CN110175121B - A method, device and computer-readable storage medium for determining officially launched pages - Google Patents

Abstract

The application provides a formal online page determining method, a formal online page determining device and a computer readable storage medium. By implementing the scheme of the application, flow distribution is respectively carried out on a plurality of different test pages, and simultaneously, the online test is carried out on the plurality of different test pages, and then the online effect is analyzed to determine the formally online page, so that the data reliability of the page test and the page optimization efficiency are improved, and the development cost is reduced.

Description

A method, device and computer-readable storage medium for determining officially launched pages

Technical field

The present application relates to the field of electronic technology, and in particular to a method, device and computer-readable storage medium for determining an official online page.

Background technique

With the continuous development of terminal technology, the popularity of terminals is getting higher and higher, and users are using terminals more and more frequently in their daily lives. Accordingly, users' needs for terminals are becoming more diverse and complex. In order to To better meet user needs, terminal product developers need to continuously iteratively optimize the application products on the terminal.

A typical product optimization scenario is the optimization scenario of application pages. In the current page optimization scenario, product developers usually determine the page optimization direction based on internal analysis of user needs, and then develop the corresponding optimized pages and then directly proceed to the official page optimization scenario. online. However, in actual applications, the product developer's analysis of user needs may not necessarily be in line with the actual situation. This may lead to a decrease in the user conversion rate of the application product compared to the old version after the new page version is launched. On the other hand, It may be necessary to continue iterative optimization, resulting in reduced page optimization efficiency and increased development costs.

Contents of the invention

The embodiments of this application provide a method, device and computer-readable storage medium for determining the official online page, which can at least solve the problem of user conversion rate and user conversion rate caused by insufficient understanding of the actual needs of users when product developers optimize application pages in related technologies. The problem of reduced page optimization efficiency and increased development costs.

The first aspect of the embodiment of this application provides a method for determining an official online page, including:

Configure multiple different test pages;

Allocate test traffic to the plurality of different test pages respectively;

Put each test page online at the same time on the corresponding allocated test traffic, and collect statistics on the page effect representation data after each test page goes online;

Based on the comparison results obtained by comparing the performance characterization data of all pages, the official online page is determined.

The second aspect of the embodiment of this application provides a device for determining an official online page, including:

Configuration module, used to configure multiple different test pages;

An allocation module, configured to allocate test traffic to the plurality of different test pages;

A statistics module, used to put each test page online at the same time on the corresponding allocated test traffic, and count the page effect representation data after each test page goes online;

The determination module is used to determine the official online page based on the comparison results obtained by comparing the performance characterization data of all pages.

The third aspect of the embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned third aspect of the embodiment of the present application is implemented. On the one hand, the steps in the method of determining the official launch page are provided.

The fourth aspect of the embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for determining the official online page provided by the first aspect of the embodiment of the present application is implemented. Each step.

It can be seen from the above that according to the method, device and computer-readable storage medium for determining the official online page provided by this application plan, multiple different test pages are first configured, then test traffic is allocated to multiple different test pages, and then each The test pages are launched simultaneously on the corresponding allocated test traffic, and the page performance representation data of each test page after it is online is collected. Finally, based on the comparison results obtained by comparing the performance representation data of all pages, the official online page is determined. Through the implementation of this application plan, traffic is allocated to multiple different test pages respectively, and multiple different test pages are tested online at the same time, and then the online effect is analyzed to determine the official online page, which improves the data credibility of the page test. And page optimization efficiency reduces development costs.

Description of drawings

Figure 1 is a basic flow chart of a method for determining an officially launched page provided by the first embodiment of the present application;

Figure 2 is a basic flow diagram of another method for determining an officially launched page provided by the first embodiment of the present application;

Figure 3 is a basic flow diagram of another method for determining an officially online page provided by the first embodiment of the present application;

Figure 4 is a detailed flow chart of the method for determining the official online page provided by the second embodiment of the present application;

Figure 5 is a schematic diagram of a program module of a device for determining an official online page provided by the third embodiment of the present application;

FIG. 6 is a schematic structural diagram of an electronic device provided by the fourth embodiment of the present application.

Detailed ways

In order to make the purpose, features, and advantages of the invention of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the description The embodiments are only some of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the scope of protection of this application.

In order to solve the defects in related technologies that product developers do not fully grasp the actual needs of users when optimizing application pages, resulting in reduced user conversion rates and page optimization efficiency, and increased development costs, the first embodiment of the present application provides a method of officially launching Page determination method. Figure 1 is a basic flow chart of the method for determining the official online page provided in this embodiment. The method for determining the official online page includes the following steps:

Step 101. Configure multiple different test pages.

In this embodiment, the product developer can obtain multiple alternative page display solutions after analyzing user needs. Since it is difficult to guarantee that the selected page will best meet the actual needs of the user using traditional solutions, In this embodiment, multiple page display solutions are tested online to obtain the page with the best effect. It should be understood that the page in this embodiment may be a page of an application store, game, browser, etc.

Optionally, configuring multiple different test pages includes: first configuring one of multiple different test pages, and the test page includes multiple cards; if the remaining test pages have the same cards as the configured test page, then When configuring the remaining test pages in sequence, the same cards in the configured test pages are directly extracted and reused to complete the configuration of multiple different test pages.

Specifically, cards can be presented on the page in the form of a rectangle, and one card contains all information related to a certain type of topic. In addition, the multiple different test pages in this embodiment include the following situations: first, different test pages only have different card styles at a certain position within the page; second, different test pages only have different card styles at certain positions within the page. The styles are different; thirdly, the different test pages are completely different as a whole. However, it should be understood that the functions of multiple different test pages in this embodiment may be the same, but all cards in each test page are different from each other when taken as a whole.

It should be noted that when there are multiple different test pages, if the configuration process of each test page is kept independent, that is, there is no correlation between the configurations of all pages, then the cards of all test pages need to be configured separately. configuration. However, in actual applications, usually only some of the card styles in multiple different test pages are different, so there are many common cards among the test pages. If the configuration process of each test page is completely separated according to the aforementioned method, , then the shared cards need to be reconfigured repeatedly, which will increase the page configuration workload. Based on this, in this embodiment, a page is first configured, and then when configuring subsequent pages, the card shared by the page to be configured and the configured page is first found, and the shared card in the configured page is directly reused. Only the proprietary card of the page to be configured needs to be designed separately, and so on, until the configuration of all test cards is completed, thus greatly reducing the workload of page configuration. It should also be noted that in this embodiment, the cards used in each test page are common cards, that is, the cards included in all test pages are of the same type.

Step 102: Allocate test traffic to multiple different test pages.

Specifically, in this embodiment, different test pages need to be delivered to different users at the same time for comparative testing. Therefore, test traffic needs to be allocated to each test page. It should be understood that the online test in this embodiment is a low-traffic test, that is, users who maintain large traffic still run the current version of the page, and a small number of separated users are used to launch the test page. For example, when 80% of users run the application, the page to be optimized remains the old version page, and 20% of the users are used for page online testing. This means that these 20% of users are assigned to multiple different test pages using preset rules. It is understood that the traffic delivered by each test page does not overlap with each other.

It should be noted that, in a preferred implementation, allocating test traffic to multiple different test pages includes: allocating the same amount of test traffic to multiple different test pages. That is to say, the test traffic is equally distributed to each test page. For example, 20% of the total traffic is allocated to four test pages. Using an equal distribution method, each test page is allocated 5% of the traffic.

Optionally, allocating test traffic to multiple different test pages includes: demarcating a traffic set whose user label is the preset user label from all available traffic; and in the delineated traffic set, assigning multiple different test pages respectively Allocate test traffic.

Specifically, the user tag in this embodiment is used to identify user attributes, and the user attributes include one or more of gender, region, age, membership level, etc. In this embodiment, the user group of a specific user tag is first delineated, and then the user group corresponding to the user tag is diverted for page online testing to improve the directivity of the page online testing. For example, the male user group is selected from all user groups, and then the selected male user group is distributed to each test page.

Step 103: Launch each test page simultaneously on the corresponding allocated test traffic, and collect statistics on the page effect representation data of each test page after it goes online.

Specifically, in this embodiment, the long-term page online testing process is concentrated in the same time dimension for execution, realizing the only control of the time variable during the page online testing process, saving the time cost of page testing, and Improved the data reliability of page testing. It should be understood that the page effect representation data in this embodiment is used to indicate the online effect of the test page under the allocated test traffic, and may specifically include downloads, consumption, shares and other indicators that can measure the page content conversion rate.

Step 104: Determine the official online page based on the comparison results obtained by comparing the performance characterization data of all pages.

Specifically, this embodiment conducts online testing on multiple different test pages at the same time dimension, and then conducts a comprehensive analysis of the online effects of each page, and then determines the official online page based on the analysis results, that is, the page used for page version optimization. , improves the data credibility of page testing and page optimization efficiency, and reduces development costs.

Figure 2 shows a flow chart of another method for determining an officially online page provided by this embodiment. Optionally, based on the comparison results obtained by comparing all page effect characterization data, determining the official online page specifically includes the following steps. :

Step 201: Compare all page effect representation data and determine the optimal page effect representation data;

Step 202: Determine the test page corresponding to the optimal page effect representation data as the optimal test page;

Step 203: Determine the official online page based on the optimal test page.

Specifically, in this embodiment, the official online page is determined based on the page with the best page effect. In one implementation, the optimal test page is determined as the official online page, that is, multiple different test pages Compare the online results, and use the page with the best online results as the final version that will be officially launched.

In another optional implementation of this embodiment, determining the official online page based on the optimal test page includes: obtaining the card effect representation data of each card in the optimal test page, where the test page includes multiple cards; based on all cards Based on the effect characterization data, adjust the position of each card in the optimal test page to obtain the official online page.

Specifically, after obtaining the test page with the best online effect among all test pages, the online effect of each card in the page is also obtained, and then based on the effect of each card, the card position in the page is adjusted, that is, Based on the optimal test page, the page effect is further optimized to obtain a page with better effect, which will be used as the official online page. It should be noted that, in some implementations, each card can be arranged in sequence in the vertical or horizontal direction of the page according to the order of card effects.

In some implementations of this embodiment, the method of allocating test traffic to multiple different test pages is: delineate traffic sets whose user labels are different preset user labels from all available traffic; In the collection, test traffic is allocated to multiple different test pages.

Specifically, different from the above-mentioned shunting and publishing of pages in only one user group, in this implementation, all test pages are shunted in multiple different user groups, and then the pages are shunted in multiple user groups. test. Correspondingly, Figure 3 shows a flow chart of another method for determining the officially online page provided by this embodiment. Optionally, the official online page is determined based on the comparison results obtained by comparing all page effect characterization data. Specifically, it includes the following steps:

Step 301: Compare all page effect representation data under each traffic set based on the traffic set as a unit, and obtain multiple optimal page effect representation data;

Step 302: Determine the test pages corresponding to multiple optimal page effect representation data as optimal test pages;

Step 303: Determine the official online page based on the determined multiple optimal test pages.

Specifically, when multiple user groups conduct online testing of multiple different test pages, correspondingly, a page with the best online effect can be obtained for each user group, and then based on the multiple optimal results determined Use the best pages to determine the online page. Since a wider range of sample types are considered when conducting online testing, the final determined online page will have greater applicability among the user group.

It should be noted that, optionally, based on the multiple optimal test pages determined, determining the official online page specifically includes the following two methods:

Method 1: Compare the optimal page performance representation data corresponding to multiple optimal test pages, determine the better optimal test page among the multiple optimal test pages based on the comparison results, and combine the better optimal test page Confirmed to be the official online page.

Method 2: Obtain the card effect representation data of each card in each optimal test page, where the test page includes multiple cards, and the card types of each test page are the same; determine the optimal card effect representation data of each type of card; Determine the optimal cards of each type corresponding to the performance representation data of each optimal card, and the position information of each type of optimal card in the page to which it belongs; multiplex the optimal cards of each type to a blank page according to the position information, and get Officially launched page.

Specifically, when the types of cards used in all test pages are the same, the card effect representation data of each card in each optimal test page is first determined, and then the optimal card effect representation data of each type of card is obtained, and then Determine the position of the optimal card corresponding to each optimal card effect representation data in the page to which it belongs. Finally, according to the determined position, re-layout the optimal cards of each type on the blank page to obtain the official online page. It should be noted that the same card type here can be understood as the same functional type of the card, and is not limited to the same card style.

Based on the technical solutions of the above embodiments of the present application, multiple different test pages are first configured, and then test traffic is allocated to the multiple different test pages respectively, and then each test page is launched simultaneously on the corresponding allocated test traffic. And the page performance representation data of each test page after it goes online is collected. Finally, based on the comparison results obtained by comparing the performance representation data of all pages, the official online page is determined. Through the implementation of this application plan, traffic is allocated to multiple different test pages respectively, and multiple different test pages are tested online at the same time, and then the online effect is analyzed to determine the official online page, which improves the data credibility of the page test. And page optimization efficiency reduces development costs.

The method in Figure 4 is a refined method for determining the official online page provided by the second embodiment of the present application. The method for determining the official online page includes:

Step 401: Configure one of multiple different test pages; all test pages contain the same type of cards.

Step 402: When configuring the remaining test pages, extract cards of the same type from the configured test pages and reuse them in preset positions to complete the configuration of multiple different test pages.

In this embodiment, the types of cards included in all pages are the same, so that one page can be configured first, and then when configuring subsequent pages, the corresponding cards are directly extracted from the configured page, and then the extracted cards are multiplexed to The card position that meets the conditions is sufficient, thus greatly reducing the workload of page configuration.

Step 403: Select a traffic set whose user label is the preset user label from all available traffic.

Step 404: In the circled traffic set, allocate test traffic equally to multiple different test pages.

In this embodiment, the user group of a specific user tag is first delineated, and then the user groups corresponding to the user tag are divided for page online testing to improve the directivity of the page online testing. It should be noted that the user tag is used to identify user attributes, which include one or more of gender, region, age, membership level, etc. It should also be understood that in one implementation, the equal distribution in this embodiment may be to equally distribute the traffic in the traffic set, and in another implementation, it may also be to allocate the same amount of traffic. For each test page, it is not required to divide all the traffic in the traffic set.

Step 405: Launch each test page simultaneously on the corresponding allocated test traffic, and collect statistics on the page effect representation data of each test page after it goes online.

Step 406: Compare all page effect representation data to determine the optimal page effect representation data.

Step 407: Determine the optimal test page corresponding to the optimal page effect representation data as the official online page.

In this embodiment, multiple different test pages are diverted and delivered to the corresponding traffic at the same time, and then a parallel online test is performed. Based on the page effect characterization data obtained from the test, the test page with the best page effect is determined as the official online page. , improves the data credibility of page testing and page optimization efficiency, and reduces development costs.

The embodiment of this application discloses a method for determining the official online page. First, multiple different test pages are configured, and then the user tag is delineated as a traffic set with a preset user tag. From the delineated traffic set, multiple different test pages are configured. Allocate the test traffic equally to the pages, then launch each test page simultaneously with the corresponding allocated test traffic, and calculate the page performance representation data after each test page goes online. Finally, determine the test page with the optimal page performance representation data. This is the official launch page. Through the implementation of this application plan, traffic is allocated to multiple different test pages respectively, and multiple different test pages are tested online at the same time. Then the test page with the best online effect is determined to be the official online page, which improves page testing. The data credibility and page optimization efficiency reduce development costs.

Figure 5 is a device for determining an official online page provided by the third embodiment of the present application. The device for determining an officially online page can be used to implement the method for determining an officially online page in the foregoing embodiment. As shown in Figure 5, the device for determining the official online page mainly includes:

Configuration module 501, used to configure multiple different test pages;

The allocation module 502 is used to allocate test traffic to multiple different test pages;

The statistics module 503 is used to put each test page online at the same time on the corresponding allocated test traffic, and count the page effect representation data of each test page after it goes online;

The determination module 504 is used to determine the official online page based on the comparison results obtained by comparing all page effect representation data.

In an optional implementation of this embodiment, the configuration module 501 is specifically configured to first configure one of multiple different test pages. The test page includes multiple cards; if the remaining test pages are different from the configured test pages, If the card has the same card, when configuring the remaining test pages in sequence, the same card in the configured test page will be directly extracted and reused to complete the configuration of multiple different test pages.

In an optional implementation of this embodiment, the allocation module 502 is specifically configured to delineate a traffic set whose user label is a preset user label from all available traffic; in the delineated traffic set, each of them is a plurality of different Test pages allocate test traffic.

Further, in an optional implementation of this embodiment, the allocation module 502 is specifically configured to delineate traffic sets whose user labels are different preset user labels from all available traffic; among the different delineated traffic sets, Allocate test traffic to multiple different test pages. Correspondingly, the determination module 504 is specifically configured to compare all page effect characterization data under each traffic set based on the traffic set, and obtain multiple optimal page effect characterization data; The corresponding test pages are all determined as the optimal test pages; based on the multiple optimal test pages determined, the official online page is determined.

Further, in an optional implementation of this embodiment, when determining the official online page based on the determined multiple optimal test pages, the determination module 504 is specifically configured to determine the official online page corresponding to the multiple optimal test pages. Compare the optimal page performance representation data, determine the better optimal test page among multiple optimal test pages based on the comparison results, and determine the better optimal test page as the official online page.

Further, in another optional implementation of this embodiment, when determining the official online page based on the determined multiple optimal test pages, the determination module 504 is specifically used to obtain each of the optimal test pages. The card effect representation data of the card, where the test page includes multiple cards, and the card types of each test page are the same; determine the optimal card effect representation data of each type of card; determine the respective card effect representation data corresponding to each optimal card effect data. The best cards of each type, as well as the location information of the best cards of each type in the pages to which they belong; according to the location information, the best cards of each type are reused to the blank page to obtain the official online page.

In an optional implementation of this embodiment, the allocation module 502 is specifically configured to allocate the same amount of test traffic to multiple different test pages.

In an optional implementation of this embodiment, the determination module 504 is specifically configured to compare all page effect representation data and determine the optimal page effect representation data; determine the test page corresponding to the optimal page effect representation data as The optimal test page; determine the official online page based on the optimal test page.

Further, in an optional implementation of this embodiment, when determining the officially launched page based on the optimal test page, the determination module 504 is specifically configured to determine the optimal test page as the officially launched page.

Further, in an optional implementation of this embodiment, when determining the official online page based on the optimal test page, the determination module 504 is specifically used to obtain the card effect representation data of each card in the optimal test page, and test The page includes multiple cards; based on all card effect representation data, the position of each card in the optimal test page is adjusted to obtain the official online page.

It should be noted that the officially online page determination methods in the first and second embodiments can be implemented based on the official online page determination device provided in this embodiment. Those of ordinary skill in the art can clearly understand that, for the convenience of description and To be concise, for the specific working process of the device for determining the official online page described in this embodiment, reference can be made to the corresponding process in the foregoing method embodiment, which will not be described again here.

According to the officially launched page determination device provided in this embodiment, multiple different test pages are first configured, then test traffic is allocated to the multiple different test pages, and then each test page is simultaneously configured on the corresponding allocated test traffic. Go online, and count the page performance representation data of each test page after it goes online. Finally, based on the comparison results obtained by comparing all page performance representation data, determine the official online page. Through the implementation of this application plan, traffic is allocated to multiple different test pages respectively, and multiple different test pages are tested online at the same time, and then the online effect is analyzed to determine the official online page, which improves the data credibility of the page test. And page optimization efficiency reduces development costs.

Please refer to FIG. 6 , which shows an electronic device according to a fourth embodiment of the present application. The electronic device can be used to implement the method for determining the official online page in the foregoing embodiment. As shown in Figure 6, the electronic device mainly includes:

A memory 601, a processor 602, a bus 603 and a computer program stored on the memory 601 and executable on the processor 602. The memory 601 and the processor 602 are connected through the bus 603. When the processor 602 executes the computer program, the method for determining the official online page in the aforementioned embodiment is implemented. The number of processors may be one or more.

The memory 601 may be a high-speed random access memory (RAM) memory or a non-volatile memory (non-volatile memory), such as a disk memory. The memory 601 is used to store executable program codes, and the processor 602 is coupled to the memory 601 .

Further, embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium may be provided in the electronic device in the above embodiments. The computer-readable storage medium may be the computer-readable storage medium shown in FIG. 6 . memory in the illustrated embodiment.

A computer program is stored on the computer-readable storage medium. When the program is executed by the processor, the method for determining the official online page in the foregoing embodiment is implemented. Furthermore, the computer-storable medium can also be a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a RAM, a magnetic disk or an optical disk, and other media that can store program codes.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or modules, and may be in electrical, mechanical or other forms.

Modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software function modules.

Integrated modules can be stored in a computer-readable storage medium if they are implemented in the form of software function modules and sold or used as independent products. Based on this understanding, the technical solution of the present application is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a readable storage. The medium includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned readable storage media include: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and other media that can store program code.

It should be noted that for the convenience of description, the foregoing method embodiments are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence. Because according to this application, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary for this application.

In the above embodiments, each embodiment is described with its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

The above is a description of the officially online page determination method, electronic device and computer-readable storage medium provided by this application. For those skilled in the art, based on the ideas of the embodiments of this application, there will be some specific implementation methods and application scopes. Changes, in summary, the content of this specification should not be understood as a limitation on this application.

Claims (10)

1. A method for determining the official online page, which is characterized by including: Configuring multiple different test pages; the test page includes multiple cards; Allocate test traffic to the plurality of different test pages respectively; Put each test page online at the same time on the corresponding allocated test traffic, and collect statistics on the page effect representation data after each test page goes online; Compare all page effect representation data to determine the optimal page effect representation data, determine the test page corresponding to the optimal page effect representation data as the optimal test page, and obtain the values of each card in the optimal test page. The card effect representation data is based on all the card effect representation data, and the position of each card in the optimal test page is adjusted to obtain the official online page. 2. The method for determining the official online page according to claim 1, wherein the configuring multiple different test pages includes: Configure one of multiple different test pages; the test page includes multiple cards; If the remaining test pages and the configured test pages have the same cards, when configuring the remaining test pages in sequence, the same cards in the configured test pages are directly extracted for reuse, completing the multiple different tests. Configuration of the test page. 3. The method for determining the official online page according to claim 1, characterized in that allocating test traffic to the plurality of different test pages includes: Delineate the traffic set whose user label is the preset user label from all available traffic; In the circled traffic set, test traffic is allocated to the plurality of different test pages respectively. 4. The method for determining the officially launched page according to claim 1, characterized in that the same amount of test traffic is allocated to a plurality of different test pages. 5. The method for determining the official online page according to claim 1, characterized in that only some of the cards in the multiple different test pages are different, and there are many cards in common between the test pages. 6. The method for determining the official online page according to claim 3, characterized in that the traffic set delineating user tags as preset user tags from all available traffic includes: Select traffic sets whose user labels are different preset user labels from all available traffic; The method of allocating test traffic to the plurality of different test pages in the circled traffic set includes: Among the different delineated traffic sets, allocate test traffic to the plurality of different test pages; Compare all page effect representation data to determine the optimal page effect representation data, determine the test page corresponding to the optimal page effect representation data as the optimal test page, and obtain the values of each card in the optimal test page. Card effect representation data, based on all the card effect representation data, adjust the position of each card in the optimal test page, and obtain the official online page including: Taking the traffic set as the unit, compare all page effect representation data under each traffic set to obtain multiple optimal page effect representation data; Determine the test pages corresponding to the multiple optimal page effect characterization data as optimal test pages; Obtain the card effect representation data of each card in the optimal test page, and adjust the position of each card in the optimal test page based on all the card effect representation data to obtain the official online page. 7. The method for determining the official online page according to claim 6, characterized in that the card types of the test pages are all the same; and based on all the card effect characterization data, the optimal test page is The position of each card is adjusted, and the official online page includes: Determine the optimal card effect representation data for each type of card; Determine the optimal cards of each type corresponding to each of the optimal card effect representation data, and the position information of the optimal cards of each type in the pages to which they belong; According to the location information, the optimal cards of each type are multiplexed to a blank page to obtain an official online page. 8. A device for determining the official online page, which is characterized by including: A configuration module used to configure multiple different test pages; the test page includes multiple cards; An allocation module, configured to allocate test traffic to the plurality of different test pages; A statistics module, used to put each test page online at the same time on the corresponding allocated test traffic, and count the page effect representation data after each test page goes online; Determining module, used to compare all page effect representation data, determine the optimal page effect representation data, determine the test page corresponding to the optimal page effect representation data as the optimal test page, and obtain the optimal test page , the card effect representation data of each card is adjusted based on all the card effect representation data, and the position of each card in the optimal test page is adjusted to obtain the official online page. 9. An electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the computer program, the rights are realized The steps in the method of any one of claims 1 to 7. 10. A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the method of any one of claims 1 to 7 are implemented.