mouse pointer can be automatically switched to the second scene graph, and the prompt information on the superscript can be updated to “2 / 2”. The user directly moves the mouse pointer to other to-be-filled items in the item display area and clicks again, and the second scene graph is filled into the corresponding item. It can be seen that, compared with the “mouse dragging” mode, the scheme provided in the embodiment of the disclosure has higher implementation efficiency, does not need to move the mouse pointer back and forth between the item filling area and the preview area multiple times, and has a more novel implementation form, which is beneficial to improving the user experience.

[0090] In addition, in the case where the AI-generated content is multiple, especially in the case where the number of AI-generated content can be greater than the number of to-be-filled items, the selection of the AI-generated content can also be involved. However, in the embodiment of the disclosure, the user still does not need to select the AI-generated content in the preview area, but the following method is used: even if the AI-generated content needs to be selected, the “apply” option can be directly clicked to directly generate the follow-up content of the mouse pointer, but after the follow-up content is generated, if the user does not want to use this content, the follow-up content can be switched through a shortcut key. That is, after receiving the operation of switching the follow-up content performed by the user through the shortcut key, the follow-up content of the mouse pointer can be switched to another AI-generated content. The shortcut key can have multiple definitions, for example, it can be a “→” key, or it can also be implemented through a combination of keys, and the like.

[0091] Wherein, whether it is a follow-up content switching triggered after a user completes the filling of a project, or a follow-up content switching triggered by a shortcut key, in specific implementation, the follow-up content following the mouse pointer movement can be switched according to the display order of the multiple AI-generated contents in the preview area. For example, in the initial state, the AI-generated content ranked first can be defaulted as the follow-up content, and when switching, it is switched to the second one, and then to the third one, and so on. Of course, in specific implementation, there can be other implementation manners, for example, the matching degree of each AI-generated content of the user and the user demand can also be predicted, and then the follow-up content of the mouse pointer is generated in order according to the matching degree, and the like.

[0092] In summary, through the embodiments of the present disclosure, in the case of needing to apply AI-generated content to a content filling interface, if there are multiple different to-be-filled projects in the interface, an operation option for applying the AI-generated content can be provided in the preview area. After receiving an application request through the operation option, the follow-up content following the mouse pointer movement can be generated according to the AI-generated content. After detecting that the mouse pointer is moved to a target project in the interface and a click operation is performed, the follow-up content following the mouse pointer is filled into the target project. In this way, the application of AI-generated content to a specific content filling interface can be more efficiently and flexibly realized.

[0093] Wherein, in the case of multiple AI-generated contents, in the initial state after the user clicks the “apply” option, the follow-up content following the mouse pointer movement can be generated according to one of the multiple AI-generated contents. After the user fills the follow-up content into a certain project, the follow-up content of the mouse pointer will automatically switch to another AI-generated content (without the need for the user to perform a click or selection operation in the preview area again), and the user can directly move the mouse pointer to another project and perform a click operation again to fill the new follow-up content into the other project. Compared with the traditional way of mouse dragging, this way can more efficiently complete the filling of multiple AI-generated contents into multiple different projects. Moreover, since which content is filled into which project is determined by the user, and there is a ranking attribute between different projects, after a certain content is filled into a certain project, the ranking attribute of the project can be directly assigned to the content, so that the ranking of the specific content can be automatically determined during the filling process, thereby meeting the user's demand for personalized selection or ordering during the filling process.

[0094] Embodiment Two

[0095] The second embodiment is from the perspective of publishing such application scenarios for specific commodities, and provides a method for publishing commodity information, as shown in FIG. 4. The method can include:

[0096] S401: After receiving a commodity publishing request initiated by a user, a commodity information publishing interface is provided, the interface including a project display area and a first operation option for initiating an AI generation request, the project display area being used to display a plurality of to-be-filled projects;

[0097] S402: After receiving a request through the first operation option and generating AI generated content, an AI generated content preview area is provided in the interface, and a second operation option for applying the AI generated content is provided in the preview area. The AI generated content includes image or text content required in the commodity publishing process, and at least one AI generated content of the same type is generated each time a request is made;

[0098] S403: In response to a click operation on the second operation option, follow-up content following the movement of the mouse pointer is generated according to the AI generated content;

[0099] S404: After detecting that the mouse pointer is moved to a target project in the project display area and a click operation is performed, the follow-up content following the mouse pointer is filled into the target project, so that commodity publishing is performed after the content filling of the plurality of projects is completed.

[0100] Wherein, the AI generated content includes a plurality of AI generated contents of the same type. At this time, in the initial state, the follow-up content following the movement of the mouse pointer is generated according to one of the plurality of AI generated contents. After the current follow-up content is filled into the target project, the follow-up content following the movement of the mouse pointer is automatically switched to another AI generated content.

[0101] Embodiment three

[0102] As described above, in the embodiments of the present disclosure, the content filled into the content filling interface can be content generated by AI after a request is initiated in the content filling interface, or content copied from a file or document local to the terminal device and temporarily stored in the system clipboard, or content copied from a web page opened in the web browser and temporarily stored in the clipboard, etc. Therefore, another content filling interaction method is also provided in this embodiment three, as shown in FIG. 5. The method can include:

[0103] S501: Display a content filling interface, the content filling interface including a plurality of to-be-filled projects;

[0104] S502: determining at least one target content;

[0105] S503: generating following content following the movement of the mouse pointer according to the at least one target content;

[0106] S504: filling the following content following the mouse pointer into the target item after detecting that the mouse pointer is moved to the target item and a click operation is performed.

[0107] Among them, the at least one target content includes: at least one AI generated content generated after initiating a request through an operation option provided in the content filling interface for initiating an AI generation request. Alternatively, the at least one target content includes: content copied to the clipboard, which comes from a file or document local to the terminal device, or a page opened through a web browser.

[0108] For the parts not described in the above embodiments two and three, please refer to the description of the aforementioned embodiment one and other parts of this specification, which will not be repeated here.

[0109] It should be noted that the present disclosure embodiments may involve the use of user data. In actual application, user-specific personal data can be used in the schemes described herein in a manner that complies with the applicable legal and regulatory requirements of the country in which it is used (for example, with the explicit consent of the user, with the actual notification to the user, etc.), within the scope permitted by applicable laws and regulations.

[0110] Corresponding to the embodiment one, the present disclosure embodiment also provides a content filling interaction device, which can include:

[0111] An interface display unit is configured to display a content filling interface, provide an AI generated content preview area in the content filling interface after generating AI generated content according to a user-initiated artificial intelligence (AI) generation request, and provide an operation option for applying the AI generated content in the preview area.

[0112] A mouse following content generation unit is configured to generate following content following the movement of the mouse pointer according to the AI generated content in response to a click operation on the operation option.

[0113] A filling unit is configured to fill the following content following the mouse pointer into the target item after detecting that the mouse pointer is moved to the target item and a click operation is performed.

[0114] Among them, the AI generated content is multiple;

[0115] The mouse-following content generation unit can be specifically configured to:

[0116] In an initial state, generate the following content following the mouse pointer movement according to one of the plurality of AI-generated contents;

[0117] The device further comprises:

[0118] The first switching unit is configured to automatically switch the following content following the mouse pointer movement to another AI-generated content after the current following content is filled into the target item.

[0119] If the AI-generated content is in multiple copies, the device can further comprise:

[0120] The second switching unit is configured to switch the following content following the mouse pointer movement to another AI-generated content after the following content is generated, if an operation of switching the following content performed by the user through a shortcut key is received.

[0121] The following content following the mouse pointer movement can be switched according to the display order of the plurality of AI-generated contents in the preview area.

[0122] In addition, the device can further comprise:

[0123] The superscript information display unit is configured to provide superscript information in the following content, the superscript information being used to express the number of the plurality of AI-generated contents and the display position of the AI-generated content corresponding to the current following content in the preview area.

[0124] Corresponding to the second embodiment, the disclosure also provides a device for publishing commodity information, which can comprise:

[0125] The interface providing unit is configured to provide a commodity information publishing interface after receiving a commodity publishing request initiated by a user, the interface comprising an item display area and a first operation option for initiating an AI generation request, the item display area being used to display a plurality of to-be-filled items.

[0126] The preview area providing unit is configured to provide an AI-generated content preview area in the interface and a second operation option for applying the AI-generated content in the preview area after receiving a request through the first operation option and generating AI-generated content, wherein the AI-generated content comprises image or text content required in a commodity publishing process, and at least one AI-generated content of the same type is generated each time a request is received.

[0127] The mouse-following content generation unit is configured to generate, in response to a click operation on the second operation option, a following content following the mouse pointer movement according to the AI-generated content.

[0128] The filling unit is configured to fill the following content following the mouse pointer into the target item after detecting that the mouse pointer is moved to the target item in the item display area and a click operation is performed, so as to publish the goods after filling the contents of the multiple items.

[0129] The AI-generated content includes multiple AI-generated contents of the same type.

[0130] The mouse-following content generation unit can be specifically configured to generate, in an initial state, the following content following the mouse pointer movement according to one of the multiple AI-generated contents.

[0131] The device further includes:

[0132] The switching unit is configured to automatically switch the following content following the mouse pointer movement to another AI-generated content after the current following content is filled into the target item.

[0133] Corresponding to Embodiment Three, the disclosure also provides a content filling interaction device, which can include:

[0134] The interface display unit is configured to display a content filling interface, and the content filling interface includes multiple items to be filled.

[0135] The content determination unit is configured to determine at least one target content.

[0136] The mouse-following content generation unit is configured to generate a following content following the mouse pointer movement according to the at least one target content.

[0137] The filling unit is configured to fill the following content following the mouse pointer into the target item after detecting that the mouse pointer is moved to the target item and a click operation is performed.

[0138] The at least one target content includes:

[0139] At least one AI-generated content is generated after a request is initiated through an operation option provided in the content filling interface for initiating an AI generation request.

[0140] Alternatively, the at least one target content includes:

[0141] The content copied to the clipboard is from a file or a document local to the terminal device or a page opened through a web browser.

[0142] In addition, the disclosure embodiments also provide a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the method of any one of the preceding method embodiments.

[0143] An electronic device, comprising:

[0144] one or more processors; and

[0145] a memory associated with the one or more processors, the memory for storing program instructions, which, when read and executed by the one or more processors, perform the steps of the method of any one of the preceding method embodiments.

[0146] A computer program product comprising computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method of the preceding method embodiments.

[0147] In some embodiments, the electronic device can include a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, and a memory 620. The processor 610, the video display adapter 611, the disk drive 612, the input / output interface 613, the network interface 614, and the memory 620 can be connected by a communication bus 630.

[0148] The processor 610 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the disclosure.

[0149] The memory 620 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 620 can store an operating system 621 for controlling the operation of the electronic device 600, a basic input / output system (BIOS) for controlling the low-level operation of the electronic device 600. In addition, a web browser 623, a data storage management system 624, and a content filling interaction processing system 625, etc. can also be stored. The content filling interaction processing system 625 described above can be an application program that specifically implements the operations of the foregoing steps in the embodiments of the present disclosure. In summary, when the technical solutions provided by the present disclosure are implemented by software or firmware, the relevant program codes are stored in the memory 620 and executed by the processor 610.

[0150] The input / output interface 613 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0151] The network interface 614 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0152] The bus 630 includes a channel for transmitting information between various components (such as the processor 610, the video display adapter 611, the disk drive 612, the input / output interface 613, the network interface 614, and the memory 620) of the device.

[0153] It should be noted that although the above device only shows the processor 610, the video display adapter 611, the disk drive 612, the input / output interface 613, the network interface 614, the memory 620, the bus 630, etc., in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary to implement the present disclosure, and does not necessarily contain all the components shown in the figure.

[0154] Those skilled in the art can clearly understand the present disclosure by the description of the above embodiments. Based on such understanding, the technical solutions of the present disclosure can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present disclosure.

[0155] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the system or system embodiments, since it is basically similar to the method embodiments, it is described more simply, and the related parts can be referred to the part of the method embodiments. The above described system and system embodiments are only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to the actual needs, some or all of the modules can be selected to achieve the purpose of the embodiment. Those skilled in the art can understand and implement without creative labor.

[0156] The above method and electronic device provided by the present disclosure are described in detail, and the principle and implementation of the present disclosure are described by applying specific examples. The above embodiment is only used to help understand the method and core idea of the present disclosure; at the same time, for those skilled in the art, according to the idea of the present disclosure, the specific implementation and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present disclosure.

Claims

1. A content-filling interaction method, wherein, include: The content filling interface displays AI-generated content. After generating AI-generated content based on the user's AI-generated request, a preview area for the AI-generated content is provided in the content filling interface. Operation options for applying the AI-generated content are provided in the preview area. The content filling interface includes multiple items to be filled. In response to a click on the operation option, follow content that moves with the mouse pointer is generated based on the AI-generated content; After detecting that the mouse pointer has been moved to the target item and a click operation has been performed, the content following the mouse pointer is filled into the target item.

2. The method according to claim 1, wherein, The AI-generated content is in multiple parts; The step of generating follow content that moves with the mouse pointer based on the AI-generated content includes: In the initial state, the content that follows the mouse pointer movement is generated based on one of the multiple AI-generated content; The method further includes: After the currently following content is filled into the target item, the following content that follows the mouse pointer movement is automatically switched to another AI-generated content.

3. The method according to claim 1 or 2, wherein, The AI-generated content is in multiple parts; The method further includes: After generating the following content, if a user is received to switch the following content via a shortcut key, the following content that follows the mouse pointer movement will be switched to another AI-generated content.

4. The method according to claim 2 or 3, wherein, include: The content that follows the mouse pointer movement is switched according to the display order of multiple AI-generated contents in the preview area.

5. The method according to any one of claims 2 to 4, wherein, Also includes: The following content provides badge information, which is used to express the number of AI-generated content pieces and the display position of the AI-generated content corresponding to the current following content in the preview area.

6. A method for publishing product information, wherein, include: Upon receiving a product publishing request initiated by a user, a product information publishing interface is provided. The interface includes a project display area and a first operation option for initiating an AI generation request. The project display area is used to display multiple projects to be filled. After receiving a request and generating AI-generated content through the first operation option, an AI-generated content preview area is provided in the interface, and a second operation option for applying the AI-generated content is provided in the preview area; wherein, the AI-generated content includes image or text content required in the product publishing process, and at least one copy of the same type of AI-generated content is generated for each request; In response to a click on the second operation option, follow content that moves with the mouse pointer is generated based on the AI-generated content; After detecting that the mouse pointer has been moved to the target project in the project display area and a click operation has been performed, the content following the mouse pointer is filled into the target project so that the product can be published after the content of multiple projects has been filled.

7. The method according to claim 6, wherein, The AI-generated content includes multiple AI-generated pieces of the same type; The step of generating follow content that moves with the mouse pointer based on the AI-generated content includes: In the initial state, the following content that follows the mouse pointer movement is generated based on one of the multiple AI-generated content; The method further includes: After the currently following content is filled into the target item, the following content that follows the mouse pointer movement is automatically switched to another AI-generated content.

8. A content-filling interaction method, wherein, include: A content-filling interface is displayed, which includes multiple items to be filled. Identify at least one target document; Generate follow content that follows the mouse pointer movement based on the at least one target content; After detecting that the mouse pointer has been moved to the target item and a click operation has been performed, the content following the mouse pointer is filled into the target item.

9. The method according to claim 8, wherein, The at least one target content includes: After initiating a request using the operation options provided in the content filling interface for initiating an AI generation request, at least one piece of AI-generated content will be generated.

10. The method according to claim 8 or 9, wherein, The at least one target content includes: Content copied to the clipboard, wherein the content copied to the clipboard comes from a file or document on the terminal device or a page opened through a web browser.

11. A computer-readable storage medium having a computer program stored thereon, wherein, When executed by a processor, the program implements the steps of the method described in any one of claims 1 to 10.

12. An electronic device, wherein, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 10.

13. A computer program product comprising a computer program / computer-executable instructions, wherein, When the computer program / computer-executable instructions are executed by a processor in an electronic device, they implement the steps of the method according to any one of claims 1 to 10.

Images