Display object generation method and system, electronic device, and storage medium

Abstract

Embodiments of the present disclosure provide a display object generation method, a display object generation system, an electronic device, a storage medium, and a computer program product. The display object generation method comprises: acquiring object generation requirement information input by a user by means of an object creation interface; sending the object generation requirement information to a server, triggering the server to generate page data that matches the object generation requirement information; on the basis of the page data, displaying page content of a display object to be generated; and generating a display object in response to a display object generation operation triggered for the page content. When the present method is used to generate a display object, a user only needs to describe, by means of a short language, the display object that needs to be generated, and the display object that matches the requirements of the user can be quickly generated, eliminating the need for a designer to try best to write, search for an object, and design a page, thereby greatly improving the generation efficiency and speed of the display object.

Description

Display object generation method and system, electronic device and storage medium

[0001] The present disclosure claims priority to Chinese Patent Application No. 202410773739.X, filed on June 14, 2024, with the Chinese Patent Office, entitled "Display object generation method and system, electronic device and storage medium", the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates to the technical field of computer, and in particular, to a display object generation method, system, electronic device and storage medium. BACKGROUND

[0003] In the operation process, the display object of the object such as commodity, project and activity is used to display information in the form of text and / or image to achieve the purpose of information reaching. The traditional display object generation process needs multiple roles to participate in multiple generation links. For example, first, the operation personnel need to design the copy, then the designer needs to design the design script based on the design copy for different information carriers, and then the R&D personnel need to output the display object corresponding to different information carriers based on the design script. This traditional display object generation method is low in efficiency and high in cost, and cannot meet the large display object generation demand. In the prior art, there is also a scheme of generating display objects by using fine-tuning generation model and the generation model obtained by fine-tuning, but it needs to sort out the model training corpus. The sorting out of the model training corpus is time-consuming, cannot adapt to the rapid update of the model, cannot meet the dynamic display object demand, and is high in cost.

[0004] It can be seen that the display object generation method in the prior art still needs to be improved. SUMMARY

[0005] The display object generation method provided by the embodiments of the present disclosure can quickly generate display objects and is low in cost and high in efficiency.

[0006] Correspondingly, the embodiments of the present disclosure also provide a display object generation system, an electronic device, a storage medium and a computer program product to ensure the implementation and application of the above display object generation method.

[0007] In order to solve the above problems, the display object generation method disclosed by the embodiments of the present disclosure is applied to a client, and the method comprises:

[0008] Obtaining object generation requirement information input by a user through an object creation interface;

[0009] The object generation requirement information is sent to a server, and the object generation requirement information is used to trigger the server to generate page data matched with the object generation requirement information.

[0010] Based on the page data, page content of a to-be-generated display object is displayed.

[0011] In response to a display object generation operation triggered for the page content, a display object is generated.

[0012] The present disclosure also discloses a display object generation method, applied to a server, and the method comprises:

[0013] Object generation requirement information input by a user is obtained.

[0014] Based on a preset knowledge base, knowledge text and / or knowledge pictures matched with the object generation requirement information are obtained.

[0015] Based on the object generation requirement information and the knowledge text, a first preset text generation model is called to obtain structured object description information generated by the first preset text generation model.

[0016] Based on the structured object description information and / or the knowledge pictures, a preset component is combined to generate page data matched with the object generation requirement information, and the page data is used to generate a display object.

[0017] The present disclosure also discloses a display object generation method, and the method comprises:

[0018] Object generation requirement information input by a user through an object creation interface is obtained.

[0019] Based on a preset knowledge base, knowledge text and / or knowledge pictures matched with the object generation requirement information are obtained.

[0020] Based on the object generation requirement information and the knowledge text, a first preset text generation model is called to obtain structured object description information generated by the first preset text generation model.

[0021] Based on the structured object description information and / or the knowledge pictures, a preset component is combined to generate page data matched with the object generation requirement information.

[0022] Based on the page data, page content of a to-be-generated display object is displayed.

[0023] In response to a display object generation operation triggered for the page content, a display object is generated.

[0024] The display object generation system comprises a client and a server, wherein

[0025] The client is configured to execute the display object generation method for the client.

[0026] The server is configured to execute the display object generation method for the server.

[0027] The display object generation system comprises a client and a server, wherein

[0028] The display object generation system comprises a client and a server, wherein

[0029] Compared with the prior art, the display object generation system has the following advantages:

[0030] By obtaining the object generation requirement information input by the user through the object creation interface, the object generation requirement information is sent to the server to trigger the server to generate page data matched with the object generation requirement information, and then the client displays the page content of the display object to be generated based on the page data, and generates the display object in response to the display object generation operation triggered for the page content. In the whole process of display object generation, the user only needs to describe the display object to be generated through a short language, and the display object generation system can quickly generate the display object matched with the user's requirement, which changes the previous page generation mode from writing scripts, finding objects and designing pages by the designer to only inputting a sentence to intelligently generate the display object, greatly improving the generation efficiency and speed of the display object. BRIEF DESCRIPTION OF DRAWINGS

[0031] FIG. 1 is a step flowchart of the display object generation method according to an embodiment of the present disclosure;

[0032] FIG. 2 is a schematic diagram of an object creation interface in the display object generation method according to an embodiment of the present disclosure;

[0033] FIG. 3 is a schematic diagram of an object creation interface in the display object generation method according to an embodiment of the present disclosure;

[0034] FIG. 4 is a step flowchart of the display object generation method according to an embodiment of the present disclosure;

[0035] FIG. 5 is a schematic diagram of a content item editing interface of a method for generating a display object according to an embodiment of the present disclosure;

[0036] FIG. 6 is a schematic diagram of a content item editing interface of a method for generating a display object according to an embodiment of the present disclosure;

[0037] FIG. 7 is a schematic diagram of a picture editing interface of a method for generating a display object according to an embodiment of the present disclosure;

[0038] FIG. 8 is a flowchart of a method for generating a display object according to an embodiment of the present disclosure;

[0039] FIG. 9 is a flowchart of a method for generating a display object according to an embodiment of the present disclosure;

[0040] FIG. 10 is a workflow diagram of a system for generating a display object according to an embodiment of the present disclosure;

[0041] FIG. 11 is a schematic diagram of an exemplary apparatus according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] In order to make the above objectives, features and advantages of the present disclosure more obvious and understandable, the present disclosure will be further described in detail below with reference to the drawings and specific embodiments.

[0043] The method for generating a display object according to an embodiment of the present disclosure can be applied to scenarios such as website making and promotional picture making. For example, a user needs to generate a picture for introducing the functions of a platform, or a user needs to generate a website page of a shipping company.

[0044] For example, a user inputs a sentence for describing a website page or a promotional picture to be generated through a client, and then triggers a display object generation operation. The client calls a display object generation service of a server according to the sentence input by the user, so as to obtain page data matched with the generation requirement. Then, the client generates a display object according to the page data. Optionally, the display object can be automatically combined based on elements such as a script, a picture and a component. The page data can be described by using a page description language such as JSON. By using the method for generating a display object according to an embodiment of the present disclosure, a webpage or a picture can be quickly generated.

[0045] Referring to FIG. 1, the method for generating a display object according to an embodiment of the present disclosure is applied to a client, and the method comprises steps 102 to 108.

[0046] In step 102, object generation requirement information input by a user through an object creation interface is obtained.

[0047] The object generation requirement information is used to describe a to-be-generated display object, so as to guide the large language model to generate a corresponding display object.

[0048] In some optional embodiments, the object generation requirement information input by the user through the object creation interface is obtained, including: obtaining an object description sentence input by the user through the object creation interface, and taking the object description sentence as the object generation requirement information. As shown in FIG. 2, a text editing box 210 can be set in the object creation interface of the client, and the user inputs a sentence in the text editing box 210 to describe the to-be-generated display object. For example, the user can input “help me generate an introduction page about logistics and sea transportation” in the text editing box. The client obtains the input text “help me generate an introduction page about logistics and sea transportation” in the text editing box and takes it as the object generation requirement information.

[0049] In some optional embodiments, the object generation requirement information input by the user through the object creation interface is obtained, including: obtaining an object description sentence input by the user through the object creation interface; based on a user trigger, obtaining content prompt information and / or picture prompt information of the display object selected by the user, wherein the content prompt information includes one or more of the following: an application domain, a page style, a page theme, a page color tone, and a function block, and the picture prompt information includes one or more of the following: an inserted reference picture and an inserted manuscript picture; and fusing the object description sentence and / or the content prompt information and / or the picture prompt information to obtain the object generation requirement information.

[0050] As shown in FIG. 3, a text editing box can be set in the object creation interface of the client, and the user inputs a sentence in the text editing box 310 to describe the to-be-generated display object. At the same time, an AI assistant wake-up entrance 320 is also set in the object creation interface, and the client calls out an AI assistant page 330 after detecting that the AI assistant wake-up entrance 320 is triggered, so that the user can perform human-computer interaction with the client through the AI assistant page 330 to select content prompt information and / or picture prompt information of the to-be-generated display object. For example, the client can display a configuration option list of the content prompt information and a configuration option list of the picture prompt information on the AI assistant page 330, and the user selects any one option in the configuration option list to enter the content prompt information or the picture prompt information corresponding to the option for configuration.

[0051] In some optional embodiments, the application domain includes but is not limited to: logistics, funds, transactions, tax, etc. The page theme includes but is not limited to: light color system, dark color system; the page style includes but is not limited to: 3D elements, real scene, flat; the page color tone includes but is not limited to: red, orange, yellow, blue, etc. The function block is used to describe the function block to which the display object belongs, and the function block includes but is not limited to: product / function introduction, core selling point, solution, process guide, benefit card, etc. Wherein, the application domain is determined according to the actual application requirement, and the application domain is matched with the pre-trained generative model used to generate the display object. That is, the pre-trained generative model needs to be fine-tuned based on the data of the application domain.

[0052] Specifically, the client can perform the following human-computer interaction with the user through the object creation interface to obtain the object generation requirement information of the user: first, the user can input, for example, "help me generate an introduction page about logistics sea transportation" in the text editing box in the object creation interface; then, the user clicks the AI assistant button set in the object creation interface of the client to trigger the client to display the configuration option list of the content prompt information and the picture prompt information; the user can trigger the client to display the attribute selection interface of the corresponding configuration item by selecting the configuration item in the configuration option list, so as to select the attribute value of the corresponding content prompt information or picture prompt information. For example, after the user clicks the "application domain" configuration item in the configuration option list of the content prompt information, the client displays the application domain selection interface of the "application domain" content prompt information, and the candidate application domains displayed in the application domain selection interface include: logistics, funds, transactions, tax; then, the user selects a candidate application domain (such as "logistics") to complete the configuration of the application domain. For another example, the user clicks the "insert reference picture" configuration item in the configuration option list of the picture prompt information to complete the configuration of the picture prompt information.

[0053] In some optional embodiments, the object creation interface is further provided with a trigger entrance for generating a display object, such as the button 340 in FIG. 3. The user triggers the client to create a display object by clicking the button 340. After detecting that the button 340 is clicked, the client further obtains the object description sentence input in the current object creation interface and the selected content prompt information and picture prompt information, and splices the object description sentence and the currently selected content prompt information and picture prompt information to generate object generation requirement information.

[0054] The object generation requirement information can be: "help me generate an introduction page about logistics sea transportation, the application domain is: logistics, the page theme is: light color system, the page style is: real scene, the function block is: product introduction, and the reference picture is inserted".

[0055] In some optional embodiments, the category of the content prompt information and the or picture prompt information can be set as a fixed value in advance, or can be generated by using a pre-trained generative large model according to the text input by the user in the text editing box 310. The category of the content prompt information and the picture prompt information in the embodiments of the present disclosure is not limited, and the specific configuration attribute of each of the content prompt information and the picture prompt information is not limited.

[0056] In step 104, the object generation requirement information is sent to the server, and the object generation requirement information is used to trigger the server to generate page data matched with the object generation requirement information.

[0057] After the client detects that the user triggers the generation of the display object operation, the object generation requirement information is further sent to the server, and the server is triggered to generate page data of the display object to be generated based on the object generation requirement information.

[0058] Optionally, the sending of the object generation requirement information to the server includes: in response to the user triggering the generation of the display object operation through the object creation interface, generating a display object generation request carrying the object generation requirement information; and sending the display object generation request to the server. For example, the user triggers the client to create a display object by clicking the button 340 shown in FIG. 3. After the client detects that the button 340 is clicked, the object description statement input in the current object creation interface and the selected content prompt information and picture prompt information are further obtained, and the object description statement and the content prompt information and the picture prompt information currently selected by the user are spliced to generate object generation requirement information. Then, the client encapsulates the object generation requirement information according to a preset protocol, generates a display object generation request, and sends the display object generation request to the server.

[0059] In some optional embodiments, the server generating the page data matched with the object generation requirement information includes: the server obtaining the object generation requirement information input by the user, and obtaining knowledge text and / or knowledge pictures matched with the object generation requirement information based on a preset knowledge base; the server calling a first preset text generation model based on the object generation requirement information and the knowledge text, to obtain structured object description information generated by the first preset text generation model; and the server combining a preset component based on the structured object description information and / or the knowledge pictures, to generate the page data matched with the object generation requirement information.

[0060] For example, the server can parse the object generation request sent by the client according to a preset protocol to obtain the object generation requirement information input by the user, and then, based on the object generation requirement information and a preset knowledge base, the server uses similarity matching combined with artificial intelligence text generation and / or picture generation technology to obtain knowledge text and knowledge pictures matched with the object generation requirement information. The specific implementation of the server obtaining the knowledge text and / or knowledge pictures matched with the object generation requirement information based on the preset knowledge base is described in the related description of the embodiments below, and will not be repeated here.

[0061] Then, the server further generates prompt words according to the object description information and the obtained knowledge text, and calls a first preset text generation model based on the prompt words to obtain structured object description information generated by the first preset text generation model. The specific implementation of the server calling the first preset text generation model based on the object generation requirement information and the knowledge text to obtain the structured object description information generated by the first preset text generation model is described in the related description of the embodiments below, and will not be repeated here.

[0062] The structured object description information is used to describe the content item floor structure of the display object and the component information of the content items constituting each floor. Optionally, the structured object description information can be JSON structured data.

[0063] Next, the server further generates page data of the display object to be generated, i.e., page data matched with the object generation requirement information, according to the content item floor structure described by the structured object description information, the component information of the content items constituting each floor, and the knowledge pictures obtained in the foregoing step. Optionally, the page data can be a page outline of a low-code platform.

[0064] The specific implementation of the server combining preset components based on the structured object description information and / or the knowledge pictures to generate the page data matched with the object generation requirement information is described in the related description of the embodiments below, and will not be repeated here.

[0065] Step 106, based on the page data, displaying page content of the display object to be generated.

[0066] The client parses the page data and renders the page according to the page data to display the page content of the display object to be generated.

[0067] In some optional embodiments, after generating the page data matching the object generation requirement information, the server can publish the page data as the page data of the to-be-generated display object into a display object database, and send a notification message to the client, the notification message being used to indicate that the page data of the display object has been generated. After receiving the notification message, the client can access the display object database, display the page content of the to-be-generated display object, and perform subsequent processing based on user operations, for example, display the display object, edit the page content of the display object, and the like.

[0068] In some optional embodiments, after generating the page data matching the object generation requirement information, the server can push the page data to the client. After receiving the page data, the client can render the page content of the to-be-generated display object based on the page data, so that the user can perform subsequent operations on the page content of the to-be-generated display object, for example, edit the page content of the display object, and the like.

[0069] Optionally, the page data can be a page file used by the low-code development platform. For example, the page file can be a page summary file of the low-code platform, so that the display object is independent of the platform. For example, the page data of the display object can be a page file described in HTML language.

[0070] The specific implementation of the client rendering the page based on the page data to obtain the preview page of the display object can refer to the prior art, and will not be described here in the embodiments of the present disclosure.

[0071] Step 108, generating a display object in response to a display object generation operation triggered for the page content.

[0072] In some optional embodiments, the user can directly perform a display object generation operation such as generating a picture or publishing a webpage for the currently displayed page content of the client, and the client will generate a picture or a webpage or other forms of display object according to the currently displayed page content based on the display object generation operation performed by the user.

[0073] Optionally, the generating a display object in response to a display object generation operation triggered for the page content comprises: in response to a user triggering a picture generation entry, generating a picture form of display object according to the current page content; and / or, in response to a user triggering a website publishing entry, generating a webpage form of display object according to the current page content, and publishing a webpage address of the webpage form of display object

[0074] For example, a picture generation button can be set in the page content display interface of the client, and a size setting button of different format pictures can be set. After a user selects to generate a picture in a certain format and sets the size and other information of the picture, the picture display object is rendered based on the current displayed page content according to the user settings. The format of the generated picture includes but is not limited to computer posters and mobile terminal posters.

[0075] For another example, a website publishing button can be set in the page content display interface of the client. After a user triggers the website publishing button, the client sends a request to publish the current page content as a website page to the server, to trigger the server to publish a corresponding website page based on the current page content. The website page is a web page display object corresponding to the current page content. For details of the specific implementation of publishing a website page based on page content, refer to the prior art, which will not be described here in the embodiments of the present disclosure.

[0076] By generating the display object in the form of a picture or a web page, the application scenarios of the display object are expanded, and the utilization rate of the display object is improved.

[0077] In summary, the display object generation method disclosed in the embodiments of the present disclosure acquires the object generation requirement information input by a user through an object creation interface, then sends the object generation requirement information to the server, triggers the server to generate page data matched with the object generation requirement information, and then displays the page content of the display object to be generated based on the page data by the client, and generates the display object in response to the display object generation operation triggered for the page content. In the whole process of generating the display object, the user only needs to describe the display object to be generated through a short language, and the display object generation system can quickly generate the display object matched with the user requirement, which changes the previous page generation mode from writing a script, finding an object, and designing a page by a designer to only inputting a sentence to intelligently generate a display object, greatly improving the generation efficiency and speed of the display object.

[0078] Further, as shown in FIG. 4, in some optional embodiments, after displaying the page content of the display object to be generated based on the page data, the method further includes steps 107 and 1071.

[0079] Step 107: updating the page content based on an editing operation of the user on the page content.

[0080] The editing operation includes one or more of the following: deleting a content item, adding a content item, and modifying content item information.

[0081] Step 1071: displaying the updated page content.

[0082] In some embodiments of the present disclosure, as shown in FIG. 5, the page content is arranged by one or more content items in a floor structure. The user can perform an editing operation on each floor of the content item, such as any one of the content items 502, 504, or delete the content item. For example, the client sets a content item editing entry and a content item deletion entry for each content item in the page content display page, and the user can delete the content item corresponding to the entry by triggering the corresponding entry, or enter the editing interface of the corresponding content item.

[0083] Optionally, the content item information includes but is not limited to one or more of the following: title, content description, picture address. Correspondingly, when editing any content item, the title or content description of the content item can be selected for editing, or the picture can be reselected to update the picture address. Among them, the title and content description of the content item can be generated by artificial intelligence; the reselected picture can be obtained by picture search or generated by artificial intelligence. For example, the client can set an editing entry for each content item information in the editing interface of the content item, such as the title editing entry 602, the content description editing entry 604, and the picture editing entry 606 shown in FIG. 6. The user enters the corresponding content item information editing interface by triggering the editing entry of the content item information.

[0084] In some optional embodiments, the content item information includes a title, and the page content is updated based on the editing operation of the user on the page content, including one or more of the following methods: in response to the user triggering an intelligent generation script operation for the title, a title script replacement configuration interface is displayed; the title script generation prompt information input by the user in the title script replacement configuration interface is obtained; in response to the user triggering a script replacement operation, the title script generation service is called based on the current script of the title and the title script generation prompt information, and the title script generated by the script generation service is obtained; the current script of the title is replaced by the generated title script to update the page content.

[0085] For example, after the user clicks the title editing button as the title editing entry 602, the client displays a title editing interface, and the user can configure the operation of generating a title content by using artificial intelligence technology by configuring one or more configuration information including but not limited to the following: copywriting polishing, copywriting translation, copywriting word range, etc. Further, after the user triggers a title replacement operation (for example, the user triggers a button indicating a replacement file set in the title editing interface), the client obtains the current copywriting of the title, the configuration information of the user for generating the title copywriting, and generates prompt information according to the current copywriting of the title and the configuration information. Then, based on the generated prompt information, the client calls a copywriting generation service and obtains the title copywriting generated by the copywriting generation service. Then, the client replaces the current copywriting of the title with the title copywriting generated by the copywriting generation service, and refreshes and displays the title of the editing interface of the content item, thereby completing the editing operation of the title.

[0086] In some optional embodiments, the content item information includes a content description, and the operation of updating the page content based on the editing operation of the user on the page content includes: in response to the user triggering an intelligent generation copywriting operation for the content description, displaying a content description copywriting replacement configuration interface; obtaining content description copywriting generation prompt information input by the user in the content description copywriting replacement configuration interface; in response to the user triggering a copywriting replacement operation, calling a copywriting generation service based on the current copywriting of the content description and the content description copywriting generation prompt information, obtaining generated content description copywriting; and replacing the current copywriting of the content description with the generated content description copywriting to update the page content.

[0087] For example, after the user clicks the content description editing button as the content description editing entry 604, the client displays a content description editing interface, and the user can configure the operation of generating a content description by using artificial intelligence technology by configuring one or more configuration information including but not limited to the following: copywriting polishing, copywriting translation, copywriting word range, etc. Further, after the user triggers a content description replacement operation (for example, the user triggers a button indicating a replacement file set in the content description editing interface), the client obtains the current copywriting of the content description, the configuration information of the user for generating the content description copywriting, and generates prompt information according to the current copywriting of the content description and the configuration information. Then, based on the generated prompt information, the client calls a copywriting generation service and obtains the content description copywriting generated by the copywriting generation service. Then, the client replaces the current copywriting of the content description with the content description copywriting generated by the copywriting generation service, and refreshes and displays the content description of the editing interface of the content item, thereby completing the editing operation of the content description.

[0088] In some optional embodiments, the content item information includes a picture, and the updating the page content based on the editing operation of the user on the page content includes: in response to the user triggering a picture replacement operation on the picture, displaying a picture editing interface; based on an intelligent picture searching operation performed by the user on the picture editing interface, obtaining picture searching prompt information input by the user, and calling a preset picture searching service based on the picture searching prompt information to obtain a candidate picture; or, based on an artificial intelligence generated picture operation performed by the user on the picture editing interface, obtaining picture generation prompt information input by the user, and calling a preset picture generation service based on the picture generation prompt information to obtain a candidate picture; and in response to a confirmation selection operation of the user on the candidate picture, replacing the picture with the candidate picture selected by the user to update the page content.

[0089] For example, after the user clicks the picture editing button as the picture editing entrance 606, the client displays a picture editing interface, and the user can configure configuration information including but not limited to one or more of the following through the picture editing interface for the operation of searching for a picture or generating a picture by using artificial intelligence technology: picture searching prompt text, picture acquisition mode, etc. The picture acquisition mode includes but is not limited to: intelligent picture searching, picture generation by using artificial intelligence technology. As shown in FIG. 7, the picture editing interface can set options for different picture acquisition modes, such as an intelligent picture searching mode selection button 702, a picture generation by using artificial intelligence technology mode selection button 704, and a picture searching prompt text input box 706. The user can select a picture acquisition mode through the above-mentioned buttons 702 and 704, input a description of a picture to be searched or a picture to be generated in the picture searching prompt text input box 706, and then trigger the intelligent picture acquisition operation. The client detects the picture acquisition operation triggered by the user, calls a preset picture searching service or a preset picture generation service according to the picture acquisition mode selected by the user and the description of the picture to be searched or the picture to be generated input by the user, obtains a picture as a candidate picture, and displays the obtained candidate picture on the picture editing interface. The user can browse the candidate picture through the picture editing interface and select a candidate picture to replace the currently edited picture. Then, the client replaces the picture of the content item currently edited in the preview interface of the exhibition object with the candidate picture selected by the user, and completes the editing operation of the picture.

[0090] In some optional embodiments, the content item information includes a picture, and the updating the page content based on the editing operation of the user on the page content includes: in response to the user triggering a picture replacement operation on the picture, displaying a picture editing interface; based on an intelligent picture searching operation performed by the user on the picture editing interface, obtaining picture searching prompt information input by the user, and calling a preset picture searching service based on the picture searching prompt information to obtain a candidate picture; or, based on an artificial intelligence generated picture operation performed by the user on the picture editing interface, obtaining picture generation prompt information input by the user, and calling a preset picture generation service based on the picture generation prompt information to obtain a candidate picture; and in response to a confirmation selection operation of the user on the candidate picture, replacing the picture with the candidate picture selected by the user to update the page content.

[0091] After the editing of a certain content item is completed, or after a certain content item is deleted, the client will update the page data of the current page according to the editing result or the deletion result, and re-render the page content based on the updated page data.

[0092] To sum up, the display object generation method disclosed in the embodiments of the present disclosure generates page content of a display object arranged by using a floor structure, converts the page content into a page summary required by a low-code platform, realizes secondary editing of the display object, and helps to further improve the quality of the display object generated based on the page content and meet the personalized needs of users. By combining artificial intelligence copy generation and image generation technologies, and intelligent search image technology, the generated display object has more rich content on the premise of matching user needs.

[0093] Based on the above embodiments, the embodiments of the present disclosure also disclose a display object generation method applied to a server. As shown in FIG. 8, the display object generation method comprises steps 802 to 808.

[0094] Step 802, obtaining object generation requirement information input by a user.

[0095] The specific implementation of the server obtaining the object generation requirement information input by the user is described above, and will not be repeated here.

[0096] Step 804, obtaining knowledge text and / or knowledge image matched with the object generation requirement information based on a preset knowledge base.

[0097] The preset knowledge base can include a text knowledge base and a picture knowledge base. The text knowledge base is used to store pre-configured domain knowledge scripts for each application domain, and the picture knowledge base is used to store pre-configured domain knowledge pictures for each application domain. The scripts in the preset knowledge base can be scripts manually written by professionals or scripts generated by using artificial intelligence technology. Similarly, the pictures in the preset knowledge base can be pictures drawn by designers or pictures generated by using artificial intelligence technology. The embodiments of the present disclosure do not limit the generation method of the scripts and pictures in the preset knowledge base.

[0098] In some optional embodiments, the display object generation system comprises a preset component library. The preset component library is used to store components constituting a display object, and each component corresponds to an application domain. For example, the preset component library can include components of a freight application domain, components of a financial application domain, components of an insurance application domain, etc.

[0099] Further, the components corresponding to each application domain can include multiple. Each component can include different numbers of content areas, and each content area further has the same or different content attributes. Taking components corresponding to the freight application domain in the preset component library as an example, the components include component 1, component 2, and component 3. Component 1 can be a component including two content areas, and the content areas include illustrations. Component 2 can be a component including three content areas, and the content areas include iconic icons. Component 3 can be a component including only one content area, and the content area includes illustrations and icons. Each floor corresponds to a content item, and a single content item can include one or more content areas.

[0100] The components stored in the preset component library are configured for each application domain. In actual implementation, the application domain applicable to each component can be specified, so as to facilitate the query of the components of the specified application domain.

[0101] The generation manner of the preset component library and the type of the components in the preset component library are not limited in the embodiments of the present disclosure.

[0102] Optionally, the knowledge in the text knowledge base is indexed and stored based on the application domain, so as to facilitate the subsequent search of the knowledge text of the specified application domain, for example, stored as a key-value pair of the application domain and the knowledge text. Similarly, the knowledge in the picture knowledge base is indexed and stored based on the application domain, so as to facilitate the subsequent search of the knowledge picture of the specified application domain, for example, stored as a key-value pair of the application domain and the picture.

[0103] In some optional embodiments, the object generation requirement information includes a requirement description text, and the obtaining of the knowledge text and / or the knowledge picture matched with the object generation requirement information based on the preset knowledge base includes: converting the requirement description text into a first vector; calculating a first similarity between the requirement description text and each knowledge text based on the first vector and a second vector of each knowledge text in the preset text knowledge base, and obtaining the knowledge text matched with the object generation requirement information according to the first similarity; and / or calculating a second similarity between the requirement description text and each picture text based on the first vector and a third vector of each knowledge picture in the preset text picture knowledge base, and obtaining the knowledge picture matched with the object generation requirement information according to the second similarity.

[0104] In some embodiments of the present disclosure, in order to improve the retrieval efficiency of the knowledge base, a RAG (Retrieval Augmented Generation) retrieval augmented generation technology is used for knowledge base retrieval. First, the knowledge text and the knowledge picture are respectively represented by vectors, and an index is established for each knowledge corresponding to the vector, thereby obtaining the second vector of each knowledge text in the preset text knowledge base, and the third vector of each knowledge picture in the preset picture knowledge base. For example, the text is segmented into blocks, and these blocks are embedded into a vector and transformer encoder (transformer structure encoder) model to create a vector representation of each knowledge text. For another example, the picture is divided into regions, and these regions are embedded into a vector and transformer encoder model to create a vector representation of each knowledge picture.

[0105] When the preset knowledge base needs to be retrieved, for example, when the knowledge text matched with the demand description text input by the query user is queried, first, the vectorization of the demand description text is completed by using the encoder model to obtain the first vector, and then the index search of this query vector is performed to find the most relevant top-k result. In the process of index retrieval, the first similarity of the first vector with the second vector of each knowledge text in the preset text knowledge base is calculated, and then the k1 knowledge texts with the best first similarity are selected as the knowledge texts matched with the object generation demand information. On the other hand, in the process of index retrieval, the second similarity of the first vector with the third vector of each knowledge picture in the preset picture knowledge base is calculated, and then the k2 pictures with the highest second similarity are selected as the knowledge pictures matched with the object generation demand information. Wherein, k1 is an integer greater than or equal to 1, and k2 is an integer greater than or equal to 0.

[0106] In some embodiments of the present disclosure, the knowledge text matched with the object generation demand information is obtained according to the first similarity, including: in response to the existence of a third similarity, selecting at least one knowledge text corresponding to the third similarity as the knowledge text matched with the object generation demand information, wherein the third similarity is greater than or equal to the first preset threshold of the first similarity; in response to the existence of a fourth similarity, generating the knowledge text matched with the object generation demand information based on the knowledge text corresponding to the fourth similarity by using a second preset text generation model, wherein the fourth similarity is greater than the second preset threshold and less than the first preset threshold of the first similarity. Wherein, the second preset threshold is less than the first preset threshold.

[0107] To further improve the matching degree of the acquired knowledge and the query knowledge input by the user, thereby improving the matching degree of the generated display object and the user demand, some embodiments of the present disclosure set similarity thresholds, i.e., a first preset threshold, a second preset threshold, and a third preset threshold. When acquiring the knowledge text matching the object generation demand information, a knowledge text with a first similarity to the object generation demand information greater than or equal to the first preset threshold is preferably selected as the knowledge text matching the object generation demand information. If the first similarity of the knowledge text in the preset text knowledge base to the object generation demand information is less than the first preset threshold, an artificial intelligence is further used to generate the knowledge text. For example, one or more knowledge texts with a first similarity to the object generation demand information less than the first preset threshold and greater than a second preset threshold are selected as part of the prompt information, and a second preset text generation model is called to generate the knowledge text matching the object generation demand information.

[0108] The first preset threshold and the second preset threshold can be set according to specific application requirements. For example, the first preset threshold can be set to 93%, and the second preset threshold can be set to 80%.

[0109] In some embodiments of the present disclosure, the acquiring of the knowledge picture matching the object generation demand information according to the second similarity includes: in response to the existence of a fifth similarity, selecting at least one knowledge picture corresponding to the fifth similarity as the knowledge matching the object generation demand information, wherein the fifth similarity is the second similarity greater than or equal to a third preset threshold; and in response to the non-existence of the fifth similarity, generating a knowledge picture matching the object generation demand information based on the object generation demand information using a preset text-to-image model.

[0110] When acquiring the knowledge picture matching the object generation demand information, a knowledge picture with a second similarity to the object generation demand information greater than or equal to a third preset threshold is preferably selected as the knowledge picture matching the object generation demand information. If the second similarity of the knowledge picture in the preset picture knowledge base to the object generation demand information is less than the third preset threshold, an artificial intelligence is further used to generate the knowledge picture. For example, the object generation demand information is taken as part of the prompt information, and a preset text-to-image model is called to generate the knowledge picture matching the object generation demand information.

[0111] The third preset threshold and the second preset threshold can be set according to specific application requirements. For example, the third preset threshold can be set to 80%.

[0112] At step 806, the first preset text generation model is called based on the object generation requirement information and the knowledge text to obtain structured object description information generated by the first preset text generation model.

[0113] Next, first, based on the object generation requirement information and the matched knowledge text, the structured object description information of the display object is generated by using artificial intelligence technology.

[0114] In some optional embodiments, the first preset text generation model is called based on the object generation requirement information and the knowledge text to obtain structured object description information generated by the first preset text generation model, including: generating a prompt word according to a preset template based on the object generation requirement information and the text knowledge, wherein the prompt word includes a protocol of the structured object description information to be generated; calling the first preset text generation model based on the prompt word to obtain the structured object description information generated by the first preset text generation model. Wherein, the first preset text generation model can be a pre-trained generative large language model.

[0115] Taking the object generation requirement information as "T1", the matched text knowledge as "T2", and the protocol of the structured object description information to be generated as "T3" as an example, the generation of the prompt word according to the preset template can be represented as: "You will answer the question according to the following knowledge "T2", my question is "T1", and return in the format of "T3". Wherein, the protocol of the structured object description information can adopt a floor structure description, and each floor description shows the structure of one content item of the display object. Based on the generated prompt word, the first preset text generation model will output the generated content in the format of "T3", and the generated content is taken as the structured object description information in the embodiment of the disclosure.

[0116] Specifically, the protocol can be used to describe the floor structure between the content items included in the structured object description information, the content items included in each floor structure, and the content area further included in each content item, the title text corresponding to each content area, the content description, and other attribute values. Optionally, the protocol of the structured object description information can be represented in JSON structure.

[0117] In the embodiments of the present disclosure, by pre-entering the content script related to the display object into the preset knowledge base, the preset knowledge base is used to query the preset knowledge base to obtain knowledge text, and when the display object of the page or the picture is generated, the knowledge text obtained by querying is fed into the large model together with the object generation requirement information input by the user, so that the script with higher user demand fitting degree and more in line with user needs can be returned. The efficiency is higher, and the model can be replaced at any time, which is not only convenient to update, but also has high model compatibility.

[0118] In step 808, a page data matching the object generation requirement information is generated based on the structured object description information and / or the knowledge picture combination preset component, and the page data is used to generate the display object.

[0119] Next, the low-code development platform (such as the display object generation system) parses the structured object description information, and assembles and renders the display object according to the structured object description information.

[0120] In some optional embodiments, the structured object description information is used to describe the content item floor structure of the display object, and the page data matching the object generation requirement information is generated based on the structured object description information and / or the knowledge picture combination preset component, and the page data is used to generate the display object, including: obtaining a target application domain matched with the object generation requirement information; parsing the structured object description information to obtain the number of pictures included in the display object and the content item floor structure matched with the display object; obtaining a target component matched with the target application domain and the obtained content item floor structure from the preset component; in response to the number of pictures being greater than the number of knowledge pictures, calling a preset text-to-image model based on the object generation requirement text to obtain a supplementary picture generated by the preset text-to-image model; instantiating the target component based on the supplementary picture, the knowledge picture and the script content to generate the page data matching the object generation requirement information; and in response to the number of pictures being less than or equal to the number of knowledge pictures, instantiating the target component based on the knowledge picture and the script content to generate the page data matching the object generation requirement information.

[0121] The target application domain can be an application domain selected by the user through a client interface, or an application domain matched with the knowledge text obtained by querying the knowledge text based on the object generation requirement information input by the user.

[0122] According to the preset protocol, the structured object description information is parsed to obtain a floor structure including content items in the generated display object, which includes but is not limited to one or more of the following structural information: the number of included content items, the floor where the content items are located, the position and number of content areas included in the content items, the text in the content areas, the number of pictures included in each content item, etc. Wherein, the content area is the page area where the title, content description and other texts in the display object are located, and the picture can be an illustration or an icon.

[0123] Next, component matching is performed according to the application domain and the content item floor structure. For example, component matching is performed in the preset components suitable for the target application domain, and components matching each floor of content items are obtained according to the structural information such as the number of content areas included in each floor, the number and type of pictures included.

[0124] Then, for content items that do not contain pictures, the obtained components can be instantiated and assembled based on the structured object description information obtained in the foregoing steps to obtain a display object. For example, by parsing the structured object description information, the title text and content description text of each content area of each content item (corresponding to each floor) are obtained, the text content variable in the corresponding component is formatted based on the obtained text to instantiate the component, and finally, the components corresponding to each content item are assembled according to the floor structure to obtain page data matching the object generation requirement information.

[0125] On the other hand, for content items containing pictures, the obtained components can be instantiated and assembled based on the structured object description information obtained in the foregoing steps, knowledge pictures, to obtain a display object. For example, by parsing the structured object description information, the title text and content description text of each content area of each content item (corresponding to each floor) are obtained, the text content variable in the corresponding component is formatted based on the obtained text, and the illustration variable or illustration variable in the component is formatted based on the obtained knowledge pictures to instantiate the component, and finally, the components corresponding to each content item are assembled according to the floor structure to obtain page data matching the object generation requirement information.

[0126] In some optional embodiments, if it is determined that the number of pictures included in the generated display object exceeds the number of knowledge pictures obtained in the foregoing steps after parsing the structured object description information, it is necessary to further generate supplementary pictures using artificial intelligence technology, and the illustration variable or illustration variable in the component is formatted based on the supplementary pictures and the knowledge pictures to instantiate the component. For specific implementation of calling a preset text-to-image model to generate supplementary pictures based on the object generation requirement text, refer to the prior art, which will not be described here in detail.

[0127] The page data is a page summary of the low-code platform. The low-code platform can perform page rendering based on the page data to display a page corresponding to the to-be-generated display object.

[0128] After the server generates the page data, the page data is pushed to the client, so that the client can display page content of the to-be-generated display object based on the page data and generate the display object in response to a display object generation operation triggered for the page content.

[0129] The client can display page content of the to-be-generated display object based on the page data and generate the display object in response to a display object generation operation triggered for the page content. For details, refer to the related description in the foregoing embodiments, which will not be described here again.

[0130] In summary, the display object generation method disclosed in the embodiments of the present disclosure includes the following steps: obtaining object generation requirement information input by a user, obtaining knowledge text and / or knowledge pictures matched with the object generation requirement information based on a preset knowledge base, calling a first preset text generation model based on the object generation requirement information and the knowledge text to obtain structured object description information generated by the first preset text generation model, combining a preset component based on the structured object description information and / or the knowledge pictures to generate page data matched with the object generation requirement information, and enabling a client to generate a display object based on the page data. In the whole process of display object generation, the user only needs to briefly describe the display object to be generated in language, and the display object generation system can quickly generate a display object matched with the user's requirement, which changes the previous page generation mode of writing a script, finding an object, and designing a page by a designer. Only one sentence needs to be input to intelligently generate a display object, which greatly improves the generation efficiency and speed of the display object.

[0131] Based on the foregoing embodiments, the embodiments of the present disclosure further disclose a display object generation method. As shown in FIG. 9, the method includes steps 902 to 912.

[0132] Step 902: Obtain object generation requirement information input by a user through an object creation interface.

[0133] Step 904: Obtain knowledge text and / or knowledge pictures matched with the object generation requirement information based on a preset knowledge base.

[0134] Step 906: Call a first preset text generation model based on the object generation requirement information and the knowledge text to obtain structured object description information generated by the first preset text generation model.

[0135] Step 908, combining a preset component based on the structured object description information and / or the knowledge picture, generating page data matched with the object generation requirement information;

[0136] Step 910, based on the page data, displaying page content of the to-be-generated display object;

[0137] Step 912, in response to a display object generation operation triggered for the page content, generating a display object.

[0138] The specific implementation of each step can be referred to the related description in the foregoing embodiments, which will not be repeated here.

[0139] To sum up, the display object generation method disclosed by the embodiments of the present disclosure, by obtaining object generation requirement information input by a user through an object creation interface, then, based on a preset knowledge base, obtaining knowledge text and / or knowledge picture matched with the object generation requirement information, then, based on the object generation requirement information and the knowledge text, calling a first preset text generation model to obtain structured object description information generated by the first preset text generation model, finally, combining a preset component based on the structured object description information and / or the knowledge picture, generating page data matched with the object generation requirement information, based on the page data, displaying page content of the to-be-generated display object, in response to a display object generation operation triggered for the page content, generating a display object, in the whole process of display object generation, the user only needs to describe the display object to be generated through a short language, and no longer needs a designer to write a script, find an object, and design a page generation method, only needs to input a sentence to intelligently generate a display object, greatly improving the generation efficiency and speed of the display object.

[0140] Based on the foregoing embodiments, the embodiments of the present disclosure further disclose a display object generation system for implementing the foregoing display object generation method. The display object generation system comprises a client and a server. The implementation of the display object generation system will be described below in combination with the interaction process of FIG. 10.

[0141] Step 1002, the client obtains object generation requirement information input by a user through an object creation interface.

[0142] Step 1004, the client sends the object generation requirement information to the server.

[0143] Step 1006, the server obtains the object generation requirement information input by the user.

[0144] Step 1008, the server, based on a preset knowledge base, obtains knowledge text and / or knowledge picture matched with the object generation requirement information.

[0145] In step 1010, the server generates requirement information based on the object and calls a first preset text generation model based on the knowledge text to obtain structured object description information generated by the first preset text generation model.

[0146] In step 1012, the server generates page data matched with the object generation requirement information based on the structured object description information and / or the knowledge picture by combining preset components.

[0147] In step 1014, the client obtains the page data.

[0148] In step 1016, the client displays page content of the to-be-generated display object based on the page data.

[0149] In step 1018, the client generates a display object in response to a display object generation operation triggered for the page content.

[0150] The specific implementation of the client and the server in the above steps can refer to the related description in the foregoing embodiments, which will not be described here.

[0151] In summary, the display object generation system disclosed in the embodiments of the present disclosure can quickly generate a display object matched with the user's requirement after the user inputs object generation requirement information through the client, and the user only needs to describe the to-be-generated display object in a short language, and the display object generation system can generate the display object matched with the user's requirement, which changes the previous page generation mode of writing a script, finding an object, and designing a page by a designer, and only needs to input a sentence to intelligently generate a display object, which greatly improves the generation efficiency and speed of the display object.

[0152] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present disclosure are not limited to the order of the described actions, because according to the embodiments of the present disclosure, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present disclosure.

[0153] On the basis of the above-mentioned embodiments, the present embodiment further provides a display object generation device, applied to a client, the device comprising:

[0154] An object generation requirement information acquisition module is configured to acquire object generation requirement information input by a user through an object creation interface.

[0155] An object generation requirement information sending module is configured to send the object generation requirement information to a server, the object generation requirement information being used to trigger the server to generate page data matched with the object generation requirement information.

[0156] A page content generation module is configured to display page content of a display object to be generated based on the page data.

[0157] A display object generation module is configured to generate a display object in response to a display object generation operation triggered for the page content.

[0158] Optionally, the object generation requirement information input by the user through the object creation interface comprises:

[0159] An object description sentence input by the user through the object creation interface is acquired, and the object description sentence is taken as the object generation requirement information.

[0160] Optionally, the object generation requirement information input by the user through the object creation interface comprises:

[0161] An object description sentence input by the user through the object creation interface is acquired.

[0162] Content prompt information and / or picture prompt information of the display object selected by the user are acquired based on a user trigger, wherein the content prompt information comprises one or more of the following: an application domain, a page style, a page theme, a page color tone, and a function block, and the picture prompt information comprises one or more of the following: an inserted reference picture and an inserted manuscript picture.

[0163] The object description sentence and / or the content prompt information and / or the picture prompt information are fused to obtain the object generation requirement information.

[0164] Optionally, after the page content of the display object to be generated is displayed based on the page data, the method further comprises:

[0165] In response to an editing operation of the page content by the user, the page content is updated based on the editing operation, wherein the editing operation comprises one or more of the following: deleting a content item, adding a content item, and modifying content item information.

[0166] The updated page content is displayed.

[0167] Optionally, the content item information includes a title, and the updating the page content based on the editing operation of the user on the page content comprises one or more of the following methods:

[0168] In response to the user triggering an intelligent generation of text operation for the title, a title text replacement configuration interface is displayed.

[0169] The title text generation prompt information input by the user in the title text replacement configuration interface is obtained.

[0170] In response to the user triggering a text replacement operation, a title text generated by a text generation service based on the current text of the title and the title text generation prompt information is obtained.

[0171] The current text of the title is replaced by the generated title text to update the page content.

[0172] Optionally, the content item information includes a content description, and the updating the page content based on the editing operation of the user on the page content comprises:

[0173] In response to the user triggering an intelligent generation of text operation for the content description, a content description text replacement configuration interface is displayed.

[0174] The content description text generation prompt information input by the user in the content description text replacement configuration interface is obtained.

[0175] In response to the user triggering a text replacement operation, a content description text generated by a text generation service based on the current text of the content description and the content description text generation prompt information is obtained.

[0176] The current text of the content description is replaced by the generated content description text to update the page content.

[0177] Optionally, the content item information includes a picture, and the updating the page content based on the editing operation of the user on the page content comprises:

[0178] In response to the user triggering a picture replacement operation for the picture, a picture editing interface is displayed.

[0179] Based on the intelligent search picture operation performed by the user on the picture editing interface, the search picture prompt information input by the user is acquired, and a preset search picture service is called based on the search picture prompt information to acquire candidate pictures; or, based on the artificial intelligence generated picture operation performed by the user on the picture editing interface, the picture generation prompt information input by the user is acquired, and a preset picture generation service is called based on the picture generation prompt information to acquire candidate pictures.

[0180] In response to the confirmation selection operation of the user on the candidate picture, the picture is replaced by the candidate picture selected by the user to update the display object.

[0181] Optionally, in response to the display object generation operation triggered for the page content, a display object is generated, including:

[0182] In response to the user triggering a picture generation entry, a picture form display object is generated according to the current page content; and / or,

[0183] In response to the user triggering a website publishing entry, a web page form display object is generated according to the current page content, and a web page address of the web page form display object is published.

[0184] In response to the user triggering a picture generation entry set in the client interface, a picture of the display object is generated.

[0185] In response to the user triggering a website publishing entry set in the client interface, a web page corresponding to the display object is generated, and an address of the web page is published.

[0186] The display object generation apparatus disclosed in the embodiments of the present disclosure is used to implement the display object generation method described above, and the specific implementation of each module of the apparatus is described in the specific implementation of the corresponding steps in the foregoing method embodiments, which will not be described here.

[0187] In summary, the display object generation apparatus disclosed in the embodiments of the present disclosure acquires the object generation requirement information input by the user through the object creation interface, then sends the object generation requirement information to the server to trigger the server to generate page data matched with the object generation requirement information, and then displays the page content of the display object to be generated based on the page data by the client, and generates a display object in response to the display object generation operation triggered for the page content. In the whole process of display object generation, the user only needs to input a short language description of the display object to be generated, and the display object generation system can quickly generate a display object matched with the user's requirement, changing the previous page generation mode from designing personnel writing copy, finding objects, and designing pages to only inputting a sentence to intelligently generate a display object, greatly improving the generation efficiency and speed of the display object.

[0188] Based on the above-mentioned embodiments, the present embodiment further provides a display object generation device, applied to a server side, comprising:

[0189] An object generation requirement information acquisition module is configured to acquire object generation requirement information input by a user;

[0190] A knowledge matching module is configured to acquire, based on a preset knowledge base, knowledge text and / or knowledge pictures matched with the object generation requirement information;

[0191] An object generation requirement information acquisition module is configured to call a first preset text-to-text model based on the object generation requirement information and the knowledge text, to obtain structured object description information generated by the first preset text-to-text model;

[0192] A display object generation module is configured to combine preset components based on the structured object description information and / or the knowledge pictures, to generate page data matched with the object generation requirement information, the page data being used to generate a display object.

[0193] Optionally, the combination of the structured object description information and / or the knowledge pictures with the preset components to generate page data matched with the object generation requirement information comprises:

[0194] Acquiring a target application domain matched with the object generation requirement information;

[0195] Parsing the structured object description information to obtain a number of pictures included in the display object and a content item floor structure matched with the display object;

[0196] Acquiring, from preset components, target components matched with the target application domain and the obtained content item floor structure;

[0197] In response to the number of pictures being greater than the number of knowledge pictures, calling a preset text-to-picture model based on the object generation requirement text to obtain supplementary pictures generated by the preset text-to-picture model; and instantiating the target components based on the supplementary pictures, the knowledge pictures and the script content to generate page data matched with the object generation requirement information;

[0198] In response to the number of pictures being less than or equal to the number of knowledge pictures, instantiating the target components based on the knowledge pictures and the script content to generate page data matched with the object generation requirement information.

[0199] Optionally, the object generation requirement information comprises a requirement description text, and the acquisition of knowledge text and / or knowledge pictures matched with the object generation requirement information based on a preset knowledge base comprises:

[0200] transforming the requirement description text into a first vector;

[0201] based on the first vector and a second vector of each knowledge text in a preset text knowledge base, respectively calculating a first similarity between the requirement description text and each of the knowledge texts, and obtaining a knowledge text matched with the object generation requirement information according to the first similarity; and / or,

[0202] based on the first vector and a third vector of each knowledge picture in a preset text picture knowledge base, respectively calculating a second similarity between the requirement description text and each of the picture texts, and obtaining a knowledge picture matched with the object generation requirement information according to the second similarity.

[0203] Optionally, the obtaining of the knowledge text matched with the object generation requirement information according to the first similarity comprises:

[0204] in response to the existence of a third similarity, selecting at least one of the knowledge texts corresponding to the third similarity as the knowledge text matched with the object generation requirement information, wherein the third similarity is the first similarity greater than or equal to a first preset threshold value;

[0205] in response to the existence of a fourth similarity, generating the knowledge text matched with the object generation requirement information based on the knowledge text corresponding to the fourth similarity using a second preset text generation model, wherein the fourth similarity is the first similarity greater than a second preset threshold value and less than the first preset threshold value.

[0206] Optionally, the obtaining of the knowledge picture matched with the object generation requirement information according to the second similarity comprises:

[0207] in response to the existence of a fifth similarity, selecting at least one of the knowledge pictures corresponding to the fifth similarity as the knowledge picture matched with the object generation requirement information, wherein the fifth similarity is the second similarity greater than or equal to a third preset threshold value;

[0208] in response to the non-existence of the fifth similarity, generating the knowledge picture matched with the object generation requirement information based on the object generation requirement information using a preset text-to-picture model.

[0209] Optionally, the calling of the first preset text generation model based on the object generation requirement information and the knowledge text to obtain the structured object description information generated by the first preset text generation model comprises:

[0210] generating a prompt word according to a preset template based on the object generation requirement information and the text knowledge, wherein the prompt word includes a protocol of the structured object description information to be generated.

[0211] invoke a first preset text-to-text model based on the prompt word, to obtain structured object description information generated by the first preset text-to-text model.

[0212] The display object generation apparatus disclosed in the embodiments of the present disclosure is used to implement the display object generation method described above. The specific implementation of each module of the apparatus is described in the specific implementation of the corresponding steps in the foregoing method embodiments, which will not be described here again.

[0213] In summary, the display object generation apparatus disclosed in the embodiments of the present disclosure, after obtaining the object generation requirement information input by the user, acquires the knowledge text and / or knowledge picture matched with the object generation requirement information based on the preset knowledge base. Then, the first preset text-to-text model is invoked based on the object generation requirement information and the knowledge text, to obtain the structured object description information generated by the first preset text-to-text model. Then, the preset component is combined based on the structured object description information and / or the knowledge picture, to generate the page data matched with the object generation requirement information, so that the client generates the display object based on the page data. In the whole process of display object generation, the user only needs to describe the display object to be generated in a short language, and the display object generation system can quickly generate the display object matched with the user requirement. This changes the previous page generation mode of writing a script, finding an object, and designing a page by a designer. Only one sentence needs to be input to intelligently generate a display object, which greatly improves the generation efficiency and speed of the display object.

[0214] Based on the foregoing embodiments, the present disclosure further discloses a display object generation apparatus, which comprises:

[0215] An object generation requirement information acquisition module acquires the object generation requirement information input by the user through an object creation interface;

[0216] A knowledge acquisition module is configured to acquire the knowledge text and / or knowledge picture matched with the object generation requirement information based on a preset knowledge base;

[0217] A structured object description information generation module is configured to invoke a first preset text-to-text model based on the object generation requirement information and the knowledge text, to obtain the structured object description information generated by the first preset text-to-text model;

[0218] A page data generation module is configured to combine a preset component based on the structured object description information and / or the knowledge picture, to generate the page data matched with the object generation requirement information;

[0219] A page content generation module is configured to display the page content of the display object to be generated based on the page data;

[0220] a display object generation module configured to generate a display object in response to a display object generation operation triggered for the page content.

[0221] The display object generation apparatus disclosed in the embodiments of the present disclosure is configured to implement the display object generation method described above. The specific implementation of each module of the apparatus is described in the specific implementation of the corresponding steps in the foregoing method embodiments, which will not be described here again.

[0222] To sum up, the display object generation apparatus disclosed in the embodiments of the present disclosure acquires object generation requirement information input by a user through an object creation interface. Then, based on a preset knowledge base, knowledge text and / or knowledge pictures matching the object generation requirement information are acquired. Then, based on the object generation requirement information and the knowledge text, a first preset text generation model is called to obtain structured object description information generated by the first preset text generation model. Finally, based on the structured object description information and / or the knowledge pictures, a preset component is combined to generate page data matching the object generation requirement information. Based on the page data, page content of a display object to be generated is displayed. In response to a display object generation operation triggered for the page content, a display object is generated. In the whole process of display object generation, the user only needs to describe the display object to be generated in a short language, and no longer needs to write a script, find an object, and design page generation mode by a designer. Only one sentence needs to be input to intelligently generate a display object, which greatly improves the generation efficiency and speed of the display object.

[0223] The embodiments of the present disclosure further provide a nonvolatile readable storage medium, which stores one or more programs. When the one or more programs are applied to a device, the device can execute instructions of each method step in the embodiments of the present disclosure.

[0224] The embodiments of the present disclosure further provide a computer readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are configured to implement the method described in the embodiments of the present disclosure.

[0225] The embodiments of the present disclosure further provide an electronic device, which includes a processor and a memory connected with the processor in communication. The memory stores computer execution instructions. The processor executes the computer execution instructions stored in the memory to implement the method described in the embodiments of the present disclosure. In the embodiments of the present disclosure, the electronic device includes a server, a terminal device, and the like.

[0226] The embodiments of the present disclosure further disclose a computer program product, comprising computer program / computer executable instructions, wherein the computer program / computer executable instructions, when executed by a processor in an electronic device, implement the method according to the embodiments of the present disclosure.

[0227] Embodiments of the present disclosure can be implemented as an apparatus configured to perform desired functions using any suitable hardware, firmware, software, or any combination thereof. The apparatus can include a server (cluster), a terminal, and the like electronic device. FIG. 11 schematically shows an exemplary apparatus 1100 that can be used to implement various embodiments described in the present disclosure.

[0228] For one embodiment, FIG. 11 shows an exemplary apparatus 1100 having one or more processors 1102, a control module (chipset) 1104 coupled to at least one of the processor(s) 1102, a memory 1106 coupled to the control module 1104, a non-volatile memory (NVM) / storage device 1108 coupled to the control module 1104, one or more input / output devices 1110 coupled to the control module 1104, and a network interface 1112 coupled to the control module 1104.

[0229] The processor(s) 1102 can include one or more single core or multi core processors, which can include any combination of general-purpose processors or dedicated processors (such as graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 1100 can be configured as a server, a terminal, and the like device described in the embodiments of the present disclosure.

[0230] In some embodiments, the apparatus 1100 can include one or more computer readable media (such as the memory 1106 or the NVM / storage device 1108) having instructions 1114 and one or more processors 1102 incorporated with the one or more computer readable media configured to execute the instructions 1114 to implement modules to perform actions described in the present disclosure.

[0231] For one embodiment, the control module 1104 can include any suitable interface controllers to provide any suitable interface to at least one of the processor(s) 1102 and / or any suitable device or component in communication with the control module 1104.

[0232] The control module 1104 can include a memory controller module to provide an interface to the memory 1106. The memory controller module can be a hardware module, a software module, and / or a firmware module.

[0233] Memory 1106 can be used to load and store data and / or instructions 1114, for example, for device 1100. For one embodiment, memory 1106 can include any suitable volatile memory, such as suitable DRAM. In some embodiments, memory 1106 can include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0234] For one embodiment, control module 1104 can include one or more input / output controllers to provide an interface to NVM / storage device 1108 and input / output device(s) 1110.

[0235] For example, NVM / storage device 1108 can be used to store data and / or instructions 1114. NVM / storage device 1108 can include any suitable non-volatile memory (e.g., flash memory) and / or can include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0236] NVM / storage device 1108 can include a storage resource that is part of a device on which device 1100 is installed, or that is accessed by that device and that can not necessarily be part of that device. For example, NVM / storage device 1108 can be accessed by device 1100 over a network via input / output device(s) 1110.

[0237] Input / output device(s) 1110 can provide an interface for device 1100 to communicate with any other suitable device, which can include communication components, audio components, sensor components, etc. Network interface 1112 can provide an interface for device 1100 to communicate over one or more networks, which device 1100 can wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, such as to access a wireless network based on a communication standard, such as Bluetooth, WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.

[0238] For one embodiment, at least one of the processor(s) 1102 can be packaged together with logic for one or more controllers of the control module 1104 (e.g., a memory controller module). For one embodiment, at least one of the processor(s) 1102 can be packaged together with logic for one or more controllers of the control module 1104 to form a system in a package (SiP). For one embodiment, at least one of the processor(s) 1102 can be fabricated together with logic for one or more controllers of the control module 1104 on the same die. For one embodiment, at least one of the processor(s) 1102 can be fabricated together with logic for one or more controllers of the control module 1104 on the same die to form a system on a chip (SoC).

[0239] In various embodiments, the apparatus 1100 can be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, the apparatus 1100 can have more or less components, and / or different architectures. For example, in some embodiments, the apparatus 1100 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including touch screen displays), non- volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0240] In various embodiments, the apparatus 1100 can be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, the apparatus 1100 can have more or less components, and / or different architectures. For example, in some embodiments, the apparatus 1100 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including touch screen displays), non- volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0241] The embodiments of the present disclosure further provide an electronic device, comprising: a processor; and a memory having stored thereon executable code that, when executed by the processor, causes the processor to perform the method according to any one of the embodiments of the present disclosure. The memory in the embodiments of the present disclosure can store various data, such as target files, file and application association data, and the like, and can further include user behavior data and the like, thereby providing a data basis for various processing.

[0242] The embodiments of the present disclosure further provide one or more machine readable medium having stored thereon executable code that, when executed by a processor, is configured to cause the processor to perform the method according to any one of the embodiments of the present disclosure.

[0243] For the apparatus embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts are referred to the part of the method embodiments.

[0244] The various embodiments in the specification are described in progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts among the various embodiments can be mutually referred to.

[0245] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device that implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0246] These computer program instructions can also be stored in a computer readable storage medium that can direct the computer or other programmable data processing terminal devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including instruction devices that implement the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0247] These computer program instructions can also be loaded into a computer or other programmable data processing terminal device, so that a series of operation steps are performed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0248] Although the preferred embodiments of the embodiments of the present disclosure have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present disclosure.

[0249] Finally, it needs to be pointed out that in this article, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or terminal device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of other identical elements in the process, method, article or terminal device including the element.

[0250] The above provides a detailed introduction to the method, system, electronic device and storage medium provided by the present disclosure. The principles and implementation modes of the present disclosure are described by applying specific examples in this article. The above example 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 mode and application range will be changed; in view of the above, the content of the specification should not be understood as a limitation of the present disclosure.

Claims

1. A method for generating a display object, applied to a client, wherein, The method comprises: obtaining object generation requirement information input by a user through an object creation interface; sending the object generation requirement information to a server, the object generation requirement information being used to trigger the server to generate page data matched with the object generation requirement information; displaying page content of a to-be-generated display object based on the page data; generating a display object in response to a display object generation operation triggered for the page content.

2. The method of claim 1, wherein, The obtaining of the object generation requirement information input by the user through the object creation interface comprises: obtaining an object description sentence input by the user through the object creation interface, and taking the object description sentence as the object generation requirement information.

3. The method of claim 1, wherein, The obtaining of the object generation requirement information input by the user through the object creation interface comprises: obtaining an object description sentence input by the user through the object creation interface; based on a user trigger, obtaining content prompt information and / or picture prompt information of the display object selected by the user; fusing the object description sentence and / or the content prompt information and / or the picture prompt information to obtain the object generation requirement information.

4. The method according to any one of claims 1 to 3, wherein, After the displaying of the page content of the to-be-generated display object based on the page data, the method further comprises: updating the page content based on an editing operation of the user for the page content in response to the editing operation of the user for the page content, wherein the editing operation comprises one or more of the following: deleting a content item, adding a content item, and modifying content item information; displaying the updated page content.

5. The method of claim 4, wherein, The content item information comprises a title, and the updating of the page content based on the editing operation of the user for the page content in response to the editing operation of the user for the page content comprises one or more of the following methods: displaying a title text replacement configuration interface in response to a user triggering of an intelligent text generation operation for the title; obtaining title text generation prompt information input by the user in the title text replacement configuration interface; in response to the user triggering of a text replacement operation, calling a text generation service based on a current text of the title and the title text generation prompt information, and obtaining a title text generated by the text generation service; replacing the current text of the title with the generated title text to update the page content.

6. The method of claim 4, wherein, The content item information comprises content description, and the updating of the page content based on the editing operation of the user for the page content in response to the editing operation of the user for the page content comprises: displaying a content description text replacement configuration interface in response to a user triggering of an intelligent text generation operation for the content description; obtaining content description text generation prompt information input by the user in the content description text replacement configuration interface; in response to the user triggering of a text replacement operation, calling a text generation service based on a current text of the content description and the content description text generation prompt information, and obtaining a generated content description text; replacing the current text of the content description with the generated content description text to update the page content.

7. The method of claim 4, wherein, The content item information comprises a picture, and the updating of the page content based on the editing operation of the user for the page content in response to the editing operation of the user for the page content comprises: In response to a user triggering a picture replacement operation for the picture, a picture editing interface is displayed; Based on an intelligent picture searching operation performed by the user in the picture editing interface, search prompt information input by the user is obtained, and a preset picture searching service is called based on the search prompt information to obtain candidate pictures; or, based on an artificial intelligence generated picture operation performed by the user in the picture editing interface, picture generation prompt information input by the user is obtained, and a preset picture generation service is called based on the picture generation prompt information to obtain candidate pictures; In response to a confirmation selection operation of the candidate pictures by the user, the picture is replaced by the candidate picture selected by the user to update the display object.

8. The method according to any one of claims 1 to 7, wherein, The display object generation operation triggered in response to the page content includes: In response to a user triggering a picture generation entry, a display object in the form of a picture is generated according to the current page content; and / or, In response to a user triggering a website publishing entry, a display object in the form of a webpage is generated according to the current page content, and a webpage address of the display object in the form of a webpage is published. 9.A method for generating a display object, applied to a server, wherein, The method comprises: Obtaining object generation requirement information input by a user; Based on a preset knowledge base, knowledge text and / or knowledge pictures matching the object generation requirement information are obtained; Based on the object generation requirement information and the knowledge text, a first preset text generation model is called to obtain structured object description information generated by the first preset text generation model; Based on the structured object description information and / or the knowledge pictures, a preset component is combined to generate page data matching the object generation requirement information, and the page data is used to generate a display object.

10. The method of claim 9, wherein, The combination of the structured object description information and / or the knowledge pictures to generate page data matching the object generation requirement information comprises: Obtaining a target application domain matching the object generation requirement information; Parsing the structured object description information to obtain the number of pictures included in the display object and the content item floor structure matching the display object; From the preset component, a target component matching the target application domain and the obtained content item floor structure is obtained; In response to the number of pictures being greater than the number of knowledge pictures, a preset picture generation model is called based on the object generation requirement text to obtain supplementary pictures generated by the preset picture generation model; based on the supplementary pictures, the knowledge pictures and the script content, the target component is instantiated to generate page data matching the object generation requirement information; In response to the number of pictures being less than or equal to the number of knowledge pictures, the target component is instantiated based on the knowledge pictures and the script content to generate page data matching the object generation requirement information.

11. The method of claim 9 or 10, wherein, The object generation requirement information comprises a requirement description text, and the combination of the structured object description information and / or the knowledge pictures to generate page data matching the object generation requirement information comprises: The requirement description text is converted into a first vector; The first similarity between the requirement description text and each of the knowledge texts is calculated based on the first vector and a second vector of each of the knowledge texts in a preset text knowledge base, and the knowledge text matched with the object generation requirement information is obtained according to the first similarity; and / or, The second similarity between the requirement description text and each of the picture texts is calculated based on the first vector and a third vector of each of the picture texts in a preset text-picture knowledge base, and the knowledge picture matched with the object generation requirement information is obtained according to the second similarity.

12. The method of claim 11, wherein, The knowledge text matched with the object generation requirement information is obtained according to the first similarity, including: In response to the existence of the third similarity, at least one of the knowledge texts corresponding to the third similarity is selected as the knowledge text matched with the object generation requirement information, wherein the third similarity is the first similarity greater than or equal to a first preset threshold. In response to the existence of the fourth similarity, the knowledge text matched with the object generation requirement information is generated based on the knowledge text corresponding to the fourth similarity by using a second preset text generation model, wherein the fourth similarity is the first similarity greater than a second preset threshold and less than the first preset threshold.

13. The method of claim 11 or 12, wherein, The knowledge picture matched with the object generation requirement information is obtained according to the second similarity, including: In response to the existence of the fifth similarity, at least one of the knowledge pictures corresponding to the fifth similarity is selected as the knowledge matched with the object generation requirement information, wherein the fifth similarity is the second similarity greater than or equal to a third preset threshold. In response to the non-existence of the fifth similarity, the knowledge picture matched with the object generation requirement information is generated based on the object generation requirement information by using a preset text-to-picture model.

14. The method according to any one of claims 9 to 13, wherein, The structured object description information generated by the first preset text generation model is obtained by calling the first preset text generation model based on the object generation requirement information and the knowledge text, including: The prompt word is generated according to a preset template based on the object generation requirement information and the text knowledge, wherein the prompt word includes a protocol of the structured object description information to be generated. The structured object description information generated by the first preset text generation model is obtained by calling the first preset text generation model based on the prompt word.

15. A method of generating a presentation object, wherein, The method includes: Obtaining object generation requirement information input by a user through an object creation interface; Obtaining the knowledge text and / or the knowledge picture matched with the object generation requirement information based on a preset knowledge base; Obtaining the structured object description information generated by the first preset text generation model by calling the first preset text generation model based on the object generation requirement information and the knowledge text; Generating the page data matched with the object generation requirement information by combining a preset component based on the structured object description information and / or the knowledge picture; Displaying the page content of the to-be-generated display object based on the page data; Generating the display object in response to a display object generation operation triggered for the page content.

16. A display object generation system, wherein, The system includes a client and a server, wherein The client is configured to perform the method of any one of claims 1-8. The server is configured to perform the method of any one of claims 9-14.

17. An electronic device, comprising: Comprising: a processor, and a memory connected to the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method of any one of claims 1-15.

18. A computer readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method of any one of claims 1-15.

19. A computer program product comprising computer program / computer executable instructions which when executed cause a computer to perform the method of claim 18. The computer program / computer-executable instructions, when executed by a processor in an electronic device, implement the method of any one of claims 1-15.

Images