Landing page positioning method, computing device and storage medium

Abstract

The present invention discloses a landing page positioning method, a computing device and a storage medium, wherein the landing page positioning method includes: collecting the historical stay behavior data of users for each main page and the historical stay behavior data for each sub-page of each main page with N levels of depth; wherein N is greater than or equal to 1; for each main page, statistically analyzing the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-page of the main page with N levels of depth, to obtain the comprehensive stay parameter of the main page; according to the comprehensive stay parameters of each main page, selecting a target main page from multiple main pages as the landing page when the client is cold started. The scheme utilizes the historical stay behavior data of users for the main page and its sub-pages, and can locate the landing page based on the user's usage preference for the main page, thereby realizing the precise positioning of the landing page and well meeting the actual usage needs of the user.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a landing page positioning method, a computing device and a storage medium. Background Art

[0002] With the continuous development of Internet technology, various clients have been developed. In many clients, a client interface in the style of a tab page is set, and different Tab tags correspond to different Tab pages. In the prior art, when a client is cold-started, a fixed Tab page is usually used as the landing page when the client is cold-started, or the last Tab page where the user stayed when he last exited the client is used as the landing page when the client is cold-started next time. However, the above-mentioned landing page positioning method does not fully consider the user's preference for the main page, resulting in low positioning accuracy for the landing page, which is difficult to meet the actual usage needs of users. Summary of the invention

[0003] In view of the above problems, the present invention is proposed to provide a landing page positioning method, computing device and storage medium that overcome the above problems or at least partially solve the above problems.

[0004] According to one aspect of the present invention, a landing page positioning method is provided, comprising:

[0005] Collecting historical stay behavior data of users on each main page and historical stay behavior data on N-level-deep sub-pages of each main page; wherein N is greater than or equal to 1;

[0006] For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page to obtain the comprehensive stay parameters of the main page;

[0007] According to the comprehensive stay parameters of each main page, a target main page is selected from multiple main pages as the landing page when the client is cold started.

[0008] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0009] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:

[0010] Collecting historical stay behavior data of users on each main page and historical stay behavior data on N-level-deep sub-pages of each main page; wherein N is greater than or equal to 1;

[0011] For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page to obtain the comprehensive stay parameters of the main page;

[0012] According to the comprehensive stay parameters of each main page, a target main page is selected from multiple main pages as the landing page when the client is cold started.

[0013] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned landing page locating method.

[0014] According to the technical solution provided by the present invention, the comprehensive dwell parameters of each main page are determined based on the user's historical dwell behavior data for each main page and the historical dwell behavior data for the sub-pages of each main page. The comprehensive dwell parameters of the main page can reflect the user's preference for the main page. According to the comprehensive dwell parameters of each main page, the main page that the user is interested in can be conveniently selected from multiple main pages as the landing page when the client is cold started, thereby realizing the positioning of the landing page based on the user's preference for the main page, effectively improving the positioning accuracy of the landing page, and well meeting the user's actual usage needs.

[0015] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0017] Figure 1 A schematic diagram of the process of a landing page positioning method according to the first embodiment of the present invention is shown;

[0018] Figure 2a A schematic diagram of the process of a landing page positioning method according to the second embodiment of the present invention is shown;

[0019] Figure 2b Shows a schematic diagram of the e-book client interface Figure 1 ;

[0020] Figure 2c Schematic diagram 2 showing an e-book client interface;

[0021] Figure 3 A schematic diagram of the structure of a computing device according to a fourth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0022] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0023] Embodiment 1

[0024] Figure 1 A schematic diagram of a method for locating a landing page according to the first embodiment of the present invention is shown. Figure 1 As shown, the method comprises the following steps:

[0025] Step S101 : collecting historical stay behavior data of users on each main page and historical stay behavior data on N-level deep sub-pages of each main page.

[0026] Usually, multiple Tab tags are set in the client interface, and different Tab tags correspond to different Tab pages. After starting the client, the user can choose the Tab page of interest to browse according to his or her preferences. The main page in this embodiment may specifically include a Tab page. Those skilled in the art may also set the main page to include other pages, which is not limited here. The user's browsing, clicking, sliding and other dwelling behaviors on the page can reflect the degree of his or her preference for using the page. This embodiment determines the main page of interest to the user based on the user's historical dwelling behavior data on the page, and locates it as the landing page for the next cold start of the client. Historical dwelling behavior data refers to the behavior data generated by the user's dwelling on the page during the historical use of the client. Among them, the acquisition and use of historical dwelling behavior data are authorized and approved by the user.

[0027] Specifically, considering that for the main page, in addition to the historical stay behavior data corresponding to the main page that can reflect the user's preference for the main page, the first-level sub-page, second-level sub-page and other sub-pages of the main page are also subsidiary pages of the main page, and the historical stay behavior data corresponding to these subsidiary pages can also reflect the user's preference for the main page to a certain extent. In order to achieve the accurate position of the landing page, in step S101, it is necessary to collect the user's historical stay behavior data for each main page and the historical stay behavior data for the N-level depth sub-pages of each main page, where N is greater than or equal to 1, that is, N is an integer greater than or equal to 1. Those skilled in the art can set the value of N according to actual needs, and it is not limited here. When N is equal to 1, the sub-pages of N levels of depth include the first-level sub-pages; when N is greater than 1, the sub-pages of N levels of depth include the first-level sub-pages to the N-th level sub-pages.

[0028] Step S102 , for each main page, statistically analyzing the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page, to obtain a comprehensive stay parameter of the main page.

[0029] For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages of the main page at N levels of depth, so as to integrate the user's stay situation on the main page with the user's stay situation on the sub-pages of the main page at N levels of depth, thereby obtaining the comprehensive stay parameter of the main page. Among them, the comprehensive stay parameter refers to a parameter obtained by integrating the user's stay situation on the page and its sub-pages to reflect the comprehensive stay situation of the user on the page.

[0030] Specifically, the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth can be obtained by analyzing the historical dwell behavior data, and then the dwell parameters of the main page and the dwell parameters of the sub-pages at N levels of depth of the main page can be counted to obtain the comprehensive dwell parameters of the main page. The dwell parameter refers to a parameter used to reflect the dwell situation of the user on a single page.

[0031] Step S103 , selecting a target home page from the plurality of home pages as a landing page when the client is cold started according to the comprehensive stay parameters of each home page.

[0032] Among them, the comprehensive stay parameter of the main page can reflect the comprehensive stay of the user in the main page. The comprehensive stay parameter corresponds to the user's usage preference. If the comprehensive stay parameter of a main page is higher, it means that the user has a higher usage preference for the main page, and he likes to use the main page in the process of using the client. After obtaining the comprehensive stay parameters of each main page, a main page with the highest comprehensive stay parameter can be selected from multiple main pages as the selected main page, that is, the target main page, and the target main page is positioned as the landing page when the client is cold started, that is, when the client is started by cold start, the landing page will be displayed to the user.

[0033] Utilizing the landing page positioning method provided in the present embodiment, the comprehensive dwell parameters of each main page are determined based on the user's historical dwell behavior data for each main page and the historical dwell behavior data for the sub-pages of each main page. The comprehensive dwell parameters of the main page can reflect the user's preference for the main page. Based on the comprehensive dwell parameters of each main page, the main page that the user is interested in can be conveniently selected from multiple main pages as the landing page when the client is cold started, thereby realizing the positioning of the landing page based on the user's preference for the main page, effectively improving the positioning accuracy of the landing page, and well meeting the user's actual usage needs.

[0034] Embodiment 2

[0035] Figure 2a A schematic diagram of a landing page location method according to Embodiment 2 of the present invention is shown. Figure 2a As shown, the method comprises the following steps:

[0036] Step S201, collecting historical stay behavior data of users on each main page.

[0037] In this embodiment, the main page that the user is interested in is located based on the historical stay behavior data of the user for the main page and the historical stay behavior data for the sub-pages of each main page, so as to achieve accurate positioning of the landing page. In step S201, the historical stay behavior data of the user for each main page can be collected from the client or the server. The historical stay behavior data refers to the behavior data generated by the user staying on the page during the historical use of the client, for example, it refers to the behavior data generated by the user staying on the page in one or more previous use cycles. Specifically, the process from the cold start of the client to the clearing of the client process is called a use cycle. Among them, the historical stay behavior data may specifically include page browsing data, page click data, page sliding data, etc.

[0038] Step S202, obtain the recorded historical page operation links of the user for each main page, determine the N-level deep sub-pages of each main page based on the historical page operation links corresponding to each main page, and collect the historical stay behavior data of the user for the N-level deep sub-pages of each main page.

[0039] In order to obtain the historical stay behavior data of users on the sub-pages of the main page, the page linker can be used to record the historical page operation links of users on each main page during the use cycle when the user uses the client. Assume that the historical page operation link recorded for the main page A is "A→B→C→D", where A is the main page, B is the first-level sub-page of A, C is the second-level sub-page of A, and D is the third-level sub-page of A, which means that the user first browses the main page A, then jumps from the main page A to the first-level sub-page B, then jumps from the first-level sub-page B to the second-level sub-page C, and finally jumps from the second-level sub-page C to the third-level sub-page D.

[0040] In step S202, the historical page operation links of the user for each main page recorded by the page linker can be obtained, and then the sub-pages of each main page with N levels of depth are determined according to the historical page operation links corresponding to each main page, and the historical stay behavior data of the user for the sub-pages of N levels of depth for each main page are collected from the client or server, etc. Wherein, N is greater than or equal to 1. Those skilled in the art can set the value of N according to actual needs. For example, when N=1, it means that the depth of the collected sub-page is 1, and it is necessary to collect the historical stay behavior data of the user for the sub-pages of the 1st level of depth of the main page, that is, collect the historical stay behavior data of the first-level sub-page; when N=3, it means that the depth of the collected sub-page is 3, and it is necessary to collect the historical stay behavior data of the user for the sub-pages of the 3rd level of depth of the main page, that is, collect the historical stay behavior data of the first to third-level sub-pages. Wherein, the acquisition and use of the historical stay behavior data are authorized and approved by the user.

[0041] Step S203, for each main page, respectively analyze the historical dwell behavior data corresponding to the main page and the historical dwell behavior data corresponding to each sub-page at N levels of depth, obtain the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth, and perform statistics on the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth of the main page to obtain the comprehensive dwell parameters of the main page.

[0042] The historical stay behavior data may specifically include page browsing data, page click data, page sliding data, etc. For the calculation of the stay parameter of each main page, the historical stay behavior data corresponding to the main page may be analyzed to obtain the page browsing time and the number of interactive behaviors of the user on the main page, and then the page browsing time and the number of interactive behaviors of the user on the main page are weightedly calculated to obtain the stay parameter of the main page.

[0043] Among them, page browsing time refers to the total duration from the time the user enters the page to the time the user leaves or closes the page. Interactive behaviors may include click behaviors, sliding behaviors, etc. The page browsing time and the number of interactive behaviors of different interactive behaviors have their own weights. The page browsing time and the number of interactive behaviors of the user on the main page are weighted and calculated, and the weighted calculation result is used as the stay parameter of the main page. In specific applications, the analysis and statistics of page browsing time can also be achieved through a timer. For example, when the client turns on / unlocks the screen, enters the page, or returns to the page from other pages, the timer starts; when the client turns off / locks the screen or enters other pages, the timer is paused.

[0044] The calculation method of the dwell parameter for each sub-page of N levels of depth is similar to the calculation method of the dwell parameter for each main page. Specifically, the historical dwell behavior data corresponding to each sub-page of N levels of depth is analyzed to obtain the page browsing time and the number of interactive behaviors of the user in each sub-page of N levels of depth, and the page browsing time and the number of interactive behaviors of the user in each sub-page of N levels of depth are weightedly calculated to obtain the dwell parameter of each sub-page of N levels of depth.

[0045] Specifically, compared with page browsing behavior, the user's click behavior and sliding behavior on the page can better reflect the user's high interest in the content of the page, so a higher weight can be set for the number of click behaviors and the number of sliding behaviors, and a lower weight can be set for the page browsing time. For example, the weight corresponding to the page browsing time can be set to 1, the weight corresponding to the number of click behaviors can be set to 15, and the weight corresponding to the number of sliding behaviors can be set to 10.

[0046] For each main page, after calculating the dwell parameter of the main page and the dwell parameter of each sub-page of the main page at N levels of depth, the dwell parameter of the main page and the dwell parameter of each sub-page of the main page at N levels of depth can be counted to obtain a comprehensive dwell parameter of the main page. In an optional embodiment, the dwell parameter of the main page and the dwell parameter of each sub-page of the main page at N levels of depth can be directly accumulated, and the accumulated result can be used as the comprehensive dwell parameter of the main page. In another optional embodiment, different weights can be set for the main page and sub-pages of different depths, and by weighted calculation of the dwell parameter of the main page and the dwell parameter of each sub-page of the main page at N levels of depth, the weighted calculation result can be used as the comprehensive dwell parameter of the main page.

[0047] Optionally, the method may also include: storing the comprehensive stay parameters of each main page in the client or server according to the user dimension, so as to be used when determining the landing page. Specifically, the comprehensive stay parameters of each main page corresponding to different users are stored in blocks according to the user dimension. Then, even if different users log in to the client using the same device, the comprehensive stay parameters of each main page corresponding to different users can be clearly stored, and there is no impact between user data. For example, after user A logs in to the client using a device, user B logs in to the client using the device again. Since the comprehensive stay parameters are stored according to the user dimension, user B will not inherit the comprehensive stay parameters of each main page corresponding to user A.

[0048] Step S204: Select a home page with the highest comprehensive stay parameter from the multiple home pages as a target home page, and use the target home page as the landing page for the next cold start of the client.

[0049] The comprehensive dwell parameter of the main page corresponds to the user's preference for the main page. The higher the comprehensive dwell parameter of a main page, the higher the user's preference for the main page. After obtaining the comprehensive dwell parameters of each main page, a main page with the highest comprehensive dwell parameter can be selected from multiple main pages as the target main page, and the target main page is used as the landing page of the client's next cold start. That is, the next time the user starts the client through a cold start, the client will display the landing page to the user.

[0050] Considering that the determined landing page may not have a search entry, if the user has a search requirement, he needs to switch from the landing page to other pages with a search entry to search. In the scenario where the landing page does not have a search entry, in order to make the determined landing page meet the user's search needs well, a search entry can be set for the landing page when it is determined that the user has a search requirement, which can be specifically implemented through steps S205 and S206.

[0051] Step S205, determine whether the user has a search requirement; if so, execute step S206; if not, there is no need to set a search entry, and the method ends.

[0052] In an optional implementation, it can be determined whether the comprehensive stay parameters of the specified type of home page in each home page meet the first preset condition; if so, it is determined that the user has a search demand. The specified type can specifically be a content search type, etc. Those skilled in the art can set the specified type and the first preset condition according to actual needs. For example, the first preset condition may include: the sum of the comprehensive stay parameters of multiple home pages of the specified type is greater than or equal to a first preset threshold, wherein the first preset threshold can be determined based on the comprehensive stay parameters of the target home page, such as the first preset threshold is equal to the comprehensive stay parameter of the target home page, or the first preset threshold is equal to 0.8 times the comprehensive stay parameter of the target home page, etc.

[0053] Take the e-book client as an example. Figure 2b Shows a schematic diagram of the e-book client interface Figure 1 ,like Figure 2b As shown, there are 5 tabs at the bottom of the e-book client interface, namely, the "Bookshelf" tab, the "Discover" tab, the "Publish" tab, the "Novel" tab, and the "My" tab. The tab page corresponding to each tab is the main page. The main page corresponding to the "Publish" tab and the main page corresponding to the "Novel" tab are both content search type pages. Multiple e-books of the corresponding type will be displayed on these two main pages. Users can search for e-books of interest on the main page corresponding to the "Publish" tab and the main page corresponding to the "Novel" tab.

[0054] Due to business requirements, there is no search entry in the main page corresponding to the "My" tag. Assuming that the landing page determined by processing through steps S201 to S204 is the main page corresponding to the "My" tag, if the sum of the comprehensive stay parameters of the main page corresponding to the "Publishing" tag and the main page corresponding to the "Novel" tag is greater than or equal to the first preset threshold, it means that the user is a book-seeking user and has a search requirement.

[0055] In another optional implementation, the comprehensive stay parameters of the search page can be calculated, and based on the comprehensive stay parameters of the search page, it is determined whether the user has a search demand, wherein the search page is specifically the page corresponding to the search entry. Specifically, the user's historical stay behavior data for the search page and the historical stay behavior data for the sub-pages of the search page with an M-level depth can be collected, wherein M is greater than or equal to 1, and those skilled in the art can set the value of M according to actual needs. When M is equal to 1, the sub-pages of the M-level depth include the first-level sub-pages; when M is greater than 1, the sub-pages of the M-level depth include the first-level sub-pages to the M-th-level sub-pages. The historical stay behavior data corresponding to the search page and the historical stay behavior data corresponding to the sub-pages of the M-level depth of the search page are statistically analyzed to obtain the comprehensive stay parameters of the search page. Among them, the calculation method for the comprehensive stay parameters of the search page is similar to the calculation method for the comprehensive stay parameters of the main page, which will not be repeated here.

[0056] After obtaining the comprehensive stay parameter of the search page, it is determined whether the comprehensive stay parameter of the search page meets the second preset condition; if so, it is determined that the user has a search demand. Those skilled in the art can set the second preset condition according to actual needs. For example, the second preset condition includes: the comprehensive stay parameter of the search page is greater than or equal to the second preset threshold. Among them, the second preset threshold can be determined according to the comprehensive stay parameter of the target home page, such as the second preset threshold is equal to 0.3 times the comprehensive stay parameter of the target home page.

[0057] Step S206, setting a search entry in the landing page.

[0058] When it is determined that the user has a search need, a search entry is set in the landing page, so that the determined landing page can not only meet the user's preference for the main page, but also meet the user's search needs well, so that the user can perform the search operation in the landing page, reducing the user's interactive steps to find the search entry. Assuming that the determined landing page is the main page corresponding to the "My" tag, then Figure 2c As shown, a search entry 21 may be set at the upper right corner of the main page corresponding to the "My" tag.

[0059] By utilizing the landing page positioning method provided in the present embodiment, by analyzing the historical dwell behavior data corresponding to the main page and each of its sub-pages, the page browsing time and the number of interaction behaviors of the user on the main page and its sub-pages can be conveniently obtained, and based on the page browsing time and the number of interaction behaviors, the comprehensive dwell parameters of the main page are accurately calculated; based on the comprehensive dwell parameters of each main page, the main page of interest to the user can be conveniently selected from multiple main pages as the landing page when the client is cold started; in addition, when it is determined that the user has a search need, a search entry can be set in the landing page, so that the determined landing page can not only meet the user's preference for the main page, but also meet the user's search needs well, so that the user can conveniently perform search operations in the landing page, reducing the user's interactive steps to find the search entry.

[0060] Embodiment 3

[0061] Embodiment 3 of the present invention provides a non-volatile storage medium, wherein the storage medium stores at least one executable instruction, and the executable instruction can execute the landing page locating method in any of the above method embodiments.

[0062] The executable instructions can be specifically used to enable the processor to perform the following operations: collect the user's historical stay behavior data for each main page and the historical stay behavior data for the sub-pages of each main page at N levels of depth; where N is greater than or equal to 1; for each main page, perform statistical analysis on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages of the main page at N levels of depth to obtain comprehensive stay parameters of the main page; based on the comprehensive stay parameters of each main page, select a target main page from multiple main pages as the landing page when the client is cold started.

[0063] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: collect the user's historical stay behavior data for each main page; obtain the recorded historical page operation links of the user for each main page, determine the N-level deep sub-pages of each main page based on the historical page operation links corresponding to each main page, and collect the user's historical stay behavior data for the N-level deep sub-pages of each main page.

[0064] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: respectively analyze the historical dwell behavior data corresponding to the main page and the historical dwell behavior data corresponding to each sub-page at N levels of depth to obtain the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth; and perform statistics on the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth to obtain the comprehensive dwell parameters of the main page.

[0065] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: analyze the historical dwell behavior data corresponding to the main page to obtain the page browsing time and the number of interaction behaviors of the user in the main page, and perform weighted calculation on the page browsing time and the number of interaction behaviors of the user in the main page to obtain the dwell parameters of the main page; analyze the historical dwell behavior data corresponding to each sub-page of N levels of depth to obtain the page browsing time and the number of interaction behaviors of the user in each sub-page of N levels of depth, and perform weighted calculation on the page browsing time and the number of interaction behaviors of the user in each sub-page of N levels of depth to obtain the dwell parameters of each sub-page of N levels of depth.

[0066] In an optional implementation, the executable instructions further cause the processor to perform the following operations: select a home page with the highest comprehensive stay parameter from multiple home pages as the target home page; and use the target home page as the landing page for the next cold start of the client.

[0067] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: determine whether the user has a search requirement; if so, set a search entry in the landing page.

[0068] In an optional implementation, the executable instructions further cause the processor to perform the following operations: determine whether the comprehensive stay parameters of the main pages of a specified type among the main pages meet the first preset condition; if so, determine that the user has a search demand.

[0069] In an optional implementation, the first preset condition includes: the sum of comprehensive stay parameters of multiple home pages of a specified type is greater than or equal to a first preset threshold.

[0070] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: collect the user's historical stay behavior data for the search page and the historical stay behavior data for the sub-pages of the search page with an M-level depth; wherein M is greater than or equal to 1; perform statistical analysis on the historical stay behavior data corresponding to the search page and the historical stay behavior data corresponding to the sub-pages of the search page with an M-level depth to obtain comprehensive stay parameters of the search page; determine whether the comprehensive stay parameters of the search page meet the second preset condition; if so, determine that the user has a search demand.

[0071] In an optional implementation, the second preset condition includes: a comprehensive stay parameter of the search page is greater than or equal to a second preset threshold.

[0072] In an optional implementation, the executable instructions further cause the processor to perform the following operations: storing the comprehensive stay parameters of each main page in the client or server according to the user dimension.

[0073] Embodiment 4

[0074] Figure 3 A schematic diagram of the structure of a computing device according to Embodiment 4 of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0075] like Figure 3 As shown, the computing device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0076] in:

[0077] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0078] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0079] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned landing page positioning method embodiment.

[0080] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0081] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0082] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0083] Program 310 can be specifically used to enable processor 302 to perform the following operations: collect historical stay behavior data of users for each main page and historical stay behavior data for sub-pages at N levels of depth of each main page; wherein N is greater than or equal to 1; for each main page, perform statistical analysis on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to sub-pages at N levels of depth of the main page to obtain comprehensive stay parameters of the main page; based on the comprehensive stay parameters of each main page, select a target main page from multiple main pages as the landing page when the client is cold started.

[0084] In an optional embodiment, program 310 further enables processor 302 to perform the following operations: collect historical stay behavior data of users for each main page; obtain recorded historical page operation links of users for each main page, determine the N-level deep sub-pages of each main page based on the historical page operation links corresponding to each main page, and collect historical stay behavior data of users for the N-level deep sub-pages of each main page.

[0085] In an optional embodiment, the program 310 further enables the processor 302 to perform the following operations: respectively analyze the historical dwell behavior data corresponding to the main page and the historical dwell behavior data corresponding to each sub-page at N levels of depth to obtain the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth; and perform statistics on the dwell parameters of the main page and the dwell parameters of each sub-page at N levels of depth to obtain the comprehensive dwell parameters of the main page.

[0086] In an optional embodiment, the program 310 further enables the processor 302 to perform the following operations: analyze the historical dwell behavior data corresponding to the main page to obtain the page browsing time and the number of interaction behaviors of the user in the main page, and perform weighted calculation on the page browsing time and the number of interaction behaviors of the user in the main page to obtain the dwell parameters of the main page; analyze the historical dwell behavior data corresponding to each sub-page of N levels of depth to obtain the page browsing time and the number of interaction behaviors of the user in each sub-page of N levels of depth, and perform weighted calculation on the page browsing time and the number of interaction behaviors of the user in each sub-page of N levels of depth to obtain the dwell parameters of each sub-page of N levels of depth.

[0087] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations: select a home page with the highest comprehensive stay parameter from multiple home pages as a target home page; and use the target home page as the landing page for the next cold start of the client.

[0088] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: determine whether the user has a search requirement; if so, set a search entry in the landing page.

[0089] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: determine whether the comprehensive stay parameters of the homepages of the specified type among the homepages meet the first preset condition; if so, determine that the user has a search demand.

[0090] In an optional implementation, the first preset condition includes: the sum of comprehensive stay parameters of multiple home pages of a specified type is greater than or equal to a first preset threshold.

[0091] In an optional embodiment, program 310 further enables processor 302 to perform the following operations: collect historical dwell behavior data of users for search pages and historical dwell behavior data for sub-pages of the search page at M levels of depth; wherein M is greater than or equal to 1; perform statistical analysis on the historical dwell behavior data corresponding to the search page and the historical dwell behavior data corresponding to sub-pages of the search page at M levels of depth to obtain comprehensive dwell parameters of the search page; determine whether the comprehensive dwell parameters of the search page meet the second preset condition; if so, determine that the user has a search demand.

[0092] In an optional implementation, the second preset condition includes: a comprehensive stay parameter of the search page is greater than or equal to a second preset threshold.

[0093] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: storing the comprehensive stay parameters of each main page in the client or server according to the user dimension.

[0094] The specific implementation of each step in program 310 can refer to the description of the corresponding steps in the above-mentioned landing page positioning embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0095] Through the solution provided in this embodiment, the user's historical stay behavior data on the main page and its sub-pages can be used to locate the landing page based on the user's usage preference for the main page, thereby achieving accurate positioning of the landing page and well meeting the user's actual usage needs.

[0096] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0097] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0098] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0099] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0100] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0101] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including a number of different elements and by means of a suitably programmed computer. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims

1. A landing page positioning method, comprising: Collecting historical stay behavior data of users on each main page and historical stay behavior data on N-level-deep sub-pages of each main page; wherein N is greater than or equal to 1; For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page to obtain the comprehensive stay parameters of the main page; According to the comprehensive stay parameters of each main page, a target main page is selected from multiple main pages as the landing page when the client is cold started; The collecting of the historical stay behavior data of users on each main page and the historical stay behavior data on the sub-pages with N levels of depth of each main page further includes: Collect historical user behavior data on each home page; Obtain the recorded historical page operation links of users for each main page, determine the N-level-deep sub-pages of each main page according to the historical page operation links corresponding to each main page, and collect the historical stay behavior data of users for the N-level-deep sub-pages of each main page; For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page to obtain the comprehensive stay parameters of the main page, further comprising: Analyze the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to each sub-page at N levels of depth respectively, and obtain the stay parameters of the main page and the stay parameters of each sub-page at N levels of depth; Statistics are collected on the stay parameter of the main page and the stay parameter of each sub-page of N levels of depth of the main page to obtain a comprehensive stay parameter of the main page.

2. According to the method of claim 1, the step of respectively analyzing the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to each sub-page at N levels of depth to obtain the stay parameters of the main page and the stay parameters of each sub-page at N levels of depth further comprises: Analyze the historical stay behavior data corresponding to the main page to obtain the page browsing time and the number of interactive behaviors of the user on the main page, and perform weighted calculation on the page browsing time and the number of interactive behaviors of the user on the main page to obtain the stay parameter of the main page; Analyze the historical dwell behavior data corresponding to each subpage of N levels of depth, obtain the page browsing time and the number of interactive behaviors of the user in each subpage of N levels of depth, and perform weighted calculation on the page browsing time and the number of interactive behaviors of the user in each subpage of N levels of depth, to obtain the dwell parameters of each subpage of N levels of depth.

3. According to the method of claim 1, the step of selecting a target home page from a plurality of home pages as a landing page when the client is cold started based on the comprehensive stay parameters of each home page further comprises: Select the homepage with the highest comprehensive stay parameter from multiple homepages as the target homepage; The target main page is used as the landing page when the client is cold started next time.

4. The method according to any one of claims 1 to 3, further comprising: Determine whether the user has a search demand; If so, a search entry is set in the landing page.

5. According to the method of claim 4, the step of determining whether the user has a search requirement further comprises: Determine whether the comprehensive stay parameter of the main page of the specified type among the main pages meets the first preset condition; If so, it is determined that the user has a search demand.

6. The method according to claim 5, wherein the first preset condition comprises: The sum of the comprehensive stay parameters of the plurality of main pages of the specified type is greater than or equal to a first preset threshold.

7. According to the method of claim 4, the step of determining whether the user has a search requirement further comprises: Collecting historical stay behavior data of users on the search page and historical stay behavior data on sub-pages of the search page with a depth of M levels; wherein M is greater than or equal to 1; Performing statistical analysis on the historical stay behavior data corresponding to the search page and the historical stay behavior data corresponding to the sub-pages of the search page at a depth of M levels to obtain a comprehensive stay parameter of the search page; Determining whether the comprehensive stay parameter of the search page meets a second preset condition; If so, it is determined that the user has a search demand.

8. The method according to claim 7, wherein the second preset condition comprises: The comprehensive stay parameter of the search page is greater than or equal to a second preset threshold.

9. The method according to any one of claims 1 to 3, further comprising: According to the user dimension, the comprehensive stay parameters of each main page are stored in the client or server.

10. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: Collecting historical stay behavior data of users on each main page and historical stay behavior data on N-level-deep sub-pages of each main page; wherein N is greater than or equal to 1; For each main page, statistical analysis is performed on the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to the sub-pages at N levels of depth of the main page to obtain the comprehensive stay parameters of the main page; According to the comprehensive stay parameters of each main page, a target main page is selected from multiple main pages as the landing page when the client is cold started; The executable instructions further cause the processor to perform the following operations: Collect historical user behavior data on each home page; Obtain the recorded historical page operation links of users for each main page, determine the N-level-deep sub-pages of each main page according to the historical page operation links corresponding to each main page, and collect the historical stay behavior data of users for the N-level-deep sub-pages of each main page; Analyze the historical stay behavior data corresponding to the main page and the historical stay behavior data corresponding to each sub-page at N levels of depth respectively, and obtain the stay parameters of the main page and the stay parameters of each sub-page at N levels of depth; Statistics are collected on the stay parameter of the main page and the stay parameter of each sub-page of N levels of depth of the main page to obtain a comprehensive stay parameter of the main page.

11. The computing device of claim 10, wherein the executable instructions further cause the processor to: Analyze the historical stay behavior data corresponding to the main page to obtain the page browsing time and the number of interactive behaviors of the user on the main page, and perform weighted calculation on the page browsing time and the number of interactive behaviors of the user on the main page to obtain the stay parameter of the main page; Analyze the historical dwell behavior data corresponding to each subpage of N levels of depth, obtain the page browsing time and the number of interactive behaviors of the user in each subpage of N levels of depth, and perform weighted calculation on the page browsing time and the number of interactive behaviors of the user in each subpage of N levels of depth, to obtain the dwell parameters of each subpage of N levels of depth.

12. The computing device of claim 10, wherein the executable instructions further cause the processor to: Select the homepage with the highest comprehensive stay parameter from multiple homepages as the target homepage; The target main page is used as the landing page when the client is cold started next time.

13. The computing device of any one of claims 10 to 12, wherein the executable instructions further cause the processor to perform the following operations: Determine whether the user has a search demand; If so, a search entry is set in the landing page.

14. The computing device of claim 13, wherein the executable instructions further cause the processor to: Determine whether the comprehensive stay parameter of the main page of the specified type among the main pages meets the first preset condition; If so, it is determined that the user has a search demand.

15. The computing device according to claim 14, wherein the first preset condition comprises: The sum of the comprehensive stay parameters of the plurality of main pages of the specified type is greater than or equal to a first preset threshold.

16. The computing device of claim 13, wherein the executable instructions further cause the processor to: Collecting historical stay behavior data of users on the search page and historical stay behavior data on sub-pages of the search page with a depth of M levels; wherein, M is greater than or equal to 1; Performing statistical analysis on the historical stay behavior data corresponding to the search page and the historical stay behavior data corresponding to the sub-pages of the search page at a depth of M levels to obtain a comprehensive stay parameter of the search page; Determining whether the comprehensive stay parameter of the search page meets a second preset condition; If so, it is determined that the user has a search demand.

17. The computing device according to claim 16, wherein the second preset condition comprises: The comprehensive stay parameter of the search page is greater than or equal to a second preset threshold.

18. The computing device of any one of claims 10-12, wherein the executable instructions further cause the processor to perform the following operations: According to the user dimension, the comprehensive stay parameters of each main page are stored in the client or server.

19. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the landing page locating method as described in any one of claims 1-9.

Images