WO2013044560A1

WO2013044560A1 - Method and system for recommending website and network server

Info

Publication number: WO2013044560A1
Application number: PCT/CN2011/083681
Authority: WO
Inventors: 吴军; 王欣; 金键
Original assignee: 中国科学院计算机网络信息中心
Priority date: 2011-09-26
Filing date: 2011-12-08
Publication date: 2013-04-04
Also published as: CN102316167B; CN102316167A

Abstract

The present invention provides a method and a system for recommending a website and a network server. The method comprises: a network server acquires characteristic information of websites accessed by users according to Internet access information of the users in a preset time interval; forming clusters of the users according to the characteristic information to acquire a plurality of user clusters; and determining whether the users comprise a first user corresponding to a user identifier when a network access request comprising a user identifier and sent by a user terminal is received; and if yes, determining a website to be recommended to the first user according to characteristic information of the rest users in a user cluster where the first user is positioned, embedding the website address of the recommended website into a network access response, and returning the network access response to the user terminal. The network server can be used for recommending more websites to the network access user based on global user network access behaviors, thereby enabling the user to acquire more information of interests.

Description

Website recommendation method and system and web server

Technical field

The present invention relates to communication technologies, and in particular, to a website recommendation method and system and a network server. Background technique

With the development of electronic information technology, the Internet has changed people's lifestyles. For example, people can use the Internet to get books, movies, music, and even products that they are interested in. Therefore, the Internet has brought us efficient and convenient life. People have become accustomed to using computers, mobile phones and other Internet-enabled devices to learn, entertain, and shop by browsing the web pages they are interested in to meet their multi-faceted needs.

People can use the network to obtain rich information for learning and entertainment more efficiently. Specifically, the web server will recommend the same type of related website to the user for reference according to the type of website visited by the user, for example, the user accesses information technology. For a type of website, the web server will recommend other websites in the information technology type for users to refer to. The web server records the websites that users frequently visit and obtains related website recommendations to users, so that users can obtain more information of interest. .

However, the network server in the prior art only recommends the relevant website to the user for reference according to the user's own network access behavior, so that the information obtained by the user is limited, and has certain limitations. Summary of the invention

The foregoing embodiments of the present invention provide a website recommendation method and system, and a network server.

An embodiment of the present invention provides a website recommendation method, including:

The network server acquires the feature information of the website accessed by the user who accesses the network within the preset time period according to the locally stored online information;

The network server performs cluster analysis on the user according to the feature information to obtain a plurality of user clusters, so as to determine the network access request when the user terminal sends the network access request including the user identifier. Determining whether the user includes the first user corresponding to the user identifier, and if yes, determining a website recommended to the first user according to the feature information of the user in the user cluster where the first user is located, and The URL of the recommended website is embedded in the network access response and returned to the user terminal.

An embodiment of the present invention provides a network server, including:

The first ear block is configured to acquire, according to the locally stored Internet information, feature information of a website accessed by a user who accesses the network within a preset time period;

a second acquiring module, configured to perform cluster analysis on the user according to the feature information to obtain multiple user clusters;

a determining module, configured to: when receiving a network access request that includes a user identifier sent by the user terminal, determining whether the user includes a first user corresponding to the user identifier;

a processing module, configured to determine, according to the feature information of the user in the user cluster where the first user is located, to the first user, if the user is determined to be the first user corresponding to the user identifier a website, and embedding the URL of the recommended website into a network access response and returning to the user terminal.

Embodiments of the present invention provide a website recommendation system, including the foregoing network server and user terminal.

The website recommendation method and system and the network server provided by the embodiment of the present invention obtain the feature information corresponding to the website accessed by the user according to the online information of the user in the preset time period, and cluster the user according to the feature information to obtain multiple users. a cluster, in order to receive a network access request including a user identifier sent by the user terminal, if it is determined that the user includes the first user corresponding to the user identifier, determining, according to the feature information of the remaining users in the user cluster where the first user is located, The website recommended by the first user, and embedding the website address of the recommended website into the network access response and returning to the user terminal, thereby realizing that the network server can recommend more websites to the user who performs network access based on the global user network access behavior, thereby Enable users to get more information of interest. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a flowchart of an embodiment of a website recommendation method according to the present invention;

2 is a flowchart of another embodiment of a website recommendation method according to the present invention;

3 is a schematic structural diagram of an embodiment of a network server according to the present invention;

FIG. 4 is a schematic structural diagram of an embodiment of a website recommendation system according to the present invention. The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. The embodiments are a part of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without departing from the inventive scope are the scope of the present invention.

FIG. 1 is a flowchart of an embodiment of a website recommendation method according to the present invention. As shown in FIG. 1, the method includes:

Step 100: The network server acquires, according to the locally stored online information, feature information of a website visited by a user who accesses the network within a preset time period;

The user can send a network access request to the network server for network access through a user terminal having a network function such as a mobile phone or a computer, and the network server can store the online information of the user who accesses the network for a period of time according to a preset refresh time. It can be understood that, in this embodiment, the refresh time of the network server is set according to a specific application requirement, for example, three days or one week. The online information of the user stored by the network server specifically includes: a user identifier of the user, a website start time and an end time of each visit.

It should be noted that the user identifier in this embodiment is used to distinguish different users, and there are many forms of user identifiers that can be understood by those skilled in the art according to different application scenarios and different information processing methods. The example does not limit the specific form of the user identification. For example, in a local area network, the user terminal used by each user has a fixed IP address to identify different users, and the user identifier in the online information of the user stored on the network server of the local area network is the IP address of the user terminal; or the local area network In order to ensure the security of the network access of the user, the user is required to perform the identity information authentication through the external electronic device when accessing the network. Therefore, the user identifier in the online information of the user stored on the network server of the local area network is used. It can be the identity information of the user.

The network server obtains the feature information corresponding to the website accessed by the user who accesses the network in the preset time period according to the information stored in the local network. It is to be noted that the feature information in this embodiment includes each user within a preset time period. Access frequency characteristics of each website and / or each time you visit The server performs setting. For example, if the preset time period is from zero to 24 o'clock every day, that is, the web server collects statistics based on the stored Internet information at 24 o'clock every day to obtain each user who has visited the network within the previous 24 hours. Access the frequency characteristics of each website and/or the time period characteristics of each visit. In a specific implementation process, the network server performs analog-to-digital conversion on the obtained frequency feature or time period feature. If the feature information includes the frequency feature and the time period feature, the digital quantity of the two is weighted to obtain the corresponding feature information. It is to be noted that the feature information in this embodiment is not limited to the frequency feature and the time zone feature, and may be adjusted according to the obtained specific access information to obtain other feature information. The specific processing procedure is as above, and details are not described herein. . In order to explain the meaning of the feature information more clearly, as shown in Table 1, Table 1 shows the feature information corresponding to the website visited by the user who performs network access within a preset time period, and the feature information is for each user. The values obtained by performing the analog-to-digital conversion weighting of the frequency characteristics and the time period features of each website during the time period are set.

Table 1

Step 101: The network server clusters the user according to the feature information to obtain a plurality of user clusters; corresponding feature information, and performs cluster analysis on all users who perform network access on the network server in the time period. Multiple user clusters. Cluster Analysis, also known as group analysis, is a process of classifying data into different classes or clusters, so objects in the same cluster have great similarities, and objects between different clusters are very large. The difference. The calculation methods of cluster analysis mainly include partitioning methods, hierarchical methods, density-based methods, grid-based methods and model-based models. Model-based methods „ The specific implementation process of each clustering method belongs to the prior art. In order to explain the process of clustering analysis more clearly, the K-mean value in the splitting method is used as an example to illustrate the rest. The clustering method is no longer - repeat.

The algorithm that combines the K-means described in Table 1 above is as follows:

Step (1): When the user cluster k=2 is taken as an example, two users are randomly selected from the user 1 to the user 4 as the initial centroid (the center of the category), and it is assumed that the user 1 and the user 2 are selected;

Step (2): Calculate the distance to each centroid for each remaining user: Assume that the calculation result of user 3 to user 1 is a; assume that the calculation result of user 3 to user 1 is b, if a<b, Then, the distance from user 3 to user 1 is closer, and user 3 and user 1 are divided into one class; and the remaining users are analogized in turn, and finally all users can be divided into two with user 1 and user 2 as the center of mass. In class

Step (3): Recalculate the centroid for each class. The calculation method is to average the weights of each user. After calculating the new centroid of each class, calculate the distance to each centroid for all users, and so on. Until the center of mass no longer changes.

Step (4): For each class, calculate the mean square error within the class, that is, the distance from all users in the class to the centroid, and compare their mean square error. The trend should be gradually reduced. When the mean square error value drops significantly to no Then the significantly degraded K value can be used as the final K, which is the number of user clusters.

Step 102: When receiving a network access request that includes the user identifier sent by the user terminal, determining whether the user includes a first user corresponding to the user identifier, and if yes, according to the user cluster in which the first user is located The feature information of the remaining users determines a website recommended to the first user, and embeds the website address of the recommended website into the network access response and returns it to the user terminal.

When receiving the network access request that is sent by the user terminal, including the user identifier, the network server queries the clustered user according to the user identifier to determine whether the first user corresponding to the user identifier is included. If it is determined that the first user is included in the clustered user, the first user is also subjected to cluster analysis, and the user cluster acquired in step 101 is queried according to the user identifier, and the user cluster where the first user is located is determined. It can be known that the user in the user cluster has similar network access behavior as the first user. Obtaining the feature information of the user in the user cluster where the first user is located, and determining the website recommended to the first user according to the set recommendation rule according to the feature information. For example, the user may be obtained according to the feature information of the user in the user cluster. The website visited during the preset time period will be divided The website visited by the remaining users other than the first user and not visited by the first user is recommended to the first user. It should be noted that the recommendation rule is specifically set according to a specific application scenario, and the specific recommendation rule is not limited in this embodiment.

The web server embeds the URL of the website recommended by the first user into the network access response and returns it to the user terminal. The website address includes a domain name and/or an IP address, and the website address of the website accessed by the user in the online information stored on the network server is represented by a domain name or an IP address, and if it is determined according to the online information, the website recommended to the first user is obtained. The URL is an IP address. The network server can directly embed the IP address into the network access response and return it to the user terminal. It can also send a domain name anti-query request including the IP address to the domain name server. The domain name server resolves to the network server through the PTR type domain name resolution. Returning the domain name corresponding to the IP address, the network server embeds the IP address of the website and the corresponding domain name into the network access response and returns it to the user terminal for reference by the first user, and returns the domain name to the user terminal, so that the user can memorize and write. Make it easier for users to retrieve and access recommended websites. If it is determined according to the online information that the website name recommended by the first user is a domain name, the network server may directly embed the domain name into the network access response and return it to the user terminal, or may send a domain name query request including the domain name to the domain name server, the domain name server. The IP address corresponding to the domain name is returned to the network server by the domain name resolution of the A type, and the network server embeds the IP address of the website and the corresponding domain name into the network access response, and returns it to the user terminal for reference by the first user, and returns to the user terminal. The IP address, so that the user can directly search and access the recommended website, and does not need to initiate a domain name query request to the domain name server.

In the website recommendation method provided by the embodiment, the web server obtains feature information corresponding to the website accessed by the user who accesses the network in the preset time period according to the online information of the user, and performs cluster analysis on the user according to the feature information to obtain multiple users. a cluster, when the network server receives the network access request including the user identifier, if it is determined that the clustered user includes the first user corresponding to the user identifier, determining, according to the feature information of the user in the user cluster where the first user is located, The website recommended by the first user, and embedding the URL of the recommended website into the network access response and returning to the user terminal, thereby realizing that the network server can recommend more websites to the user who performs network access based on the global user network access behavior, thereby Enable users to get more information of interest.

2 is a flowchart of another embodiment of a website recommendation method according to the present invention. As shown in FIG. 2, the method includes:

Step 200: The network server performs the preset time period according to the locally stored Internet access information. The information accessed by the user accessing the website by the network access;

Step 201: The network server clusters the user according to the feature information to obtain multiple user clusters.

Step 202: The network server, when receiving the network access request that is sent by the user terminal, including the user identifier, determines whether the user includes the first user corresponding to the user identifier, and if not, broadcasts the information to the remaining network servers. The user information and the online information query request of the preset time period, if the online information of the first user returned by the remaining network servers in the preset time period is received, according to the online information acquisition The feature information corresponding to the website visited by the first user;

When receiving the network access request, including the user identifier, sent by the user terminal, the network server queries the clustered user according to the user identifier to determine whether the first user corresponding to the user identifier is included. If it is determined that the first user is not included in the clustered user, the first user does not perform network access through the network server within a preset time period, that is, the network server is in a preset time period. The user who performs network access within does not include the first user.

The network server broadcasts the online information query request including the user identifier of the first user and the preset time period to the remaining network servers in the Internet system, and the remaining network servers query the request according to the received Internet information, and each network server is based on the first user. The user identifier is queried from the online information stored in the preset time period of the local storage to include the online information of the first user, and if the network server can receive the Internet access of the first user returned by the remaining network servers within a preset time period The information of the website that is accessed by the first user is obtained according to the information about the first user. For the process of obtaining the specific feature information, refer to step 100 in the first embodiment, and details are not described herein.

Step 203: The network server acquires corresponding aggregated contour information according to the feature information of the user in each user cluster, and determines, according to the feature information of the first user and the aggregated contour information, by using a similarity measure. Describe the user cluster to which the first user belongs;

The network server obtains the corresponding aggregated profile information according to the feature information of the user in each user cluster obtained in the foregoing step 201, and the aggregated profile information, that is, the average weight of the feature information corresponding to the website visited by the user in each user cluster;

The network server performs the similarity measurement according to the feature information of the first user and the acquired aggregated contour information. It is noted that the method of the similarity measure is, for example, a Pearson correlation coefficient or a cosine coefficient, etc., which is not specifically limited in this embodiment. Get the website visited by the first user through the similarity measure A matching score of the corresponding feature information and each of the aggregated contour information is used to determine a user cluster to which the first user belongs. The greater the matching score, the higher the similarity between the first user and the user in the user cluster, and the user who selects the maximum matching score. The cluster is determined to be the user cluster to which the first user belongs.

Step 204: Determine, according to the feature information of the user in the user cluster where the first user is located, a website recommended to the first user, and embed the URL of the recommended website into a network access response and return it to the website. User terminal.

Obtaining feature information of the user in the user cluster where the first user is located, and determining a website recommended to the first user according to the set recommendation rule according to the feature information, specifically, the remaining users in the user cluster where the first user is located The feature information is weighted and averaged to obtain the recommended scores of the websites visited by the remaining users, and the recommended scores for each website are determined according to the recommended recommendation criteria of each website accessed by the remaining users, for example, according to the recommended scores of each website. The ranking is high and the sites are not accessed by the first user, and the selected website is used as the website recommended to the first user until the number of preset recommended websites. The network server embeds the URL of the recommended website into the network access response and returns it to the user terminal for reference by the first user. For the specific process, refer to the foregoing embodiment, and details are not described herein.

For the specific implementation process of step 201 and step 202 in this embodiment, refer to the embodiment shown in FIG. 1, and details are not described herein again.

In the website recommendation method provided by the embodiment, the web server obtains feature information corresponding to the website accessed by the user who accesses the network in the preset time period according to the online information of the user, and performs cluster analysis on the user according to the feature information to obtain multiple users. When the network server receives the network access request including the user identifier, if it is determined that the clustered user does not include the first user corresponding to the user identifier, the network server performs a broadcast query to the remaining network servers, and if the remaining network servers are received, Returning the online information of the first user, determining the user cluster where the first user is located, and determining the website recommended to the first user according to the feature information of the user in the user cluster where the first user is located, and embedding the URL of the recommended website Returning to the user terminal in the network access response, the network server can further recommend more websites to users who perform network access based on the global user network access behavior, thereby enabling the user to obtain more information of interest.

A person skilled in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by using hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed. Including the steps of the above method embodiments; The storage medium includes: a ROM, a RAM, a magnetic disk, or an optical disk, and the like, which can store program codes.

3 is a schematic structural diagram of an embodiment of a network server according to the present invention. As shown in FIG. 3, the network server includes: a first obtaining module 11, a second obtaining module 12, a determining module 13, and a processing module 14, wherein the first obtaining The ear module 11 is configured to acquire, according to the locally stored Internet access information, feature information of a website visited by a user who accesses the website in a preset time period; and the second obtained module 12 is configured to perform cluster analysis on the user according to the feature information to obtain multiple The user cluster; the determining module 13 is configured to: when receiving the network access request that includes the user identifier sent by the user terminal, determine whether the user includes the first user corresponding to the user identifier; and the processing module 14 is configured to determine, if the learned user includes the user identifier The first user determines the website recommended to the first user according to the feature information of the user in the user cluster where the first user is located, and embeds the website address of the recommended website into the network access response to return to the user terminal.

For the embodiment shown in FIG. 3, the second obtaining module 12 can perform cluster analysis on the user according to the feature information by a split method, a hierarchical method, a density-based method, a grid-based method, and a model-based method.

For the functions and processing procedures of the modules in the network server provided in this embodiment, refer to the method embodiment shown in FIG. 1 , and the implementation principle and technical effects are similar, and details are not described herein again.

Based on the embodiment shown in FIG. 3, the processing module 14 is further configured to: if it is determined that the user does not include the first user corresponding to the user identifier, broadcast the online information including the user identifier and the preset time period to the remaining network servers. The query request, if receiving the online information of the first user returned by the remaining network servers in the preset time period, acquiring the feature information corresponding to the website accessed by the first user according to the online information; obtaining the feature information of the user in each user cluster Corresponding aggregated profile information, and determining, by the similarity measure, the user cluster to which the first user belongs according to the feature information of the first user and the aggregated profile information.

For the functions and processing procedures of the modules in the network server provided in this embodiment, refer to the method embodiment shown in FIG. 2, and the implementation principle and technical effects are similar, and details are not described herein again.

4 is a schematic structural diagram of an embodiment of a website recommendation system according to the present invention. As shown in FIG. 4, the system includes: a network server 1 and a user terminal 2, wherein the network server 1 can be a network server provided by an embodiment of the present invention. The terminal 2 is a user terminal according to an embodiment of the present invention. The functions and processing procedures of the devices in the website recommendation system provided in this embodiment can be referred to the foregoing method and device embodiment. The implementation principle and technical effects are similar. Let me repeat. It should be noted that the above embodiments are only for explaining the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: The technical solutions described in the foregoing embodiments are modified, or some of the technical features are equivalently replaced. The modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

Claim

A website recommendation method, comprising:

The network server performs cluster analysis on the user according to the feature information to obtain a plurality of user clusters, so as to determine whether the user includes the user identifier when receiving the network access request including the user identifier sent by the user terminal. Corresponding first user, if yes, determining a website recommended to the first user according to the feature information of the user in the user cluster where the first user is located, and embedding the website address of the recommended website into the network Returned to the user terminal in the access response.

The website recommendation method according to claim 1, wherein, if it is determined that the user does not include the first user corresponding to the user identifier, the method further includes:

The network server broadcasts an online information query request including the user identifier and the preset time period to the remaining network servers, and if the first user returned by the remaining network servers is received within the preset time period The online information, the feature information corresponding to the website accessed by the first user is obtained according to the online information;

And obtaining, by the network server, corresponding aggregation profile information according to the feature information of the user in each user cluster, and determining, by using the similarity measure, the first according to the feature information of the first user and the aggregated profile information. The user cluster to which the user belongs.

The website recommendation method according to claim 1, wherein the performing cluster analysis on the user according to the feature information comprises:

The user is clustered according to the feature information by a splitting method, a hierarchical method, a density-based method, a grid-based method, and a model-based method.

The website recommendation method according to claim 1, wherein the determining, according to the feature information of the remaining users in the user cluster in which the first user is located, the website recommended to the first user comprises:

Obtaining a recommendation score of the website visited by the remaining users according to the feature information of the remaining users in the user cluster in which the first user is located;

A website recommended to the first user is determined according to the recommended recommendation criteria according to the recommended recommendation score.

The website recommendation method according to any one of claims 1 to 4, wherein The levy information includes: a frequency characteristic of the user visiting the website and/or a time period feature of each access within a preset time period.

The website recommendation method according to any one of claims 1 to 4, wherein the website address comprises: a domain name and/or an IP address.

7. A network server, comprising:

The network server according to claim 7, wherein the processing module is further configured to:

If it is determined that the user does not include the first user corresponding to the user identifier, the network information query request including the user identifier and the preset time period is broadcasted to the remaining network servers, if the remaining network is received Obtaining, by the server, the online information of the first user in the preset time period, and acquiring the feature information corresponding to the website accessed by the first user according to the online information;

Obtaining corresponding aggregated contour information according to the feature information of the user in each user cluster, and determining, by the similarity measure, the user to which the first user belongs according to the feature information of the first user and the aggregated profile information cluster.

The network server according to claim 8, wherein the second acquiring module is specifically configured to:

10. A website recommendation system, comprising: any one of claims 7 or 8 or 9 The network server described in the item, and the user terminal.