CN116821554B

CN116821554B - Page analysis method and device, electronic equipment and medium

Info

Publication number: CN116821554B
Application number: CN202311102123.1A
Authority: CN
Inventors: 赵鸿翔; 刘力伟; 王根镇; 滕春金; 施大龙
Original assignee: AVIC INTERNATIONAL E-BUSINESS Inc
Current assignee: AVIC INTERNATIONAL E-BUSINESS Inc
Priority date: 2023-08-30
Filing date: 2023-08-30
Publication date: 2023-11-14
Anticipated expiration: 2043-08-30
Also published as: CN116821554A

Abstract

The embodiment of the application provides a page analysis method, a device, electronic equipment and a medium, and relates to the technical field of data analysis, wherein the method comprises the following steps: and acquiring a first DOM node with the largest click rate in a first preset time period, at least one second DOM node except the first DOM node and the first click rate of the second DOM node in the first preset time period from all the designated DOM nodes included in the designated page. Then, obtaining a second click rate of a second DOM node in the first updated page within a second preset time period; the first updated page is a page obtained by changing the first type attribute value of the second DOM node in the appointed page into the first type attribute value of the first DOM node. And then comparing the first click quantity with the second click quantity to obtain an influence result of the first attribute value on the click quantity, and obtaining the page improvement strategy on the appointed page according to the influence result. Thereby improving the recommending effect of the page to the main pushing commodity or advertisement.

Description

Page analysis method and device, electronic equipment and medium

Technical Field

The present application relates to the field of data analysis technologies, and in particular, to a method and apparatus for page analysis, an electronic device, and a medium.

Background

With the increase of interactions between World Wide Web (Web) applications and users and the increase of information types displayed on application pages, the design of application pages is more and more complex. Currently, designers typically determine the layout and format of page content, such as hyperlinks to merchandise or advertising hyperlinks, empirically when designing application pages. The design mode transits to rely on manual experience, and the levels of different designers have gaps, so that the designed application page is difficult to accurately accord with the preference of a user, and a good recommendation effect can not be achieved for the main pushing of commodities or advertisements.

Disclosure of Invention

The embodiment of the application aims to provide a page analysis method, a page analysis device, electronic equipment and a page analysis medium, so as to improve the recommending effect of pages on a main pushing commodity or advertisement. The specific technical scheme is as follows:

in a first aspect of an embodiment of the present application, there is provided a page analysis method, including:

acquiring a first DOM node with the largest click rate in a first preset time period, at least one second DOM node except the first DOM node and a first click rate of the second DOM node in the first preset time period from all the designated DOM nodes included in the designated page;

Acquiring a second click rate of the second DOM node in the first updated page within a second preset time period; the second preset time period and the first preset time period have equal duration, and the first update page is: changing a first type attribute value of the second DOM node in the appointed page into a page obtained after the first type attribute value of the first DOM node is changed, wherein the first type attribute value is the position or the content format of the DOM node in the page;

comparing the first click quantity with the second click quantity to obtain an influence result of the first type attribute value on the click quantity;

and obtaining the page improvement strategy for the specified page according to the influence result of the first type attribute value on the click quantity.

Optionally, the comparing the first click rate with the second click rate to obtain an influence result of the first attribute value on the click rate includes:

judging whether the difference value between the second click quantity and the first click quantity is larger than a preset difference value or not;

if yes, determining that the first type attribute value has an influence on the click rate;

if not, determining that the first type attribute value has no influence on the click quantity.

Optionally, the page improvement policy is: and modifying the preset first type attribute value of the main push DOM node into the first type attribute value of the first DOM node.

Optionally, the obtaining a page improvement policy for the specified page according to the result of the influence of the first attribute value on the click rate includes:

if the influence result indicates that the first type attribute value has no influence on the click rate, acquiring a third click rate of the second DOM node in a second updated page in a third preset time period, wherein the third preset time period is equal to the first preset time period in duration, and the second updated page is: changing a second type attribute value of the second DOM node in the appointed page into a page obtained after the second type attribute value of the first DOM node is changed, wherein the second type attribute value is a position or a content format of the DOM node in the page, and the second type attribute value is different from the first type attribute value;

comparing the first click quantity with the third click quantity to obtain an influence result of the second type attribute value on the click quantity;

and obtaining the page improvement strategy for the appointed page according to the influence result of the second type attribute value on the click quantity.

Optionally, the method further comprises:

receiving a page acquisition request sent by a terminal, wherein the page acquisition request is used for requesting to open the specified page or refreshing the specified page;

Acquiring a preference tag set of the specified user, wherein the preference tag set comprises: the appointed user history clicks labels of objects recommended by all DOM nodes in all appointed DOM nodes included in the appointed page;

determining a plurality of push objects according to the preference tag set, and sending a page acquisition response to the terminal, wherein the page acquisition response comprises display information of each push object, so that the terminal displays a recommendation DOM node for recommending each push object in the appointed page according to the display information of each push object;

in the time period from the time when the terminal opens the appointed page to the time when the appointed page is closed, the label of the push object recommended by the clicked recommended DOM node in the appointed page forms a click label set;

and updating the preference tag set according to the click tag set.

Optionally, the preference tag set further includes a count value of each tag, where the count value is used to indicate a degree of interest of the specified user in the tag; the determining a plurality of push objects according to the preference tag set includes:

acquiring a first number of labels from the preference label set according to the sequence of the count value from large to small, and screening push objects with the first number of labels from an object library;

Judging whether the total number of the screened pushing objects is smaller than the designated number;

if yes, the first number is reduced according to a preset step length, the reduced first number of labels are obtained from the preference label set according to the sequence of the count value from large to small, push objects with the reduced first number of labels are screened from the object library, and the step of judging whether the total number of the screened push objects is smaller than the specified number is returned until the specified number of push objects are obtained.

Optionally, before the first number of tags is obtained from the preference tag set in the order of from the count value to the count value, the method further includes:

judging whether count values of all tags included in the preference tag set are lower than a preset threshold value or not;

if yes, randomly selecting a second number of labels from the preference label set, screening a plurality of pushing objects with the second number of labels from the object library, and randomly acquiring the plurality of pushing objects from the object library;

if not, executing the step of acquiring the first number of tags from the preference tag set according to the sequence of the count value from the large to the small.

Optionally, the preference tag set further includes a count value of each tag, where the count value is used to indicate a degree of interest of the specified user in the tag; the updating the preference tag set according to the click tag set comprises the following steps:

determining whether the label exists in the preference label set for each label included in the click label set;

if so, adding one to the count value of the tag in the preference tag set;

if the label is not present, determining the count value of the label to be one, and adding the label and the count value of the label to the preference label set.

determining whether the label exists in the preference label set for each label included in the click label set; if so, adding one to the count value of the tag in the preference tag set; if the preference label is not present, determining that the count value of the label is one, and adding the label and the count value of the label into the preference label set;

A push label set composed of labels of all push objects is obtained, whether the label is included in the click label set is judged according to each label included in the push label set, and if the label is not included in the click label set, the count value of the label in the preference label set is reduced by one.

Optionally, before the subtracting the count value of the tag in the preference tag set by one, the method further includes:

judging whether the count value of the tag in the preference tag set is greater than one;

if yes, executing the step of subtracting one from the count value of the tag in the preference tag set;

if not, keeping the count value corresponding to the label in the preference label set unchanged.

In a second aspect of the embodiment of the present application, there is provided a page analysis apparatus, including:

the acquisition module is used for acquiring a first DOM node with the largest click rate in a first preset time period, at least one second DOM node except the first DOM node and a first click rate of the second DOM node in the first preset time period from all the designated DOM nodes included in the designated page;

the obtaining module is further configured to obtain a second click rate of the second DOM node in the first updated page within a second preset time period; the second preset time period and the first preset time period have equal duration, and the first update page is: changing a first type attribute value of the second DOM node in the appointed page into a page obtained after the first type attribute value of the first DOM node is changed, wherein the first type attribute value is the position or the content format of the DOM node in the page;

The comparison module is used for comparing the first click rate and the second click rate acquired by the acquisition module to obtain an influence result of the first type attribute value on the click rate;

and the generation module is used for obtaining the page improvement strategy for the appointed page according to the influence result of the first type attribute value on the click quantity, which is obtained by the comparison module.

Optionally, the comparison module is specifically configured to:

Optionally, the generating module is specifically configured to:

Optionally, the apparatus further includes:

the receiving module is used for receiving a page acquisition request sent by the terminal, wherein the page acquisition request is used for requesting to open the appointed page or refreshing the appointed page;

the obtaining module is further configured to obtain a preference tag set of the specified user, where the preference tag set includes: the appointed user history clicks labels of objects recommended by all DOM nodes in all appointed DOM nodes included in the appointed page;

the determining module is used for determining a plurality of push objects according to the preference tag set acquired by the acquiring module, and sending a page acquisition response to the terminal, wherein the page acquisition response comprises display information of each push object, so that the terminal displays a recommended DOM node for recommending the push object in the designated page according to the display information of each push object;

the construction module is used for forming a click tag set by the tags of the push objects recommended by the clicked recommended DOM nodes in the appointed page in the time period from the moment the appointed page is opened to the moment the appointed page is closed by the terminal;

And the updating module is used for updating the preference tag set according to the click tag set obtained by the construction module.

Optionally, the preference tag set further includes a count value of each tag, where the count value is used to indicate a degree of interest of the specified user in the tag; the determining module is specifically configured to:

Optionally, the apparatus further includes:

the judging module is used for judging whether the count value of each tag included in the preference tag set is lower than a preset threshold value before the first number of tags are acquired from the preference tag set according to the sequence of the count values from the large to the small;

The screening module is used for randomly selecting a second number of labels from the preference label set if the judgment result of the judgment module is yes, screening a plurality of pushing objects with the second number of labels from the object library, and randomly acquiring a plurality of pushing objects from the object library;

and the calling module is used for calling the determining module to execute the step of acquiring the first number of labels from the preference label set according to the sequence of the count value from large to small if the judging result of the judging module is negative.

Optionally, the preference tag set further includes a count value of each tag, where the count value is used to indicate a degree of interest of the specified user in the tag; the updating module is specifically configured to:

if so, adding one to the count value of the tag in the preference tag set;

Optionally, the apparatus further includes:

the judging module is used for judging whether the count value of the tag in the preference tag set is larger than one before the count value of the tag in the preference tag set is subtracted by one;

the calling module is used for calling the updating module to execute the step of subtracting one from the count value of the tag in the preference tag set if the judging result of the judging module is yes;

and the holding module is used for holding the count value corresponding to the label in the preference label set unchanged if the judging result of the judging module is negative.

In a third aspect of the embodiment of the present application, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any one of the first aspects when executing a program stored on a memory.

In a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the method steps of any of the first aspects.

In a fifth aspect of embodiments of the present application, there is also provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first aspects described above.

The embodiment of the application has the beneficial effects that:

according to the page analysis method, the device, the electronic equipment and the medium, the first type attribute value of at least one second DOM node in the page can be changed into the first type attribute value of the first DOM node with the largest click rate, and then the change of the click rate of the second DOM node before and after the page is changed is compared to obtain whether the first type attribute value affects the click rate or not, so that page improvement suggestions are obtained. The embodiment of the application can analyze the influence of the attribute values such as the position of the DOM node, the content format and the like on the click quantity, so that a designer can design the position of the DOM node of the main push commodity or the DOM node of the advertisement at the position with the largest click quantity, or design the content format into the format with the largest click quantity and the like, thereby improving the recommendation effect on the main push commodity or the advertisement.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the application, and other embodiments may be obtained according to these drawings to those skilled in the art.

FIG. 1 is a flow chart of a page analysis method according to an embodiment of the present application;

FIG. 2 (a) is an exemplary schematic diagram of a designated page provided by an embodiment of the present application;

FIG. 2 (b) is an exemplary schematic diagram of a first update page according to an embodiment of the present application;

FIG. 2 (c) is an exemplary diagram of a second update page according to an embodiment of the present application;

FIG. 3 is a flowchart of a method for pushing an object to a user according to an embodiment of the present application;

FIG. 4 is a flowchart of a method for determining a push object according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a page analysis device according to an embodiment of the present application;

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.

In order to improve the recommending effect of pages on the push commodity or advertisement, the embodiment of the application provides a page analysis method, and a system related to the method comprises a server and a terminal.

The terminal is used for displaying the designated page, receiving clicking operation of a user in the designated page, collecting relevant information of the clicking operation and sending the collected information to the server.

And the server is used for carrying out page analysis according to the information sent by the terminal.

The page analysis method provided by the embodiment of the application is applied to the server in the system. As shown in fig. 1, the method comprises the steps of:

s101, acquiring a first DOM node with the largest click rate in a first preset time period, at least one second DOM node except the first DOM node and the first click rate of the second DOM node in the first preset time period from all the designated document object model (Document Object Model, DOM) nodes included in the designated page.

In the embodiment of the application, the appointed page comprises a plurality of DOM nodes, and the appointed DOM nodes are appointed partial DOM nodes in the appointed page. For example, the designated page may be a shopping website top page, and the shopping website top page includes advertisement DOM nodes, commodity DOM nodes, user information DOM nodes, and the like, where the designated DOM nodes may be advertisement DOM nodes and commodity DOM nodes.

After the terminal displays the designated page, the user can click on the DOM node in the designated page displayed by the terminal, and the terminal can correspondingly record the route information of the currently displayed page, the node information of the clicked DOM node and the click time stamp and send the corresponding relation of the record to the server. The terminal may obtain the route information of the currently displayed page through a window method, for example, the route information includes a uniform resource locator (Uniform Resource Locator, URL) of the page. The node information of the DOM node may include: the name or identification number (Identity document, id) of the object recommended by the DOM node, the position of the DOM node in the page, the link of the page to which the DOM node needs to jump after clicking, etc. The click timestamp is the time at which the DOM node was clicked by the user. The object recommended by the DOM node is an object described by the content of the DOM node, and the content of the DOM node may include a title, a brief introduction, a picture, and the like. The object recommended by the DOM node may be a commodity, a website, an application, or the like.

Alternatively, the terminal may collect other data, including text entered by the user in an input box of the specified page, for example, in addition to the node information of the DOM node clicked by the user in the specified page, and send the collected data to the server.

The server may receive the correspondence relationship sent by the plurality of terminals, and then use the page corresponding to each URL as a designated page, or use the page corresponding to the designated URL as a designated page. And then screening all the clicked DOM nodes in the first preset time period aiming at each appointed page, so as to obtain the first DOM node with the largest click rate in the first preset time period, at least one second DOM node except the first DOM node and the first click rate of the second DOM node in the first preset time period. The second DOM node is a selected DOM node from the specified DOM nodes with the largest non-click quantity. The selection mode comprises random selection or manual selection and the like.

Optionally, the server may also display the click rate of each specific DOM node in the specific page in a thermodynamic diagram manner. For example, DOM nodes with the click rate smaller than 100 in a designated page are marked green, DOM nodes with the click rate within the range of 100-500 are marked blue, and DOM nodes with the click rate exceeding 500 are marked red, so that an analyst can more intuitively see the difference of the click rates of different DOM nodes.

S102, obtaining a second click rate of a second DOM node in the first updated page in a second preset time period.

The first update page is as follows: and changing the first type attribute value of the second DOM node in the appointed page into a first type attribute value of the first DOM node to obtain the page, wherein the first type attribute value is the position or the content format of the DOM node in the page. That is, after S101, the typesetting of the specified page or the content format of the DOM node may be changed, for example, the position of the first DOM node in the specified page and the position of the second DOM node are interchanged, or the title format of the second DOM node in the specified page is changed to the title format of the first DOM node, or the text format of the second DOM node in the specified page is changed to the text format of the first DOM node, so as to obtain the first updated page.

Because the duration has an influence on the click rate, the duration of the second preset time period and the duration of the first preset time period in the embodiment of the application are equal, so that the influence of the duration on page analysis is avoided.

S103, comparing the first click quantity with the second click quantity to obtain an influence result of the first type attribute value on the click quantity.

It will be appreciated that if the second click rate is higher than the first click rate, this indicates that the first attribute value has an effect of increasing the click rate, and if the second click rate is lower than or equal to the first click rate, this indicates that the first attribute value has no effect of increasing the click rate.

S104, obtaining a page improvement strategy for the designated page according to the influence result of the first type attribute value on the click quantity.

After the page improvement strategy is generated, page design references can be provided for page designers, so that the click rate of the main push commodity or advertisement is increased, and the recommendation effect is improved.

According to the page analysis method provided by the embodiment of the application, the first type attribute value of at least one second DOM node in the page can be changed into the first type attribute value of the first DOM node with the largest click quantity, and then the change of the click quantity of the second DOM node before and after the page is changed is compared to obtain whether the first type attribute value affects the click quantity or not, so that page improvement suggestion is obtained. The embodiment of the application can analyze the influence of the attribute values such as the position of the DOM node, the content format and the like on the click quantity, so that a designer can design the position of the DOM node of the main push commodity or the DOM node of the advertisement at the position with the largest click quantity, or design the content format into the format with the largest click quantity and the like, thereby improving the recommendation effect on the main push commodity or the advertisement.

In the embodiment of the present application, the step S103 of comparing the first click quantity with the second click quantity to obtain the effect result of the first attribute value on the click quantity includes the following steps:

Step one, judging whether the difference value between the second click quantity and the first click quantity is larger than a preset difference value. If yes, executing the second step; if not, executing the third step.

Assuming that the specifying DOM node in the specified page includes: a. b, c and d, wherein the first attribute value is the position of the DOM node in the page, b is the first DOM node with the largest click rate, c is randomly selected as the second DOM node, and the positions of b and c in the appointed page are interchanged. And then judging whether the difference between the second click quantity N 'and the first click quantity N of the position before and after the position exchange is larger than a preset difference value N, namely judging whether N' -N > N is true or not.

Wherein the preset difference is greater than 0, for example, the preset difference is 10.

And step two, determining that the first type attribute value has an influence on the click rate.

If the judgment result is yes, the first type attribute value of the first DOM node has a remarkable increasing effect on the click rate of the second DOM node, so that the influence of the first type attribute value on the click rate is determined.

And thirdly, determining that the first type attribute value has no influence on the click quantity.

If the judgment result is negative, the first type attribute value of the first DOM node has no obvious effect of increasing the click rate of the second DOM node, so that the first type attribute value is determined to have no influence on the click rate.

By the method, the embodiment of the application can obtain whether the first type attribute value has influence on the click quantity by comparing whether the click quantity is increased before and after updating the first type attribute value of the second DOM node, thereby realizing automatic analysis on the reason of increasing the click quantity. So that when the page is specified to be upgraded or modified, a designer can improve the recommendation effect of the page after being upgraded or modified on advertisements or main push commodities based on the page improvement strategy.

In the embodiment of the present application, the manner of obtaining the page improvement policy for the specified page according to the result of the influence of the first type attribute value on the click rate in S104 includes the following two cases:

in the first case, if the influence result of the first type attribute value on the click rate indicates that the first type attribute value has an influence on the click rate, generating a page improvement strategy by using the influence result of the first type attribute value on the click rate. The page improvement policy may be: and modifying the preset first type attribute value of the push-to-main DOM node into the first type attribute value of the first DOM node. The push DOM node may be a DOM node for recommending push goods or advertisements.

In the second case, if the impact result of the first type attribute value on the click rate indicates that the first type attribute value has no impact on the click rate, acquiring a third click rate of a second DOM node in a second updated page in a third preset time period, comparing the first click rate with the third click rate to acquire an impact result of the second type attribute value on the click rate, and acquiring a page improvement strategy for the specified page according to the impact result of the second type attribute value on the click rate.

The third preset time period and the first preset time period are equal in duration. The second update page is: and changing the second type attribute value of the second DOM node in the appointed page into the second type attribute value of the first DOM node to obtain the page.

The second type of attribute value is a position or content format of the DOM node in the page, and the second type of attribute value is different from the first type of attribute value. For example, the first type of attribute value is the position of the DOM node in the page, and the second type of attribute value is the content format of the DOM node. Or the first type of attribute value is the content format of the DOM node, and the second type of attribute value is the position of the DOM node in the page.

The method for analyzing the effect of the second type attribute value on the click rate is the same as the method for analyzing the effect of the first type attribute value on the click rate, and reference is made to the above description, which is not repeated here. The method for obtaining the page improvement policy for the specified page according to the effect result of the second type attribute value on the click quantity is the same as the method for obtaining the page improvement policy for the specified page according to the effect result of the first type attribute value on the click quantity, and reference is made to the above description and will not be repeated here.

Optionally, when the impact result of the second type attribute value on the click rate indicates that the second type attribute value has no impact on the click rate, the analysis according to the method of the second case may be continued for other attribute values of the DOM node until the attribute value having impact on the click rate is obtained. For example, the first type of attribute value is the position of the DOM node in the page, the second attribute value is the title format of the DOM node, and the other attribute values are the profile format, color system, picture style, etc. of the DOM node.

By the method, the embodiment of the application can analyze the influence of different types of attribute values on the click quantity to obtain the attribute value with positive influence on the click quantity, so that the obtained page improvement strategy has more reference value.

The following is an illustration of the overall flow of the page analysis method provided by the embodiment of the present application with reference to fig. 2 (a) -2 (c):

fig. 2 (a) is a search page, which includes 4 DOM nodes, DOM node 1 includes a search box, DOM node 2 includes a title, a picture, and a profile, DOM node 3 includes a title and a profile, and DOM node 4 includes a title and a picture. For example, DOM node 2 has the heading "id-some encyclopedia", DOM node 2 has the heading "id (Identity document), and is an identification number, account number, unique code, proprietary number. The picture of DOM node 2 is the picture to the left of the outline of DOM node 2.

The specified DOM node of the page is: DOM node 2, DOM node 3, and DOM node 4. Assuming that the designated DOM node with the largest click rate in the first preset time period is DOM node 2, the positions of DOM node 2 and DOM node 3 are interchanged, and the obtained first updated page is shown in fig. 2 (b).

Assuming that the difference between the second click rate of the DOM node 3 in the page shown in fig. 2 (b) in the second preset time period and the first click rate of the DOM node 3 in the page shown in fig. 2 (a) in the first preset time period is 0, the difference is not greater than the preset threshold value 0, which indicates that the position of the DOM node has no influence on the click rate.

The title format of DOM node 3 may then be changed to the title format of DOM node 2 for the interface shown in fig. 2 (a), i.e. the title of DOM node 3 is set to have an underline and bolded, resulting in a second updated page as shown in fig. 2 (c).

Assuming that the difference between the third click rate of the DOM node 3 in the page shown in fig. 2 (c) in the third preset time period and the first click rate of the DOM node 3 in the page shown in fig. 2 (a) in the first preset time period is 50, the difference is greater than the preset threshold value 0, which indicates that the title format of the DOM node has an influence on the click rate. A page improvement policy for a given page can thus be generated as: the title format of the DOM node of the push commodity or advertisement is modified to the title format of DOM node 2.

The server provided by the embodiment of the application can analyze the preference of the user besides obtaining the page improvement strategy. That is, referring to fig. 3, the server may also perform the following steps:

s301, receiving a page acquisition request sent by a terminal. The page acquisition request is used for requesting to open the specified page or refreshing the specified page.

For example, the terminal may send a page acquisition request to the server when detecting that the user instructs to open the specified page, or when detecting that the user instructs to refresh the specified page.

S302, acquiring a preference label set of a specified user. Wherein the preference tag set comprises: the specified user marks the object recommended by each DOM node clicked in history in each specified DOM node included in the specified page.

In the embodiment of the application, the terminal can send the route information, DOM node information and the clicking time stamp to the server and also send the user information of the user to which the clicking operation belongs to the server. For example, the user information may include a user id. So that the server can determine each DOM node clicked by each user in each page according to the data sent by the terminal.

Each specified DOM node in the specified page is used to recommend an object, each object having at least one preset tag. For example, a commodity DOM node is used to recommend a down jacket having a tag comprising: lady, warm keeping, lovely, etc.

S303, determining a plurality of pushing objects according to the preference label set, and sending a page acquisition response to the terminal. The page acquisition response comprises display information of each push object, so that the terminal displays a recommendation DOM node for recommending each push object in a designated page according to the display information of each push object.

The display information of the pushing object comprises: the title, text, picture, link, etc. of the push object.

The manner in which the plurality of push objects are determined may be described below.

S304, in the time period from the opening of the appointed page to the closing of the appointed page, designating the label of the push object recommended by the clicked recommended DOM node in the page, and forming a click label set.

Optionally, after the specified page is opened this time, the terminal may send, in real time, route information of the specified page, node information of the clicked recommended DOM node, a click timestamp, user information, and the like to the server when detecting that the user clicks the recommended DOM node in the specified page, so that the server may update the click tag set in real time. Then, the terminal may send a message for indicating that the terminal closes the designated page to the server when it is detected that the user instructs to close the designated page.

Or after the specified page is opened this time, the terminal can record the route information of the specified page, the node information of the clicked recommended DOM node, the click time stamp and the user information in real time when detecting that the user clicks the recommended DOM node in the specified page. And then when the user closing the designated page is detected, the recorded information is sent to the server.

The terminal can automatically close the appointed page when detecting that a user clicks any appointed DOM node in the appointed page so as to jump to other pages. Or, the terminal may temporarily not close the specified page when detecting that the user clicks any of the specified DOM nodes in the specified page, so as to jump to other pages, and close the specified page again when detecting that the user instructs to close the specified page.

S305, updating the preference label set according to the click label set.

Because the object recommended by the DOM node clicked by the user is the object of interest to the user, the embodiment of the application can continuously update the preference label set of the user according to the label of the DOM node clicked by the user, so that the object recommended to the user based on the preference label set can be more in line with the preference of the user.

In the embodiment of the present application, referring to fig. 4, the determining, by the S303 server, a manner of pushing a plurality of objects according to a preference tag set includes the following steps:

s401, judging whether count values of all tags included in the preference tag set are lower than a preset threshold value. If yes, executing S402; if not, then S403 is performed.

In the embodiment of the application, the preference tag set further comprises a count value of each tag, wherein the count value is used for indicating the interest degree of a specified user in the tags. Therefore, the count value of the tag is lower than the preset threshold value, which indicates that the interest degree of the designated user on the tag is lower.

For example, the preset threshold is 2, and assuming that the preference tag set is [ A1, B1, C1, D1 ], where each letter represents a tag and the number after the letter represents the count value of the tag, the count value of each tag included in the preference tag set is lower than the preset threshold 2.

S402, randomly selecting a second number of labels from the preference label set, screening a plurality of push objects with the second number of labels from the object library, and randomly acquiring the plurality of push objects from the object library. Wherein each object in the object library has at least one tag.

Because the interest degree of the user on the labels in the preference label set is low, a plurality of push objects can be randomly acquired on the basis of screening the push objects by using the preference label set, so that the preference of the user is explored.

Optionally, the number of push objects with the second number of tags selected from the object library and the number of push objects randomly acquired from the object library may be preset. For example, the number of recommended objects acquired at a time is a specified number, and the number of push objects with the second number of tags screened from the object library may be set to be: specified number x 0.6; the number of push objects randomly acquired from the object library is set to be a specified number×0.4.

S403, acquiring a first number of labels from the preference label set according to the sequence of the count value from large to small, and screening push objects with the first number of labels from the object library.

For example, the preference tag set is [ A7, B5, C3, D1 ], where each letter represents a tag and the number following the letter represents the count value of the tag. Assuming that the first number is 3, the following tags are selected in order of the count value from high to low: A. b and C. Assuming that the tag of object 1 in the object library is [ A, B, C, E ], the tag of object 2 is [ A, B, D ], since the tag of object 1 includes A, B and C, object 1 is taken as a push object.

S404, judging whether the total number of the screened pushing objects is smaller than the specified number. If yes, S405 is executed. If not, obtaining the specified number of push objects.

The specified number can be preset according to the actual situations such as the number of objects which can be displayed simultaneously on the specified page, data transmission delay and the like.

S405, reducing the first number according to a preset step length, acquiring the reduced first number of labels from the preference label set according to the sequence of the count value from large to small, screening the push objects with the reduced first number of labels from the object library, and returning to S404.

The initial value of the first number is preset. For example, the first number is 3, the preset step size is 1, when the first iteration executes S405, the first number is updated to 3-1=2, and assuming that the preference tag set is [ A7, B5, C3, D1 ], the following tags are selected according to the order of the count value from large to small: a and B. Assuming that the label of the object 1 in the object library is [ A, B, C, E ], the label of the object 2 is [ A, B, D ], since the labels of the object 1 and the object 2 both include a and B, the object 1 and the object 2 are both push labels.

Because repeated objects possibly exist among the push objects obtained from the object library each time, the obtained push objects can be subjected to de-duplication to obtain push objects reserved after de-duplication.

Through the method, the push object with the tag which is possibly interested by the user can be recommended to the user according to the preference tag set of the user, so that the probability that the object pushed for the user is favored by the user is improved, and the probability that the user clicks the DOM node of the push object is also improved.

The above S305 server updates the preference tag set according to the click tag set, including the following two ways:

in one mode, for each tab included in the click tab set, it is determined whether the tab exists in the preference tab set. If so, the count value of the tag in the preference tag set is incremented by one. If the label is not present, the count value of the label is determined to be one, and the label and the count value of the label are added into the preference label set.

For example, the click tag set is [ A, M, J, K ], the preference tag set is [ A1, B1, C1, D1 ], and for the tag a in the click tag set, since the tag a is included in the preference tag set, the count value of the tag a in the preference tag set is updated to 1+1=2. For the labels M in the click label set, since the preference label set does not comprise the labels M, the count value of the labels M is set to be 1, and the labels M and the count value 1 are added into the preference label set, so that the updated preference label set is [ A2, B1, C1, D1, M1, J1, K1 ].

In the second mode, based on the first mode, a push label set formed by labels of all push objects may be further obtained, and for each label included in the push label set, whether the label is included in the click label set is determined, and if not, the count value of the label in the preference label set is decremented by one.

For example, push tab set is [ A, J, K ], click tab set is [ B, D ], preference tab set is [ A2, B1, C1, D1, M1, J1, K1 ]. Because all the tags included in the push tag set are not clicked by the user, for the tag A in the push tag set, the count value of the tag A in the preference tag set is 2-1=1, and the like, so that the updated preference tag set is [ A1, B1, C1, D1, M1, J0, K0 ].

Optionally, the server may further determine whether the count value of the tag in the set of preference tags is greater than one before subtracting one from the count value of the tag in the set of preference tags. If yes, the step of subtracting one from the count value of the tag in the preference tag set is executed. If not, keeping the count value corresponding to the label in the preference label set unchanged.

In this way, the embodiment of the application can enable the minimum count value of the tags in the preference tag set to be 1, so that the situation that the count value of the tags is 0 or negative, so that the tags are deleted from the preference tag set is avoided.

For example, push tab set is [ A, J, K ], click tab set is [ B, D ], preference tab set is [ A2, B1, C1, D1, M1, J1, K1 ]. Because all the tags included in the push tag set are not clicked by the user, the count value of the tag A in the preference tag set is updated to 2-1=1 for the tag A in the push tag set; for the label J in the push label set, the count value of the label J in the preference label set is not more than 1, so that the count value of the label J in the preference label set is kept unchanged, and similarly, the count value of the label K in the preference label set is kept unchanged, and the updated preference label set is obtained as [ A1, B1, C1, D1, M1, J1, K1 ].

Because the tags included in the click tag set are tags of interest to the user with high probability, the preference tag set of the user is updated by using the click tag set, so that the preference tag set can be more in line with the preference of the user. Moreover, the labels included in the push label set are not in the click label set, which indicates that the user is not interested in the labels with high probability, so that the preference label set can be updated by using the push label set, and the preference label set is more in line with the preference of the user.

Based on the same inventive concept, the embodiment of the present application further provides a page analysis device, as shown in fig. 5, including: an acquisition module 501, a comparison module 502 and a generation module 503;

the obtaining module 501 is configured to obtain, from each specified DOM node included in the specified page, a first DOM node with a largest click rate in a first preset time period, at least one second DOM node except the first DOM node, and a first click rate of the second DOM node in the first preset time period;

the obtaining module 501 is further configured to obtain a second click rate of a second DOM node in the first update page within a second preset period of time; the second preset time period and the first preset time period have equal duration, and the first update page is: changing a first type attribute value of a second DOM node in a designated page into a first type attribute value of the first DOM node to obtain a page, wherein the first type attribute value is the position or content format of the DOM node in the page;

The comparison module 502 is configured to compare the first click rate and the second click rate obtained by the obtaining module 501, and obtain an influence result of the first attribute value on the click rate;

and the generating module 503 is configured to obtain a page improvement policy for the specified page according to the impact result of the first type attribute value on the click rate obtained by the comparing module 502.

Optionally, the comparing module 502 is specifically configured to:

judging whether the difference between the second click quantity and the first click quantity is larger than a preset difference or not;

Optionally, the page improvement policy is: and modifying the preset first type attribute value of the push-to-main DOM node into the first type attribute value of the first DOM node.

Optionally, the generating module 503 is specifically configured to:

if the influence result indicates that the first type attribute value has no influence on the click quantity, acquiring a third click quantity of a second DOM node in a second updated page in a third preset time period, wherein the third preset time period is equal to the first preset time period in duration, and the second updated page is: changing a second type attribute value of a second DOM node in the appointed page into a second type attribute value of a first DOM node to obtain a page, wherein the second type attribute value is a position or a content format of the DOM node in the page, and the second type attribute value is different from the first type attribute value;

Optionally, the apparatus further comprises:

the receiving module is used for receiving a page acquisition request sent by the terminal, wherein the page acquisition request is used for requesting to open a designated page or refreshing the designated page;

the obtaining module 501 is further configured to obtain a preference tag set of the specified user, where the preference tag set includes: designating labels of objects recommended by each DOM node clicked in history in each designated DOM node included in the designated page by the user;

the determining module is used for determining a plurality of pushing objects according to the preference label set acquired by the acquiring module, and sending a page acquiring response to the terminal, wherein the page acquiring response comprises display information of each pushing object, so that the terminal displays a recommendation DOM node for recommending each pushing object in a designated page according to the display information of each pushing object;

the construction module is used for forming a click tag set by the tags of the push objects recommended by the clicked recommended DOM nodes in the appointed page in the time period from the moment of opening the appointed page to the moment of closing the appointed page by the terminal;

And the updating module is used for updating the preference label set according to the click label set obtained by the construction module.

Optionally, the preference tag set further includes a count value of each tag, the count value being used to indicate a degree of interest of the specified user in the tag; the determining module is specifically configured to:

if yes, reducing the first number according to the preset step length, acquiring the reduced first number of labels from the preference label set according to the sequence of the count value from large to small, screening the push objects with the reduced first number of labels from the object library, and returning to the step of judging whether the total number of the screened push objects is smaller than the specified number or not until the specified number of push objects are obtained.

Optionally, the apparatus further comprises:

the judging module is used for judging whether the count value of each tag included in the preference tag set is lower than a preset threshold value before the first number of tags are acquired from the preference tag set according to the sequence of the count values from large to small;

The screening module is used for randomly selecting a second number of labels from the preference label set if the judgment result of the judgment module is yes, screening a plurality of pushing objects with the second number of labels from the object library, and randomly acquiring the plurality of pushing objects from the object library;

Optionally, the preference tag set further includes a count value of each tag, the count value being used to indicate a degree of interest of the specified user in the tag; the updating module is specifically used for:

if so, adding one to the count value of the tag in the preference tag set;

if the label is not present, the count value of the label is determined to be one, and the label and the count value of the label are added into the preference label set.

Determining whether the label exists in the preference label set for each label included in the click label set; if so, adding one to the count value of the tag in the preference tag set; if the label does not exist, determining the count value of the label to be one, and adding the label and the count value of the label into a preference label set;

Optionally, the apparatus further comprises:

the judging module is used for judging whether the count value of the tag in the preference tag set is larger than one before subtracting one from the count value of the tag in the preference tag set;

The embodiment of the application also provides an electronic device, as shown in fig. 6, which comprises a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602 and the memory 603 complete communication with each other through the communication bus 604,

A memory 603 for storing a computer program;

the processor 601 is configured to implement the method steps executed by the server in the above-described method embodiment when executing the program stored in the memory 603.

The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-ProgrammableGate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present application, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of any of the page analysis methods described above.

In yet another embodiment of the present application, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the page analysis methods of the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method of page analysis, the method comprising:

Obtaining a page improvement strategy for the appointed page according to the influence result of the first type attribute value on the click quantity;

the obtaining a page improvement strategy for the specified page according to the influence result of the first type attribute value on the click quantity comprises the following steps:

2. The method of claim 1, wherein comparing the first click volume with the second click volume results in an impact of a first type of attribute value on click volume, comprising:

3. The method of claim 1, wherein the page improvement policy is: and modifying the preset first type attribute value of the main push DOM node into the first type attribute value of the first DOM node.

4. The method according to claim 1, wherein the method further comprises:

and updating the preference tag set according to the click tag set.

5. The method of claim 4, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the determining a plurality of push objects according to the preference tag set includes:

6. The method of claim 5, wherein prior to the obtaining the first number of tags from the set of preference tags in the order of the count value from greater to lesser, the method further comprises:

7. The method of claim 4, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the updating the preference tag set according to the click tag set comprises the following steps:

If so, adding one to the count value of the tag in the preference tag set;

8. The method of claim 4, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the updating the preference tag set according to the click tag set comprises the following steps:

9. The method of claim 8, wherein prior to said decrementing the count value for the tag in the set of preference tags, the method further comprises:

10. A page analysis device, the device comprising:

the generation module is used for obtaining a page improvement strategy for the appointed page according to the influence result of the first type attribute value on the click quantity, which is obtained by the comparison module;

the generating module is specifically configured to:

11. The apparatus according to claim 10, wherein the comparison module is specifically configured to:

12. The apparatus of claim 10, wherein the page improvement policy is: and modifying the preset first type attribute value of the main push DOM node into the first type attribute value of the first DOM node.

13. The apparatus of claim 10, wherein the apparatus further comprises:

14. The apparatus of claim 13, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the determining module is specifically configured to:

15. The apparatus of claim 14, wherein the apparatus further comprises:

16. The apparatus of claim 13, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the updating module is specifically configured to:

if so, adding one to the count value of the tag in the preference tag set;

17. The apparatus of claim 13, wherein the set of preference tags further comprises a count value for each tag, the count value being indicative of a degree of interest in the tag by the specified user; the updating module is specifically configured to:

18. The apparatus of claim 17, wherein the apparatus further comprises:

19. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any one of claims 1-9 when executing a program stored on a memory.

20. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-9.