Page display method and device, intelligent agent, equipment and storage medium

Abstract

The invention provides a page display method and device based on artificial intelligence, an intelligent agent, equipment and a storage medium, and relates to the technical field of computers, in particular to the artificial intelligence fields of large models, deep learning, natural language processing and the like and the technical fields of rendering, software development and the like. According to the specific implementation scheme, target interaction information input through an interaction interface is received; the target interaction information is used for indicating generation of a target page; in response to a received preview instruction for the target page, sequentially displaying a plurality of page objects of the target page in a preview interface based on a plurality of code blocks used for rendering the target page to obtain the target page; wherein the multiple code blocks are obtained by calling the large model to process the target interaction information.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to artificial intelligence fields such as large models, deep learning, natural language processing, and technical fields such as rendering and software development, and specifically to an artificial intelligence-based page display method, apparatus, intelligent body, device, storage medium, and program product. Background Art

[0002] During page development, it's often necessary to develop and design pages of various types and functions. In related technologies, automatic page generation requires waiting for page data to be fully generated before rendering. This approach results in high latency and a poor user experience. Summary of the Invention

[0003] The present disclosure provides an artificial intelligence-based page display method, device, electronic device, storage medium, and program product.

[0004] According to one aspect of the present disclosure, an artificial intelligence-based page display method is provided, comprising: receiving target interaction information input through an interactive interface; the target interaction information is used to indicate generation of a target page; in response to receiving a preview instruction for the target page, based on multiple code blocks for rendering the target page, multiple page objects of the target page are sequentially displayed in the preview interface to obtain the target page; wherein the multiple code blocks are obtained by calling a large model to process the target interaction information.

[0005] According to another aspect of the present disclosure, an artificial intelligence-based page display device is provided, including a receiving module for receiving target interaction information input through an interactive interface; the target interaction information is used to indicate the generation of a target page; and a display module for, in response to receiving a preview instruction for the target page, sequentially displaying multiple page objects of the target page in the preview interface based on multiple code blocks for rendering the target page to obtain the target page; wherein the multiple code blocks are obtained by calling a large model to process the target interaction information.

[0006] According to another aspect of the present disclosure, an artificial intelligence agent is provided, comprising: an input module for receiving input information; a processing module for determining a target task based on the input information received by the input module, determining a large model based on the target task, and obtaining output information by calling the large model to execute the steps of the above method; and an output module for outputting the output information obtained by the processing module.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the above method.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the steps of the above method.

[0009] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0012] Figure 1 The following schematically illustrates an exemplary system architecture to which the artificial intelligence-based page display method and apparatus according to an embodiment of the present disclosure can be applied;

[0013] Figure 2 The following schematically shows a flow chart of a page display method based on artificial intelligence according to an embodiment of the present disclosure;

[0014] Figure 3 Schematically shows the effect of generating a page frame by using a page frame code according to an embodiment of the present disclosure;

[0015] Figure 4 A schematic diagram schematically shows the correspondence between code blocks and page objects according to an embodiment of the present disclosure;

[0016] Figure 5 The following schematically shows the effect of rendering a page object according to an embodiment of the present disclosure;

[0017] Figure 6 Schematically illustrates a schematic diagram of updating a target page object using a parameter update pop-up window according to an embodiment of the present disclosure;

[0018] Figure 7 A schematic diagram illustrating updating a target page object by using an interactive pop-up window according to an embodiment of the present disclosure is shown;

[0019] Figure 8 A block diagram of an artificial intelligence-based page display device according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 9 A block diagram schematically illustrates an artificial intelligence agent according to an embodiment of the present disclosure; and

[0021] Figure 10 A block diagram of an electronic device suitable for implementing an artificial intelligence-based page display method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0022] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] Figure 1 An exemplary system architecture to which an artificial intelligence-based page display method and apparatus can be applied according to an embodiment of the present disclosure is schematically illustrated.

[0024] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments, or scenarios. For example, in another embodiment, the system architecture to which the "artificial intelligence-based page display method and apparatus" provided by the embodiments of the present disclosure may include a terminal device, but the terminal device may implement the artificial intelligence-based page display method and apparatus provided by the embodiments of the present disclosure without interacting with a server.

[0025] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0026] A user may use a first terminal device 101, a second terminal device 102, or a third terminal device 103 to interact with a server 105 via a network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software (for example only).

[0027] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0028] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports content browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0029] It should be noted that the artificial intelligence-based page display method provided in the embodiments of the present disclosure can generally be executed by the first terminal device 101, the second terminal device 102, and the third terminal device 103. Correspondingly, the artificial intelligence-based page display device provided in the embodiments of the present disclosure can also be set in the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0030] Alternatively, the artificial intelligence-based page display method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the artificial intelligence-based page display device provided in the embodiment of the present disclosure may generally be set in the server 105. The artificial intelligence-based page display method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the artificial intelligence-based page display device provided in the embodiment of the present disclosure may also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0031] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0032] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0033] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0034] It should be noted that the sequence numbers of the operations in the following method are only used to indicate the operation for the purpose of description, and should not be regarded as indicating the order in which the operations should be performed. Unless explicitly stated, the method does not need to be performed in the order shown.

[0035] Figure 2 A flowchart of an artificial intelligence-based page display method according to an embodiment of the present disclosure is schematically shown.

[0036] like Figure 2 As shown, the method includes operations S210 to S220.

[0037] In operation S210 , target interaction information input through an interaction interface is received, where the target interaction information is used to instruct generation of a target page.

[0038] In operation S220 , in response to receiving a preview instruction for a target page, multiple page objects of the target page are sequentially displayed in a preview interface based on multiple code blocks for rendering the target page to obtain the target page.

[0039] Multiple code blocks are obtained by calling a large model to process target interaction information.

[0040] Exemplarily, the method may be executed by a terminal device. The large model may be configured in the terminal device, but the present disclosure is not limited thereto. The large model may also be arranged in a cloud server.

[0041] Alternatively, a cloud server, also known as a cloud computing server or cloud host, is a hosting product within the cloud computing service ecosystem. It addresses the management difficulties and limited scalability of traditional physical servers and VPS services ("Virtual Private Servers" or "VPS"). A cloud server can also be a distributed system server or a server integrated with blockchain.

[0042] Exemplarily, the user may input target interaction information in an interactive interface with a page generation function, and the target interaction information may be analyzed and processed by calling a large model configured on a terminal device or a cloud server to generate multiple code blocks.

[0043] The target interaction information may also be sent to the server, and the target interaction information may be analyzed and processed by a large model configured on the server to generate multiple code blocks and send the multiple code blocks to the terminal device.

[0044] The target page can be a single page or multiple pages. Each page can contain one or more page objects. Page objects can be objects of different modalities, such as text, images, animated images, audio, and video.

[0045] For example, if the target interaction information is "Generate a birthday invitation," the target page could be a page about "birthday invitations." Multiple page objects could include the text "Happy Birthday," the invitation time, the invitation location, and birthday-related celebratory images, such as cakes and balloons.

[0046] A code block can render one or more page objects in the target page. Multiple code blocks are used to render multiple page objects in the target page in sequence to obtain the target page.

[0047] The large model can be a large language model with code generation capabilities. The large model can be a general large language model, or it can be obtained by fine-tuning a general large language model. However, it is not limited to this. It can also be a multimodal large model. In the case where the page objects include non-text page objects such as images, videos, and voice, the code blocks corresponding to the non-text page objects can be generated by the multimodal large model. The input information of the large model can include target interaction information, and the output result of the large model includes the code blocks used to render the page objects.

[0048] Alternatively, the large model can be a multimodal model comprising multiple model branches. Multiple model branches can be used to process target interaction information separately, resulting in multiple code blocks responsible for rendering page objects in different modalities. Alternatively, multiple model branches can be used to process portions of the target interaction information separately, resulting in multiple code blocks responsible for rendering page objects in different modalities. Multiple model branches can process target interaction information in parallel to improve processing efficiency.

[0049] For example, the multiple model branches may include a text model branch, an image model branch, a map model branch, and the like. The text model branch may generate a code block for rendering a text-type page object. The image model branch may generate a code block for rendering an image-type page object. The map model branch may generate a code block for rendering a map-type page object.

[0050] According to the embodiments of the present disclosure, since the target page is generated by calling a large model to process the target interaction information, generating multiple code blocks and using these code blocks to sequentially render multiple page objects, the target page can be rendered according to the granularity of the page objects to achieve the effect of page streaming generation. This allows some page objects of the target page to be displayed in a timely manner, reducing the latency of page display. As a result, users can see the gradual construction process of the target page during the target page generation process, reducing waiting time and enhancing users' confidence and sense of interaction in generating the target page.

[0051] According to the embodiments of the present disclosure, Figure 2 Operation S210, shown as receiving target interaction information input through the interactive interface, may include repeatedly performing the following interaction operations until the target interaction information is obtained: receiving interaction information for the current round input through the interactive interface; and, if a recognition result indicates that the received interaction information does not fully describe the target page, outputting feedback information on the interactive interface for supplementing the information. The recognition result is obtained by performing integrity verification on the received interaction information.

[0052] Identifying the integrity of received interactive information may include: checking each field or non-text element in the interactive information one by one based on preset rules to determine whether the received interactive information meets integrity requirements. The present disclosure is not limited to this, and deep learning models may also be used to automatically identify the integrity of received interactive information.

[0053] Illustratively, when a user first inputs interactive information, the subject of the first interactive information can be identified, and the target description information required to generate the target page can be determined based on the subject of the first interactive information. If it is determined that the first interactive information does not meet the target description information, the received interactive information is determined to be incomplete. Based on the information lacking in the received interactive information compared to the target description information, feedback information is output on the interactive interface to supplement the information. By comparing the received interactive information with the target description information, feedback information is continuously output on the interactive interface until the received interactive information matches the target description information.

[0054] For example, the interaction information of the current round is "generate a birthday invitation", and the subject of the interaction information can be determined to be "birthday invitation". According to the subject of "birthday invitation", it is determined that the target description information also needs to include name, time, place and other information. Therefore, feedback information requesting the user to provide the name, time, place and other supplementary information required for the "birthday invitation" can be output on the interaction interface until the complete target interaction information is obtained.

[0055] According to an embodiment of the present disclosure, target interaction information for generating a target page is acquired through multiple rounds of interaction operations, thereby ensuring the integrity and validity of the information required to generate the target page.

[0056] According to an embodiment of the present disclosure, code blocks can be generated in the following manner: calling a large model to perform the following operations based on the target interaction information: generating page structure information based on the page theme of the target page represented by the target interaction information; the page structure information is used to identify the page layout of multiple page objects; based on the page structure information and the object content information in the target interaction information, determining the object attribute information used to describe the page object, and obtaining multiple object attribute information; and generating code blocks based on the object attribute information to obtain multiple code blocks.

[0057] For example, a page skeleton code may be generated based on the page structure information. The page skeleton code may be stored in a storage space of the terminal device. Based on the page skeleton code, a page skeleton of the target page may be determined. The page skeleton may include one or more initial pages. The initial pages may initially define the page layout of multiple page objects. However, at this time, no page objects are rendered in the initial pages.

[0058] The page structure information can be generated based on the page theme of the target page represented by the target interaction information. For example, taking the page theme of "Birthday Invitation" as an example, the page structure information may include one target page, and the page layouts of the page object containing the text "Happy Birthday" and the page object containing the image of a cake.

[0059] Figure 3 The schematic diagram schematically shows the effect of generating a page frame by using a page frame code according to an embodiment of the present disclosure.

[0060] like Figure 3 As shown, a large model can be used to generate page skeleton code 410 based on page structure information. The page skeleton code can include multiple blocks, such as a first block 311, a second block 312, and a third block 313. Each block is used to represent a different code block and is configured with its own unique identifier, such as container1, container2, and container3. Each block can be identified with information such as the storage location of the corresponding code block and the page layout.

[0061] Therefore, the page layout of the page objects of the target page is limited based on the page skeleton code, for example, the page layout among the page objects A, B, and C in the page skeleton 320 is limited.

[0062] Taking the large model to generate page framework code as an example, the network structure of the large model is further detailed. For example, the large model may include a framework model branch for generating page framework code. The framework model branch can be used as the main branch to process target interaction information and identify the theme of the target page. According to the page theme, the page structure information including multiple page objects and the page layout of each of the multiple page objects is determined. Based on the page structure information, the following is generated: Figure 3 The page frame code shown.

[0063] In response to the preview instruction, the page frame code may be run first to determine the size, background, and other related information of the target page. In addition, multiple page objects in the target page and the page layout of each page object may also be determined.

[0064] Exemplarily, the large model can be used to identify the object content information in the target interaction information, obtain the specific object content information of each page object in the target interaction information, combine the specific object content information of the page object with the object layout information of the page object, and obtain the object attribute information of the page object.

[0065] Optionally, based on using the framework model branch of the large model to process the target interaction information and generate the page framework code, the framework model branch can also be used to determine multiple object attribute information based on the page structure information and the object content information in the target interaction information.

[0066] Generate code blocks for each of the multiple page objects based on their respective object attribute information, and render the page objects using the code blocks to obtain target pages.

[0067] Figure 4 The diagram schematically shows the correspondence between code blocks and page objects according to an embodiment of the present disclosure.

[0068] like Figure 4 As shown, the code block set 420 may include code block A, code block B and code block C, code block A is used to render the page object of "Happy Birthday", code block B is used to render the page objects of "Invitation Time" and "Invitation Location", and code block C is used to render the "Cake Image", thereby rendering multiple page objects in the target page 410.

[0069] According to the embodiments of the present disclosure, by invoking a large model to process target interaction information, page structure information and object content information are obtained. The total-to-specific relationship between page structure information and object attribute information is then used to perform a global planning of multiple page objects based on the page structure information. This results in object attribute information for each page object, which is then used to generate code blocks corresponding to each page object, achieving fine-grained page content segmentation. This allows for the parallel generation of multiple code blocks, improving code block generation efficiency while reducing the difficulty of developing page rendering code.

[0070] Continuing with the example of the "Birthday Invitation" page theme, object attribute information can be determined based on the page structure information and the object content information in the target interaction information. The object attribute information can include the object content information of "Happy Birthday" and the object layout information of the page object. The object layout information can include, for example, information indicating the location of the text "HappyBirthday" as a page object in the page layout of the target page, such as page position information, and information indicating the page style of "Happy Birthday," such as font, color, size, and other information.

[0071] According to an embodiment of the present disclosure, generating a code block based on object attribute information may also include: when the object content information in the object attribute information indicates that the page object is an image type, performing a text-image operation based on the object content information to generate an object image; and generating a code block based on the object image and the object layout information in the object attribute information.

[0072] The object content information may include the content of the page object to be generated by the user, for example, the object content information of "HappyBirthday". However, this is not limited to this. The object content information may also include descriptive information of the page object to be generated, for example, the object content information of "cake image".

[0073] Illustratively, a method for generating a code block corresponding to a page object can be determined based on object content information. If the object content information indicates that the page object is an image, prompt information for a Vincent image operation is generated based on the object content information. The prompt information is processed using a large model to perform the Vincent image operation and output the object image. The present disclosure is not limited to this, and Vincent image operations can also be performed by invoking other artificial intelligence drawing tools.

[0074] For example, the object image and object layout information in the object attribute information can be processed into a structured format, such as JSON format, and then populated into a code block template based on the object layout information and object image to generate a code block. This code block is then used to render the page objects on the target page, generating the object image on the target page. However, this is not limiting. Alternatively, a large model can be used to generate a code block based on the object image and object layout information.

[0075] Optionally, a gated selector can be configured for the large model, which determines the model branch to call based on the object content information in the object attribute information. For example, if the object content information indicates that the page object is of text type, the object content information and the object layout information in the object attribute information can be input into the text model branch to obtain the code block for rendering the text type page object.

[0076] When the object content information indicates that the page object is of text type, the object content information and the object layout information in the object attribute information can be input into the text model branch to obtain a code block. Alternatively, the text type page object and the object layout information can both be used as code parameters in the code block.

[0077] Exemplarily, taking the example of a large model using an image model branch to generate a code block for rendering an object image, the specific processing operation of the image model branch is explained.

[0078] The image model branch can use object content information to perform text-based image operations, generate an object image, and then generate a code block for rendering the image-type page object based on the object image and the object layout information in the object attribute information. Optionally, the object image can be stored in a storage space, and the storage address and object layout information can be used as code parameters for the code block.

[0079] According to an embodiment of the present disclosure, by generating an object image based on the object content information in the object attribute information, and combining the object image and the object layout information to generate a code block, the generation of a code block for rendering the object image can be quickly realized, thereby reducing the richness of the information in the code block and reducing the difficulty of rendering.

[0080] According to an embodiment of the present disclosure, generating a code block based on object attribute information may further include: when the object content information in the object attribute information indicates that the page object is of a map type, obtaining map data that matches the object content information; and generating a code block based on the map data and the object layout information in the object attribute information.

[0081] Illustratively, the page object may be determined to be a map type when it is determined that the target interaction information contains map-related object content information such as location description, traffic route description, etc. An appropriate map data service interface may be called based on the object content information to obtain map data.

[0082] Map data can be specific geographic information that matches the map content information, such as geographic coordinates, road networks, markers, area boundaries, and other information.

[0083] Exemplarily, taking the example of a large model using a map model branch to generate a code block for rendering a map-type page object, the specific processing operation of the map model branch is explained.

[0084] The map model branch uses object content information to call tools, obtain map data from the map data service interface through the map engine tool, and store the map data in the storage space. Based on the storage address of the map data and the object layout information in the object attribute information as code parameters, a code block for rendering the map type page object is generated.

[0085] It should be noted that there is no limitation on the network structure of the map model branch, text model branch, framework model branch, gate selector and image model branch. For example, it may include one or more of the encoder-decoder, attention mechanism and convolutional neural network, as long as it can perform the above functional operations.

[0086] Use this code block to render the target page's page object, thereby displaying a map as the page object. For example, in the "Birthday Invitation" target page, a location map of the birthday location is displayed.

[0087] According to the embodiments of the present disclosure, by identifying the object content information in the object attribute information that characterizes the page object as a map type, the map data that matches it is automatically obtained, and the code blocks that can be used for rendering are generated in combination with the object layout information, an automated process from map requirement description to visual presentation is realized, thereby improving the development efficiency of the map page.

[0088] According to an embodiment of the present disclosure, multiple page objects of the target page are displayed in sequence in the preview interface, and obtaining the target page may include: when it is determined that the code block has been updated to the storage space, based on the code block, displaying the page object corresponding to the code block in the preview interface; wherein the time when the multiple code blocks are updated to the storage space is different.

[0089] For example, the storage space may be configured in the terminal device. The storage space may be monitored, and when the content stored in the storage space, such as a code block, is updated, the code block is used to render the page object to display the corresponding page object on the preview interface.

[0090] Because the target page can include multiple page objects of different modalities, and the different modalities of these page objects lead to different levels of difficulty and time required to generate the code blocks used to render them, a large model is used to process the target interaction information, outputting multiple code blocks generated at different times. This allows code blocks generated at different times to be used to render their respective page objects, thus achieving streamed rendering of multiple page objects.

[0091] Figure 5 The following schematically shows the effect of rendering a page object according to an embodiment of the present disclosure.

[0092] like Figure 5 As shown, when it is determined that the code block corresponding to page object A has been stored in the storage space, the first block 511 of the page skeleton code 510 can be updated. For example, if the object content of page object A is marked as "Happy Birthday" in the body, the code block corresponding to the first block 511 is used to render page object A, and "Happy Birthday" is displayed on the target page 520. When it is determined that the code block corresponding to page object B has been stored in the storage space, the second block 512 of the page skeleton code is updated. For example, if the object content of page object A is marked as "Invitation time, Invitation location" in the body, the code block corresponding to the second block 512 is used to render page object B, and the page object with content such as "Invitation time, Invitation location" is displayed on the target page 520. The code block corresponding to page object C has not yet been stored in the storage space. See the third block 513 of the page skeleton code, so page object C has not yet been rendered. When multiple code blocks used to render the target page are not completely generated, page objects can be rendered separately at different times, thereby achieving streaming rendering of page objects.

[0093] According to an embodiment of the present disclosure, by rendering a page object when it is determined that a code block has been updated to a storage space, rendering efficiency is improved and latency is reduced.

[0094] According to an embodiment of the present disclosure, based on a code block, displaying a page object corresponding to a code block in a preview interface may include: running the code block by calling a rendering tool, and displaying the page object in the preview interface according to the page layout and page style represented by the object layout information in the code block; and matching the rendering tool with the programming language of the code block.

[0095] The page layout may include layout information such as the position and direction of the page object, and the page style includes format information such as the color, font, and size of the page object.

[0096] Rendering tools can render page objects, such as text, images, and videos, into the preview interface according to the specified page layout and page style based on the object layout information in the code. Rendering tools are compatible with the programming language of the code block. There are no restrictions here; any rendering tool that can run code blocks will be used.

[0097] According to the embodiments of the present disclosure, by calling a rendering tool that matches the code block language, the object layout information in the code block is parsed, and the expected page objects are generated in the preview interface. This ensures the consistency of code logic and visual presentation, and improves the diversity and richness of page generation.

[0098] According to an embodiment of the present disclosure, after obtaining the target page, it may also include: obtaining a first object update instruction for the target page object input through a parameter update pop-up window; based on the first object update instruction, updating the target parameters in the code block corresponding to the target page object to obtain a first updated code block; and based on the first updated code block, displaying the updated target page object on the preview interface.

[0099] For example, the user can select the target page object on the target page, thereby popping up a parameter update pop-up window. The parameter update pop-up window can preset multiple modification tools, and the user can trigger the first object update instruction by selecting the modification option control.

[0100] For example, a user can trigger a font or color update instruction for a target page object by modifying the preset font, color, and other option controls in a parameter update pop-up window.

[0101] Optionally, according to the first object update instruction, the target parameter of the code block can be modified based on the modification information to obtain a first updated code block. The target page object is rendered using the first updated code block, and the updated target page object is displayed on the preview interface.

[0102] Figure 6 A schematic diagram of modifying a target page object by using a parameter update pop-up window according to an embodiment of the present disclosure is schematically shown.

[0103] like Figure 6 As shown, by selecting "Happy birthday" on the target page 610, a parameter update pop-up window 620 can pop up. The parameter update pop-up window 620 can include multiple modification controls, such as font, color, bold, italic, underline, etc. By selecting the corresponding modification control for modification, the first object update instruction can be triggered to update the code block and re-render the target page object using the updated code block, and display the updated target page object on the target page.

[0104] According to an embodiment of the present disclosure, since the generated page may not satisfy the user, in order to meet the user's needs, the user can quickly trigger the modification of the target page object through the parameter update pop-up window to regenerate the target page. This page object update method is simple and fast.

[0105] According to an embodiment of the present disclosure, based on the first object update instruction, the target parameters in the code block corresponding to the target page object are updated to obtain the first updated code block, which may include: based on the first object update instruction, obtaining the code block corresponding to the target page object from the storage space; and updating the target parameters to obtain the first updated code block.

[0106] Exemplarily, the first object update instruction may include an identifier of the target page object and modification information. Based on the identifier of the page object, a code block corresponding to the target page object may be retrieved from the storage space. Target parameters of the code block are updated based on the modification information to obtain a first updated code block.

[0107] The first updated code block can be stored in the storage space, and the code block with the same identifier in the storage space can be overwritten to complete the update of the code block in the storage space. After the first updated code block is stored in the storage space, the target page object is rendered based on the first updated code block, and the updated target page object is displayed on the preview interface.

[0108] According to an embodiment of the present disclosure, by directly updating the parameters of the code block in the storage space, the update and storage of the local code block are achieved, thereby improving the update efficiency of the code block.

[0109] According to another embodiment of the present disclosure, after obtaining the target page, it may also include: obtaining a second object update instruction for the target page object input through an interactive pop-up window; obtaining a second update code block corresponding to the target page object; the second update code block is generated by calling a large model to process the second object update instruction; based on the second update code block, the updated target page object is displayed in the preview interface.

[0110] For example, the target page may pop up an interactive pop-up window in response to a user's activation operation, such as a selection operation, on an object on the target page, and the user may directly input a second object update instruction in natural language in the interactive pop-up window.

[0111] Figure 7 A schematic diagram schematically illustrates updating a target page object using an interactive pop-up window according to an embodiment of the present disclosure.

[0112] like Figure 7As shown, by selecting the "Happy Birthday" page object on the target page 710, an interactive pop-up window 720 can also pop up, and the user can directly enter the second object update instruction in natural language in the interactive pop-up window 720. For example, the user can generate a second object update instruction by selecting the control options such as abbreviating, expanding, polishing, and modifying the target text selected in the target page in the interactive pop-up window.

[0113] Illustratively, the large model can be used to identify the second object update instruction, determine the target page object to be modified and the target parameters to be modified, retrieve the code block corresponding to the target page object from the storage space, and update the code block corresponding to the target page object based on the target parameters to be modified to obtain a second updated code block. The present disclosure is not limited to this, and the large model can also be used to process the second update instruction, directly generate a second updated code block, store the second updated code block in the storage space, and overwrite the code block with the same identifier.

[0114] According to an embodiment of the present disclosure, by using a large model to process the second object update instruction to obtain a second update code block, not only can the accuracy and efficiency of the modification be improved, but also different modification requirements can be met, and the richness and flexibility of the update can be improved.

[0115] Figure 8 A block diagram of an artificial intelligence-based page display device according to an embodiment of the present disclosure is schematically shown.

[0116] like Figure 8 As shown, the artificial intelligence-based page display device 800 includes a receiving module 810 and a display module 820.

[0117] The receiving module 810 is configured to receive target interaction information input through an interactive interface; the target interaction information is used to instruct generation of a target page.

[0118] The display module 820 is used to respond to receiving a preview instruction for the target page, render multiple code blocks of the target page, and display multiple page objects of the target page in the preview interface in sequence to obtain the target page; wherein, the multiple code blocks are obtained by calling the large model to process the target interaction information.

[0119] According to an embodiment of the present disclosure, the receiving module 810 includes a receiving submodule and a supplementing submodule, which is configured to repeatedly perform an interaction operation until target interaction information is obtained.

[0120] The receiving submodule is used to receive the interaction information of the current round input through the interaction interface.

[0121] The supplement submodule is used to output feedback information for supplementing information on the interactive interface when the recognition result indicates that the received interactive information is incomplete in describing the target page; the recognition result is obtained by performing integrity recognition on the received interactive information.

[0122] According to an embodiment of the present disclosure, a code block is generated based on target interaction information by calling a large model module, wherein the large model module includes a first generation submodule, a determination submodule, and a second generation submodule.

[0123] The first generating submodule is configured to generate page structure information based on the page theme of the target page represented by the target interaction information, where the page structure information is used to identify the page layout of multiple page objects.

[0124] The determination submodule is used to determine object attribute information used to describe the page object based on the page structure information and the object content information in the target interaction information, and obtain multiple object attribute information.

[0125] The second generating submodule is used to generate a code block based on the object attribute information to obtain multiple code blocks.

[0126] According to an embodiment of the present disclosure, the second generation submodule includes an image generation unit and a code block generation unit.

[0127] The image generating unit is configured to generate an object image by performing a text-to-image operation based on the object content information when the object content information in the object attribute information indicates that the page object is of an image type.

[0128] The first code block generating unit is configured to generate a code block based on the object image and object layout information in the object attribute information. The object layout information includes information representing the page layout of the page object and information representing the page style of the page object.

[0129] According to an embodiment of the present disclosure, the second generation submodule includes an acquisition unit and a second code block generation unit.

[0130] The acquiring unit is configured to acquire map data matching the object content information when the object content information in the object attribute information indicates that the page object is of a map type.

[0131] The second code block generating unit generates a code block based on the map data and the object layout information in the object attribute information.

[0132] According to an embodiment of the present disclosure, the presentation module includes a page object presentation submodule.

[0133] The page object display submodule is used to display the page object corresponding to the code block in the preview interface based on the code block when it is determined that the code block has been updated to the storage space; wherein, the time when multiple code blocks are updated to the storage space is different.

[0134] According to an embodiment of the present disclosure, the page object display submodule includes a rendering unit.

[0135] The rendering unit is used to run the code block by calling the rendering tool, and display the page object in the preview interface according to the page layout and page style represented by the object layout information in the code block; the rendering tool matches the programming language of the code block.

[0136] According to an embodiment of the present disclosure, the page display device further includes a first acquisition module, a code block update module, and a display update module.

[0137] The first acquisition module is configured to acquire a first object update instruction input through a parameter update pop-up window for a target page object.

[0138] The code block updating module is configured to update target parameters in the code block corresponding to the target page object based on the first object updating instruction to obtain a first updated code block.

[0139] The first display update module is used to display the updated target page object on the preview interface based on the first update code block.

[0140] According to an embodiment of the present disclosure, the code block update module includes a code block acquisition submodule and a first update submodule.

[0141] The code block acquisition submodule is configured to acquire a code block corresponding to a target page object from a storage space based on the first object update instruction.

[0142] The first updating submodule is used to update the target parameters to obtain a first updated code block.

[0143] According to an embodiment of the present disclosure, the page display device further includes a second acquisition module, a third acquisition module and a second display update module.

[0144] The second acquisition module is configured to acquire a second object update instruction input through an interactive pop-up window for a target page object.

[0145] The third acquisition module is used to acquire a second update code block corresponding to the target page object, where the second update code block is generated by calling the large model to process the second object update instruction.

[0146] The second display update module is used to display the updated target page object on the preview interface based on the second update code block.

[0147] According to embodiments of the present disclosure, any multiple modules in the receiving module 810 and the display module 820 can be combined into a single module, or any one of them can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the receiving module 810 and the display module 820 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the receiving module 810 and the display module 820 can be at least partially implemented as a computer program module that, when executed, can perform the corresponding functionality.

[0148] Figure 9 The structural block diagram of an artificial intelligence agent according to an embodiment of the present disclosure is schematically shown.

[0149] In the embodiments of the present disclosure, Figure 9 As shown, the AI agent 900 may include an input module 910 , a processing module 920 and an output module 930 .

[0150] The input module 910 is used to receive input information.

[0151] The processing module 920 is used to determine the target task based on the input information received by the input module, determine the big model based on the target task, and execute the artificial intelligence-based page display method provided according to the embodiment of the present disclosure by calling the big model.

[0152] The output module 930 is used to output the output information obtained by the processing module.

[0153] According to an embodiment of the present disclosure, the input module 910 is responsible for receiving or perceiving information such as queries, requests, instructions, signals, or data from the outside world (e.g., a user or the external environment) and converting it into a format that can be understood and processed by the AI agent 900. The input module 910 is the primary link for the AI agent 900 to interact with the outside world. It enables the AI agent 900 to efficiently and accurately obtain the necessary "sensory" information from the outside world and respond to this information.

[0154] In an example, the input module 910 may input the target interaction information described above, and the like.

[0155] In the example, the processing module 920 is the core support for the AI agent 900 to handle complex tasks. The processing module 920 can execute the page display method based on artificial intelligence described above.

[0156] In this example, the performance of processing module 920 may be closely related to the large model underlying AI agent 900. To fully leverage the capabilities of the large model, the internal structure of processing module 920 may be designed to be highly configurable and extensible to handle a variety of different tasks and requirements in real-world scenarios.

[0157] In the example, after the AI agent 900 obtains the target interaction information, the processing module 920 can process the target interaction information using a large model, obtain a code block, and pass the code block to the output module 930.

[0158] Understandably, while the large model possesses excellent language understanding and generation capabilities, like humans, it can only perform limited tasks without the aid of tools. However, once AI Agent 900 is empowered with tool-based capabilities, it can perform tasks such as mathematical calculations using a calculator, data analysis using Python, and weather forecasting using search engines.

[0159] In an example, the output module 930 may output the code block described above.

[0160] The AI agent 900 according to the embodiment of the present disclosure can simply and effectively improve the level of intelligence, and enhance flexibility and versatility.

[0161] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0162] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0163] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above method.

[0164] According to an embodiment of the present disclosure, a computer program product includes a computer program, and the computer program implements the above method when executed by a processor.

[0165] Figure 10A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is schematically shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0166] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. RAM 1003 may also store various programs and data required for the operation of device 1000. Computing unit 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to bus 1004.

[0167] Various components in device 1000 are connected to an input / output (I / O) interface 1005, including an input unit 1006, such as a keyboard and mouse; an output unit 1007, such as various types of displays and speakers; a storage unit 1008, such as a magnetic disk and optical disk; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0168] The computing unit 1001 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as the artificial intelligence-based page display method. For example, in some embodiments, the artificial intelligence-based page display method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the artificial intelligence-based page display method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the artificial intelligence-based page display method in any other appropriate manner (eg, by means of firmware).

[0169] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0173] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0175] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0176] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A page display method based on artificial intelligence, comprising: receiving target interaction information input through the interactive interface; The target interaction information is used to instruct the generation of a target page; In response to receiving a preview instruction for the target page, based on multiple code blocks for rendering the target page, sequentially displaying multiple page objects of the target page in a preview interface to obtain the target page; Among them, multiple code blocks are obtained by calling a large model to process the target interaction information.

2. The method according to claim 1, wherein The code block is generated as follows: The large model is called to perform the following operations based on the target interaction information: Generate page structure information based on the page theme of the target page represented by the target interaction information; The page structure information is used to identify the page layout of the plurality of page objects; Determining object attribute information for describing the page object based on the page structure information and the object content information in the target interaction information, and obtaining a plurality of object attribute information; as well as Based on the object attribute information, the code block is generated to obtain a plurality of the code blocks.

3. The method according to claim 2, wherein: The generating the code block based on the object attribute information includes: In a case where the object content information in the object attribute information indicates that the page object is of an image type, performing a text-to-image operation based on the object content information to generate an object image; and The code block is generated based on the object image and object layout information in the object attribute information; the object layout information includes information representing the page layout of the page object and information representing the page style of the page object.

4. The method according to claim 2 or 3, wherein: The generating the code block based on the object attribute information includes: When the object content information in the object attribute information indicates that the page object is of a map type, acquiring map data that matches the object content information; and The code block is generated based on the map data and the object layout information in the object attribute information.

5. The method according to any one of claims 1 to 4, wherein The receiving target interaction information input through the interactive interface includes: Repeat the following interaction operations until the target interaction information is obtained: receiving interaction information of the current round input through the interaction interface; and When the recognition result indicates that the received interactive information does not fully describe the target page, feedback information for supplementing the information is output on the interactive interface; the recognition result is obtained by performing integrity recognition on the received interactive information.

6. The method according to any one of claims 1 to 5, further comprising: Obtain a first object update instruction input through a parameter update pop-up window for a target page object; Based on the first object update instruction, a target parameter in a code block corresponding to the target page object is updated to obtain a first updated code block; as well as Based on the first update code block, the updated target page object is displayed on the preview interface.

7. The method according to claim 6, wherein: The updating of the target parameters in the code block corresponding to the target page object based on the first object update instruction to obtain a first updated code block includes: Based on the first object update instruction, obtaining a code block corresponding to the target page object from a storage space; and The target parameter is updated to obtain the first updated code block.

8. The method according to any one of claims 1 to 7, further comprising: Obtain a second object update instruction input through an interactive pop-up window for a target page object; Obtaining a second update code block corresponding to the target page object; The second update code block is generated by calling the large model to process the second object update instruction; Based on the second update code block, the updated target page object is displayed on the preview interface.

9. The method according to any one of claims 1 to 8, wherein The step of sequentially displaying multiple page objects of the target page in a preview interface based on multiple code blocks for rendering the target page to obtain the target page includes: When it is determined that the code block has been updated to the storage space, based on the code block, displaying the page object corresponding to the code block in the preview interface; The multiple code blocks are updated to the storage space at different times.

10. The method according to claim 9, wherein: The displaying, based on the code block, the page object corresponding to the code block in the preview interface includes: The code block is run by calling a rendering tool, and the page object is displayed in the preview interface according to the page layout and page style represented by the object layout information in the code block; the rendering tool is matched with the programming language of the code block.

11. A page display device based on artificial intelligence, comprising: A receiving module, configured to receive target interaction information input through an interactive interface; The target interaction information is used to instruct the generation of a target page; a display module configured to, in response to receiving a preview instruction for the target page, sequentially display multiple page objects of the target page in a preview interface based on multiple code blocks for rendering the target page, thereby obtaining the target page; Among them, multiple code blocks are obtained by calling a large model to process the target interaction information.

12. An artificial intelligence agent, comprising: An input module, used for receiving input information; a processing module, configured to determine a target task based on the input information received by the input module, determine a large model based on the target task, and obtain output information by executing the method according to any one of claims 1 to 10 by calling the large model; An output module is used to output the output information obtained by the processing module.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images