KR20200003665A - Method and server for recommending webpage - Google Patents

Abstract

The present invention relates to a method for recommending a webpage which is performed by a webpage recommendation server. The method for recommending a webpage comprises the steps of: storing a visiting history of a webpage visited through a user terminal; generating a search tree from a target node to an interest node based on the visiting history; selecting a plurality of main nodes based on a browsing time of each node included in the search tree; evaluating recommendation worth of each of the plurality of main nodes based on a visiting probability of each of the plurality of main nodes and a time consumed when moving from the target node to each of the plurality of main nodes; and recommending the webpage based on the recommendation worth of each of the plurality of main nodes.

Description

How to recommend web pages and servers {METHOD AND SERVER FOR RECOMMENDING WEBPAGE}

The present invention relates to a method and server for recommending a web page.

In the related art, a web page is recommended through the screen of an initial web browser immediately after execution of the web browser or immediately after the creation of a new tab on the web browser.

In addition, only web pages with high frequency of visits are recommended among the URL addresses of web pages that the user directly inputs in the address bar.

Korean Laid-Open Patent Publication No. 2017-0032037 (published Mar. 22, 2017)

The present invention is to generate a search tree from the target node to the node of interest based on the visit history of the web page visited by the user through the user terminal, and recommends the web page using the generated search tree.

In addition, the present invention intends to recommend a web page to a plurality of main nodes included in a search tree. Specifically, the present invention evaluates the recommendation value of each main node based on the visit probability of each of the plurality of main nodes and the time required to move from the target node to each of the plurality of main nodes, and based on the recommendation value of each main node. I would like to recommend a web page. However, the technical problem to be achieved by the present embodiment is not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, the web page recommendation method performed by the web page recommendation server according to the first aspect of the present invention comprises the steps of: storing the visit history of the web page visited through the user terminal; Generating a search tree from a target node to a node of interest based on the visit history; Selecting a plurality of main nodes based on a browsing time of each node included in the search tree; Evaluating a recommendation value of each of the plurality of main nodes based on the probability of visit to each of the plurality of main nodes and the time required to move from the target node to each of the plurality of main nodes; And recommending a web page based on recommendation values of each of the plurality of main nodes.

Web page recommendation server for recommending a web page according to a second aspect of the present invention includes a visit history storage unit for storing the visit history of the web page visited through the user terminal; A search tree generator configured to generate a search tree from a target node to a node of interest based on the visit history; A main node selector configured to select a plurality of main nodes based on a browsing time of each node included in the search tree; A recommendation value evaluator for evaluating recommendation values of each of the plurality of main nodes based on visit probability to each of the plurality of main nodes and time required to move from the target node to each of the plurality of main nodes; And a web page recommender for recommending a web page based on the recommendation values of each of the plurality of main nodes.

The above-mentioned means for solving the problems are merely exemplary, and should not be construed to limit the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description of the invention.

According to any one of the above-described problem solving means of the present invention, the present invention skips the web page corresponding to the non-major node (web page passing through the middle) during the web browsing process of the user, the user may be interested In order to directly access the web page corresponding to the main node, the web page corresponding to the main node can be recommended. Through this, it is possible to reduce the movement process and time between the unnecessary web pages (web pages corresponding to non-primary nodes), and to reduce the data usage and access traffic load consumed when accessing unnecessary web pages.

In addition, the present invention may automatically recommend a web page determined as a main node (including a node of interest and a branch node) in the search tree, regardless of whether the user inputs the URL address of the web page.

1 is a block diagram of a web page recommendation system according to an embodiment of the present invention.
2 is a block diagram of the web page recommendation server shown in FIG. 1 according to an embodiment of the present invention.
3 is a view for explaining a method of evaluating recommendation values for each of a plurality of main nodes according to an embodiment of the present invention.
4A through 4D are diagrams for describing a method of recommending a web page, according to an exemplary embodiment.
5 is a flowchart illustrating a method of recommending a web page in a web page recommendation server according to an exemplary embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components unless otherwise stated.

In the present specification, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized by both. In addition, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware.

Some of the operations or functions described as being performed by a terminal or a device in the present specification may instead be performed in a server connected to the terminal or device. Similarly, some of the operations or functions described as being performed by the server may be performed by a terminal or a device connected to the server.

Hereinafter, with reference to the accompanying configuration diagram or processing flow chart, it will be described in detail for the practice of the present invention.

1 is a block diagram of a web page recommendation system according to an embodiment of the present invention.

Referring to FIG. 1, the web page recommendation system may include a web page recommendation server 100 and a user terminal 110. However, since the web page recommendation system of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 and may be configured differently from FIG. 1 according to various embodiments of the present invention. .

In general, each component of the web page recommendation system of FIG. 1 is connected through a network (not shown). A network refers to a connection structure capable of exchanging information between nodes such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), and the Internet (WWW: World). Wide Web), wired / wireless data communication network, telephone network, wired / wireless television communication network, and the like. Examples of wireless data networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, Infrared communication, Ultrasound Communication, visible light communication (VLC), liFi (LiFi), and the like, but are not limited thereto.

The web page recommendation server 100 may store a visit history of a web page visited by the user through the user terminal 110. For example, the web page recommendation server 100 may store visit histories for a plurality of web pages that the user has visited during the preset period for each preset period.

The web page recommendation server 100 may generate a search tree from the target node to the node of interest based on the visit history of the web page. Here, the target node may be an initial web page or a web page currently being browsed, and the node of interest may be a web page that the user wishes to visit. For example, a web page in which the number of visits by the user to the web page is greater than or equal to a predetermined number of times or the average residence time (browsing time) of the web page is greater than or equal to a predetermined time may be set as the interest node.

The web page recommendation server 100 may select a plurality of main nodes based on the browsing time of each node included in the search tree. Here, the main node may include a node of interest and a branch node connected to the plurality of nodes. Meanwhile, the search tree may include non-major nodes (nodes except target nodes and main nodes) connected to only one node.

The web page recommendation server 100 may evaluate the recommendation value of each of the plurality of main nodes based on the probability of visit to each of the plurality of main nodes and the time required to move from the target node to each of the plurality of main nodes.

The web page recommendation server 100 may recommend the web page to the user terminal 110 based on the recommendation value of each of the plurality of main nodes. In detail, the web page recommendation server 100 may recommend web pages in ascending order of recommendation of each of the plurality of main nodes.

When the free network is connected, the user terminal 110 may download the recommended web page recommended by the web page recommendation server 100 from the web page recommendation server 100 in advance. Through this, the amount of data consumed through the mobile communication network can be reduced.

When the user terminal 110 accesses the recommended web page downloaded by the user terminal 110 in advance in the mobile communication network, the user terminal 110 indicates that the recommended web page is downloaded in advance and downloads it again from the mobile communication network. The selection function can be displayed on the screen.

The user terminal 110 may include, for example, a mobile terminal capable of wired and wireless communication as well as a laptop and a desktop PC. The mobile terminal is a wireless communication device that guarantees portability and mobility, and is not only a smartphone, a tablet PC, and a wearable device, but also Bluetooth, Bluetooth, Low Energy, NFC, RFID, Ultrasonic, Infrared, and WiFi. Various devices equipped with a communication module such as WiFi, LiFi, or the like may be included. However, the user terminal 110 is not limited to those illustrated above.

Hereinafter, the operation of each component of the web page recommendation system of FIG. 1 will be described in more detail.

2 is a block diagram of the web page recommendation server 100 shown in FIG. 1 in accordance with an embodiment of the present invention.

Referring to FIG. 2, the web page recommendation server 100 includes a visit history storage unit 200, a search tree generator 210, a main node selector 220, a recommendation value evaluator 230, and a web page recommender. 240 may be included. Here, the web page recommender 240 may include a web browser page provider 242 and an input information monitor 244. However, the web page recommendation server 100 shown in FIG. 2 is just one implementation example of the present invention, and various modifications are possible based on the elements shown in FIG. 2.

Hereinafter, a description will be given with reference to FIGS. 3 to 4D along with FIG. 2.

The visit history storage unit 200 may store the visit history of the web page visited through the user terminal 110. For example, the visit history storage unit 200 may store visit history for a plurality of web pages that the user has visited during the preset period.

For example, assuming that the user enjoys a specific Tuesday webtoon of the A portal every week, the visit history storage unit 200 moves from the initial web page that the user first accesses to the webpage of the specific Tuesday webtoon of the A portal. Information about web pages included in can be stored.

The search tree generator 210 may select, as a target node, an initial web page first visited by a user from the visit history of the web page for a preset period. Alternatively, the search tree generator 210 may select the web page currently being browsed as the target node through the user terminal 110.

The navigation tree generation unit 210 may determine the frequency of the user's visits (eg, the number of scrolls to the web page, the number of clicks, etc.) of the plurality of web pages visited by the user based on the visit history of the web page, or more than a preset number. A web page whose average residence time on the web page is greater than or equal to a predetermined time may be selected as the node of interest. Here, the node of interest may be a web page that the user wishes to visit.

The search tree generator 210 may select a web page that is most likely to be visited from a web page (target node) that the user currently visits based on the visit history of the web page, and select the selected web page as a node of interest. .

The navigation tree generator 210 may search a web page that is most likely to be visited by a user through a specific link page that is pointed by an input device (eg, a mouse cursor) within the web page currently being browsed based on the visit history of the web page. Can be selected as the node of interest.

The search tree generator 210 may determine, as a node of interest, a web page having a high probability of a user's visit from the visit history of the web page using a statistical model or a deep neural network, machine learning, or the like.

The search tree generator 210 may generate a search tree from the target node to the node of interest using the target node and the plurality of interest nodes selected based on the visit history of the web page. In this case, the search tree may include non-major nodes connected to only one node. In addition, the search tree generator 210 may periodically update the generated search tree based on a visit history of a web page that has been recently visited.

Here, each node constituting the search tree means a web page visited by the user, and the target node may be a web page that is a reference on the search tree (a tree that is a recommendation criterion of the web page). For example, when starting web browsing, if the initial web page recommends a web page to be visited by the user, the target node may be the initial web page. In another example, the target node when the web page currently being browsed recommends a web page to be visited by the user may be the web page currently being browsed. As another example, a target node when recommending a web page to be visited by a user through a specific link page pointed to by an input device on a specific web page may be a web page currently being browsed.

For example, referring to FIG. 3, when a user visits a web page corresponding to the first node 300, when the user wants to recommend a web page that is expected to be visited by the user, the first node 300 may be used. Can be a target node. In this case, the fourth node 306 and the sixth node 310 may be nodes of interest.

Referring back to FIG. 2, the search tree generator 210 has a predetermined distance from the first node 300 to the fourth node 306 and the sixth node 310 based on the first node 300 that is the target node. You can create a search tree for only nodes within it. For example, the search tree generator 210 selects and searches for nodes having a cumulative dwell time within a predetermined time among the nodes passing through from the first node 300 to the fourth node 306. A tree may be generated and a search tree may be generated by selecting nodes having a cumulative dwell time within a predetermined time from among nodes passing through reaching the first node 300 to the sixth node 310.

The main node selector 220 may select a plurality of main nodes based on the browsing time of each node included in the generated search tree. For example, the main node selector 220 may select a web page having a browsing time of the web page longer than a preset time (for example, 5 seconds) as the main node. For example, the primary node may include a node of interest and a branch node that connects to a plurality of nodes.

Here, the browsing time of each node may be calculated through Equation 1 based on the total time the user stays in each web page corresponding to each node and the total number of visits.

[Equation 1]

(i)는 특정 웹 페이지에서 사용자가 체류한 총 시간이고, N(i)는 사용자가 방문한 특정 웹 페이지의 총 방문 횟수이다. here,

(i) is the total time the user stayed in the particular web page, and N (i) is the total number of visits of the particular web page visited by the user.

Meanwhile, referring back to FIG. 3, the primary node is the node of interest (fourth node 306 and sixth node 310) and two or more different nodes, for example, the node of interest (fourth node 306 and second). It may include a branch node (third node 304) connected to the six nodes 310.

All nodes (second node 302 and first) that do not correspond to the target node (first node 300) and main node (third node 304, fourth node 306, and sixth node 310). The five node 308 corresponds to a non-major node, and the non-major node simply passes through a web page to the main node (third node 304, fourth node 306, and sixth node 310). Therefore, the dwell time at the non-primary node can be a waste of time for the user. Accordingly, the present invention allows the user to skip over unnecessary web pages (non-primary nodes) and quickly access nodes of interest (fourth node 306 and sixth node 310). Web pages corresponding to the four nodes 306 and the sixth node 310 are recommended to the user.

Referring back to FIG. 2, the recommendation value evaluator 230 recommends values of each of the plurality of main nodes based on visit probability to each of the plurality of main nodes and time required to move from the target node to each of the plurality of main nodes. Can be evaluated. At this time, the recommendation value can be calculated by how much time wasted in accessing unnecessary web pages.

Referring back to FIG. 3, the edge of the navigation tree ('→') is the transition probability P (j | i) of the user moving from one web page (i) to another web page (j). it means. For example, if the total number of visits from web page A to web page B is 7 times, and the number of times the browser is immediately closed from web page B is 3, then the probability of transition P from web page A to web page B (B | A) is 0.7 (70%).

The visit probability to each of the plurality of main nodes may be calculated as a product of the transition probabilities of nodes passing from the target node to each main node.

For example, to visit the third node 304 corresponding to the branch node from the first node 300 corresponding to the target node, the first node 300 → the second node 302 → the third node 304. Since the third node 304 corresponds to the branch node, the probability of visit of the third node 304 is P (second node | first node) x P (third node | second node) = 1.0 x 1.0 = 1 ( 100%).

For another example, in order to visit from the first node 300 corresponding to the target node to the fourth node 306 corresponding to the node of interest, the first node 300 → the second node 302 → the third node ( 304) → since the fourth node 306 needs to go through, the probability of visit of the fourth node 306 corresponding to the node of interest is P (second node | first node) x P (third node | second node). ) x P (fourth node | third node) = 1.0 x 1.0 x 0.7 = 0.7 (70%).

For another example, in order to visit from the first node 300 corresponding to the target node to the sixth node 310 corresponding to the node of interest, the first node 300 → the second node 302 → the third node. (304)-> fifth node 308-> sixth node 310, so the probability of visit of the sixth node 310 corresponding to the node of interest is P (second node | first node) x P (Third node | second node) x P (5th node | third node) x P (6th node | 5th node) = 1.0 x 1.0 x 0.3 x 1.0 = 0.3 (30%) .

The time taken to move from the target node to each of the plurality of main nodes may be calculated as the sum of the average dwell times of all the non-major and branch nodes passing through the visited path. At this time, the browsing time at the target node and the node of interest may not be considered.

For example, assuming that the third node 304 corresponding to the branch node is visited from the first node 300 (that is, when visiting the third node 304 without recommending the webpage of the present invention), The time required for moving from the first node 300 corresponding to the target node to the third node 304 corresponding to the branch node may be calculated as 1 second, which is a browsing time at the second node 302.

For another example, suppose that the fourth node 306 corresponding to the node of interest is visited from the first node 300 (ie, visiting the fourth node 306 without the webpage recommendation of the present invention). The time required for moving from the first node 300 corresponding to the target node to the fourth node 306 corresponding to the node of interest is the browsing time (1 second) at the second node 302 and the third node. 2 seconds, which is the sum of the browsing time (1 second) at 304.

For another example, suppose that the sixth node 310 corresponding to the node of interest is visited from the first node 300 (that is, when visiting the sixth node 310 without recommending the webpage of the present invention). ), The time required to move from the first node 300 corresponding to the target node to the sixth node 310 corresponding to the node of interest is the browsing time (1 second) and the third time at the second node 302. 3 seconds, which is the sum of the browsing time at node 304 (1 second) and the browsing time at fifth node 308 (1 second).

The recommendation value of each major node may be calculated as the product of the probability of visiting each of the major nodes and the time required to move from the target node to each of the plurality of major nodes. For example, the recommendation value for the third node 304 corresponding to the branch node is the probability of visit 1 to the third node 304 and the third node 304 from the first node 300 corresponding to the target node. It can be calculated as 1, which is the product of the time (1 second) when moving to In this case, when the third node 304 corresponding to the branch node is recommended to the user, the temporal benefit obtained by the user may be 1 second.

For example, the recommendation value for the fourth node 306 corresponding to the node of interest is the probability of visit (0.7) of the fourth node 306 and the fourth node 306 from the first node 300 corresponding to the target node. It can be calculated as 1.4, which is the product of the time required to move to (2 seconds). In this case, when the fourth node 306 corresponding to the node of interest is recommended to the user, the time gain obtained by the user may be 1.4 seconds.

For example, the recommendation value for the sixth node 310 corresponding to the node of interest is the visit probability 0.3 of the sixth node 310 and the sixth node 310 from the first node 300 corresponding to the target node. It can be calculated as 0.9, which is the product of the time required to move to (). In this case, when the sixth node 310 corresponding to the node of interest is recommended to the user, the temporal benefit obtained by the user may be 0.9 second.

The web page recommender 240 may recommend a web page based on a recommendation value of each of the plurality of main nodes. In detail, the web page recommender 240 may recommend the web pages in the order of the high recommendation value of each of the plurality of main nodes. For example, referring to FIGS. 3 and 4A, the web page recommender 240 may display an initial web browser page 400 immediately after the user first launches the web browser or immediately after creating a new tab for browsing the web page. ), The first recommendation web page corresponding to the fourth node 306, the second recommendation web page corresponding to the sixth node 310, and the third corresponding to the third node 304 in the order of high recommendation value. Recommend web pages.

The web browser page providing unit 242 provides the user terminal 110 with a web browser page including a browsing area for browsing a web page and a web page recommendation area for a web page recommendation, and recommends the web page recommendation area. Information of a web page. For example, referring to FIGS. 3 and 4B, the web browser page providing unit 242 may provide a browsing area 404 and a web page for browsing the web page through the web browser page 402 that the user is currently browsing. A web page recommendation area 406 may be provided for recommendation of. In this case, the window corresponding to the web page recommendation area 406 may be activated or deactivated through a separate web browser option setting or a designated shortcut key by the user.

In addition, the web browser page providing unit 242 may correspond to the first recommendation web page corresponding to the fourth node 306 and the sixth node 310 in the order of high recommendation value through the web page recommendation area 406. Information about the third recommendation web page corresponding to the second recommendation web page and the third node 304 may be provided (eg, information including a title and a thumbnail of the recommendation web page).

The input information monitoring unit 244 may monitor input information on the web browser page from the user terminal 110. For example, referring to FIG. 4C, the input information monitoring unit 244 links 410 of a web browser page by an input device (eg, a mouse, a touch, etc.) on a web browser page 408 that the user is currently browsing. Monitoring information 412 may be monitored. The input information monitoring unit 244 may monitor the pointing information 412 for the link 410 indicated by the cursor of the input device among the plurality of links included in the web browser page 408.

The web browser page providing unit 242 may provide the user terminal 110 with a pop-up page including information of the recommended web page based on the input information about the web browser page. For example, referring to FIGS. 3, 4C, and 4D, the web browser page providing unit 242 may include the first recommendation web page corresponding to the fourth node 306 and the sixth node (in order of highest recommendation value). Pop-up page 414 including a second recommendation web page corresponding to 310, information about the third recommendation web page corresponding to third node 304 (eg, information including a title and a thumbnail of the recommendation web page). May be provided to the user terminal 110 in the form of a pop-up window. In this case, the pop-up page 414 may be activated or deactivated when a separate shortcut key is input by the user while the cursor of the input device is placed on the link.

On the other hand, those skilled in the art, visit history storage unit 200, search tree generation unit 210, the main node selection unit 220, recommendation value evaluation unit 230, web page recommendation unit 240, web browser page provider It will be fully understood that each of 242 and input information monitoring unit 244 may be implemented separately, or one or more of them may be integrated and implemented.

5 is a flowchart illustrating a method of recommending a web page in the web page recommendation server 100 according to an exemplary embodiment of the present invention.

The web page recommendation method according to the embodiment shown in FIG. 5 includes steps that are processed in time series in the web page recommendation server 100 and the user terminal 110 according to the embodiment shown in FIGS. 1 to 4D. Therefore, even if omitted below, the contents described with respect to the web page recommendation server 100 and the user terminal 110 of FIGS. 1 to 4D may be applied to the web page recommendation method according to the embodiment shown in FIG. 5. .

Referring to FIG. 5, in operation S501, the web page recommendation server 100 may store a visit history of a web page visited through the user terminal 110.

In operation S503, the web page recommendation server 100 may generate a search tree from the target node to the node of interest based on the visit history. Here, the target node may be an initial web page or a web page currently being browsed, and the node of interest may be a web page that the user wishes to visit. Here, the search tree may include non-major nodes connected to only one node.

In operation S505, the web page recommendation server 100 may select a plurality of main nodes based on the browsing time of each node included in the search tree. Here, the main node may include a node of interest and a branch node connected to the plurality of nodes.

In operation S507, the web page recommendation server 100 may evaluate the recommendation value of each of the plurality of main nodes based on the time required to move to each of the plurality of main nodes and the probability of visit to each of the plurality of main nodes. have.

In operation S509, the web page recommendation server 100 may recommend the web page based on the recommendation values of the plurality of main nodes.

Although not shown in FIG. 5, in step S509, the web page recommendation server 100 may recommend the web pages in ascending order of recommendation of each of the plurality of main nodes.

Although not shown in FIG. 5, in operation S509, the web page recommendation server 100 may transmit a web browser page including a browsing area for browsing the web page and a web page recommendation area for the recommendation of the web page to the user terminal 110. Can provide.

Although not shown in FIG. 5, in operation S509, the web page recommendation server 100 may provide information of the recommended web page to the web page recommendation area.

Although not shown in FIG. 5, in step S509, the web page recommendation server 100 monitors input information on the web browser page from the user terminal 110, and includes a pop-up including information of the recommended web page based on the input information. The page may be provided to the user terminal 110. Here, the input information may be pointing information on a link of a web browser page of the input device.

In the above description, steps S501 to S509 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted as necessary, and the order between the steps may be changed.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by the computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. .

100: web page recommendation server
110: user terminal
200: visit history store
210: navigation tree generation unit
220: main node selection unit
230: recommended value evaluation unit
240: web page recommendation
242: web browser page provider
244: input information monitoring unit

Claims (15)

In the web page recommendation method performed by the web page recommendation server,
Storing a visit history of the web page visited through the user terminal;
Generating a search tree from a target node to a node of interest based on the visit history;
Selecting a plurality of main nodes based on a browsing time of each node included in the search tree;
Evaluating a recommendation value of each of the plurality of main nodes based on the probability of visit to each of the plurality of main nodes and the time required to move from the target node to each of the plurality of main nodes; And
Recommending a web page based on a recommendation value of each of the plurality of main nodes
That includes, web page recommendation method.
The method of claim 1,
The target node is an initial web page or a web page currently being browsed,
And wherein the node of interest is a web page that the user wishes to visit.
The method of claim 1,
Wherein said primary node comprises a node of interest and a branch node to a plurality of nodes.
The method of claim 1,
Wherein the navigation tree includes non-primary nodes that connect only to one node.
The method of claim 1,
The recommending of the web page comprises recommending the web page in ascending order of recommendation of each of the plurality of main nodes.
The method of claim 2,
Recommend the web page,
And providing a web browser page including a browsing area for browsing a web page and a web page recommendation area for recommending a web page to the user terminal.
The method of claim 6,
Recommend the web page,
And providing information of the recommended web page in the web page recommendation area.
The method of claim 2,
Recommend the web page,
Monitoring input information on a web browser page from the user terminal; And
Providing a pop-up page including information of the recommended web page to the user terminal based on the input information.
The method of claim 8,
And the input information is pointing information for a link of the web browser page of the input device.
In the web page recommendation server that recommends a web page,
A visit history storage unit for storing a visit history of a web page visited through a user terminal;
A search tree generator configured to generate a search tree from a target node to a node of interest based on the visit history;
A main node selector configured to select a plurality of main nodes based on a browsing time of each node included in the search tree;
A recommendation value evaluator for evaluating recommendation values of each of the plurality of main nodes based on visit probability to each of the plurality of main nodes and time required to move from the target node to each of the plurality of main nodes; And
Web page recommendation unit for recommending a web page based on the recommendation value of each of the plurality of main nodes
That includes, the web page recommendation server.
The method of claim 10,
The target node is an initial web page or a web page currently being browsed,
The node of interest is a web page that the user wishes to visit.
The method of claim 10,
Wherein the primary node comprises a node of interest and a branch node to a plurality of nodes.
The method of claim 10,
And the web page recommendation unit recommends the web pages in ascending order of recommendation of each of the plurality of main nodes.
The method of claim 11,
The web page recommendation unit provides a web browser page including a browsing area for browsing a web page and a web page recommendation area for recommending a web page to the user terminal, and the web page recommendation area of the recommended web page. Informational web browser page provider
That includes, the web page recommendation server.
The method of claim 14,
The web page recommendation unit is an input information monitoring unit for monitoring the input information on the web browser page from the user terminal
More,
The web browser page providing unit provides a pop-up page including information of the recommended web page to the user terminal based on the input information.

Images