Target page generation method and device

Abstract

The present disclosure provides a method and device for generating a target page, which relates to the field of artificial intelligence technology, specifically natural language processing, computer vision, deep learning and other technical fields. The specific implementation scheme is: receiving page description information input by a user; extracting initial business information based on the page description information; generating a page framework including at least one theme module based on the acquired industry page information; filling each theme module in the page framework based on the initial business information to obtain a target page. This implementation method improves the generation efficiency of the target page.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as natural language processing, computer vision, and deep learning, and in particular to a method and device for generating a target page, an electronic device, a computer-readable medium, and a computer program product. Background Art

[0002] In the process of creating traditional advertising marketing pages, advertisers need to prepare pictures and text materials, and then drag and drop them in a visual editor to finally generate a page for advertising. During this process, it involves editing pictures, modifying texts, and modifying the overall style. This process can take several hours and is costly. In addition, the design and layout of the process also greatly test the professionalism of the advertiser. Summary of the invention

[0003] Provided are a target page generation method and device, an electronic device, a computer-readable storage medium, and a computer program product.

[0004] According to a first aspect, a method for generating a target page is provided, the method comprising: receiving page description information input by a user; extracting initial business information based on the page description information; generating a page frame including at least one subject module based on the acquired industry page information; and filling each subject module in the page frame based on the initial business information to obtain a target page.

[0005] According to the second aspect, a target page generating device is provided, which includes: a receiving unit, configured to receive page description information input by a user; an information extraction unit, configured to extract initial business information based on the page description information; a generating unit, configured to generate a page frame including at least one subject module based on the acquired industry page information; and a filling unit, configured to fill each subject module in the page frame based on the initial business information to obtain a target page.

[0006] According to a third aspect, 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 so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0008] According to a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in any implementation manner of the first aspect when executed by a processor.

[0009] The target page generation method and device provided by the embodiment of the present disclosure firstly receives the page description information input by the user; secondly, extracts the initial business information based on the page description information; thirdly, generates a page frame including at least one theme module based on the acquired industry page information; finally, fills each theme module in the page frame based on the initial business information to obtain the target page. Thus, the advertiser only needs to provide the page description information through a simple dialogue, and the creation of the entire target page can be completed based on the current industry page information, which provides an overall layout method for creating the target page, greatly reduces the cost of the advertiser to build the page, improves the generation efficiency of the target page, and improves the quality of the target page.

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

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a flow chart of an embodiment of a method for generating a target page according to the present disclosure;

[0013] Figure 2 It is a schematic diagram of the structure of color update in the target page generation method according to the present disclosure;

[0014] Figure 3 It is a structural schematic diagram of the text update in the target page generation method disclosed in the present invention;

[0015] Figure 4 It is a schematic diagram of the structure of using a large language model to generate a target page in the target page generation method disclosed in the present invention;

[0016] Figure 5 is a structural schematic diagram of an embodiment of a target page generating device according to the present disclosure;

[0017] Figure 6 It is a block diagram of an electronic device used to implement the target page generating method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art 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.

[0019] In this embodiment, "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0020] The overall advertising landing page carries all the product information that the advertiser wants to convey to netizens, and is the key to attracting netizens to leave clues. The construction of traditional advertising landing pages mainly has the following two scenarios in order to create a high-quality landing page:

[0021] The first scenario: Companies / agents with design capabilities:

[0022] First, professionals give the outline and marketing copy of the overall business page based on their understanding of the industry; then designers design illustrations that suit the specific modules based on the above outline; finally, the page producers use the visual editor provided by the platform to build the landing page based on the above outline, copy, and illustrations.

[0023] In this scenario, the overall link process will be relatively long, and each link will be carried out by different roles. Once the final output page does not meet expectations, the specific responsible person must be found to make secondary modifications.

[0024] The second scenario: Companies / individuals without design capabilities:

[0025] Through the industry templates provided by the platform, you can combine your own business scenarios to perform secondary editing in the visual editor to generate your own landing page.

[0026] In this scenario, since some pre-made templates on the platform are used, some pictures and texts are not suitable for the business characteristics of the customers and need to be modified twice, which only saves the cost of the overall page design of the customers. At the same time, since industry templates are shared by the industry, there will be a disadvantage that the created pages have little visual difference. In the current process, a large number of advertisers are small and medium-sized customers who have no Internet experience. The threshold for building a page is very high for them.

[0027] The present invention provides a method for generating a target page. By interacting with natural language and combining the experience of building high-quality pages in the online industry, the method ultimately reduces the threshold for advertisers to create pages, improves the quality of target pages, and ultimately brings lead conversions to advertisers. Figure 1 A process 100 according to an embodiment of a target page generation method of the present disclosure is shown. The target page generation method includes the following steps:

[0028] Step 101: receiving page description information input by a user.

[0029] In this embodiment, the page description information refers to a set of description information related to the target page, and the page description information can be used to describe the user's business demands for the target page.

[0030] In this embodiment, the execution entity on which the target page generation method runs can create an interactive page for interacting with the user. The user enters page description information on the interactive page through natural language interaction without having to understand complex product interactions, thereby reducing the user's usage cost on the platform.

[0031] In this embodiment, the page description information can be obtained by the user selecting traditional page building data. Optionally, the above step 101 can also include: obtaining the data of the historical page built by the advertiser; displaying the data of the historical page on the interactive page; receiving the user's selection operation on the historical page data to obtain the page description information.

[0032] For example, the page description information includes: we hope to make a marketing page that provides car key duplication services, the target service objects are netizens who have key duplication needs, the page uses red as the theme color, and the target lead types are phone calls and forms.

[0033] Optionally, the above step 101 may also include: obtaining the user's registration information, and determining the user's industry based on the registration information; while the user enters the page description information, based on the user's industry, recommending industry information related to the user's industry to the user, and the page description information that the customer needs to enter will be recommended based on the customer's industry, further reducing the customer's input cost.

[0034] Step 102: extracting initial business information based on the page description information.

[0035] In this embodiment, the initial business information is information related to the business goal of the target page, and the initial business information is also business information in the page description information that is consistent with the content of the target page.

[0036] In this embodiment, the initial business information includes: business point, the business point user describes the specific business content of the target page. Optionally, the initial business information may also include: target service object, page style, and lead collection method; wherein the target service object is the target audience of the content (such as advertisement) displayed on the target page; the page style is used to determine the style and color of the target page; and the lead collection method determines the final marketing plan of the target page.

[0037] In the page description information of the above example, the extracted initial business information includes: business point, target service object, page style, and clue collection method; among them, business point: car key matching; target service object: netizens who need key matching; page style: red; clue collection method: telephone, form; therefore, the user only needs to enter the page description information to generate a target page.

[0038] Step 103: Generate a page framework including at least one subject module based on the acquired industry page information.

[0039] In this embodiment, the page frame is a page structure corresponding to the entire page of the target page. After obtaining the page structure, the page structure corresponding to the page frame is processed into modules. The page frame can be divided into a frame with at least one theme module. According to the theme of the theme module, the theme module is filled with content to complete the content generation of the page frame. Among them, at least one theme module may include: a header image module, a list module, a lead conversion module, etc.

[0040] In this embodiment, the industry page information is the page information obtained after sorting out the high-quality online pages (pages with high conversion rates) of various industries. The industry page information can be an industry page pre-set by the user. The industry page information can also be a page related to the user's page description information searched through the Internet by the execution entity on which the target page generation method runs.

[0041] In this embodiment, the industry pages corresponding to the industry page information have different subject areas, and therefore each subject module of the page frame also corresponds to a corresponding subject area. Based on the various subject areas in the industry pages in the industry page information, corresponding areas are allocated to the subject modules, and the corresponding areas of the subject modules are filled to obtain the target page.

[0042] For pages created based on templates using traditional technologies, there is a problem of page homogeneity. In this embodiment, when generating pages, it is not based on a specific template, but on a page's industry-quality page design idea. Therefore, in the same industry, the problem of page homogeneity created by different advertisers can be avoided.

[0043] In this embodiment, the industry page information can be input into the large language model, so that the large language model can learn in combination with high-quality industry pages, and then combined with the advertiser's business scenario to generate a target page that fits the advertiser.

[0044] Step 104, based on the initial business information, fill in each subject module in the page frame to obtain the target page.

[0045] In this embodiment, the target page is the page corresponding to the page description information input by the user, and is also the page that the user (eg, advertiser) expects to generate.

[0046] In this embodiment, the target page may be a landing page, which is a marketing webpage that integrates the acquisition of user information, sales, or allowing users to take certain actions, and is also called a landing page.

[0047] In this embodiment, the target page may include: a header image, content, and a marketing component.

[0048] In this embodiment, the above step 104 includes: determining business points of different themes based on initial business information; determining business information corresponding to the business points based on the business points; filling the business information corresponding to each theme into the area corresponding to the theme to obtain the target page.

[0049] Optionally, the above step 104 also includes: determining the target service object of the target page based on the initial business information; based on the target service object, filtering the business information corresponding to each business point to obtain final information; filling the final information corresponding to each topic into the area corresponding to the topic to obtain the target page.

[0050] For traditional companies with design capabilities, the production of a page depends on many roles, the overall page generation link is too long, and the cost of secondary modification is also very high. The target page generation method provided by the embodiment of the present disclosure can guide customers to describe their business demands through interactive dialogues and upload the customer's existing information. The preparation and generation of the overall materials all rely on the execution subject, and there is basically no material preparation cost. At the same time, the underlying high-quality landing page based on the industry will generate a page that can better improve the conversion of leads, reduce the operating threshold of advertisers, and improve the quality of page creation.

[0051] The target page generation method provided by the embodiment of the present disclosure first receives page description information input by the user; secondly, extracts initial business information based on the page description information; thirdly, generates a page framework including at least one theme module based on the acquired industry page information; finally, fills each theme module in the page framework based on the initial business information to obtain the target page. Thus, the advertiser only needs to provide page description information through a simple dialogue, and the creation of the entire target page can be completed based on the current industry page information, which provides an overall layout method for creating the target page, greatly reduces the cost of the advertiser to build the page, improves the generation efficiency of the target page, and improves the quality of the target page.

[0052] In some embodiments of the present disclosure, the target page generation method further includes: extracting an initial color of the target page; obtaining an adjusted color based on the initial color; and adjusting the target page based on the adjusted color to obtain an adjusted target page.

[0053] The target page generation method provided in this embodiment receives page description information input by a user; extracts initial business information based on the page description information; and generates a page framework including at least one theme module based on the acquired industry page information.

[0054] The target page generation method provided in this embodiment extracts the initial color of the target page, and obtains the adjusted color based on the initial color; based on the adjusted color, the target page is adjusted to obtain the adjusted target page. To this end, the overall effect of the target page is further optimized by adjusting the color. The bottom layer of the target page of this application can be optimized in color based on the color scheme of the first screen, thereby reducing the visual difference of the target page.

[0055] Optionally, the above-mentioned target page generation method also includes: displaying the target page in a visual editor, and in the visual editor, in response to a change in the image of the target page, determining an adjustment color of the target page based on the new image; and adjusting the target page based on the adjustment color to obtain an adjusted target page.

[0056] In this embodiment, when the user is not satisfied with the target page, he can enter the visual editor to perform a secondary edit on the target page. Since the overall color tone of the previously generated target page is based on the overall header image, if the color is not modified, it is easy to find that the aesthetics of the page is reduced after the modification.

[0057] Specifically, Figure 2 As shown, the target page is displayed in the visual editor, and the user Figure 2 Modify the picture in Figure 2The "new picture" is taken, and the color is picked for the "new picture" to get the adjusted color. Figure 2 Adjust the image in to get the adjusted target page. Figure 2 Different areas of the target page shown have different color tokens, such as color tokens t1, t2, and t3. Each color token represents a different color RGB. The color RGB (xx, xx, xx) of different color tokens can be used to set the adjustment color for each color token area, thereby obtaining the adjusted target page.

[0058] In this embodiment, if the customer is not satisfied with the image generated in the target page, he can right-click and call the ability of the large language model. Through the "Change" operation, based on the customer's industry characteristics and the current image as input, the search and generation capabilities of the large language model are called to generate a new image. In this way, it is convenient for customers to modify the image. Among them, the above-mentioned "Change" refers to the function of generating images from images. Taking the current image as the base image, the model generated by the image, such as Wenxin Yige, is called to generate a similar image.

[0059] Alternatively, the above-mentioned "change" means searching for new pictures in the existing picture copyright library based on the current customer's business points, module demands, and color demands.

[0060] In this embodiment, in the visual editor, if the image is changed, the color picking service will be called based on the new image to generate a new color. This new color will update a color token at the bottom of the page, so that when the user re-edits the image of the target page, the style of the entire page can still be kept unified.

[0061] In some optional implementations of this embodiment, the above-mentioned extraction of the initial color of the target page includes: extracting the color of the largest color block in the target page to obtain the initial area color; extracting the color of the preset color block in the target page to obtain the initial emphasis color; using the initial area color and the initial emphasis color as the initial color. The above-mentioned acquisition of the adjusted color based on the initial color includes: acquiring a discarded color based on the color of pages of different industries; and acquiring an adjusted color based on the initial color and the discarded color.

[0062] In this embodiment, the initial area color is the color of the largest color block in the image of the target page. The initial emphasis color is the most prominent color in the image of the target page, and the preset color block is the most prominent color block in the target page.

[0063] In this embodiment, the discarded color is a color that does not match the current target page and is also a color that needs to be removed from the current target page. The above-mentioned adjustment color is obtained based on the initial color and the discarded color, including: removing the discarded color from the initial area color, removing the discarded color from the initial emphasis color, and obtaining the adjustment color.

[0064] In this embodiment, the area color and accent color of the page can be extracted based on the generated home page, and applied to the overall background and marketing components of the page. At the same time, color tokens can be combined to ensure that the visual experience of the overall page is the best under various colors.

[0065] The target page generation method provided by the embodiment of the present disclosure, when extracting the initial color of the target page, simultaneously extracts the color of the largest color block and the color of the preset color block in the target page, and uses the color of the largest color block and the color of the preset color block as the initial color of the target page, thereby improving the color generation efficiency of the target page.

[0066] Optionally, the above-mentioned extraction of the initial color of the target page includes: extracting the colors of all color blocks of the target page, and performing weighted summation on the colors of all color blocks to obtain the initial color; the above-mentioned obtaining the adjusted color based on the initial color includes: comparing the initial color with a preset matching color, and in response to the initial color matching the matching color, using the initial color as the adjusted color; in response to the initial color not matching the matching color, changing the initial color to obtain the adjusted color.

[0067] In some embodiments of the present disclosure, the above-mentioned target page generation method also includes: obtaining selected text after the user performs a selection operation on the text in the target page; inputting the selected text into the first largest language model to obtain modified text output by the first largest language model; and replacing the selected text with the modified text.

[0068] In this embodiment, the first language model is a large language model, which is used to characterize the correspondence between the selected text and the modified text, wherein the large language model (LLM) refers to a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. The large language model can handle a variety of natural language tasks, such as text classification, question and answer, dialogue, etc., and is an important way to artificial intelligence. The core idea of ​​the large language model is to learn the patterns and language structures of natural language through large-scale unsupervised training, which can simulate the language cognition and generation process of human beings to a certain extent.

[0069] In this embodiment, the selected text is input into the first largest language model, and the first largest language model performs model understanding on the selected text to obtain a modified text, wherein the modified text is a text different from the selected text.

[0070] In this embodiment, the first largest language model can be a model that understands the page description information and obtains the initial business information. Further, by inputting the selected text into the first largest language model, a modified text output by the first largest language model can be obtained. The modified text is a text that is more in line with the page description information, and the modified text is also a text that conforms to the initial business information.

[0071] like Figure 3 As shown, the target page can be displayed in a visual editor. The user selects text in the visual editor by right-clicking or other means to obtain the selected text. Based on the selected text, the selected text (such as Figure 3 The text in 3) is modified (including polishing, expansion, review avoidance and other operations), and relevant prompt information (prompt) is generated, and then the first language model is called to process the modified text to obtain the modified text to meet the user's pain points in copy modification.

[0072] Optionally, in Figure 3 In the process of calling the first language model, the selected text is passed in, and then the target requirements of the target page (the requirements for the advertisements on the page) are added. Then some high-quality advertising and marketing words are given to the large language model. This can achieve the effect of polishing.

[0073] Audit avoidance means that based on the selected text, some audit standards or known audit rejection reasons are combined to enable the first language model to avoid the audit problem when generating modified text.

[0074] The target page generation method provided by this optional implementation manner determines the selected text of the user's operation in a visual editor in response to the user's selection operation on the text in the target page; inputs the selected text into the first largest language model to obtain the modified text output by the first largest language model, and replaces the selected text with the modified text, thereby providing a reliable implementation method for replacing the selected text based on the analysis capability of the first largest language model.

[0075] Optionally, the above method also includes: obtaining selected text after the user performs a selection operation on the text in the target page; correcting the selected text using an error correction model to obtain error correction text, and replacing the selected text with the error correction text.

[0076] In some embodiments of the present disclosure, the above-mentioned target page generation method also includes: obtaining a selected image after the user performs a selection operation on the image in the target page; inputting the selected image into the second largest language model to obtain a modified image output by the second largest language model; and replacing the selected image with the modified image.

[0077] In this embodiment, the second largest language model is a large language model, which is used to characterize the correspondence between the selected picture and the modified picture. The large language model is a model based on machine learning and natural language processing technology. It is trained on a large amount of text data to learn and serve human language understanding and generation capabilities.

[0078] In this embodiment, the selected picture is input into the second largest language model, and the selected picture is analyzed by the second largest language model to obtain a modified picture, wherein the modified picture is a picture different from the selected picture.

[0079] In this embodiment, the second largest language model can be the same model as the first largest language model, and the first largest language model can understand the page description information to obtain a model of the initial business information. For this reason, the modified image output by the second largest language model is more in line with the requirements of the page description information, and the modified image is also a picture that conforms to the initial business information.

[0080] The target page generation method provided by this optional implementation manner, in a visual editor, responds to a selected image after a user performs a selection operation on an image in a target page; the selected image is input into a second largest language model to obtain a modified image output by the second largest language model, and the modified image is used to replace the selected image, thereby providing a reliable implementation method for replacing the selected image based on the analysis capability of the second largest language model.

[0081] In some optional implementations of the present disclosure, the above-mentioned extraction of initial business information based on page description information includes: inputting the page description information into a third language model to obtain the initial business information output by the third language model, and the third language model is used to characterize the correspondence between the page description information and the initial business information.

[0082] In this embodiment, the third language model is a large language model, which is used to characterize the correspondence between page description information and initial business information. The large language model is a model based on machine learning and natural language processing technology. It is trained on a large amount of text data to learn to serve human language understanding and generation capabilities. The core idea of ​​the large language model is to learn natural language patterns and language structures through large-scale unsupervised training.

[0083] In this embodiment, the page description information is input into the third language model, and the page description information is analyzed by the third language model to obtain initial business information related to the business of the target page, wherein the initial business information is the main information related to the business of the target page in the page description information.

[0084] In this embodiment, the third largest language model may be the same model as the first largest language model and the second largest language model.

[0085] like Figure 4 As shown, the initial business information includes: business point, target service object, page style, and lead collection method.

[0086] The method for extracting initial business information provided by this optional implementation inputs page description information into a third language model to obtain initial business information output by the third language model. With the help of the large language model's ability to understand text, reliable initial business information is obtained, thereby providing an optional implementation method for obtaining the initial business information.

[0087] Optionally, the third language model can also output: pictures and text, such as Figure 4 As shown, the above-mentioned extraction of initial business information based on page description information includes: inputting the page description information into the third language model to obtain pictures, texts and initial business information output by the third language model; the pictures and texts output by the third language model can be used to fill in various subject modules in the page frame.

[0088] In this embodiment, with the help of the third language model, the user's desire to establish a target page is understood, and text and pictures that meet the user's business characteristics are generated.

[0089] In another embodiment of the present disclosure, the above-mentioned target page generation method also includes: while inputting the page description information into the third largest language model, determining the information input plug-in selected by the user; obtaining business insertion information from the information input plug-in, and inputting the business insertion information into the third largest language model.

[0090] In this embodiment, Figure 4 As shown, the information input plug-in is connected to the third language model and is used to input business insertion information into the third language model. The business insertion information includes: official website content information and local file information. There can be multiple information input plug-ins, for example, crawler plug-ins and file processing plug-ins. The crawler plug-in can crawl the official website content of the user; the file processing plug-in can extract the content of the user's local files. Through the user's selection operation, the auxiliary information of the third language model that the user expects to input can be determined.

[0091] In this embodiment, in order to make the generated target page more suitable for the user's scenario, after the user (advertiser) enters the page description information, the user can select the corresponding plug-in to enter other text content. For example, if the user has his own official website and wants to generate a landing page based on the content of the official website, he can select a crawler plug-in. The crawler plug-in can crawl the content of the customer's official website and input the crawled content into the third language model for cleaning.

[0092] Or if the user has other compressed files locally that contain text, pictures, and other content, they can directly choose to upload them, extract the content through the file processing plug-in, and then input the content into the third language model as the material for subsequent page generation.

[0093] The target page generation method provided in this embodiment determines the information input plug-in selected by the user while inputting the page description information into the third language model; obtains the business insertion information from the information input plug-in, and inputs the business insertion information into the third language model, so that the third language model can obtain more information related to the business of the target page, thereby improving the diversity of information input to the third language model and improving the accuracy of obtaining the initial business information.

[0094] In one embodiment of the present disclosure, generating a page framework including at least one subject module based on the acquired industry page information includes: inputting the acquired industry page information into a fourth language model to obtain an initial framework output by the fourth language model; dividing the initial framework into modules of different subjects to obtain a page framework including at least one subject module.

[0095] In this embodiment, the fourth language model is a large language model, which is used to characterize the correspondence between industry page information and the initial framework. The core idea of ​​the large language model is to learn the patterns and language structures of natural language through large-scale unsupervised training.

[0096] In this embodiment, the industry page information is input into the fourth language model, and the industry page information is analyzed by the fourth language model to obtain an initial framework related to the page layout in the industry page information.

[0097] In this embodiment, the fourth largest language model may be the same model as the first largest language model, the second largest language model, and the third largest language model.

[0098] In this embodiment, the initial framework is the page language structure of the corresponding industry page information obtained after the fourth language model analyzes the industry page information. For different language structures (page structures) in the initial framework, the initial framework can be distinguished into different themes to obtain different theme modules in the initial framework. After filling content into each theme module, the target page is obtained.

[0099] In this embodiment, the page frame is a page structure related to the page layout of the target page. After obtaining the initial frame, the above-mentioned division of the initial frame into modules of different themes to obtain a page frame including at least one theme module includes: determining all themes in the initial frame, allocating corresponding areas to each theme in the initial frame, and sorting all themes to obtain the page frame.

[0100] In this embodiment, the industry page information is common in the industry and is consistent with the layout of the target page. In order to generate a high-quality target page (such as a landing page), the fourth language model needs to be informed of what a good page is. Therefore, the execution subject on which the target page generation method runs obtains the industry page information, uses the fourth language model to analyze the industry page information, and determines the initial framework that adapts to the industry page information. Since the initial framework does not divide the various topics on the page, the different topic contents on the initial framework are sorted and laid out to obtain the page framework.

[0101] In this embodiment, framework generation: For the framework generation part, the online high-quality pages (pages with high conversion rates) are sorted out by industry and provided to the large model for learning. In this way, when a new user input is received and combined with the industry information, the fourth language model can generate a page framework (landing page structure) that is consistent with the industry's high-quality pages and adapts to the user's business.

[0102] The method for generating a page framework provided in this embodiment inputs industry page information into the fourth language model to obtain an initial framework output by the fourth language model, divides the initial framework into modules of different themes, and obtains a page framework including at least one theme module. The industry page is understood as a whole through the understanding of the fourth language model, thereby improving the reliability of the page framework.

[0103] In some embodiments of the present disclosure, the above-mentioned industry page information is obtained through the following steps: obtaining at least one initial industry page; detecting whether the conversion rate of each initial industry page in the at least one initial industry page is greater than a preset conversion rate value; in response to the conversion rate of the initial industry page being greater than the preset conversion rate value, using the initial industry page as the industry page information.

[0104] In this optional implementation, the initial industry page is a page of the industry corresponding to the page description information, and the initial industry page can be obtained by crawling with a web crawler.

[0105] In this optional implementation, the conversion rate refers to the ratio of the number of completed conversion behaviors to the total number of clicks on the promotional information within a statistical period. Specifically, the conversion rate is equal to the number of conversions divided by the click-through rate multiplied by 100%. The conversion rate can be used to measure the attractiveness of web page content to visitors and the promotional effect of the website.

[0106] In this embodiment, the preset conversion rate value is an empirical value. For example, the preset conversion rate value is 60%. When the conversion rate of the initial industry page is greater than the preset conversion rate value, it is determined that the conversion rate of the initial industry page is high, which has corresponding appeal to visitors and also has a certain publicity effect.

[0107] In this optional implementation, when the target page is a landing page, by selecting an initial industry page with a higher conversion rate among the initial industry pages as the industry page information, reliable resource support can be provided for the generation of the target page.

[0108] In some optional implementations of the present embodiment, the above-mentioned filling of each subject module in the page frame based on the initial business information to obtain the target page includes: for each subject module in the page frame, using the fourth language model to analyze the initial business information to obtain the image and / or text of the subject module; filling the image and / or text of the subject module into the corresponding area of ​​the subject module.

[0109] In this embodiment, each block of content is filled: Since the large language model does not perform well when performing complex tasks, in order to ensure the quality of online production pages, after obtaining the overall page structure, we divide the page into modules, such as header module, list module, lead conversion module, etc. Each block repeatedly calls the large model to produce the pictures and texts required by each module, and finally completes the content generation of each block.

[0110] In this embodiment, for each subject module in the page frame, the fourth language model is used to analyze the initial business information to obtain the image and / or text of the subject module, including: inputting the subject and initial business information of the subject module in the page frame into the fourth language model to obtain the image and / or text of the subject module.

[0111] The method for obtaining a target page provided in this embodiment uses the fourth language model to analyze initial business information for each subject module in a page frame to obtain images and / or texts of the subject module, and fills the images and / or texts of the subject module into the area where the subject module is located to obtain the target page. Thus, the corresponding area of ​​the subject module is filled by using the fourth language model's ability to understand images and texts, thereby improving the accuracy and reliability of target page generation.

[0112] Optionally, the above-mentioned filling of various subject modules in the page frame based on the initial business information to obtain the target page includes: obtaining the user's industry name and company name based on the page description information, and filling the industry name and company name into corresponding areas of different subject modules of the page frame respectively.

[0113] Further references Figure 5As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a target page generation device. Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0114] like Figure 5 As shown, the target page generation device 500 provided in this embodiment includes: a receiving unit 501, an information extraction unit 502, a generation unit 503, and a filling unit 504. Among them, the above-mentioned receiving unit 501 can be configured to receive page description information input by a user. The above-mentioned information extraction unit 502 can be configured to extract initial business information based on the page description information. The above-mentioned generation unit 503 can be configured to generate a page frame including at least one theme module based on the acquired industry page information. The above-mentioned filling unit 504 can be configured to fill each theme module in the page frame based on the initial business information to obtain the target page.

[0115] In this embodiment, in the target page generating device 500, the specific processing of the receiving unit 501, the information extracting unit 502, the generating unit 503, and the filling unit 504 and the technical effects thereof can be referred to in Figure 1 The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0116] In some optional implementations of this embodiment, the target page generating device 500 further includes: a color extraction unit (not shown in the figure), a color obtaining unit (not shown in the figure), and an adjustment unit (not shown in the figure). The color extraction unit may be configured to extract the initial color of the target page. The color obtaining unit may be configured to obtain an adjusted color based on the initial color. The adjustment unit may be configured to adjust the target page based on the adjusted color to obtain an adjusted target page.

[0117] In some optional implementations of this embodiment, the color extraction unit is further configured to: extract the color of the largest color block in the target page to obtain the initial area color; extract the color of the preset color block in the target page to obtain the initial emphasis color; use the initial area color and the initial emphasis color as the initial color. The color acquisition unit is further configured to: obtain the discarded color based on the color of the pages of different industries; and obtain the adjusted color based on the initial color and the discarded color.

[0118] In some optional implementations of the present disclosure, the target page generation device 500 further includes: a text acquisition unit (not shown in the figure), a text obtaining unit (not shown in the figure), and a text replacement unit (not shown in the figure). Among them, the text acquisition unit can be configured to obtain the selected text after the user performs a selection operation on the text in the target page. The text obtaining unit can be configured to input the selected text into the first largest language model to obtain the modified text output by the first largest language model, and the first largest language model is used to characterize the correspondence between the selected text and the modified text. The text replacement unit can be configured to replace the selected text with the modified text.

[0119] In some optional implementations of the present disclosure, the target page generation device 500 further includes: a picture acquisition unit (not shown in the figure), a picture obtaining unit (not shown in the figure), and a picture replacement unit (not shown in the figure), wherein the picture acquisition unit can be configured to obtain a selected picture after the user performs a selection operation on a picture in the target page. The picture obtaining unit can be configured to input the selected picture into the second largest language model to obtain a modified picture output by the second largest language model, and the second largest language model is used to characterize the correspondence between the selected picture and the modified picture. The picture replacement unit can be configured to replace the selected picture with the modified picture.

[0120] In some optional implementations of the present disclosure, the above-mentioned information extraction unit 502 is further configured to: input the page description information into a third language model to obtain the initial business information output by the third language model, and the third language model is used to characterize the correspondence between the page description information and the initial business information.

[0121] In some optional implementations of the present disclosure, the above-mentioned device 500 also includes: a plug-in input unit (not shown in the figure), which is configured to determine the information input plug-in selected by the user while inputting the page description information into the third language model; obtain business insertion information from the information input plug-in, and input the business insertion information into the third language model.

[0122] In some optional implementations of the present disclosure, the generation unit 503 is further configured to: input the acquired industry page information into a fourth language model to obtain an initial framework output by the fourth language model, wherein the fourth language model is used to characterize the correspondence between the industry page information and the initial framework; and divide the initial framework into modules of different themes to obtain a page framework including at least one theme module.

[0123] In some optional implementations of the present disclosure, the above-mentioned industry page information is obtained through a conversion unit (not shown in the figure), and the above-mentioned conversion unit is configured to: obtain at least one initial industry page; detect whether the conversion rate of each initial industry page in the at least one initial industry page is greater than a preset conversion rate value; in response to the conversion rate of the initial industry page being greater than the preset conversion rate value, use the initial industry page as industry page information.

[0124] In some optional implementations of the present disclosure, the filling unit 504 is further configured to: for each theme module in the page frame, use the fourth language model to analyze the initial business information to obtain the image and / or text of the theme module; and fill the image and / or text of the theme module into the corresponding area of ​​the theme module.

[0125] The target page generation device provided by the embodiment of the present disclosure is as follows: first, the receiving unit 501 receives the page description information input by the user; secondly, the information extraction unit 502 extracts the initial business information based on the page description information; thirdly, the generation unit 503 generates a page frame including at least one theme module based on the acquired industry page information; finally, the filling unit 504 fills each theme module in the page frame based on the initial business information to obtain the target page. Thus, the advertiser only needs to provide the page description information through a simple dialogue, and the creation of the entire target page can be completed based on the current industry page information, which provides an overall layout method for creating the target page, greatly reduces the cost of the advertiser to build the page, improves the generation efficiency of the target page, and improves the quality of the target page.

[0126] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0127] 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.

[0128] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is 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 processing, cellular phones, smart phones, 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 required herein.

[0129] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0130] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0131] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the target page generation method. For example, in some embodiments, the target page generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or a communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the target page generation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the target page generation method in any other appropriate manner (e.g., by means of firmware).

[0132] Various implementations of the systems and techniques described above herein 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), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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.

[0133] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable target page generating 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 may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0134] 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, device, or equipment. 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, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] 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).

[0136] The systems and techniques described herein may 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 may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0137] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0138] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0139] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a target page, the method comprising: Receive page description information input by the user; Inputting the page description information into a third language model to obtain initial business information output by the third language model, wherein the third language model can represent a corresponding relationship between the page description information and the initial business information; Using the fourth language model to obtain industry page information, and based on the industry page information, obtaining an initial framework output by the fourth language model, wherein the fourth language model can characterize the corresponding relationship between the industry page information and the initial framework; Dividing the initial framework into modules of different themes to obtain a page framework including at least one theme module, wherein the fourth language model and the third language model are the same model, and the industry page information is determined based on pages related to the page description information searched on the Internet; Based on the initial business information, each subject module in the page frame is filled to obtain a target page, including: for each subject module in the page frame, the initial business information is analyzed using the fourth language model to obtain an image and / or text of the subject module; and the image and / or text of the subject module is filled into a corresponding area of ​​the subject module.

2. The method according to claim 1, further comprising: Extracting the initial color of the target page; Based on the initial color, obtaining an adjusted color; Based on the adjustment color, the target page is adjusted to obtain an adjusted target page.

3. The method according to claim 2, wherein: The extracting the initial color of the target page comprises: Extract the color of the largest color block in the target page to obtain an initial area color; Extracting the color of a preset color block in the target page to obtain an initial emphasis color; Using the initial area color and the initial emphasis color as initial colors; The obtaining of the adjusted color based on the initial color includes: obtaining a discarded color based on the colors of pages of different industries; Based on the initial color and the discarded color, an adjusted color is obtained.

4. The method according to claim 1, further comprising: Acquire the selected text after the user performs a selection operation on the text in the target page; Inputting the selected text into a first large language model to obtain a modified text output by the first large language model, wherein the first large language model is used to characterize a corresponding relationship between the selected text and the modified text; The selected text is replaced with the modified text.

5. The method according to claim 1, further comprising: Obtaining a selected image after the user performs a selection operation on an image in the target page; Inputting the selected image into a second largest language model to obtain a modified image output by the second largest language model, wherein the second largest language model is used to represent the corresponding relationship between the selected image and the modified image; The modified image is used to replace the selected image.

6. The method according to claim 1, further comprising: While inputting the page description information into the third language model, determining an information input plug-in selected by the user; The service insertion information is obtained from the information input plug-in, and the service insertion information is input into the third language model.

7. According to the method of claim 1, the industry page information is obtained by the following steps: Get at least one initial industry page; Detecting whether the conversion rate of each initial industry page in the at least one initial industry page is greater than a preset conversion rate value; In response to the conversion rate of the initial industry page being greater than a preset conversion rate value, the initial industry page is used as industry page information.

8. A target page generating device, the device comprising: A receiving unit, configured to receive page description information input by a user; an information extraction unit, configured to input the page description information into a third language model to obtain initial business information output by the third language model, wherein the third language model can represent a corresponding relationship between the page description information and the initial business information; A generating unit is configured to obtain industry page information by using a fourth language model, and obtain an initial framework output by the fourth language model based on the industry page information, wherein the fourth language model can represent a corresponding relationship between the industry page information and the initial framework; Dividing the initial framework into modules of different themes to obtain a page framework including at least one theme module, wherein the fourth language model and the third language model are the same model, and the industry page information is determined based on pages related to the page description information searched on the Internet; The filling unit is configured to fill each theme module in the page frame based on the initial business information to obtain a target page, including: using the fourth language model to analyze the initial business information for each theme module in the page frame to obtain a picture and / or text of the theme module; and filling the picture and / or text of the theme module into a corresponding area of ​​the theme module.

9. The device according to claim 8, further comprising: A color extraction unit, configured to extract the initial color of the target page; A color obtaining unit, configured to obtain an adjusted color based on the initial color; The adjustment unit is configured to adjust the target page based on the adjustment color to obtain an adjusted target page.

10. The device according to claim 9, wherein: The color extraction unit is further configured to: extract the color of the largest color block in the target page to obtain an initial area color; extract the color of a preset color block in the target page to obtain an initial emphasis color; use the initial area color and the initial emphasis color as initial colors; The color obtaining unit is further configured to: obtain a discarded color based on the colors of pages of different industries; and obtain an adjusted color based on the initial color and the discarded color.

11. The device according to claim 8, further comprising: A text acquisition unit, configured to acquire selected text after the user performs a selection operation on the text in the target page; a text obtaining unit configured to input the selected text into a first large language model to obtain a modified text output by the first large language model, wherein the first large language model is used to characterize a corresponding relationship between the selected text and the modified text; The text replacement unit is configured to replace the selected text with the modified text.

12. The device according to claim 8, further comprising: A picture acquisition unit is configured to acquire a selected picture after the user performs a selection operation on the picture in the target page; A picture obtaining unit is configured to input the selected picture into a second largest language model to obtain a modified picture output by the second largest language model, wherein the second largest language model is used to represent a corresponding relationship between the selected picture and the modified picture; The picture replacement unit is configured to replace the selected picture with the modified picture.

13. The device according to claim 8, further comprising: a plug-in input unit, configured to determine an information input plug-in selected by a user while inputting the page description information into the third language model; The service insertion information is obtained from the information input plug-in, and the service insertion information is input into the third language model.

14. According to the device according to claim 8, the industry page information is obtained through a conversion unit, and the conversion unit is configured to: obtain at least one initial industry page; detect whether the conversion rate of each initial industry page in the at least one initial industry page is greater than a preset conversion rate value; in response to the conversion rate of the initial industry page being greater than the preset conversion rate value, use the initial industry page as industry page information.

15. An electronic device, characterized in that: include: 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 7.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

17. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images