Method, device and system for generating landing page and storage medium

Abstract

The invention discloses a landing page generation method, device and system and a storage medium, and relates to the technical field of Internet. The method comprises the following steps: in response to detection of a landing page generation request sent by a client, obtaining at least two preset theme style combinations; for each preset theme style combination, determining a prediction effect score of the preset theme style combination based on historical promotion data corresponding to the preset theme style combination; selecting a target theme style combination from the preset theme style combinations based on the prediction effect scores; and generating a target landing page based on the target theme and the target style in the target theme style combination, and sending the target landing page to the client. According to the embodiment of the invention, the problem that the theme and style of the landing page are relatively fixed is solved, and the marketing promotion effect of the landing page is improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, system and storage medium for generating a landing page. Background Art

[0002] With the rapid development of the Internet industry, landing pages are gradually being chosen by more and more Internet platforms. Landing pages attract potential users with their concise and guiding style, which can effectively reduce page bounce rates and thus increase advertising conversion rates.

[0003] Landing pages usually include outer pages and inner pages. The outer pages are mainly used to receive advertising clicks or searches from within and outside the site, while the inner pages are mainly used to display extended content related to the click content or search content.

[0004] In the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art:

[0005] Traditional landing pages are designed and laid out by developers based on themes and styles, and different themes often share the same style of landing pages. However, users frequently browse landing pages with homogeneous themes and styles, which can easily lead to aesthetic fatigue, thus reducing the marketing and promotion effect of landing pages. Summary of the invention

[0006] Embodiments of the present invention provide a method, device, system and storage medium for generating a landing page to solve the problem that the theme and style of the landing page are relatively fixed and improve the marketing and promotion effect of the landing page.

[0007] According to an embodiment of the present invention, a method for generating a landing page is provided, the method comprising:

[0008] In response to detecting a landing page generation request sent by a client, obtaining at least two preset theme style combinations;

[0009] For each preset theme style combination, based on the historical promotion data corresponding to the preset theme style combination, determine the predicted effect score of the preset theme style combination;

[0010] Based on the predicted effect scores, selecting a target theme style combination from the preset theme style combinations;

[0011] Based on the target theme and the target style in the target theme style combination, a target landing page is generated, and the target landing page is sent to the client.

[0012] According to another embodiment of the present invention, a device for generating a landing page is provided, the device comprising:

[0013] A preset theme style combination acquisition module, used to acquire at least two preset theme style combinations in response to detecting a landing page generation request sent by a client;

[0014] A prediction effect score determination module, configured to determine, for each preset theme style combination, a prediction effect score of the preset theme style combination based on historical promotion data corresponding to the preset theme style combination;

[0015] A target theme style combination determination module, configured to select a target theme style combination from each of the preset theme style combinations based on each of the predicted effect scores;

[0016] A target landing page sending module is used to generate a target landing page based on a target theme and a target style in the target theme style combination, and send the target landing page to the client.

[0017] According to another embodiment of the present invention, a system for generating a landing page is provided, and the system for generating a landing page includes: a client and a terminal device;

[0018] The client is used to send a landing page generation instruction to a terminal device, and receive a target landing page sent by the terminal device;

[0019] The terminal device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a landing page described in any embodiment of the present invention.

[0020] According to another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a landing page described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention, by responding to detecting a landing page generation request sent by the client, determines the predicted effect scores corresponding to each preset theme style combination based on the historical promotion data corresponding to at least two preset theme style combinations, selects a target theme style combination from each preset theme style combination based on each predicted effect score, and generates a target landing page based on the target theme and target style in the target theme style combination, and sends the target landing page to the client, thereby realizing the combined screening of multiple landing page themes and multiple landing page styles, solving the problem of relatively fixed traditional landing page themes and styles, and helping to improve the marketing promotion effect of the landing page.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a method for generating a landing page provided by an embodiment of the present invention;

[0025] Figure 2 A flowchart of another method for generating a landing page provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a landing page generation device provided by an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of the structure of a landing page generation system provided by an embodiment of the present invention;

[0028] Figure 5 An architecture diagram of a specific example of a landing page generation system provided by an embodiment of the present invention;

[0029] Figure 6 A schematic diagram of the structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "preset", "target", "reference", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Figure 1 This is a flowchart of a method for generating a landing page provided by an embodiment of the present invention. This embodiment is applicable to the case of generating a landing page for a client. The method can be executed by a landing page generating device. The landing page generating device can be implemented in the form of hardware and / or software. The landing page generating device can be configured in a terminal device. Figure 1 As shown, the method includes:

[0033] S110. In response to detecting a landing page generation request sent by a client, obtaining at least two preset theme style combinations.

[0034] In a specific embodiment, the landing page generation request may be generated and sent by the client based on a preset operation input by the user. Exemplary preset operations include but are not limited to click operations, sliding operations, and search operations, etc., and the generation method of the landing page generation request is not limited here.

[0035] Specifically, the preset theme style combination is used to represent the combination of the preset theme and the preset style. The preset theme can be used to represent the subject content of the landing page, and the preset style can be used to represent the display style and structural style of the landing page.

[0036] Exemplarily, the subject content includes but is not limited to item categories, item brands, promotional activities, etc. For example, the item category may be facial cleanser or notebook, etc.

[0037] Specifically, the display style can be used to characterize the display attributes of each element component in the preset style, such as display attributes including but not limited to component category, component color, component size, text content, etc. The structural style can be used to characterize the structural attributes of each element component in the preset style, such as structural attributes including but not limited to component quantity, component position, display order, etc.

[0038] In a specific embodiment, each preset theme style combination may be pre-set, or may be generated based on a combination of a theme list and a style list. The theme list includes multiple preset themes, and the style list includes multiple preset styles. The preset styles may be pre-customized uploaded by the user, or may be generated based on a combination of multiple display styles and multiple structural styles corresponding to multiple element components. The preset styles are configured based on a combination of multiple display styles and multiple structural styles as much as possible.

[0039] S120. For each preset theme style combination, based on the historical promotion data corresponding to the preset theme style combination, determine the predicted effect score of the preset theme style combination.

[0040] In a specific embodiment, historical promotion data includes historical combination promotion data, and the historical combination promotion data represents the promotion data corresponding to the preset theme and preset style in the preset theme style combination; wherein the promotion data includes at least two promotion quantities of historical exposure, historical clicks and historical conversions, and the predicted effect score is a predicted click-through rate score, a predicted conversion rate score or a predicted statistical score, and the predicted statistical score represents the statistical value corresponding to the predicted click-through rate score and the predicted conversion rate score.

[0041] In one embodiment, when the promotion data includes historical exposure and historical clicks, the predicted effect score is the predicted click-through rate score; when the promotion data includes historical clicks and historical conversions, the predicted effect score is the predicted conversion rate score, specifically, the predicted conversion rate score is the predicted click-through rate score; when the promotion data includes historical exposure and historical conversions, the predicted effect score is the predicted conversion rate score, specifically, the predicted conversion rate score is the predicted exposure-conversion rate score.

[0042] Taking the predicted effect score as the predicted click rate score as an example, the predicted click rate score satisfies the formula:

[0043]

[0044] Among them, score ij Represents the preset theme style combination z ij The corresponding predicted click-through rate score, clk ij Represents the preset theme style combination z ij The corresponding historical click volume, imp ij Represents the preset theme style combination z ij The corresponding historical exposure. Among them, the preset theme style combination z ij Represents the combination of the i-th preset theme and the j-th preset style.

[0045] In one embodiment, when the promotion data includes historical exposure, historical clicks, and historical conversions, the predicted effect score is a predicted statistical score. Wherein, the statistical value includes, but is not limited to, a maximum value, a minimum value, or an average value, and the statistical value is not limited here, and can be customized according to actual needs.

[0046] In another specific embodiment, the historical promotion data also includes historical theme promotion data, the historical theme promotion data represents promotion data of all preset styles corresponding to the preset theme, and the predicted effect score is determined based on an upper bound confidence algorithm.

[0047] Among them, the upper confidence bound (UCB) algorithm is an optimistic MAB (Multi-Armed Bandit) algorithm. The UCB algorithm uses the Chernoff-HoeffdingBound law to measure the gap between the predicted effect score and the historical effect score.

[0048] Taking the predicted effect score as the predicted click-through rate score as an example, assuming that each exposure clicks click1,…,click i , …, click n is an independent and identically distributed random variable with a value of {0, 1}, where n represents the historical exposure, click i Indicates whether the i-th exposure is clicked, i.e. click i The value of is 0 or 1. represents the historical sampling mean, p represents the distribution mean, and the Chernoff-Hoff bounding law proves that the historical sampling mean and the distribution mean satisfy the formula:

[0049]

[0050] If δ is taken as Then we can get:

[0051]

[0052] Right now

[0053]

[0054] So The probability of being true is that when n is large enough, The difference between and p is small enough. The UCB algorithm optimistically as the mean of the distribution.

[0055] In this example, the predicted CTR score satisfies the formula:

[0056]

[0057] Among them, imp sum Represents the historical exposure of all styles corresponding to the i-th preset theme.

[0058] The advantage of this setting is that, on the basis of the historical effect score, an exploration score δ is added to measure the uncertainty factor, thereby improving the reliability of the predicted effect score.

[0059] On the basis of the above embodiments, specifically, based on the historical promotion data corresponding to the preset theme style combination, the predicted effect score of the preset theme style combination is determined, including: when the historical promotion data corresponding to the preset theme style combination meets the preset promotion conditions, based on the historical promotion data corresponding to the preset theme style combination, the predicted effect score of the preset theme style combination is determined; when the historical promotion data corresponding to the preset theme style combination does not meet the preset promotion conditions, based on the historical promotion data corresponding to the preset theme style combination, the reference effect score of the preset theme style combination is determined, and based on the preset proportional coefficient and the reference effect score, the predicted effect score is determined; wherein the preset promotion conditions include that at least one promotion quantity in the historical promotion data is greater than the preset promotion threshold corresponding to each promotion quantity, and the preset proportional coefficient is greater than one.

[0060] Specifically, the preset promotion thresholds corresponding to each promotion quantity may be the same or different. The specific parameter value of each preset promotion threshold is not limited here, and can be customized according to actual needs.

[0061] Specifically, when the reference effect score is not 0, the product of the preset proportion score and the reference effect score is used as the predicted effect score of the preset theme style combination; when the reference effect score is 0, the preset score is used as the predicted effect score of the preset theme style combination. Exemplarily, the preset score can be 0.8, and the preset score is not limited here, and can be customized according to actual needs.

[0062] If the historical promotion data meets the preset promotion conditions, it means that the number of promotions in the historical promotion data is sufficient, so the predicted effect score can accurately express the promotion value of the preset theme style combination. However, if the historical promotion data does not meet the preset promotion conditions, such as the preset theme in the preset theme style combination is a newly added theme and / or the preset style is a newly added style, it means that the number of promotions in the historical promotion data is small, so the predicted effect score will have a relatively large uncertainty and cannot accurately express the promotion value of the preset theme style combination.

[0063] In order to improve the accuracy of the predicted effect scores of preset theme style combinations that do not meet the preset promotion conditions, the embodiments of the present invention proportionally amplify or modify the calculated reference effect scores so that preset theme style combinations with a smaller number of promotions can also get exposure opportunities, thereby increasing the number of promotions in the historical promotion data for the newly added themes and / or new styles in the preset theme style combinations.

[0064] S130: Select a target theme style combination from various preset theme style combinations based on the prediction effect scores.

[0065] Specifically, the preset subject style combination with the largest prediction effect score is used as the target subject style combination.

[0066] S140. Generate a target landing page based on the target theme and target style in the target theme style combination, and send the target landing page to the client.

[0067] The technical solution of this embodiment, by responding to the detection of a landing page generation request sent by the client, determines the predicted effect scores corresponding to each preset theme style combination based on the historical promotion data corresponding to at least two preset theme style combinations, selects a target theme style combination from each preset theme style combination based on each predicted effect score, and generates a target landing page based on the target theme and target style in the target theme style combination, and sends the target landing page to the client, thereby realizing the combined screening of multiple landing page themes and multiple landing page styles, solving the problem of relatively fixed traditional landing page themes and styles, and helping to improve the marketing promotion effect of landing pages.

[0068] Figure 2 This is a flowchart of another method for generating a landing page provided by an embodiment of the present invention. This embodiment further refines the "obtaining at least two preset theme style combinations" in the above embodiment. Figure 2 As shown, the method includes:

[0069] S210. In response to detecting a landing page generation request sent by a client, obtaining at least two preset themes corresponding to the personalized identifier in the landing page generation request.

[0070] In this embodiment, the personalized identifier includes an advertisement position identifier and / or a user identifier.

[0071] Specifically, the ad slot identifier is used to uniquely identify the display position of the landing page in the entire display page, and the user identifier is used to uniquely identify the user operation corresponding to the landing page generation request. Exemplarily, the unique identifier can be composed of one or more of text, numbers, uppercase letters, lowercase letters and special characters. The composition form of the unique identifier is not limited here, and it can be customized according to actual needs.

[0072] In a specific embodiment, when the personalized identifier includes an advertisement slot identifier, at least two preset themes corresponding to the advertisement slot identifier are obtained based on a preset mapping list, wherein the preset mapping list includes at least two preset themes corresponding to each advertisement slot identifier.

[0073] In a specific embodiment, when the personalized identifier includes a user identifier, a user portrait corresponding to the user identifier is obtained, and at least two preset themes corresponding to the user portrait are obtained. Exemplarily, the user portrait includes but is not limited to gender, age, consumption habits, and the like.

[0074] In a specific embodiment, when the personalized identifier includes an ad slot identifier and a user identifier, the intersection of at least two preset themes corresponding to the ad slot identifier and at least two preset themes corresponding to the user identifier is used as the at least two preset themes corresponding to the personalized identifier. For example, the preset themes corresponding to the ad slot identifier include Theme 1, Theme 2, and Theme 3, and the preset themes corresponding to the user identifier include Theme 2, Theme 3, and Theme 4, and the preset themes corresponding to the personalized identifier include Theme 2 and Theme 3.

[0075] S220: For each preset theme, obtain at least one preset style corresponding to the preset theme, and generate at least one preset theme style combination based on the preset theme and each preset style.

[0076] In one specific embodiment, at least one corresponding preset style is pre-set for each preset theme. In another specific embodiment, all styles generated by the combined configuration are used as preset styles corresponding to the preset theme.

[0077] To ensure that at least two preset theme style combinations are obtained, in another specific embodiment, the number of preset themes corresponding to the personalized identifier is at least one, and the number of preset styles corresponding to the preset themes is at least two.

[0078] S230: For each preset theme style combination, based on the historical promotion data corresponding to the preset theme style combination, determine the predicted effect score of the preset theme style combination.

[0079] S240: Select a target theme style combination from various preset theme style combinations based on the prediction effect scores.

[0080] S250. Generate a target landing page based on the target theme and target style in the target theme style combination, and send the target landing page to the client.

[0081] S230-S250 in this embodiment are similar to those in the above embodiment. Figure 1The S120 - S140 shown in FIG. 1 are identical or similar to each other and will not be described in detail here.

[0082] On the basis of the above embodiments, specifically, the method also includes: determining a predicted topic score of a preset topic based on historical topic promotion data corresponding to the preset topic, and deleting the preset topic from the topic list when the predicted topic score is less than a topic score threshold; and / or determining a predicted style score of a preset style based on historical style promotion data corresponding to a preset style, and deleting the preset style from the style list when the predicted style score is less than a style score threshold.

[0083] Specifically, the predicted topic score is a topic click rate score, a topic conversion rate score or a topic statistical score. Exemplarily, the topic score threshold is 0.6. The topic score threshold is not limited here and can be customized according to actual needs.

[0084] Specifically, the predicted style score is a style click rate score, a style conversion rate score or a style statistical score. Exemplarily, the style score threshold is 0.6. The style score threshold is not limited here and can be customized according to actual needs.

[0085] The advantage of this setting is that by updating and removing pre-stored preset themes and / or preset styles, the combination quality of preset theme style combinations can be improved, the number of combinations of preset theme combinations can be reduced, and the generation efficiency of landing pages can be improved.

[0086] On the basis of the above embodiment, specifically, sending the target landing page to the client includes: implanting promotion data into the target landing page, obtaining the target landing page after the embedding, and sending the target landing page after the embedding to the client; the method also includes: updating the historical promotion data corresponding to the preset theme style combination based on the real-time promotion data sent by the client.

[0087] Specifically, the promotional embedding data is used to characterize the embedding data related to the promotional data. For example, when the promotional embedding data includes exposure embedding data, the exposure embedding data includes that the display time of the target landing page is greater than the preset time threshold. Exemplarily, the preset time threshold can be 5s. When the promotional embedding data includes click embedding data, the click embedding data includes that the outer page of the target landing page is clicked and / or the inner page of the target landing page is clicked. When the promotional embedding data includes conversion embedding data, the conversion embedding data includes that the conversion component of the target landing page is clicked. Exemplarily, the conversion component includes but is not limited to downloading, installation, registration, real-name authentication, ordering or payment, etc.

[0088] The advantage of this setting is that the rapid return of real-time promotion data and the real-time update of historical promotion data can effectively improve the generation quality of the target landing pages corresponding to subsequent landing page generation requests, thereby further improving the marketing promotion effect of the landing pages.

[0089] The technical solution of this embodiment obtains at least two preset themes corresponding to the personalized identifier in the landing page generation request; wherein the personalized identifier includes an ad slot identifier and / or a user identifier, and for each preset theme, obtains at least one preset style corresponding to the preset theme, and generates at least one preset theme style combination based on the preset theme and each preset style, thereby solving the problem that the landing page cannot be generated in a personalized manner, and realizes the generation and display of different landing pages in different ad slots and / or for different users, further reducing the degree of homogeneity of the landing pages, thereby further improving the marketing promotion effect of the landing pages.

[0090] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0091] The following is an embodiment of a landing page generation device provided in an embodiment of the present invention. The device and the landing page generation method of the above embodiment belong to the same inventive concept. For details not fully described in the embodiment of the landing page generation device, reference can be made to the contents of the landing page generation method in the above embodiment.

[0092] Figure 3 This is a schematic diagram of a landing page generation device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a preset theme style combination acquisition module 310, a predicted effect score determination module 320, a target theme style combination determination module 330 and a target landing page sending module 340.

[0093] The preset theme style combination acquisition module 310 is used to acquire at least two preset theme style combinations in response to detecting a landing page generation request sent by a client;

[0094] The prediction effect score determination module 320 is used to determine the prediction effect score of each preset theme style combination based on the historical promotion data corresponding to the preset theme style combination;

[0095] A target theme style combination determination module 330 is used to select a target theme style combination from each preset theme style combination based on each prediction effect score;

[0096] The target landing page sending module 340 is used to generate a target landing page based on the target theme and target style in the target theme style combination, and send the target landing page to the client.

[0097] The technical solution of this embodiment realizes the combined screening of multiple landing page themes and multiple landing page styles, solves the problem that traditional landing page themes and styles are relatively fixed, and helps to improve the marketing and promotion effect of landing pages.

[0098] In an optional embodiment, the historical promotion data includes historical combination promotion data, and the historical combination promotion data represents promotion data corresponding to a preset theme and a preset style in a preset theme style combination;

[0099] Among them, the promotion data includes at least two promotion quantities among historical exposure volume, historical click volume and historical conversion volume. The predicted effect score is the predicted click rate score, the predicted conversion rate score or the predicted statistical score. The predicted statistical score represents the statistical value corresponding to the predicted click rate score and the predicted conversion rate score.

[0100] In an optional embodiment, the historical promotion data also includes historical theme promotion data, the historical theme promotion data represents promotion data of all preset styles corresponding to the preset theme, and the predicted effect score is determined based on an upper bound confidence algorithm.

[0101] In an optional embodiment, the prediction effect score determination module 320 is specifically configured to:

[0102] In the case where the historical promotion data corresponding to the preset theme style combination meets the preset promotion conditions, determining the predicted effect score of the preset theme style combination based on the historical promotion data corresponding to the preset theme style combination;

[0103] In the case where the historical promotion data corresponding to the preset theme style combination does not meet the preset promotion conditions, a reference effect score of the preset theme style combination is determined based on the historical promotion data corresponding to the preset theme style combination, and a predicted effect score is determined based on the preset proportional coefficient and the reference effect score;

[0104] The preset promotion conditions include that at least one promotion quantity in the historical promotion data is greater than a preset promotion threshold value corresponding to each promotion quantity, and the preset proportional coefficient is greater than one.

[0105] In an optional embodiment, the landing page generation request includes a personalized identifier, and the preset theme style combination acquisition module 310 is specifically used to:

[0106] Obtain at least two preset themes corresponding to the personalized identifier in the landing page generation request; wherein the personalized identifier includes an ad space identifier and / or a user identifier;

[0107] For each preset theme, at least one preset style corresponding to the preset theme is obtained, and at least one preset theme style combination is generated based on the preset theme and the preset styles.

[0108] In an optional embodiment, the device further comprises:

[0109] a topic deletion module, configured to determine a predicted topic score of a preset topic based on historical topic promotion data corresponding to the preset topic, and to delete the preset topic from the topic list when the predicted topic score is less than a topic score threshold; and / or,

[0110] The style deletion module is used to determine the predicted style score of the preset style based on the historical style promotion data corresponding to the preset style, and delete the preset style from the style list when the predicted style score is less than the style score threshold.

[0111] In an optional embodiment, the target landing page sending module 340 is specifically used to:

[0112] Implant promotion point embedding data into the target landing page, obtain the target landing page after embedding, and send the target landing page after embedding to the client;

[0113] The device also includes:

[0114] Based on the real-time promotion data received from the client, the historical promotion data corresponding to the preset theme style combination is updated.

[0115] The landing page generation device provided in the embodiment of the present invention can execute the landing page generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] Figure 4 A structural diagram of a landing page generation system provided for an embodiment of the present invention. Specifically, the landing page generation system 400 includes a client 410 and a terminal device 420, wherein the client 410 is used to send a landing page generation instruction to the terminal device 420, and receive a target landing page sent by the terminal device 420.

[0117] The terminal device 420 in this embodiment can be configured with the landing page generation device in the above embodiment, and can provide services for the landing page generation method in the above embodiment.

[0118] On the basis of the above-mentioned embodiment, specifically, the landing page generation system also includes a landing page management platform 420, which is used to store, update and maintain the styles or element components uploaded by users.

[0119] Figure 5The following is an architecture diagram of a specific example of a landing page generation system provided by an embodiment of the present invention. Specifically, the landing page generation system includes a client, a terminal device, and a landing page management platform, wherein the landing page management platform is used to store, maintain, and update styles uploaded by users, combine and configure element components uploaded by users, generate styles, and store both styles uploaded by users and styles generated by the landing page management platform in a style list.

[0120] In this example, the terminal device provides a tracking service and a screening service. Specifically, the client sends a landing page generation request to the terminal device, the terminal device pulls the style list from the landing page management platform, and sends multiple preset themes in the theme list and multiple styles in the style list to the screening service respectively. The screening service configures multiple preset theme style combinations based on multiple preset themes and multiple preset style combinations, and for each preset theme style combination, based on the historical promotion data corresponding to the preset theme style combination, determines the predicted effect score of the preset theme style combination, and based on each predicted effect score, selects a target theme style combination from each preset theme style combination, and feeds the target theme style combination back to the terminal device. The terminal device generates a target landing page based on the target theme and target style in the target theme style combination, and uses the tracking service to implant promotion tracking data into the target landing page, and sends the obtained target landing page after tracking to the client.

[0121] Based on the promotion embedding data in the target landing page, the client collects real-time promotion data of the target landing page, writes the real-time promotion data into the embedding data table, and sends the embedding data table to the terminal device. The terminal device updates the historical promotion data corresponding to the target theme style combination in the screening service in real time based on the received embedding data table.

[0122] Figure 6 A schematic diagram of the structure of a terminal device provided for one embodiment of the present invention. The terminal device 420 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 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0123] like Figure 4As shown, the terminal device 420 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the terminal device 420 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through the bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0124] A number of components in the terminal device 420 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the terminal device 420 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0125] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for generating a landing page provided in the above embodiment.

[0126] In some embodiments, the method for generating a landing page provided in the above embodiments may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the terminal device 420 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the method for generating a landing page described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for generating a landing page in any other appropriate manner (e.g., by means of firmware).

[0127] 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.

[0128] The computer program for implementing the method for generating a landing page of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0130] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0132] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0133] 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 described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0134] The above specific implementations do not constitute a limitation on the protection scope of the present invention. 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 invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a landing page, characterized in that: include: In response to detecting a landing page generation request sent by a client, obtaining at least two preset theme style combinations; For each preset theme style combination, based on the historical promotion data corresponding to the preset theme style combination, determine the predicted effect score of the preset theme style combination; Based on the predicted effect scores, selecting a target theme style combination from the preset theme style combinations; Based on the target theme and the target style in the target theme style combination, a target landing page is generated, and the target landing page is sent to the client.

2. The method according to claim 1, characterized in that The historical promotion data includes historical combination promotion data, and the historical combination promotion data represents promotion data corresponding to the preset theme and the preset style in the preset theme style combination; Among them, the promotion data includes at least two promotion quantities among historical exposure volume, historical click volume and historical conversion volume, and the predicted effect score is a predicted click-through rate score, a predicted conversion rate score or a predicted statistical score, and the predicted statistical score represents the statistical value corresponding to the predicted click-through rate score and the predicted conversion rate score.

3. The method according to claim 2, characterized in that The historical promotion data also includes historical theme promotion data, and the historical theme promotion data represents promotion data of all preset styles corresponding to the preset theme. The predicted effect score is determined based on an upper bound confidence algorithm.

4. The method according to claim 1, characterized in that: The step of determining the predicted effect score of the preset theme style combination based on the historical promotion data corresponding to the preset theme style combination includes: In the case where the historical promotion data corresponding to the preset theme style combination meets the preset promotion condition, determining the predicted effect score of the preset theme style combination based on the historical promotion data corresponding to the preset theme style combination; In the case where the historical promotion data corresponding to the preset theme style combination does not meet the preset promotion condition, determining the reference effect score of the preset theme style combination based on the historical promotion data corresponding to the preset theme style combination, and determining the predicted effect score based on a preset proportional coefficient and the reference effect score; The preset promotion condition includes that at least one promotion quantity in the historical promotion data is greater than a preset promotion threshold value corresponding to each promotion quantity, and the preset proportional coefficient is greater than one.

5. The method according to claim 1, characterized in that The landing page generation request includes a personalized identifier, and obtaining at least two preset theme style combinations includes: Obtain at least two preset themes corresponding to the personalized identifier in the landing page generation request; wherein the personalized identifier includes an ad space identifier and / or a user identifier; For each preset theme, at least one preset style corresponding to the preset theme is obtained, and at least one preset theme style combination is generated based on the preset theme and each of the preset styles.

6. The method according to claim 5, characterized in that The method further comprises: Determine a predicted topic score of the preset topic based on the historical topic promotion data corresponding to the preset topic, and delete the preset topic from the topic list if the predicted topic score is less than a topic score threshold; and / or, Based on the historical style promotion data corresponding to the preset style, a predicted style score of the preset style is determined, and when the predicted style score is less than a style score threshold, the preset style is deleted from the style list.

7. The method according to any one of claims 1 to 6, characterized in that: The sending the target landing page to the client includes: Implant promotion embedding data into the target landing page, obtain the target landing page after embedding, and send the target landing page after embedding to the client; The method further includes: updating the historical promotion data corresponding to the preset theme style combination based on the received real-time promotion data sent by the client.

8. A device for generating a landing page, characterized in that: include: A preset theme style combination acquisition module, used to acquire at least two preset theme style combinations in response to detecting a landing page generation request sent by a client; A prediction effect score determination module, configured to determine, for each preset theme style combination, a prediction effect score of the preset theme style combination based on historical promotion data corresponding to the preset theme style combination; A target theme style combination determination module, configured to select a target theme style combination from each of the preset theme style combinations based on each of the predicted effect scores; A target landing page sending module is used to generate a target landing page based on a target theme and a target style in the target theme style combination, and send the target landing page to the client.

9. A landing page generation system, characterized in that: The landing page generation system includes: a client and a terminal device; The client is used to send a landing page generation instruction to a terminal device, and receive a target landing page sent by the terminal device; The terminal device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a landing page according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a landing page according to any one of claims 1 to 7 when executed.

Images