CN112035744A

CN112035744A - Page recommendation method, device, equipment and storage medium

Info

Publication number: CN112035744A
Application number: CN202010898605.2A
Authority: CN
Inventors: 康岩基
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: CCB Finetech Co Ltd
Priority date: 2020-08-31
Filing date: 2020-08-31
Publication date: 2020-12-04
Anticipated expiration: 2040-08-31
Also published as: CN112035744B

Abstract

The embodiment of the invention discloses a page recommendation method, a device, equipment and a storage medium. The method comprises the following steps: collecting browser behavior data of each client, and generating at least one page chain corresponding to each client respectively, wherein the page chain comprises: a page set formed according to a set organization sequence; responding to an access request of a target client to a target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client; and providing the description information of each prediction result page to the target client. The method can predict the next action of the user through the browser action data of the user, can directly provide the description information of the prediction result page corresponding to the next action to the user so as to access the prediction result page corresponding to the next action, can reduce the operation steps of the user in the browser access, and saves the operation time of the user.

Description

Page recommendation method, device, equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of communication, in particular to a page recommendation method, a device, equipment and a storage medium.

Background

A browser is an application program used to retrieve, present, and deliver World Wide Web (Web) information resources. The user may query for associated information through the browser via a hyperlink. With the development of communication technology, browsers are not only tools for information query, but also tools for some transactions, such as shopping, booking tickets or completing some workflows.

In the prior art, the content of a page is analyzed by collecting the retention time of the page in a browser and the content information of the page, so as to push related browsing information for a user. However, the push in the prior art is only a push for browsing contents, for example, when a user inquires about sports while shopping, sports-related items such as sports shoes, running clothes, yoga mats, etc. may be pushed for the user. The push in the prior art cannot predict the next action of the user, and cannot save the operation steps and the operation time of the user in the browser access.

Disclosure of Invention

The embodiment of the invention provides a page recommendation method, a device, equipment and a storage medium, which can predict the next action of a user and provide a corresponding page, and can reduce the operation steps and the operation time of the user.

In a first aspect, an embodiment of the present invention provides a page recommendation method, where the method is executed by a server, and includes:

collecting browser behavior data of each client, and generating at least one page chain corresponding to each client, wherein the page chain comprises: a page set formed according to a set organization sequence;

responding to an access request of a target client to a target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client;

and providing the description information of each prediction result page to the target client.

In a second aspect, an embodiment of the present invention provides a page recommendation method, where the method is executed by a client, and includes:

recording browser behavior data, and providing the browser behavior data to a server to instruct the server to generate at least one page chain corresponding to a client according to the browser behavior data, wherein the page chain comprises: a page set formed according to a set organization sequence;

sending an access request for a target page to the server so as to obtain page data of the target page from the server for local display;

in the process of accessing a target page, receiving description information which is provided by the server and corresponds to at least one prediction result page matched with the target page;

and displaying the description information corresponding to each prediction result page in the target page.

In a third aspect, an embodiment of the present invention further provides a page recommendation apparatus, where the apparatus is configured in a server, and includes:

the page chain generation module is used for acquiring browser behavior data of each client and generating at least one page chain corresponding to each client, and the page chain comprises: a page set formed according to a set organization sequence;

the prediction result page determining module is used for responding to an access request of a target client to a target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client;

and the description information providing module is used for providing the description information of each prediction result page to the target client.

In a fourth aspect, an embodiment of the present invention further provides a page recommendation device, where the page recommendation device is configured in a client, and the page recommendation device includes:

a browser behavior data providing module, configured to record browser behavior data, and provide the browser behavior data to a server, so as to instruct the server to generate at least one page chain corresponding to a client according to the browser behavior data, where the page chain includes: a page set formed according to a set organization sequence;

the access request sending module is used for sending an access request for a target page to the server so as to obtain page data of the target page from the server and locally display the page data;

the description information receiving module is used for receiving description information which is provided by the server and corresponds to at least one prediction result page matched with a target page in the access process of the target page;

and the description information display module is used for displaying the description information corresponding to each prediction result page in the target page.

In a fifth aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a method of page recommendation as described in any of the embodiments of the invention.

In a sixth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a page recommendation method according to any embodiment of the present invention.

According to the technical scheme of the embodiment of the invention, at least one page chain corresponding to each client is generated by collecting browser behavior data of each client, and each page chain comprises: a page set formed according to a set organization sequence; responding to an access request of a target client to a target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client; the description information of each prediction result page is provided for the target client, so that the recommendation problem of the browser page is solved, the next action of the user is predicted according to the action data of the browser of the user, the description information of the corresponding page is provided, the operation steps of the user in the browser access are reduced, and the operation time of the user is saved.

Drawings

Fig. 1 is a flowchart of a page recommendation method according to an embodiment of the present invention;

fig. 2 is a flowchart of a page recommendation method according to a second embodiment of the present invention;

fig. 3 is a flowchart of a page recommendation method provided in the third embodiment of the present invention;

fig. 4 is a flowchart of a page recommendation method provided in the third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a page recommendation apparatus according to a fourth embodiment of the present invention;

fig. 6 is a schematic structural diagram of a page recommendation device according to a fifth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a page recommendation method according to an embodiment of the present invention, where this embodiment is applicable to a case where a user predicts a user behavior to reduce user operation steps when performing a transaction in a browser, and the method may be executed by a page recommendation device, where the device may be implemented in a software and/or hardware manner, and the device may be integrated in a server, as shown in fig. 1, where the method specifically includes:

step 110, collecting browser behavior data of each client, and generating at least one page chain corresponding to each client.

Wherein, page chain includes: and page sets formed according to a set organization sequence. The client may have a browser-type access function, and may be a browser-type client or an application client of an embedded web page, for example. The browser behavior data may be data generated by a user accessing a web page at a client, and may be, for example, data related to access content of a certain web page by the user, access time, access times, and a jump relationship between pages. The collecting of the browser behavior data of the client may be that the client actively reports log data, and the browser behavior data is determined through the log data. For example, the server may determine data such as user information, access address information, access time, request mode, and request parameters by collecting log data of the client.

The server may generate a chain of pages from the browser behavior data. The page chain may refer to a data chain formed by data generated by at least one page access performed by a user in the client within a preset time period. For example, in 5 minutes, the user browses information for 2 seconds to page a, fills in a form for 4 minutes to page b, and downloads a file for 3 seconds and browses information for 55 seconds to page c in client a. The access of page a, page b and page c and the data generated by the jumping process can be used as a page chain. That is, a plurality of pages and access data of each page may be included in the page chain, where the access data may be information such as access sequence and access time.

The set organization order may be consistent with the access order. The pages in the page chain may be pages of the same website, for example, all pages resulting from an access to a certain shopping channel website. The mode of generating the page chain may be various, for example, the page chain may be generated according to data generated by access to the same website in the browser behavior data within a preset time; alternatively, a chain of pages may be generated from all data resulting from visits to the same website.

To specifically describe the page chains, in an implementation manner of the embodiment of the present invention, optionally, the acquiring browser behavior data of each client, and generating at least one page chain corresponding to each client includes: in the browser behavior data of the current client, a plurality of pages with continuous access time and jump relation between adjacent pages are obtained to form a page chain corresponding to the current client.

When a user accesses a browser in a client, the user usually stays in a certain page for a period of time and then jumps to the next page to access the browser. For example, in some transactions, a user's browser access typically has the above-described characteristics. For example, when a user purchases a product in a browser, the user usually enters a home page of the browser to search a shopping page corresponding to a certain shopping channel, and performs a login operation; then some kind of articles of interest are selected in the shopping page for searching, then some kind of articles are screened according to some attribute conditions, and then the desired articles are selected from the screened articles for purchasing. The server can take the browser behavior data generated when the above-mentioned goods are purchased as a page chain corresponding to the client. For example, the page chain may be: accessing a certain shopping page for logging in, searching certain types of articles, screening according to certain attribute conditions, and purchasing articles on a certain screening page.

In order to accurately store the page chains, in an implementation manner of the embodiment of the present invention, optionally, after acquiring browser behavior data of each client and generating at least one page chain corresponding to each client, the method further includes: and determining master station information respectively corresponding to each page chain corresponding to the current client, and storing each page chain in a classified manner according to the master station information.

When a user accesses a browser in a client, the user does not usually access the same website singly, and each page chain may not be related to a certain website. Therefore, when a prediction result page matching the target page is determined from the page chain, it may be inconvenient to operate. In order to store the page chains in a standard manner and facilitate the rapid determination of the prediction result page matched with the target page through the page chains in the later period, in the embodiment of the invention, the master station information of each page chain can be determined, and the page chains are stored in a classified manner according to the master station information.

The master station information may refer to information of a host name in a website corresponding to the page. Typically, the web address includes a protocol name such as HTTP, a host name such as www.XXX.com, and a path and file name. A hostname similar to www.XXX.com may be used as the master station information. When a user performs a transaction, multiple pages which are accessed usually have the same master station information. For example, when a user purchases a shopping channel, pages corresponding to web addresses related to the host name of the shopping channel are accessed from the first page for logging in the shopping channel to the end of shopping. For another example, the pages corresponding to the website related to the host name of the ticket booking website are all accessed from the first page of the website for booking tickets when the user logs in the ticket booking website to the ticket booking completion. For another example, when a user logs in a certain enterprise website to perform information filling declaration, all pages corresponding to the websites related to the host name of the enterprise website are accessed. The page chains are classified and stored through the main station information, so that the page chains with consistent main station information can be quickly found when a user is determined to access a certain website, and the quick matching of the prediction result pages is facilitated.

And step 120, responding to an access request of the target client to the target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client.

The user can initiate an access request of a target page in the client, and the client initiating the access request of the target page can be used as the target client. The target page may be a website accessed by the user at the client, for example, a first page of a shopping channel, a first page of a booking channel, a first page of an enterprise or a first page of a school, etc. The target page chain may be generated from historical browser behavior data resulting from page accesses by the user at the target client. The server may have a plurality of page chains corresponding to the clients, and in order to quickly match the predicted result page and to obtain the matching accuracy, a target page chain corresponding to the target client may be acquired first.

The prediction result page may be a page corresponding to the next behavior of the user determined according to the target page and a target page chain corresponding to the target client. For example, when the target page chain is that the user accesses the target page, the page d is finally accessed through the page a, the page b and the page c, and the page d can be used as a prediction result page.

Illustratively, when a target page chain is a website for a user to log in a certain shopping channel, yoga is searched, brand, price and sales are screened, and shopping is carried out on the screened page. The prediction results page may be a filtered page. When a user initiates website access of a certain shopping channel at a client, the screened page can be directly determined as a prediction result page, and the prediction result page is recommended to the user. Intermediate steps of login, search, screening and the like of the user can be skipped, the screening result is directly returned, the operation and time of the user are reduced, and the user experience is improved.

In another example, when the target page chain logs in a website of a certain booking channel for a user, the starting place and the destination are determined, the high-speed rail for departure in a certain time period in a certain departure date is determined, and ticket buying is performed. The prediction result page may be a page that determines that the origin corresponds to the destination and a high-speed rail from which the vehicle is dispatched for a certain period of time. When a user initiates website access of a certain booking channel at a client, a page corresponding to a high-speed rail where a starting place and a destination are determined and a certain time period of departure is determined can be directly used as a prediction result page, and the prediction result page is recommended to the user. The intermediate steps of login, origin and destination determination, departure time period determination, vehicle type determination and the like of the user can be skipped, and the transaction processing result is directly returned, so that the operation and time of the user are reduced, and the user experience is improved.

In another example, when the target page chain logs in a website of a certain enterprise or school for the user, the information is filled and checked, and finally, the information filling result is printed on the information filling page. The prediction result page may be an information filling page. When a user initiates a website of a certain enterprise or school at a client, the information filling page can be directly recommended to the user. The process of skipping from the first page of an enterprise or a school to the information filling page one by one can be skipped, and the information filling page is directly returned, so that the information change or result query can be conveniently carried out on the information filling page by a user, the operation and time of the user are reduced, and the user experience is improved.

It should be noted that the prediction result page of the present embodiment may also be a page of another application scenario matched according to the target page. The number of matched prediction result pages may be one or more for one target page. The result prediction page is used for reducing the operation steps and time of a user in browser access, and particularly when the user performs transaction processing operation, the intermediate steps can be skipped, the transaction processing result can be directly returned, and the transaction processing efficiency is improved.

In order to quickly match a more accurate predicted result page for a target page, in an implementation manner of the embodiment of the present invention, optionally, before determining at least one predicted result page that matches the target page according to at least one target page chain corresponding to the target client, the method further includes: and acquiring target master station information corresponding to the target page, and determining at least one target page chain corresponding to the target client according to the target master station information.

When the target client initiates an access request of the target page to the server, the server can identify the master station information of the target page as the target master station information according to the website of the target page. The server may use, as the target page chain, a page chain in which the master station information is consistent with the target master station information in the page chain corresponding to the target client. The target page chain may exist in the target page chain, for example, when the target page is a website of a certain shopping channel, the target page chain may be generated by the page and data when the user purchases through the website of the certain shopping channel. One or more target page chains may exist for one target page.

In an implementation manner of the embodiment of the present invention, optionally, determining, according to at least one target page chain corresponding to the target client, at least one predicted result page that matches the target page includes: acquiring at least one alternative page chain in each target page chain; and generating at least one prediction result page according to the last page in each alternative page chain.

For example, when a user visits the same website for multiple times to perform the same or similar transaction, the repeated page chain may be generated. The server may use any one of the repeated page chains in the target page chain and the non-repeated page chain as the alternative page chain. For example, the destination page chain includes page chain 1, page chain 2, and page chain 3. The server may use page chain 1, page chain 2, and page chain 3 as alternative page chains.

The last page of the alternative page chain refers to the page when the user performs the last operation in the website during the browser access. For example, when the user purchases, the page displayed by the item screening result may be the last page; or, when the user orders, the page displayed by the screened train number result can be the last page; or when the user fills in the information in the website, the filled information page can be a last page; or, when the user queries information in the browser, the page displayed by the final query result may be the last page, and for example, when the user queries a patent related to a web page in the browser, the page displaying the patent of the web page may be the last page.

In some scenarios, the last page may be one page or may be multiple pages. For example, when the user purchases, the last page may be a page on which the item screening result is displayed, which may facilitate the user to purchase the item again; or, the last page may also be a page where the purchase of the article is successful, which may facilitate the user to query the details of the order, the logistics information, or the refund.

The prediction result page may be a page corresponding to the last-bit page. For example, the last page is a page on which the item filtering result is displayed, and the prediction result page may also be a page on which the item filtering result is displayed. Further, the prediction result page may be one or more. The prediction result page can also be determined according to the repetition times of the page chain in the target page chain. For example, a page chain with a repetition number less than a preset number may not be used as an alternative page chain, and a corresponding prediction result page may not be generated. The prediction result page can be determined according to the page chain with the large number of times of repetition, the next action of the user can be predicted more accurately, and the interference to the user caused by too many prediction result pages provided for the user is avoided.

And step 130, providing the description information of each prediction result page to the target client.

The description information may be page identification information of the prediction result page, and may be, for example, a page name of the prediction result page, or identification information summarized according to key content displayed by the prediction result page. For example, when the prediction result page is the screened yoga product page, the description information may be the yoga product, or the yoga product with certain attributes, or the like. The client can receive the description information of each prediction result page sent by the server and can display the description information. The user can select any description information in the client, for example, clicking, double clicking or touching any description information. The client can display the prediction result page corresponding to the selected description information according to the description information selected by the user, and can skip the middle step in the transaction processing to directly reach the transaction processing result page, thereby saving the operation and time of the user.

In an implementation manner of the embodiment of the present invention, optionally, after acquiring browser behavior data of each client and generating at least one page chain corresponding to each client, the method further includes: and analyzing the user behavior of each page chain corresponding to the current client to acquire behavior result data respectively corresponding to each page chain.

The user behavior analysis may be content analysis, such as text analysis and access time analysis, on pages in the page chain. The behavior result data may be operations performed by the determined user through a page, such as product screening results or information filling results.

In an implementation manner of the embodiment of the present invention, optionally, providing description information of each prediction result page to the target client includes: and acquiring page chains respectively corresponding to the prediction result pages, and providing the description information of the prediction result pages constructed by the behavior result data of the acquired page chains to the target client.

The description information of the prediction result page may be constructed by the behavior result data of the corresponding page chain. For example, the behavior result data of the page chain is the screening yoga product, the description information of the corresponding prediction result page may be the screening result page of the yoga product, and the user can intuitively know the key content displayed on the prediction result page to be skipped to through the description information.

According to the technical scheme of the embodiment, at least one page chain corresponding to each client is generated by collecting browser behavior data of each client, and the page chain comprises: a page set formed according to a set organization sequence; responding to an access request of a target client to a target page, and determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client; the description information of each prediction result page is provided for the target client, so that the recommendation problem of the browser page is solved, the next action of the user is predicted according to the action data of the browser of the user, the description information of the corresponding page is provided, the operation steps of the user in the browser access are reduced, and the operation time of the user is saved.

Example two

Fig. 2 is a flowchart of a page recommendation method provided in a second embodiment of the present invention, which is a further refinement of the foregoing technical solution, and the technical solution in this embodiment may be combined with various alternatives in one or more of the foregoing embodiments. As shown in fig. 2, the method includes:

step 210, in the browser behavior data of the current client, a plurality of pages with continuous access time and a skip relation between adjacent pages are obtained to form a page chain corresponding to the current client.

Wherein, page chain includes: and page sets formed according to a set organization sequence.

And step 220, determining master station information respectively corresponding to each page chain corresponding to the current client, and storing each page chain according to the master station information in a classified manner.

And step 230, determining master station information respectively corresponding to each page chain corresponding to the current client, and storing each page chain according to the master station information in a classified manner.

And 240, acquiring at least one alternative page chain in each target page chain.

And step 250, generating at least one prediction result page according to the last page in each alternative page chain.

And step 260, sequencing the prediction result pages according to the chain weight of the page chain corresponding to each prediction result page, and providing the description information of each prediction result page to the target client according to the sequencing result.

Wherein the chain weight may be a weight of a chain of pages. Each page chain may have a chain weight, which may be the same for the page chains that repeat each other. The determination mode of the chain weight is various, for example, the chain weight can be determined by the repetition times of the page chain, and the higher the repetition times is, the larger the chain weight is; or the chain weight is larger as the access time is closer to the current time; or, it may be determined by presetting a chain weight value; or comprehensively determining the chain weight according to one or more chain weight determination modes.

For example, in a plurality of prediction result pages, a preset chain weight may be determined for a page chain in advance, and after the prediction result pages are sorted according to the preset chain weight, the pages are provided to a client, so that popularization of some pages can be facilitated.

The ranking of the prediction results pages may be according to the corresponding chain weights, e.g., the higher the chain weight, the earlier the ranking of the corresponding prediction results pages may be. The prediction result can be more accurate, the user can preferentially obtain the prediction result page corresponding to the most possible operation, and the user experience is improved.

Specifically, in an implementation manner of the embodiment of the present invention, optionally, after acquiring browser behavior data of each client and generating at least one page chain corresponding to each client, the method further includes: and determining the chain weight respectively corresponding to each page chain of the current client according to the access times and/or access time of each page chain corresponding to the current client.

The determination method of the chain weight of the page chain may be various. For example, a mapping relationship between the number of visits and/or visit time of a chain of pages and the weight of the chain may be established. And determining the chain weight of the page chain according to the mapping relation, and further determining the sequencing order of the corresponding prediction result pages according to the chain weight.

Illustratively, if the number of visits (number of repetitions) to the page chain is greater than 10, the chain weight may be determined to be 0.65; the number of visits (repetitions) to the page chain is greater than 5 and less than 10, and the chain weight can be determined to be 0.25; the number of visits (repetitions) to the page chain is less than 5, and the chain weight can be determined to be 0.1.

For another example, if the difference between the visit time of the page chain and the current time is less than 1 day, the chain weight may be determined to be 0.6; the time difference between the access time of the page chain and the current time is more than 1 day and less than 5 days, and the weight of the chain can be determined to be 0.2; the time difference between the access time of the page chain and the current time is more than 5 days and less than 15 days, and the weight of the chain can be determined to be 0.15; the difference between the access time of the page chain and the current time is greater than 15 days, and the weight of the chain can be determined to be 0.05. When the time difference between the access time and the current time is determined, the time difference between the access time closest to the current time and the current time may be determined.

As yet another example, the chain weight may be determined based on the number of visits and the visit time of the chain of pages. For example, if the number of visits (number of repetitions) to the page chain is greater than 10 and the difference between the visit time of the page chain and the current time is less than 1 day, the chain weight may be determined to be 0.7.

Step 270, responding to the selection instruction of the target client to the description information of the target prediction result page, and providing the page data matched with the target prediction result page to the target client.

The server may sort the prediction result pages according to the chain weight. The client can display the corresponding description information according to the sorting sequence of the prediction result pages. The user can select the description information in the client, such as clicking, double clicking or touching. The client side can send the description information selected by the user to the server, and the server can provide the page data matched with the prediction result page corresponding to the description information to the client side so that the client side can jump the target page to the prediction result page.

In order to implement the jump of the predicted result page by the client, in an implementation manner of the embodiment of the present invention, optionally, the browser behavior data at least includes: user information, access address information, a request mode and a request parameter; providing page data matched with the target prediction result page to the target client, wherein the page data comprises: and providing the user information, the access address information, the request mode and the request parameters matched with the target prediction result page to the target client.

The user information may include information of the device used by the user (or account information of the user) and information of the client. The chain of pages generated by the server may be different for different devices used and/or different clients, and the prediction result pages may also be different. For example, when different use devices of the same client are all related to shopping transactions, the prediction result page generated by the use device I may be a screening page of yoga products; the predicted results page generated for use with device II may be a filter page for basketball products.

The access address information may include a website address of the user access website, and jump information between a plurality of websites. The request mode may include a request mode when the user accesses each website, such as a post request or a get request. The request parameters comprise account information, password information, keyword information related to webpage content and the like of the user. The keyword information related to the web page content may be some information of the user during transaction processing, for example, yoga, a certain brand, a certain price, a certain sales volume, and the like.

The client side can be provided with an executor, and the executor can generate a target prediction result page according to the user information, the access address information, the request mode and the request parameters matched with the target prediction result page. For example, the request parameters and the user information are submitted to the website corresponding to the access address information in a request mode to generate a target prediction result page.

According to the technical scheme of the embodiment of the invention, all the prediction result pages are sorted according to the chain weight of the page chain corresponding to each prediction result page, and the description information of each prediction result page is provided to the target client according to the sorting result; the page data matched with the target prediction result page is provided for the target client in response to the selection instruction of the target client for the description information of the target prediction result page, so that the problem of page recommendation is solved, the prediction result page is recommended for the user according to the chain weight, the user can conveniently obtain the page which is most likely to be accessed, and the operation steps and the operation time of the user can be saved.

EXAMPLE III

Fig. 3 is a flowchart of a page recommendation method according to a third embodiment of the present invention, where this embodiment is applicable to a case where a user predicts a user behavior to reduce user operation steps when performing a transaction in a browser, and the method may be executed by a page recommendation device, where the device may be implemented in a software and/or hardware manner, and the device may be integrated in an electronic device such as a mobile phone or a computer, as shown in fig. 3, where the method specifically includes:

and step 310, recording the browser behavior data, and providing the browser behavior data to the server to instruct the server to generate at least one page chain corresponding to the client according to the browser behavior data.

The client may record the browser behavior data in the form of a log. The client can report log data to the server, namely report browser behavior data. The server may generate a corresponding page chain according to the browser behavior data, and a specific generation manner may be the same as or similar to that of the page chain in the above embodiment.

And step 320, sending an access request for the target page to the server so as to obtain the page data of the target page from the server for local display.

The user may make an access request for the target page in the client, for example, the user may input a web address of the target page in the client or enter the target page through a keyword search in the client (browser). The client may use the website of the target page, the user information, and the like as an access request to request the server to provide page data related to the target page. The client may locally display the target page according to the page data. The page data may include page user information, access address information, a request mode, and a request parameter, and may further include content data and image data required when the target page is rendered.

Step 330, during the process of accessing the target page, receiving the description information provided by the server and corresponding to at least one prediction result page matched with the target page.

The server can determine a target page chain according to the target master station information of the target page, determine a prediction result page according to the target page chain, and construct description information according to behavior result data of the page chain corresponding to the prediction result page. The process of the server determining the prediction result page and the description information according to the target page may be the same as or similar to the generation process of the prediction result page and the description information in the above embodiment, and is not described here again. When the client accesses the target page, the server can provide the client with the description information corresponding to the prediction result page.

And 340, displaying the description information corresponding to each prediction result page in the target page.

The client can display the received description information in the target page display. For example, the description information may be displayed in a menu form, and the client may determine the target prediction result page through the selection of the description information by the user. The client can request page data of the target prediction result page from the server, generate the target prediction result page according to the page data, and jump the target page to the target prediction result page. The method can realize the effect of skipping the intermediate steps in the transaction processing and directly reaching the transaction processing result, thereby saving the time of a user and the operation steps.

In an implementation manner of the embodiment of the present invention, optionally, displaying the description information corresponding to each prediction result page in the target page includes: and displaying the description information corresponding to each prediction result page in the target page according to the sequencing result of the prediction result page.

The ranking result of the predicted result page may be determined by the server according to the chain weight, and the specific determination manner may be the same as or similar to the ranking result determination manner in the above example. The client can display the description information according to the sequencing result of the corresponding prediction result page. For example, the higher the predicted result page rank is, the higher the corresponding description information rank is.

On the basis of the foregoing embodiment, optionally, after the description information corresponding to each prediction result page is displayed in the target page, the method further includes: acquiring a selection instruction of the description information corresponding to the target prediction result page, and acquiring page data matched with the target prediction result page from a server; and generating a target prediction result page according to the page data, and skipping the target page to the target prediction result page.

The user can select the description information in the client, and the client can initiate a request to the server according to the selection condition of the user. The server can determine a target prediction result page according to the corresponding relation between the description information and the prediction result page. The server may provide the page data of the target prediction result page match to the client. The client side can generate a target prediction result page through the executor according to the page data, and jump the target page to the target prediction result page. The intermediate step that the user needs to operate can be omitted, and the time of the user is saved.

It should be noted that the client may further be provided with an option for accessing the web page by user-defined, or may be set to exit the web page recommendation mode and maintain a mode for accessing the web page by user-defined when the client does not obtain a selection instruction of the description information by the user within a preset time period. The method can provide various choices for the user, can provide an operable item for the user when the user needs to perform new transaction processing through the target page, considers various functions and is convenient for the user to operate.

In an implementation manner of the embodiment of the present invention, optionally, the browser behavior data at least includes: user information, access address information, a request mode and a request parameter; acquiring page data matched with a target prediction result page from a server, wherein the page data comprises the following steps: and acquiring page user information, access address information, a request mode and request parameters matched with the target prediction result page from the server.

The client can generate the target prediction result page through the executor according to the page user information, the access address information, the request mode and the request parameter matched with the target prediction result page.

According to the technical scheme of the embodiment, the server is instructed to generate at least one page chain corresponding to the client according to the browser behavior data by recording the browser behavior data and providing the browser behavior data to the server; sending an access request to a target page to a server so as to obtain page data of the target page from the server for local display; in the process of accessing a target page, receiving description information which is provided by a server and corresponds to at least one prediction result page matched with the target page; the description information corresponding to each prediction result page is displayed in the target page, the problem of page recommendation is solved, the description information corresponding to the prediction result page is recommended to the user according to the target page, the target prediction result page is convenient to determine according to the description information selected by the user, the target prediction result page is jumped to from the target page, and the user operation steps and the operation time are saved.

Fig. 4 is a flowchart of a page recommendation method according to a third embodiment of the present invention, and as shown in fig. 4, a client may collect browser behavior data of a user, for example, record the browser behavior data in a log record form. The client may report the browser behavior data of the user, for example, report the browser behavior data in a report log form. The server can analyze and store the browser behavior data. For example, the server may record browser behavior data containing information such as user information, access address information, access time, request mode, and request parameters.

The server can generate a page chain corresponding to the client according to the browser behavior data. When a user accesses a target page in a client, the server can determine a prediction result page according to the target page and a corresponding page chain. The server can send the description information corresponding to the prediction result page to the client. The client can display the description information and acquire a selection instruction of the user on the description information. The client can request the server for the page data of the target prediction result page according to the description information selected by the user. The executor of the client can generate a target prediction result page according to the page data and jump the page, so that the clicking times of the user during browsing can be greatly reduced, and the browsing time and the operation steps of the user are saved.

Example four

Fig. 5 is a schematic structural diagram of a page recommendation apparatus according to a fourth embodiment of the present invention. Referring to fig. 5, the apparatus is configured in a server, and includes: a page chain generation module 510, a prediction result page determination module 520 and a description information providing module 530.

The page chain generating module 510 is configured to collect browser behavior data of each client, and generate at least one page chain corresponding to each client, where the page chain includes: a page set formed according to a set organization sequence;

a predicted result page determining module 520, configured to determine, in response to an access request of a target client to a target page, at least one predicted result page that matches the target page according to at least one target page chain corresponding to the target client;

and a description information providing module 530, configured to provide description information of each prediction result page to the target client.

Optionally, the page chain generating module 510 includes:

and the page chain generating unit is used for acquiring a plurality of pages with continuous access time and jump relation between adjacent pages in the browser behavior data of the current client to form a page chain corresponding to the current client.

Optionally, the apparatus further comprises:

and the master station information determining module is used for determining master station information respectively corresponding to each page chain corresponding to the current client after acquiring browser behavior data of each client and generating at least one page chain respectively corresponding to each client, and classifying and storing each page chain according to the master station information.

Optionally, the apparatus further comprises:

and the target page chain determining module is used for acquiring target master station information corresponding to the target page before determining at least one prediction result page matched with the target page according to at least one target page chain corresponding to the target client, and determining at least one target page chain corresponding to the target client according to the target master station information.

Optionally, the prediction result page determining module 520 includes:

the alternative page chain acquiring unit is used for acquiring at least one alternative page chain in each target page chain; and the prediction result page generating unit is used for generating at least one prediction result page according to the last page in each alternative page chain.

Optionally, the apparatus further comprises:

and the behavior result data acquisition module is used for performing user behavior analysis on each page chain corresponding to the current client after acquiring browser behavior data of each client and generating at least one page chain corresponding to each client, and acquiring behavior result data corresponding to each page chain.

Optionally, the description information providing module 530 includes:

and the description information providing unit is used for acquiring page chains respectively corresponding to the prediction result pages and providing the description information of the prediction result pages constructed by the behavior result data of the acquired page chains to the target client.

Optionally, the description information providing module 530 includes:

and the description information providing unit is also used for sequencing the pages of the prediction results according to the chain weight of the page chain corresponding to each page of the prediction results, and providing the description information of each page of the prediction results to the target client according to the sequencing results.

Optionally, the apparatus further comprises:

and the chain weight determining module is used for determining the chain weight respectively corresponding to each page chain of the current client according to the access times and/or the access time of each page chain corresponding to the current client after acquiring the browser behavior data of each client and generating at least one page chain respectively corresponding to each client.

Optionally, the apparatus further comprises:

and the page data providing module is used for responding to a selection instruction of the target client on the description information of the target prediction result page and providing the page data matched with the target prediction result page to the target client after providing the description information of each prediction result page to the target client.

Optionally, the browser behavior data at least includes: user information, access address information, a request mode and a request parameter;

a page data providing module comprising: and the page data providing unit is used for providing the user information, the access address information, the request mode and the request parameters which are matched with the target prediction result page to the target client.

The page recommendation device provided by the embodiment of the invention can execute the page recommendation method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

EXAMPLE five

Fig. 6 is a schematic structural diagram of a page recommendation device according to a fifth embodiment of the present invention. Referring to fig. 6, the apparatus is configured in a server, and includes: a browser behavior data providing module 610, an access request sending module 620, a description information receiving module 630 and a description information presenting module 640.

The browser behavior data providing module 610 is configured to record browser behavior data, and provide the browser behavior data to the server, so as to instruct the server to generate at least one page chain corresponding to the client according to the browser behavior data, where the page chain includes: a page set formed according to a set organization sequence;

an access request sending module 620, configured to send an access request for a target page to a server, so as to obtain page data of the target page from the server and perform local display;

a description information receiving module 630, configured to receive, during an access process to a target page, description information provided by a server and corresponding to at least one predicted result page that matches the target page;

and the description information display module 640 is configured to display the description information corresponding to each prediction result page in the target page.

Optionally, the description information displaying module 640 includes:

and the description information display unit is used for displaying the description information corresponding to each prediction result page in the target page according to the sequencing result of the prediction result page.

Optionally, the apparatus further includes:

the page data acquisition module is used for acquiring a selection instruction of the description information corresponding to the target prediction result page after the description information corresponding to each prediction result page is displayed in the target page, and acquiring page data matched with the target prediction result page from the server;

and the target prediction result page generating module is used for generating a target prediction result page according to the page data and skipping the target page to the target prediction result page.

the page data acquisition module comprises: and the page data acquisition unit is used for acquiring page user information, access address information, a request mode and request parameters which are matched with the target prediction result page from the server.

EXAMPLE six

Fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention, and as shown in fig. 7, the electronic device includes:

one or more processors 410, one processor 410 being exemplified in FIG. 7;

a memory 420;

the apparatus may further include: an input device 430 and an output device 440.

The processor 410, the memory 420, the input device 430 and the output device 440 of the apparatus may be connected by a bus or other means, for example, in fig. 7.

The memory 420 serves as a non-transitory computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a page recommendation method in the embodiments of the present invention (for example, the page chain generation module 510, the predicted result page determination module 520, and the description information providing module 530 shown in fig. 5; or the browser behavior data providing module 610, the access request sending module 620, the description information receiving module 630, and the description information presenting module 640 shown in fig. 6). The processor 410 executes various functional applications and data processing of the computer device by executing the software programs, instructions and modules stored in the memory 420, namely, implementing a page recommendation method of the above method embodiment, namely:

and providing the description information of each prediction result page to the target client. Alternatively, the first and second electrodes may be,

The memory 420 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 420 may optionally include memory located remotely from processor 410, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus. The output device 440 may include a display device such as a display screen.

EXAMPLE seven

The seventh embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a page recommendation method according to the seventh embodiment of the present invention, that is:

Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for page recommendation, performed by a server, the method comprising:

2. The method of claim 1, wherein collecting browser behavior data of each client and generating at least one page chain corresponding to each client comprises:

in the browser behavior data of the current client, a plurality of pages with continuous access time and jump relation between adjacent pages are obtained to form a page chain corresponding to the current client.

3. The method of claim 1, after collecting browser behavior data of each client and generating at least one page chain corresponding to each client, further comprising:

determining master station information respectively corresponding to each page chain corresponding to the current client, and performing classified storage on each page chain according to the master station information;

before determining at least one predicted result page matched with the target page according to at least one target page chain corresponding to the target client, the method further comprises the following steps:

and acquiring target master station information corresponding to the target page, and determining at least one target page chain corresponding to a target client according to the target master station information.

4. The method of claim 3, wherein determining at least one predicted result page matching the target page according to at least one target page chain corresponding to the target client comprises:

acquiring at least one alternative page chain in each target page chain;

and generating the at least one prediction result page according to the last page in each alternative page chain.

5. The method of claim 1, after collecting browser behavior data of each client and generating at least one page chain corresponding to each client, further comprising:

performing user behavior analysis on each page chain corresponding to the current client to acquire behavior result data corresponding to each page chain;

providing the description information of each prediction result page to the target client, including:

and acquiring page chains respectively corresponding to the predicted result pages, and providing the description information of the predicted result pages constructed by the behavior result data of the acquired page chains to the target client.

6. The method of claim 1, wherein providing the description information of each of the predicted result pages to the target client comprises:

and sequencing the pages of the prediction results according to the chain weight of the page chain corresponding to each page of the prediction results, and providing the description information of each page of the prediction results to the target client according to the sequencing results.

7. The method of claim 6, after collecting browser behavior data of each client and generating at least one page chain corresponding to each client, further comprising:

and determining the chain weight corresponding to each page chain of the current client according to the access times and/or access time of each page chain corresponding to the current client.

8. The method of claim 1, wherein after providing the description information of each of the predicted result pages to the target client, further comprising:

and responding to a selection instruction of the target client to the description information of the target prediction result page, and providing page data matched with the target prediction result page to the target client.

9. The method of claim 8, wherein the browser behavior data comprises at least: user information, access address information, a request mode and a request parameter;

providing page data matched with the target prediction result page to the target client, including:

and providing the user information, the access address information, the request mode and the request parameters matched with the target prediction result page to the target client.

10. A method for page recommendation, performed by a client, the method comprising:

11. The method of claim 10, wherein displaying the description information corresponding to each of the predicted result pages in the target page comprises:

and displaying the description information corresponding to each prediction result page in the target page according to the sequencing result of the prediction result page.

12. The method according to claim 10, further comprising, after displaying the description information corresponding to each of the predicted result pages in the target page:

acquiring a selection instruction of description information corresponding to a target prediction result page, and acquiring page data matched with the target prediction result page from a server;

and generating the target prediction result page according to the page data, and skipping the target page to the target prediction result page.

13. The method of claim 12, wherein the browser behavior data comprises at least: user information, access address information, a request mode and a request parameter;

acquiring page data matched with the target prediction result page from a server, wherein the page data comprises:

and acquiring page user information, access address information, a request mode and request parameters matched with the target prediction result page from a server.

14. A page recommendation apparatus, configured in a server, the apparatus comprising:

15. A page recommendation apparatus, configured in a client, the apparatus comprising:

16. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a page recommendation method as claimed in any one of claims 1-9; or, implementing a page recommendation method according to any of claims 10-13.

17. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a page recommendation method according to any one of claims 1 to 9; or, implementing a page recommendation method according to any of claims 10-13.