Landing page processing method and device and computing equipment

Abstract

The invention discloses a landing page processing method and device and computing equipment, and the method comprises the steps: receiving a landing page access request of a user side, and determining a response landing page of the landing page access request; if the response landing page is a baseline landing page, rendering the baseline landing page; if the response landing page is an experimental landing page, rendering the experimental landing page according to the configuration file and the page data of the baseline landing page; the configuration file is used for indicating the operation of generating the experimental landing page from the baseline landing page; performing statistics on conversion indexes of the baseline landing page and the experiment landing page, and determining whether the difference morphological characteristics are influence morphological characteristics of the conversion indexes according to a comparison result between the conversion indexes of the baseline landing page and the experiment landing page; by means of the mode, rendering of the experiment landing page can be completed according to the configuration file and the page data of the baseline landing page in the experiment process, the efficiency of accessing the experiment landing page is improved, the cost of rendering the experiment landing page is reduced, and the efficiency of experiment analysis of the landing page is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technologies, and particularly to a landing page processing method, apparatus, computing device, computer storage medium, and computer program product. Background Art

[0002] Today, with the rapid development of the Internet, profound changes have taken place in the communication media, especially in the forms of advertising communication, technical means, creative techniques, etc., with the continuous intervention of new technologies and the diversification of consumers' information access methods. For Internet advertising, the content is also rich and colorful. Among them, the advertising landing page is a specific web page that users are directed to after clicking on an online advertisement (such as a search engine advertisement, a social media advertisement, a banner advertisement, etc.). The diagnosis, analysis, and optimization of the advertising landing page are crucial for improving the advertising effect and marketing ROI (return on investment). By analyzing the various characteristics of the landing page and optimizing them, the conversion efficiency can be improved. Analyzing the behavior of users on the landing page can help design a page that better meets the needs of users and enhance the user experience and satisfaction.

[0003] In the prior art, by comparing multiple versions of the landing page to determine which version has better performance, that is, determining which version of the landing page performs best according to specific metrics, so as to achieve the feature analysis of the landing page. However, the prior art requires manually modifying the code to generate multiple versions of the landing page, which is inefficient and consumes a large amount of labor costs and related resources. Summary of the Invention

[0004] In view of the above problems, the present application is proposed to provide a landing page processing method, apparatus, computing device, computer storage medium, and computer program product that overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present application, there is provided a landing page processing method, including:

[0006] Receiving a landing page access request from a user terminal, and determining a response landing page for the landing page access request;

[0007] If the response landing page is a baseline landing page, rendering the baseline landing page;

[0008] If the response landing page is an experimental landing page, rendering the experimental landing page according to a configuration file and page data of the baseline landing page;

[0009] Wherein, the configuration file is used to indicate an operation of generating the experimental landing page from the baseline landing page, and there are difference morphological features between the experimental landing page and the baseline landing page;

[0010] Statistically analyze the conversion metrics of the baseline landing page and the experimental landing page. Based on the comparison results between the conversion metrics of the baseline landing page and the experimental landing page, determine whether the differential morphological features are the influencing morphological features of the conversion metrics.

[0011] Optionally, before rendering the experimental landing page according to the configuration file and the page data of the baseline landing page, the method further includes:

[0012] Compare the page data of the baseline landing page with the page data of the experimental landing page to determine the operation information for generating the experimental landing page from the baseline landing page, and generate a configuration file according to the operation information.

[0013] Optionally, before executing the method, it further includes:

[0014] Receive a change request from the configurator for the baseline landing page;

[0015] Generate the page data of the experimental landing page according to the change request and the page data of the baseline landing page.

[0016] Optionally, receiving a change request from the configurator for the baseline landing page further includes:

[0017] Display each morphological feature included in the baseline landing page in the design interface;

[0018] Receive a change request triggered by the configurator's drag operation and / or change operation on the morphological feature in the design interface.

[0019] Optionally, determining whether the differential morphological features are the influencing morphological features of the conversion metrics based on the comparison results between the conversion metrics of the baseline landing page and the experimental landing page further includes:

[0020] Calculate the metric difference between the conversion metrics of the experimental landing page and the baseline landing page corresponding to each experimental sample; wherein, there are the same differential morphological features between the baseline landing page and the experimental landing page corresponding to each experimental sample;

[0021] If the number of experimental samples whose metric differences meet the first preset condition meets the second preset condition, determine the differential morphological features as the influencing morphological features of the conversion metrics.

[0022] Optionally, after determining the differential morphological features as the influencing morphological features of the conversion metrics, the method further includes:

[0023] Extract the to-be-diagnosed feature data from the to-be-diagnosed landing page according to the influencing morphological features;

[0024] Input the to-be-diagnosed feature data into a preset landing page diagnosis model for diagnosis processing to obtain the diagnosis result of the to-be-diagnosed landing page.

[0025] Optionally, the morphological features are divided into morphological features in the audio-visual experience dimension, morphological features in the content information dimension, and morphological features in the conversion interaction dimension;

[0026] The morphological features in the audio-visual experience dimension include: picture quality features, component overlap features, text collocation features, and / or structural layout features;

[0027] The morphological features in the content information dimension include: keyword features and / or component features;

[0028] The morphological features in the conversion interaction dimension include: conversion component position features, conversion component animation effects features, conversion button size features, and / or form features.

[0029] According to another aspect of the present application, there is provided a landing page processing device, including:

[0030] A response module, configured to receive a landing page access request from a user terminal and determine a response landing page for the landing page access request;

[0031] A rendering module, configured to render the baseline landing page if the response landing page is the baseline landing page; and render the experimental landing page according to the configuration file and the page data of the baseline landing page if the response landing page is the experimental landing page;

[0032] Wherein, the configuration file is used to indicate the operation of generating the experimental landing page from the baseline landing page, and there are different morphological features between the experimental landing page and the baseline landing page;

[0033] An analysis module, configured to count the conversion metrics of the baseline landing page and the experimental landing page, and determine whether the different morphological features are influencing morphological features of the conversion metrics according to the comparison result between the conversion metrics of the baseline landing page and the experimental landing page.

[0034] Optionally, the device further includes:

[0035] A configuration module, configured to compare the page data of the baseline landing page with the page data of the experimental landing page, determine the operation information for generating the experimental landing page from the baseline landing page, and generate a configuration file according to the operation information.

[0036] Optionally, the configuration module is further configured to: receive a change request for the baseline landing page from the configurator; generate the page data of the experimental landing page according to the change request and the page data of the baseline landing page.

[0037] Optionally, the configuration module is further configured to: display each morphological feature included in the baseline landing page in a design interface; receive a change request triggered by a drag operation and / or a change operation on the morphological feature by the configurator in the design interface.

[0038] Optionally, the analysis module is further configured to:

[0039] Calculate the index difference of the conversion index between the experimental landing page and the baseline landing page corresponding to each experimental sample; wherein, there are the same differential morphological features between the baseline landing page and the experimental landing page corresponding to each experimental sample.

[0040] If the number of experimental samples whose index difference meets the first preset condition meets the second preset condition, determine the differential morphological feature as the influencing morphological feature of the conversion index.

[0041] Optionally, the device further includes:

[0042] A diagnosis module, configured to extract to-be-diagnosed feature data from the to-be-diagnosed landing page according to the influencing morphological feature; input the to-be-diagnosed feature data into a preset landing page diagnosis model for diagnosis processing, and obtain the diagnosis result of the to-be-diagnosed landing page.

[0043] Optionally, the morphological features are divided into morphological features in the audio-visual experience dimension, morphological features in the content information dimension, and morphological features in the conversion interaction dimension;

[0044] The morphological features in the audio-visual experience dimension include: picture quality features, component overlap features, text collocation features, and / or structural layout features;

[0045] The morphological features in the content information dimension include: keyword features and / or component features;

[0046] The morphological features in the conversion interaction dimension include: conversion component position features, conversion component animation features, conversion button size features, and / or form features.

[0047] According to another aspect of the present application, there is provided a computing device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete communication with each other through the communication bus;

[0048] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operations corresponding to the above-mentioned landing page processing method.

[0049] According to still another aspect of the present application, there is provided a computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform the operations corresponding to the above-mentioned landing page processing method.

[0050] According to yet another aspect of the present application, there is provided a computer program product, including at least one executable instruction, and the executable instruction causes a processor to perform the operations corresponding to the above-mentioned landing page processing method.

[0051] According to the landing page processing method, device, computing device, computer storage medium, and computer program product provided by the embodiments of the present application, by receiving a landing page access request from a user terminal, a response landing page for the landing page access request is determined; if the response landing page is a baseline landing page, the baseline landing page is rendered; if the response landing page is an experimental landing page, the experimental landing page is rendered according to a configuration file and page data of the baseline landing page; wherein the configuration file is used to indicate an operation of generating the experimental landing page from the baseline landing page, and there are different morphological characteristics between the experimental landing page and the baseline landing page; conversion metrics of the baseline landing page and the experimental landing page are statistically analyzed, and based on a comparison result between the conversion metrics of the baseline landing page and the experimental landing page, it is determined whether the different morphological characteristics are influencing morphological characteristics of the conversion metrics. By the above method, there is no need to generate different experimental landing pages in advance for storage, and during the experiment, the experimental landing page can be rendered according to the configuration file and the page data of the baseline landing page, improving the efficiency of accessing the experimental landing page, reducing the cost of rendering the experimental landing page, saving computing resources and storage resources, and thus improving the efficiency of landing page experiment analysis.

[0052] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0054] Figure 1 The flowchart of the landing page processing method provided by an embodiment of the present application is shown;

[0055] Figure 2 The flowchart of the landing page processing method provided by another embodiment of the present application is shown;

[0056] Figure 3 The schematic diagram of the baseline landing page in the example is shown;

[0057] Figure 4 The schematic diagram of the experimental landing page in the example is shown;

[0058] Figure 5 The flowchart of the landing page processing method provided by another embodiment of the present application is shown;

[0059] Figure 6Shows a schematic diagram of the system architecture provided by another embodiment;

[0060] Figure 7 Shows a schematic flowchart of the landing page processing method provided by another embodiment;

[0061] Figure 8 Shows a schematic diagram of the functional structure of the landing page processing device provided by an embodiment of the present application;

[0062] Figure 9 Shows a schematic diagram of the structure of an embodiment of the computing device of the present application. Detailed implementation manners

[0063] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0064] First, the noun terms related to one or more embodiments of the present application are explained.

[0065] Landing page: Also known as the landing page or target page, it is the web page that users are directed to after clicking on an advertisement. It is a key component of an advertising campaign and is usually used to display detailed information about a product or service and to encourage users to take specific actions, such as purchasing, registering, downloading, etc.

[0066] Conversion rate: It refers to the proportion of the number of users who complete a predefined goal within a specific time period to the total number of users who visit the landing page. It is one of the core indicators for measuring the effectiveness of the landing page and can be obtained through the analysis of buried point data.

[0067] Landing page tagging: It is the starting point of event tracking, involving the capture, processing, and sending of specific user behaviors or events within digital products such as websites, APPs, and mini-programs. Its core goal is to provide in-depth user behavior insights for data analysts, data product managers, and data operation personnel, so as to accurately collect data at every key node of user behavior based on business requirements or product requirements. The reporting of advertising landing page tagging is mainly applied to the following business scenarios: First, monitor the browsing, clicking, and bounce situations of the landing page. Marketing personnel can monitor access situations such as browsing, clicking, and bouncing of the landing page, and intuitively and clearly understand the traffic of the landing page; Second, optimize the page structure and content of the landing page. By analyzing heatmaps, measure the browsing and in-page click distributions of the landing page, effectively measure the quality of the landing page, and then optimize the page structure and content of the landing page; Third, measure the conversion ability of the landing page. Analyze the conversion of users entering the landing page at key nodes, measure the conversion ability of the landing page, optimize the landing page, and then improve the conversion rate. The page situations that can be analyzed through tagged data are as follows: Page overview, view the page view count and number of people, in-page click count and number of clickers, and bounce rate of the landing page, and clearly understand the access situation of the landing page; Page conversion, set conversion goals, analyze the conversion of users entering the landing page at key nodes. After setting the conversion goals, the corresponding conversion count and conversion rate can be viewed in the landing page list; Browsing heatmap, through heatmap analysis, the click hotspots of users on the landing page can be intuitively seen to guide the optimization of key areas.

[0068] JSON: A lightweight data interchange format that is easy for humans to read and write, and also easy for machines to parse and generate. It is a subset of JavaScript, but JSON is a language-independent text format, and many programming languages support the parsing and generation of JSON-formatted data.

[0069] Web A / B testing: Also known as A / B testing or split testing, it is a method of determining which version of a web page or application performs better by comparing two or more versions, with the aim of determining which version performs best based on specific metrics (such as revenue per visitor or conversion rate). A / B testing can be applied to increase web page metrics such as conversion rate and registration rate. It is a "prior" experimental system that obtains representative experimental conclusions through scientific experimental design, representativeness of sampling samples, traffic splitting, and small-traffic testing. In addition, A / B testing is not limited to web page optimization and also applies to mobile devices, requiring support for both front-end and back-end testing.

[0070] H5: The abbreviation of HTML5. HTML5 is the abbreviation of HyperText Markup Language 5. HTML5 technology combines and innovates the relevant standards of HTML4.01, meets the requirements of modern network development, and was officially released in 2008. HTML5 consists of different technologies and has been widely used in the Internet, providing more standards for enhancing network applications. Compared with traditional technologies, the syntax features of HTML5 are more obvious and incorporate the content of SVG. These contents can be used more conveniently to process multimedia content in web pages. Moreover, other elements are also incorporated in HTML5 to adjust and modify the original functions and carry out standardization work. A stable version of HTML5 was formed in 2012. The H5 advertisement landing page is an important carrier of Internet advertisement information and is widely spread on the Internet.

[0071] Figure 1 The flowchart of the landing page processing method provided by an embodiment of the present application is shown. As Figure 1 shown, the method includes the following steps:

[0072] Step S110, receive the landing page access request of the user terminal, and determine the response landing page of the landing page access request.

[0073] The method of the embodiment of the present application uses real online traffic for landing page experiments to obtain accurate experimental effects. That is, the landing page access request is a real online access request, and the response landing page is the landing page to be displayed in response to the landing page access request.

[0074] When the user clicks to enter the landing page, the user terminal triggers the landing page access request. After receiving the landing page access request initiated by the user terminal, according to the experimental traffic scheduling strategy, determine whether the response landing page of the landing page access request is the baseline landing page or the experimental landing page.

[0075] Step S120, if the response landing page is the baseline landing page, render the baseline landing page.

[0076] The purpose of the landing page is to provide a dedicated page to display the products, services or information mentioned in the advertisement and encourage users to take specific actions, such as purchasing, registering, downloading or filling out forms, etc. The display form of the landing page will affect the conversion effect. For example, the overall length of the landing page, whether the download button is on the first screen, whether the download button has animation effects, etc., will all affect the conversion effect of the landing page. In the method of the embodiment of the present application, a control experiment is carried out by changing the morphological features in the landing page to determine the morphological features that are more effective for the conversion rate.

[0077] Among them, the baseline landing page is the comparison object in the experiment. For an experimental sample, there is usually only one baseline landing page, while there are multiple experimental landing pages. The experimental landing pages are generated by making changes based on the baseline landing page.

[0078] If it is determined that the response landing page for the landing page access request is the baseline landing page, then render the baseline landing page, and the client displays the rendered baseline landing page. The user performs subsequent operations through the displayed baseline landing page.

[0079] Step S130, if the response landing page is an experimental landing page, render the experimental landing page according to the configuration file and the page data of the baseline landing page.

[0080] If it is determined that the response landing page for the landing page access request is an experimental landing page, then render the experimental landing page, and the client displays the rendered experimental landing page. The user performs subsequent operations through the displayed experimental landing page.

[0081] There are difference morphological features between the experimental landing page and the baseline landing page. The difference morphological features refer to the different morphological features between the experimental landing page and the baseline landing page, which can be having different display elements, or having the same display elements but with different display features for the same display element, or having different display styles, etc. For example, the experimental landing page has an additional button element compared to the baseline landing page, and this button element is the difference morphological feature between the two; another example is that the button element in the experimental landing page has a trigger animation effect while the same button element in the baseline landing page does not have a trigger animation effect, and the trigger animation effect of the button element is a morphological feature and is the difference morphological feature between the two landing pages.

[0082] Among them, the configuration file is used to indicate the operation of generating the experimental landing page from the baseline landing page, that is, the operation of obtaining the experimental landing page based on the baseline landing page. The experimental landing page is obtained by making changes to the baseline landing page, specifically by adding, deleting, and / or changing at least one morphological feature. Write the operation information of generating the experimental landing page from the baseline landing page in the configuration file. When rendering the experimental landing page, read the corresponding configuration file, and implement the operations corresponding to the configuration file during the process of page rendering according to the page data of the baseline landing page, and the rendering of the experimental landing page can be achieved.

[0083] Continuing with the above example, if the configuration file records information such as the landing page identifier, addition instructions, the source, size, position, etc. of the button element, then the baseline landing page is determined based on the landing page identifier, the button element is obtained according to the source of the button element, the change operation on the baseline landing page determined according to the addition instructions is to add a button element, the size and position of the button element added to the baseline landing page are determined according to the size and position of the button element, and then, based on the above operation information and the page data of the obtained baseline landing page, the experimental landing page is rendered.

[0084] Step S140, count the conversion metrics of the baseline landing page and the experimental landing page, and determine whether the difference morphological feature is the influencing morphological feature of the conversion metric according to the comparison result between the conversion metrics of the baseline landing page and the experimental landing page.

[0085] Among them, the conversion metric can refer to the conversion rate, specifically the ratio of the total number of users who complete the specified goal through the response landing page to the total number of users who visit the response landing page. The specified goal can be purchase, registration, download, form filling, etc. For example, if a landing page has 1000 visitors in a day and 50 users complete registration through the landing page, then the conversion rate is 50 / 1000×% = 5%.

[0086] The influencing morphological feature of the conversion metric specifically refers to the morphological feature that affects the conversion metric of the landing page, that is, if the influencing morphological feature included in the landing page is changed, the conversion metric of the landing page will change significantly.

[0087] Based on the user behavior data generated in the baseline landing page and the experimental landing page, count the total number of users who complete the specified goal and the total number of users who visit the page within the preset time period respectively, then calculate the conversion metrics of the baseline landing page and the experimental landing page respectively, and then determine whether there is a difference in the conversion performance between the baseline landing page and the experimental landing page and the size of the difference by comparing the conversion metrics, so as to determine the influence degree of the difference morphological feature on the conversion metric. For example, if the conversion rate of the experimental landing page is much higher than that of the baseline landing page, then the difference morphological feature between the two landing pages is determined as the influencing morphological feature of the conversion metric.

[0088] In summary, according to the landing page processing method provided in this embodiment, a landing page access request from a user terminal is received, and a response landing page for the landing page access request is determined; if the response landing page is a baseline landing page, the baseline landing page is rendered; if the response landing page is an experimental landing page, the experimental landing page is rendered according to the configuration file and the page data of the baseline landing page; wherein, the configuration file is used to indicate the operation of generating the experimental landing page from the baseline landing page, and there are different morphological characteristics between the experimental landing page and the baseline landing page; the conversion metrics of the baseline landing page and the experimental landing page are counted, and according to the comparison result between the conversion metrics of the baseline landing page and the experimental landing page, it is determined whether the different morphological characteristics are the influencing morphological characteristics of the conversion metrics. By the above method, there is no need to generate different experimental landing pages in advance for storage. During the experiment, the experimental landing page can be rendered according to the configuration file and the page data of the baseline landing page, which improves the efficiency of accessing the experimental landing page, reduces the cost of rendering the experimental landing page, saves computing resources and storage resources, and thus improves the efficiency of landing page experiment analysis.

[0089] Figure 2 FIG. shows a flowchart of a landing page processing method provided by another embodiment of the present application. As Figure 2 shown, the method includes the following steps:

[0090] Step S210, receiving a change request from a configurator for the baseline landing page; generating page data for the experimental landing page according to the change request and the page data of the baseline landing page.

[0091] The configurator refers to the relevant user who designs the experimental landing page. The configurator completes the design of the baseline landing page by making changes to the baseline landing page. The change request includes a morphological feature addition request, a morphological feature deletion request, and a morphological feature change request.

[0092] By changing the page data of the baseline landing page, the page data of the experimental landing page is generated. The page data refers to the resource data of each morphological feature included in the page. Specifically, if the change request is a morphological feature addition request, the resource data of the morphological feature to be added is added to the page data of the baseline landing page to obtain the page data of the experimental landing page; if the change request is a morphological feature deletion request, the resource data of the morphological feature to be deleted is deleted from the page data of the baseline landing page to obtain the page data of the experimental landing page; if the change request is a morphological feature change request, the resource data of the morphological feature to be changed in the page data of the baseline landing page is changed to obtain the page data of the experimental landing page.

[0093] In an alternative approach, a design interface is provided for the configurator. Various morphological features of the baseline landing page are displayed in the design interface, facilitating the configurator to add, delete, or modify the morphological features included in the baseline landing page. Specifically, each morphological feature included in the baseline landing page is displayed in the design interface; a change request triggered by the configurator's drag operation and / or modification operation on the morphological feature in the design interface is received. Among them, each morphological feature displayed in the design interface is in an editable state. The configurator can trigger a morphological feature addition request by dragging other morphological features into the editable baseline landing page, thereby adding the other morphological feature to the baseline landing page; the configurator can also trigger a morphological feature deletion request by dragging and removing the editable morphological feature in the baseline landing page, thereby deleting some morphological features in the baseline landing page; the configurator can also trigger a morphological feature modification request through the modification operation on the morphological feature, thereby implementing the modification of the morphological feature in the baseline landing page. In this way, an intuitive experimental landing page design method is provided for the configurator, which helps to improve the design efficiency of the experimental landing page.

[0094] Figure 3 FIG. shows a schematic diagram of the baseline landing page in the example, Figure 4 FIG. shows a schematic diagram of the experimental landing page in the example. By comparing Figure 3 and Figure 4 it can be seen that the baseline landing page and the experimental landing page contain the same title, body text, and background image. An additional picture 41 is added to the experimental landing page compared to the baseline landing page. By comparing the conversion effects of the baseline landing page and the experimental landing page, the impact of picture 41 on the conversion effect can be determined.

[0095] Step S220: Compare the page data of the baseline landing page with the page data of the experimental landing page, determine the operation information for generating the experimental landing page from the baseline landing page, and generate a configuration file according to the operation information.

[0096] Compare the page data of the baseline landing page with the page data of the experimental landing page, determine the differences between them, determine the operation information for generating the experimental landing page from the baseline landing page according to the differences, and generate the operation information into a configuration file. The operation information specifically includes: the baseline landing page identifier, change instruction, identifier, size, position, source, etc. of the morphological feature to be changed. Among them, the configuration file can specifically be a JSON file. By storing the operation configuration information in a JSON file, the parsing efficiency of the configuration file is improved.

[0097] An example of a configuration file is as follows:

[0098] {

[0099] "page_id": 321312321, / / Identifier of the baseline landing page to be changed

[0100] "instruction": "add", / / Operation instruction (add)

[0101] "width": "100px", / / Element width

[0102] "height": "200px" / / Element height

[0103] "type": "img" / / Element type (image)

[0104] "x": "50px" / / Element position (horizontal coordinate)

[0105] "y": "300px" / / Element position (vertical coordinate)

[0106] "url": "http: / / www.XXX.com" / / Image resource link

[0107] }

[0108] In an alternative approach, a conversion script is used to compare the page data of the baseline landing page and the experimental landing page and generate a configuration file.

[0109] Step S230: Receive the landing page access request from the client and determine the response landing page for the landing page access request.

[0110] Specifically, determine the response landing page for the landing page access request according to the traffic distribution strategy. The traffic distribution strategy includes the traffic distribution ratio. For example, if the traffic for the baseline landing page and the experimental landing page is each configured to account for 50%, then the online real access traffic is evenly distributed to the baseline landing page and the experimental landing page.

[0111] Step S240: If the response landing page is the baseline landing page, render the baseline landing page.

[0112] If it is determined that the response landing page for the landing page access request is the baseline landing page, then perform page rendering processing according to the page data of the baseline landing page. The client displays the rendered baseline landing page, and the user performs subsequent operations through the displayed baseline landing page.

[0113] Step S250: If the response landing page is the experimental landing page, render the experimental landing page according to the configuration file and the page data of the baseline landing page.

[0114] If it is determined that the response landing page for the landing page access request is the experimental landing page, then render the experimental landing page. The client displays the rendered experimental landing page, and the user performs subsequent operations through the displayed experimental landing page.

[0115] There are different morphological features between the experimental landing page and the baseline landing page. The different morphological features refer to the different morphological features existing between the experimental landing page and the baseline landing page. Preferably, there is only one different morphological feature between the experimental landing page and the baseline landing page. By using the method of controlling variables, the single morphological feature in the baseline landing page is changed, so as to analyze the influence of the single morphological feature on the performance of the landing page, and then accurately determine the page morphological features affecting the conversion index.

[0116] Specifically, the morphological features are divided into morphological features in the audio-visual experience dimension, morphological features in the content information dimension, and morphological features in the conversion interaction dimension. The morphological features in the audio-visual experience dimension include: picture quality features, component overlap features, text collocation features, and / or structural layout features. The picture quality features may include: the clarity of the core picture on the page, the recognition of the main body and content, the picture size, the picture dimension, and the picture mosaic situation. The component overlap feature refers to the stacking situation of each element component. The text collocation feature may be the text contrast value. The structural layout feature may be the number of screens on the page. The morphological features in the content information dimension include: keyword features and / or component features. The keyword feature refers to the situation where the text in the landing page contains keywords. The component feature refers to the situation where the landing page contains industry-preferred components. The morphological features in the conversion interaction dimension include: the position feature of the conversion component, the dynamic effect feature of the conversion component, the size feature of the conversion button, and / or the form feature. The conversion component is a component used to complete the conversion goal, such as a download button, an installation button, etc.

[0117] Among them, the configuration file is used to indicate the operation of obtaining the experimental landing page based on the baseline landing page. The experimental landing page is obtained by changing the baseline landing page. Write the operation information of generating the experimental landing page from the baseline landing page into the configuration file. When rendering the experimental landing page, read the corresponding configuration file and implement the operation corresponding to the configuration file during the process of page rendering according to the page data of the baseline landing page, so as to render the experimental landing page.

[0118] In step S260, count the conversion indexes of the baseline landing page and the experimental landing page, and calculate the index difference between the conversion indexes of the experimental landing page and the baseline landing page corresponding to each experimental sample. If the number of experimental samples whose index difference meets the first preset condition meets the second preset condition, determine the different morphological feature as the morphological feature affecting the conversion index.

[0119] Among them, there are the same different morphological features between the baseline landing page and the experimental landing page corresponding to each experimental sample.

[0120] In the method of the embodiments of the present application, the influence of a single morphological feature on the conversion index is studied through multiple experimental samples, and the difference morphological features between the baseline landing page and the experimental landing page corresponding to multiple experimental samples in the same group are consistent. For example, in order to analyze the influence of including a conversion button on the first screen on the conversion index, multiple different advertisements are used as experimental samples. Compared with the baseline landing page, the experimental landing page corresponding to each advertisement experimental sample adds a conversion button on the first screen, that is, the difference morphological feature between the experimental landing page and the baseline landing page is the conversion button located on the first screen.

[0121] For the baseline landing page and the experimental landing page corresponding to each experimental sample in the same group, online access traffic is evenly distributed, and based on the user behavior data, the conversion index of the baseline landing page and the conversion index of the experimental landing page are statistically calculated. The index difference is obtained by subtracting the conversion index of the baseline landing page from the conversion index of the experimental landing page. If the proportion of the number of experimental samples whose index difference in the same group reaches the first ratio (i.e., meets the first preset condition) to the total number of experimental samples reaches the second ratio (i.e., meets the second preset condition), it is determined that the difference morphological feature between the baseline landing page and the experimental landing page corresponding to this group of experimental samples will affect the conversion index. For example, there is no download button on the first screen of the baseline landing page, and the experimental landing page adds a download button on the first screen based on the baseline landing page. Then the difference morphological feature is the download button on the first screen. There are a total of 10 experimental samples, the first ratio is 40%, and the second ratio is 70%. When the conversion rate difference between the experimental landing page and the baseline landing page corresponding to at least 7 experimental samples reaches 40%, it indicates that the conversion performance of the landing page with this interactive form of the download button on the first screen is better, and it is determined that the download button on the first screen is the influencing morphological feature of the conversion rate.

[0122] Step S270, according to the influencing morphological feature, extract the to-be-diagnosed feature data from the to-be-diagnosed landing page; input the to-be-diagnosed feature data into a preset landing page diagnosis model for diagnosis processing to obtain the diagnosis result of the to-be-diagnosed landing page.

[0123] The diagnosis and analysis of the landing page can provide data-based insights to help marketers make more scientific and accurate decisions. Through diagnosis and analysis, problems leading to user bounce can be identified and solved, reducing the loss of potential customers. An efficient landing page can become a competitive advantage.

[0124] Based on this, the method of the embodiments of the present application further provides an automatic diagnosis mechanism for landing pages, which can be applied to business scenarios that require identifying defects and optimizable parts in landing pages. According to the impact morphological features determined through experiments, descriptive information of the impact morphological features, i.e., the to-be-diagnosed feature data, is extracted for the to-be-diagnosed landing page, and then the to-be-diagnosed feature data is input into a preset landing page diagnosis model for processing. The landing page diagnosis model automatically outputs a diagnosis result, and the diagnosis result is used to indicate whether the layout of each morphological feature of the to-be-diagnosed landing page is reasonable. Based on the diagnosis result, the defects existing in the to-be-diagnosed landing page and the morphological features to be optimized can be determined.

[0125] Specifically, take screenshots of the to-be-diagnosed landing page in a scrolling manner, call the OCR (Optical Character Recognition) service and the AI analysis service to obtain the text content, text coordinates, text colors, sizes of the reference images in the page, image sizes, etc. in the page, and obtain the to-be-diagnosed feature data in the content information dimension; analyze the positions of each component in the to-be-diagnosed landing page, and parse to obtain the length of the landing page, the stacking situation of components, etc., and obtain the to-be-diagnosed feature data related to the page structure features; by parsing and calculating the conversion components (such as the size and position of the download button), determine whether the first screen of the page contains conversion components and whether the conversion components have animation effects, etc., and obtain the to-be-diagnosed feature data in the conversion interaction dimension.

[0126] The landing page diagnosis model performs diagnosis processing according to the diagnosis conditions corresponding to each morphological feature, that is, determines whether the to-be-diagnosed feature data meets the corresponding diagnosis conditions; if it meets, it is determined that the morphological feature layout is reasonable; if it does not meet, it is determined that the morphological feature is a defect and a morphological feature to be optimized in the to-be-diagnosed landing page.

[0127] Specifically, for the audio-visual experience dimension, determine whether the core image of the page is clear, whether the main body and content are clearly distinguishable, whether the image size does not exceed the threshold, whether the image dimension does not exceed the threshold, whether there is no mosaic, whether there is no stacking of each element component, whether the text comparison value is not lower than the threshold, and whether the number of screens of the page does not exceed the regulations of the industry; for the content information dimension, determine whether the text in the landing page contains industry keywords, and determine whether the landing page contains industry-preferred components, such as whether the landing page in the e-commerce industry contains coupon components; for the conversion interaction dimension, determine whether the conversion component is on the first screen of the landing page, whether the conversion component has animation effects (breathing animation effect, heartbeat animation effect, flashing animation effect), whether the width of the conversion button is less than 50% of the screen width, whether the form is visible on the first screen, and whether the number of form items is reasonable.

[0128] In an optional manner, the to-be-diagnosed feature data is stored through a semantic dataset. The following is an example of a semantic dataset:

[0129] {

[0130] "main_color":"#172B4D", / / Overall page color

[0131] "page_height":"800px", / / Page length

[0132] "page_comp_count":4, / / Number of page components

[0133] "ocr_content_length":234 / / Length of text content

[0134] "ocr_font":"Used for testing" / / Text content included in the page

[0135] "page_style_type":"5" / / Page type

[0136] .... / / More

[0137] }

[0138] It should be noted that each diagnostic condition adopted by the landing page diagnosis model is also obtained through experimental statistics. The conversion indicators of the landing page with various characteristic data are obtained through a large number of experiments, and the diagnostic conditions are set according to the characteristic data when the conversion indicators are the highest.

[0139] In an optional manner, after obtaining the diagnostic result of the landing page to be diagnosed, corresponding optimization suggestions are given for the data to be diagnosed that do not meet the diagnostic conditions. For example, the diagnostic condition for the page length is: the page length is less than 1400 pixels. If the page length of the landing page to be diagnosed is 1500 pixels, an optimization suggestion that the landing page length should not exceed 1400 pixels is given.

[0140] For example, for a landing page to be diagnosed, the following diagnostic results and optimization suggestions are output: First, regarding the content information dimension, the diagnostic result: Structured content is not introduced on the page, and the ecological support requirements are not yet met. Optimization suggestion: It is recommended that one of the award-winning conditions for the marketing page in the transportation industry is that the page introduces structured content with qualified quality; Second, regarding the conversion interaction dimension, the diagnostic result: The conversion layout of the page is reasonable; The number of phone numbers in the first two screens of the page is reasonable, which is conducive to user conversion; The number of consultations in the first two screens of the page is reasonable, which is conducive to user conversion; The number of forms in the first two screens of the page is reasonable, which is conducive to user conversion; The number of button dynamic effects in the first two screens of the page is reasonable; The number of dynamic effect style components and animated pictures in the first two screens of the page is reasonable.

[0141] In summary, according to the landing page processing method provided in this embodiment, a design interface is provided for the configurator, enabling the configurator to design an experimental landing page based on the baseline landing page through simple drag-and-drop operations or modification operations, simplifying the design work of the experimental landing page and improving the efficiency of the configurator in designing the experimental landing page; by comparing the page data differences between the baseline landing page and the experimental landing page, an operation configuration file for obtaining the experimental landing page based on the baseline landing page is automatically generated, which can improve the generation efficiency and accuracy of the configuration file; when the response landing page of the access request is the experimental landing page, the configuration file is read for view rendering of the experimental landing page, improving the efficiency of accessing the experimental landing page, reducing the cost of rendering the experimental landing page, and saving computing resources and storage resources; by statistically analyzing the experimental results of multiple experimental samples, the accuracy of the influencing morphological features can be ensured; based on the influencing morphological features determined through experimental analysis, diagnostic conditions are set, and the landing page diagnosis model automatically completes the diagnosis of the feature data of the landing page to be diagnosed according to the diagnostic conditions, enabling automatic diagnosis of the landing page to be diagnosed, and can also output a diagnostic report and optimization suggestions, which helps the relevant business parties optimize the landing page form and helps the advertiser design a page that better meets the user needs.

[0142] Figure 5 The flowchart of the landing page processing method provided in another embodiment of the present application is shown. As Figure 5 shown, the method mainly includes a visualization operation link, a configuration generation link, and a landing page coverage link. In the visualization operation link, the configurator provides a design draft, which is a copy of the baseline landing page, and a new experimental landing page is created by modifying the baseline landing page copy; in the configuration generation link, the page data of the newly created experimental landing page is exported, and the conversion script compares the page data of the experimental landing page with the page data of the baseline landing page to generate a configuration file. The R & D configuration mainly configures the experimental samples, including configuring all the baseline landing pages that need to perform A / B experiments. The experimental configuration mainly configures the traffic distribution strategy during the experiment; in the landing page coverage link, when the access traffic is distributed to the experimental landing page, the experimental renderer realizes the content coverage of the response landing page through configuration file parsing, page parsing, and instruction control, thereby completing the rendering of the experimental landing page.

[0143] Figure 6The figure shows a schematic diagram of the system architecture provided by another embodiment. The system includes a material layer, a parsing layer, a data layer, an analysis layer, and an application layer. The material layer is used to receive the landing page to be diagnosed for diagnostic processing. The parsing layer provides landing page parsing services and extracts the to-be-diagnosed feature data of the landing page to be diagnosed by using feature services, image parsing services, and the AI platform. The data layer is used to manage the to-be-diagnosed feature data extracted by the parsing layer, including page length and other landing page features. The analysis layer is mainly used to automatically diagnose the to-be-diagnosed feature data and execute the judgment of the to-be-diagnosed data by using quality inspection services and defect analysis services. The application layer is used to output the diagnosis result, and the diagnosis result may include a list of defect features and a list of optimization suggestions.

[0144] Figure 7 The figure shows a schematic flowchart of the landing page processing method provided by another embodiment. As Figure 7 shown, the extraction of landing page feature data includes: the advertisement landing page passes through the feature extraction service to obtain a semanticized data set. The landing page analysis includes: analyzing the influencing morphological features through A / B testing, defining feature indicators according to the experimental results, and constructing a landing page diagnosis model. The landing page diagnosis model analyzes the semanticized data set through the analysis service and outputs a landing page diagnosis report. The advertiser optimizes the page according to the report to regenerate the advertisement landing page, and finally conducts the advertisement landing page delivery.

[0145] Figure 8 The figure shows a schematic diagram of the functional structure of the landing page processing device provided by an embodiment of the present application. As Figure 8 shown, the device includes:

[0146] A response module 810, configured to receive a landing page access request from a user terminal and determine the response landing page of the landing page access request.

[0147] A rendering module 820, configured to render the baseline landing page if the response landing page is the baseline landing page; and render the experimental landing page according to the configuration file and the page data of the baseline landing page if the response landing page is the experimental landing page.

[0148] Wherein, the configuration file is used to indicate the operation of generating the experimental landing page from the baseline landing page, and there are different morphological features between the experimental landing page and the baseline landing page.

[0149] An analysis module 830, configured to count the conversion metrics of the baseline landing page and the experimental landing page, and determine whether the different morphological features are the influencing morphological features of the conversion metrics according to the comparison result between the conversion metrics of the baseline landing page and the experimental landing page.

[0150] In an optional manner, the device further includes:

[0151] A configuration module is used to compare the page data of the baseline landing page with the page data of the experimental landing page, determine the operation information for generating the experimental landing page from the baseline landing page, and generate a configuration file according to the operation information.

[0152] In an optional manner, the configuration module is further used to: receive a change request from the configurator for the baseline landing page; generate the page data of the experimental landing page according to the change request and the page data of the baseline landing page.

[0153] In an optional manner, the configuration module is further used to: display each morphological feature included in the baseline landing page in the design interface; receive a change request triggered by the configurator's dragging operation and / or changing operation on the morphological feature in the design interface.

[0154] In an optional manner, the analysis module 830 is further used to:

[0155] Calculate the index difference of the conversion index between the experimental landing page corresponding to each experimental sample and the baseline landing page; among them, there are the same differential morphological features between the baseline landing page and the experimental landing page corresponding to each experimental sample;

[0156] If the number of experimental samples whose index difference meets the first preset condition meets the second preset condition, determine the differential morphological feature as the influencing morphological feature of the conversion index.

[0157] In an optional manner, the device further includes:

[0158] A diagnosis module is used to extract the to-be-diagnosed feature data from the to-be-diagnosed landing page according to the influencing morphological feature; input the to-be-diagnosed feature data into a preset landing page diagnosis model for diagnosis processing to obtain the diagnosis result of the to-be-diagnosed landing page.

[0159] In an optional manner, the morphological features are divided into morphological features in the audio-visual experience dimension, morphological features in the content information dimension, and morphological features in the conversion interaction dimension;

[0160] The morphological features in the audio-visual experience dimension include: picture quality feature, component overlap feature, text collocation feature, and / or structure layout feature;

[0161] The morphological features in the content information dimension include: keyword feature and / or component feature;

[0162] The morphological features in the conversion interaction dimension include: conversion component position feature, conversion component dynamic effect feature, conversion button size feature, and / or form feature.

[0163] In summary, according to the landing page processing device provided in this embodiment, there is no need to generate different experimental landing pages in advance for storage. During the experiment, the experimental landing page can be rendered according to the configuration file and the page data of the baseline landing page, which improves the efficiency of accessing the experimental landing page, reduces the cost of rendering the experimental landing page, saves computing resources and storage resources, and thus improves the efficiency of landing page experiment analysis.

[0164] An embodiment of the present application provides a non-volatile computer storage medium, and the computer storage medium stores at least one executable instruction or computer program, and the executable instruction or computer program can enable a processor to execute the operations corresponding to the landing page processing method in any of the above method embodiments.

[0165] An embodiment of the present application provides a computer program product, and the computer program product includes at least one executable instruction or computer program, and the executable instruction or computer program can enable a processor to execute the operations corresponding to the landing page processing method in any of the above method embodiments.

[0166] Figure 9 The structural schematic diagram of an embodiment of the computing device of the present application is shown, and the specific implementation of the computing device is not limited in the specific embodiments of the present application.

[0167] As Figure 9 shown, the computing device may include: a processor 902, a communication interface 904, a memory 906, and a communication bus 908.

[0168] Among them: the processor 902, the communication interface 904, and the memory 906 complete mutual communication through the communication bus 908. The communication interface 904 is used to communicate with network elements of other devices such as clients or other servers. The processor 902 is used to execute the program 910, and specifically can execute the relevant steps in the above-mentioned embodiment of the landing page processing method for the computing device.

[0169] Specifically, the program 910 may include program code, and the program code includes computer operation instructions.

[0170] The processor 902 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0171] A memory 906 for storing a program 910. The memory 906 may include a high-speed RAM memory and may also include non-volatile memory, such as at least one magnetic disk memory.

[0172] The program 910 can be specifically used to cause the processor 902 to execute the landing page processing method in any of the above method embodiments. For the specific implementation of each step in the program 910, reference can be made to the corresponding steps and the descriptions in the corresponding units in the landing page processing embodiments, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices and modules can refer to the corresponding process descriptions in the foregoing method embodiments, which will not be repeated here.

[0173] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings provided herein. The structure required to construct such systems will be apparent from the above description. In addition, the embodiments of the present application are not directed to any particular programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the descriptions of specific languages above are for disclosing the best mode of the present application.

[0174] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and technologies have not been shown in detail so as not to obscure the understanding of this specification.

[0175] Similarly, it should be understood that, in order to streamline the present application and assist in understanding one or more of the various inventive aspects, in the foregoing description of the exemplary embodiments of the present application, the various features of the embodiments of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting the intention that the claimed subject matter of the present application requires more features than are expressly recited in each claim. Rather, as reflected by the claims, the inventive aspects lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present application.

[0176] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be adopted to combine all the features disclosed in this specification (including the accompanying claims, abstract and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0177] In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of this application and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0178] Each component embodiment of this application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of this application. This application can also be implemented as a device or apparatus program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0179] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A landing page processing method, comprising: Receive a landing page access request from a user terminal, and determine a response landing page for the landing page access request; If the response landing page is a baseline landing page, render the baseline landing page; If the response landing page is an experimental landing page, render the experimental landing page according to the configuration file and the page data of the baseline landing page; The configuration file is used to instruct the operation of generating the experimental landing page from the baseline landing page, and there are different morphological features between the experimental landing page and the baseline landing page; The conversion indicators of the baseline landing page and the experimental landing page are counted, and according to the comparison result between the conversion indicators of the baseline landing page and the experimental landing page, it is determined whether the difference morphological feature is an influencing morphological feature of the conversion indicator.

2. The method according to claim 1, wherein: Before rendering the experimental landing page according to the configuration file and the page data of the baseline landing page, the method further includes: The page data of the baseline landing page is compared with the page data of the experimental landing page to determine the operation information of generating the experimental landing page from the baseline landing page, and the configuration file is generated according to the operation information.

3. The method according to claim 2, wherein: Before the method is performed, it further comprises: Receiving a request from a configuration party to change the baseline landing page; The page data of the experimental landing page is generated according to the change request and the page data of the baseline landing page.

4. The method according to claim 3, wherein: The receiving a configuration party's request to modify the baseline landing page further includes: Display the various morphological features of the baseline landing page in the design interface; Receive a change request triggered by the configuration party's drag operation and / or change operation on the morphological feature in the design interface.

5. The method according to any one of claims 1 to 4, wherein: The step of determining whether the difference morphological feature is an influencing morphological feature of the conversion index according to the comparison result between the conversion index of the baseline landing page and the experimental landing page further includes: Calculating the index difference between the conversion index of the experimental landing page and the baseline landing page corresponding to each experimental sample; wherein the baseline landing page and the experimental landing page corresponding to each experimental sample have the same difference morphological characteristics; If the number of experimental samples whose index difference satisfies the first preset condition meets the second preset condition, the difference morphological feature is determined as the influencing morphological feature of the conversion index.

6. The method according to claim 5, wherein: After determining the difference morphological feature as the influencing morphological feature of the conversion index, the method further comprises: Extracting feature data to be diagnosed from the landing page to be diagnosed according to the influencing morphological features; The characteristic data to be diagnosed is input into a preset landing page diagnosis model for diagnosis processing to obtain a diagnosis result of the landing page to be diagnosed.

7. The method according to claim 3, wherein: The morphological features are divided into morphological features of the audition experience dimension, morphological features of the content information dimension, and morphological features of the conversion interaction dimension; The morphological features of the audition experience dimension include: picture quality features, component overlap features, text matching features and / or structural layout features; The morphological features of the content information dimension include: keyword features and / or component features; The morphological features of the conversion interaction dimension include: conversion component position features, conversion component animation features, conversion button size features and / or form features.

8. A landing page processing device, comprising: A response module is used to receive a landing page access request from a user terminal and determine a response landing page for the landing page access request; A rendering module, used for rendering the baseline landing page if the response landing page is a baseline landing page; If the response landing page is an experimental landing page, render the experimental landing page according to the configuration file and the page data of the baseline landing page; The configuration file is used to instruct the operation of generating the experimental landing page from the baseline landing page, and there are different morphological features between the experimental landing page and the baseline landing page; The analysis module is used to count the conversion indicators of the baseline landing page and the experimental landing page, and determine whether the difference morphological feature is an influencing morphological feature of the conversion indicator based on the comparison result between the conversion indicators of the baseline landing page and the experimental landing page.

9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the landing page processing method as described in any one of claims 1-7.

10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the landing page processing method as described in any one of claims 1-7.

11. A computer program product, comprising at least one executable instruction, wherein the executable instruction enables a processor to perform operations corresponding to the landing page processing method as described in any one of claims 1-7.

Images