CN103425670A

CN103425670A - Method, device and equipment for providing customers with content recommendation information

Info

Publication number: CN103425670A
Application number: CN2012101531969A
Authority: CN
Inventors: 周达文
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2012-05-16
Filing date: 2012-05-16
Publication date: 2013-12-04
Anticipated expiration: 2032-05-16
Also published as: CN103425670B

Abstract

The invention provides a method, a device and equipment for providing customers with content recommendation information. The method includes: acquiring user category information of a user accessing to a webpage; acquiring the content recommendation information corresponding to the webpage and relevant to the category information; displaying the content recommendation information to the user, wherein the content recommendation information is used for recommending the user for web content information of the webpage. The method has the advantages that the user can quickly get the information concerned, time spent on webpage searching is reduced for the user, and the efficiency of the user accessing to the web information is improved.

Description

A kind of method, device and equipment that content recommendation information is provided to the user

Technical field

The present invention relates to field of computer technology, relating in particular to a kind of user provides the method for content recommendation information, device and equipment.

Background technology

In prior art, the user, when browsing page, needs the interested content of inquiry from webpage voluntarily.This can reduce the efficiency of user's acquired information undoubtedly, especially when webpage comprises a large amount of content information.

Therefore, how to the user, to recommend the interested content of its possibility in webpage, become the problem that those skilled in the art need to solve.

Summary of the invention

The purpose of this invention is to provide a kind of method, device and equipment that content recommendation information is provided to the user.

According to an aspect of the present invention, provide a kind of computer implemented method that content recommendation information is provided to the user, wherein, said method comprising the steps of:

A. obtain the user's of accessed web page user category information;

B. obtain corresponding to described webpage and relevant with described user category information content recommendation information, wherein, the web page content information of described content recommendation information for to this user, recommending described webpage;

C. present described content recommendation information to described user.

According to an aspect of the present invention, also provide a kind of recommendation apparatus that content recommendation information is provided to the user, wherein, described recommendation apparatus comprises:

The first deriving means, for the user's that obtains accessed web page user category information;

The second deriving means, for obtaining corresponding to described webpage and relevant with described user category information content recommendation information, wherein, the web page content information of described content recommendation information for to this user, recommending described webpage;

First presents device, for to described user, presenting described content recommendation information.

According to an aspect of the present invention, also provide a kind of computer equipment, wherein, this computer equipment comprises described recommendation apparatus.

Compared with prior art, the present invention has the following advantages: 1) can obtain for recommend the recommendation information of the web page content information that its webpage of accessing may be relevant to its point of interest to the user, and present to the user, so that the user can obtain the information of self being concerned about fast, reduce the time that the user searches at the page, improved the efficiency that the user obtains info web; 2) but the content information in the webpage that the extract real-time user accesses and select and this user's the corresponding content information of user category information, as the recommendation information that offers this user, make the recommendation information the provided user's request of more fitting.

The accompanying drawing explanation

By reading the detailed description that non-limiting example is done of doing with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:

A kind of computer implemented method flow diagram that content recommendation information is provided to the user that Fig. 1 is one aspect of the invention;

Fig. 2 is a preferred embodiment of the invention provides the method flow diagram of content recommendation information to the user;

Fig. 3 is one aspect of the invention provides the structural representation of the recommendation apparatus of content recommendation information to the user;

Fig. 4 is a preferred embodiment of the invention provides the structural representation of the recommendation apparatus of content recommendation information to the user.

In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.

Embodiment

Below in conjunction with accompanying drawing, the present invention is described in further detail.

Fig. 1 has illustrated a kind of computer implemented method flow diagram that content recommendation information is provided to the user of one aspect of the invention.The method according to this invention comprises step S1, step S2 and step S3.Wherein, the method according to this invention can realize by the recommendation apparatus in computer equipment, for example, by such as application module, operating system, processing controller etc. in computer equipment, realizes.Wherein, described computer equipment be a kind of can be according to the program of prior storage, automatically, the modernization intelligent electronic device that carries out at high speed massive values computation and various information processings, its hardware includes but not limited to microprocessor, FPGA, DSP, embedded device etc.Described computer equipment includes but not limited to subscriber equipment and the network equipment.Wherein, described subscriber equipment includes but not limited to computer, smart mobile phone, PDA etc.The described network equipment includes but not limited to server group or the cloud consisted of a large amount of computing machines or the webserver based on cloud computing (Cloud Computing) that single network server, a plurality of webserver form, wherein, cloud computing is a kind of of Distributed Calculation, the super virtual machine be comprised of the loosely-coupled computing machine collection of a group.Wherein, described subscriber equipment or the residing network of the described network equipment include but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN network etc.

It should be noted that; described subscriber equipment and the network equipment are only for giving an example; other subscriber equipmenies existing or that may occur from now on, the network equipment or network, as applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this with way of reference.

In step S1, recommendation apparatus obtains the user's of accessed web page user category information.Wherein, described user category information comprises one or more class of subscribers.

Particularly, the mode of user category information that described recommendation apparatus obtains the user of accessed web page includes but not limited to:

1) recommendation apparatus directly obtains the described user's of pre-stored user category information;

2) recommendation apparatus obtains the user category information from the described user of other equipment;

3) recommendation apparatus, according to the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, is determined described user's user category information.Wherein, described predetermined webpage classification packets of information is drawn together one or more webpage classifications.

Particularly, recommendation apparatus is in one or more webpage classifications that the predetermined webpage classification information of each webpage of described user access in the second predetermined amount of time comprises, select the class of subscriber of at least one webpage classification as described user, to generate described user's user category information.

For example, in predetermined 1 hour, in 3 webpages of user User_1 access, the predetermined webpage classification packets of information of webpage Web_1 is drawn together " news " and " amusement " two webpage classifications; The predetermined webpage classification packets of information of webpage Web_2 is drawn together " amusement ", " information " and " house property " three webpage classifications, the predetermined webpage classification packets of information of webpage Web_3 is drawn together " amusement " and " house property " two webpage classifications, recommendation apparatus is selected " amusement " that occurrence number is maximum class of subscriber as User_1, the user category information that comprises class of subscriber " amusement " with generation in each obtained webpage classification.

Preferably, described predetermined webpage classification packets of information is drawn together a plurality of webpage classifications and other weight information of each web page class, and described user category information comprises the weight information of a plurality of class of subscribers and each class of subscriber.

Preferably, recommendation apparatus obtains the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, and, for each the webpage classification comprised in each predetermined webpage classification information, recommendation apparatus to it weight information under each predetermined webpage classification information added up and processed, with according to the statistical treatment result, select one or more webpage classifications as described class of subscriber, and obtain the weight information of selected class of subscriber, comprise and generate based on described statistical treatment result the weight information of described class of subscriber with generation; Then, recommendation apparatus, according to the weight information of selected one or more class of subscribers and each class of subscriber thereof, generates described user's user category information.

For example, it is as shown in table 1 below that recommendation apparatus obtains three webpage Web_3, Web_4, Web_5 webpage classification information separately that in the second predetermined amount of time, user User_2 accesses:

Table 1

It is as shown in table 2 below that recommendation apparatus obtains other average weight value of each web page class:

The webpage classification	The average weight value
		The swordsman	65％
Describing love affairs	20％
		Military	42.5％
Science fiction	25％

Table 2

Recommendation apparatus is selected the webpage classification " swordsman ", " military affairs " and " science fiction " of the weight information rank front three class of subscriber as User_2, and the weighted value using the mutual ratio of these three other average weight values of web page class as corresponding class of subscriber, to generate the user category information of User_2 as shown in table 3 below:

The webpage classification	Weighted value
		The swordsman	49.0％
Military	32.1％
		Science fiction	18.9％

Table 3

It should be noted that, above-mentioned for example only for technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any predetermined webpage classification information according to each webpage of described user access in the second predetermined amount of time, determine the implementation of described user's user category information, for example, using obtained all webpage classifications as class of subscriber in the mode that generates user category information etc., all should be within the scope of the present invention.

What need to further illustrate is, above-mentioned for example only for technical scheme of the present invention is described better, but not limitation of the present invention those skilled in the art should understand that, the implementation of any user's who obtains accessed web page user category information, all should be within the scope of the present invention.

Then, in step S2, recommendation apparatus obtains corresponding to described webpage and relevant with described user category information content recommendation information, wherein, and the web page content information of described content recommendation information for to this user, recommending described webpage.

Wherein, described web page content information comprises the content information that described webpage comprises.Preferably, described web page content information includes but not limited to: 1) link address information; 2) text message; 3) multimedia messages etc.

Preferably, described content recommendation information includes but not limited to: 1) the part or all of information of described web page content information, for example, the URL that the need in webpage are recommended and the anchor text message corresponding with this URL, again for example, need one or more text key words of recommendation in webpage; 2) need the recommendation information of the content information recommended for introducing described webpage, for example, need the heading message of the video file recommended and the placard thumbnail of this video file etc. in webpage.

Particularly, the mode that described recommendation apparatus obtains corresponding to described webpage and relevant with described user category information content recommendation information includes but not limited to:

1) recommendation apparatus is selected web page content information in described webpage, and, according to selected web page content information, generates for recommending the described content recommendation information of this web page content information.Wherein, corresponding content type information and the described user category information of selected web page content information is complementary.

Wherein, this implementation will be described in detail in the embodiment shown in reference Fig. 2.

2), in the predetermined recommendation information storehouse that recommendation apparatus is correlated with at described user category information, select the web page content information of recommending to be contained in the recommendation information in described webpage, as described content recommendation information.Wherein, the recommendation information comprised in described predetermined recommendation information storehouse is for obtaining in advance.

For example, the user category information that recommendation apparatus obtains the user of accessed web page Web_6 in step S1 comprises class of subscriber " house property ", the predetermined recommendation information storehouse relevant to " house property " that recommendation apparatus obtains in advance comprises character " building ", " location ", and " http:www.abc.com "; And comprise keyword " building " in the text message of recommendation apparatus judgement webpage Web_6, and the URL that the hyperlink that in Web_6, the anchor text is " ABC " comprises is " http:www.abc.com ", recommendation apparatus is using character " building " as for recommending the content recommendation information of text message of Web_6, the content recommendation information using character " http:www.abc.com " as the hyperlink " ABC " that is used for recommending Web_6.

It should be noted that, above-mentioned for example only for technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any implementation of obtaining corresponding to described webpage and relevant with described user category information content recommendation information, all should be within the scope of the present invention.

Then, in step S3, recommendation apparatus presents described content recommendation information to described user.

Wherein, those skilled in the art should determine the mode that presents described content recommendation information to described user according to actual conditions and demand, for example, content recommendation information is presented in to the mode in the floating frame relevant to described webpage, again for example, when content recommendation information comprises keyword, the mode that the keyword overstriking in described webpage is shown etc., do not repeat them here.

As one of the preferred embodiments of the present invention, the method according to this invention also comprises step S5 (not shown) and step S6 (not shown).

In step S5, the selection operation that recommendation apparatus is carried out described content recommendation information according to described user, determine the web page content information that the user selects.

Particularly, recommendation apparatus is according to user's selection operation, the web page content information that the content recommendation information that the user is selected is recommended, the web page content information of selecting as the user.

Then, in step S6, the web page content information that recommendation apparatus is selected described user is presented to described user.

Wherein, those skilled in the art should determine the mode that the web page content information of described user's selection is presented to described user according to actual conditions and demand, for example, new pop-up window is to play the mode of user-selected video file, again for example, the position that represents of webpage is jumped to mode of the position that comprises user-selected text message etc., repeat no more herein.

As one of the preferred embodiments of the present invention, the method according to this invention also comprises step S8 (not shown).

In step S8, recommendation apparatus, according to the user category information of each user of the described webpage of access in the 3rd predetermined amount of time, is determined the webpage classification information of described webpage.Wherein, described user category information comprises one or more class of subscribers.

Wherein, described recommendation apparatus is according to the user category information of each user of the described webpage of access in the 3rd predetermined amount of time, determine the mode of the webpage classification information of described webpage, implementation 3 with abovementioned steps S1) recommendation apparatus described in is according to the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, the mode of user category information of determining described user is similar, repeats no more herein.

The method according to this invention, can obtain for recommend the recommendation information of the web page content information that its webpage of accessing may be relevant to its point of interest to the user, and present to the user.So that the user can obtain the information of self being concerned about fast, reduced the time that the user searches at the page, improved the efficiency that the user obtains info web.

What Fig. 2 had illustrated a preferred embodiment of the invention provides the method flow diagram of content recommendation information to the user.Comprise step S1, step S2 and step S3 according to the method for the present embodiment.Wherein, described step S2 further comprises step S201 and step S202.

Step S1 is described in detail in the embodiment shown in reference Fig. 1, and is contained in this by reference, repeats no more.

In step S201, recommendation apparatus is selected web page content information in described webpage, and wherein, the user category information that the content type information that selected web page content information is corresponding and recommendation apparatus obtain in step S1 is complementary.

As one of preferred version of this step, whether recommendation apparatus has comprised the identical classification that is greater than predetermined quantity according to described content type information and described user category information, judge whether described content type information and described user category information are complementary.

For example, the web page contents classification information content classification " Europe " of the content information that recommendation apparatus is selected in webpage, " diplomacy ", " current events ", comprise class of subscriber " amusement ", " Europe ", " current events " in the user category information that recommendation apparatus obtains in step S1, recommendation apparatus is determined the quantity 2 of this content type information and the identical classification comprised in this user category information, and judge that 2 are greater than predetermined quantity threshold value 1, recommendation apparatus judges that this content type information and this user category information are complementary.

As one of preferred version of this step, described content type information comprises the weight information of a plurality of content types and each content type, and described user category information comprises the weight information of a plurality of class of subscribers and each class of subscriber.

The identical category that recommendation apparatus comprises according to described content type information and described user category information, and, whether described identical weight information and the weight information in described user category information of classification in described content type information meets the predefined weight condition, judges whether described content type information and described user category information are complementary.

Wherein, described predefined weight condition includes but not limited to anyly can, according to the weight information of described identical category and this identical category, judge the condition whether described content type information and described user category information are complementary.Preferably, described predefined weight condition comprises following at least one: 1) weight information of described identical category in content type information is greater than the predefined weight threshold value; 2) weight information of described identical category in content type information and the difference of its weight information in user category information are less than the predetermined difference value threshold value.

Particularly, recommendation apparatus selects the mode of web page content information to include but not limited in described webpage:

1) recommendation apparatus selects to meet the alternative web pages content information of predetermined optional condition in described webpage; And selection needs the web page content information of recommending in described alternative web pages content information.Wherein, corresponding content type information and the described user category information of this web page content information is complementary.

Wherein, whether described predetermined optional condition is significant content information or the interested content information of user's possibility for the content information that judges webpage.Preferably, described predetermined alternative condition includes but not limited to following at least one:

A) content information does not belong to predetermined redundant information storehouse, and described redundant information comprises predetermined meaningless information in storehouse, as web advertisement information, such as meaningless character information such as " " etc.

B) content information comprises popular information.Wherein, those skilled in the art should determine whether the content information that judges selected webpage is the mode of popular information according to actual conditions and demand, for example, whether the accessed number of times that judges described content information is greater than pre-determined number, again for example, the number of times that judges the described content information of search in nearest 24 hours is greater than predetermined searched number of times etc., does not repeat them here.

Wherein, the mode of obtaining the content type information that described alternative web pages content information is corresponding includes but not limited to: the content type information corresponding with described alternative web pages content information of a) obtaining pre-stored; B) send the request of the identification information that comprises described alternative web pages content information to network, to receive the content type information corresponding with described alternative web pages content information of automatic network; C) determine in real time the content type information corresponding with described alternative web pages content information.Wherein, the mode of determining the content type information corresponding with described alternative web pages content information will be described in detail in the preferred version of follow-up the present embodiment.

Particularly, recommendation apparatus selects to meet the alternative web pages content information of predetermined optional condition in described webpage; Then, recommendation apparatus obtains the content type information that described alternative web pages content information is corresponding, with judge this content type information whether with step S1 in the user category information that obtains be complementary, and when judging that this content type information and described user category information are complementary, the web page content information of recommending this alternative web pages content information as needs.

For example, the user category information that recommendation apparatus obtains in step S1 comprises class of subscriber " amusement ", " Taiwan ", " star ", recommendation apparatus is selected the text message of webpage Web_7, and comprises popular search keyword " star " and " wedding " of first 10 of current rank in definite text message, and recommendation apparatus determines that text information is the alternative web pages content information, then, recommendation apparatus is according to the title " news_taiwan " of text information, inquiry in the web page content information prestored in this locality table corresponding to content type information, and " news_taiwan " the corresponding content type information that obtains comprises content tab information " amusement ", " news " and " Taiwan ", the matched rule that recommendation apparatus comprises at least two identical classifications according to predetermined content type information and user category information, determine that the content type information of text message " news_taiwan " and the user category information that recommendation apparatus obtains in step S1 are complementary, and select text message " news_taiwan " as needing the web page content information of recommending in Web_7.

2) web page content information of selecting one or more alternative web pages content informations to recommend as needs in the predetermined content information bank corresponding with described webpage, wherein, the described corresponding content type information of content information and the described user category information recommended of needing is complementary.Wherein, comprise the alternative web pages content information that at least one meets predetermined optional condition in described predetermined content information bank.

Wherein, recommendation apparatus, according to the identification information of described webpage, is determined the predetermined content information bank corresponding with described webpage; Then, recommendation apparatus obtains the corresponding content type information of the web page content information comprised in described predetermined content information bank, with judge this content type information whether with step S1 in the user category information that obtains be complementary, when judging that this content type information and described user category information are complementary, the web page content information of recommending this alternative web pages content information as needs.

Wherein, recommendation apparatus is according to the identification information of described webpage, the mode of determining the predetermined content information bank corresponding with described webpage includes but not limited to: a) identification information of the described webpage of inquiry in a plurality of predetermined content information banks of local pre-stored, the predetermined content information bank corresponding with described webpage with acquisition; B) identification information of described webpage is sent to network, to obtain the predetermined content information bank corresponding with described webpage in network.

Wherein, recommendation apparatus obtains content type information corresponding to web page content information comprised in described predetermined content information bank, with judge this content type information whether with step S1 in the user category information that obtains be complementary, and when judging that this content type information and described user category information are complementary, mode using this alternative web pages content information as web page content information, with aforementioned implementation 1) described in mode same or similar, repeat no more herein.

It should be noted that, above-mentioned for example only for technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, the implementation of any web page content information of selecting corresponding content type information and user category information to be complementary in described webpage, all should be within the scope of the present invention.

Then, in step S202, recommendation apparatus, according to selected web page content information, generates for recommending the described content recommendation information of this web page content information.

Particularly, recommendation apparatus obtains the part or all of information of selected web page content information, and, according to the presentation mode of predetermined content recommendation information, correspondingly generates for recommending the content recommendation information of this web page content information.

For example, the web page content information that recommendation apparatus obtains in step S201 comprises text message " news_taiwan ", the presentation mode of predetermined text message comprises the link that presents text message itself and be positioned to it, recommendation apparatus obtains the title " news_taiwan " of text information and for the link of the webpage position that is positioned to text information, generation is with the hyperlink of " news_taiwan ", as the content recommendation information of text message " news_taiwan ".

Again for example, the web page content information that recommendation apparatus obtains in step S201 comprises picture Pic_1, the presentation mode of predetermined pictorial information comprises and presents picture thumbnail and describe text, recommendation apparatus obtains the description text of Pic_1 in current web page, and generate the thumbnail of Pic_1, using this is described to text and the thumbnail content recommendation information as Pic_1.

It should be noted that, above-mentioned for example only for technical scheme of the present invention is described better, but not limitation of the present invention, those skilled in the art should understand that, any according to selected web page content information, generate the implementation of the described content recommendation information for recommending this web page content information, all should be within the scope of the present invention.

Then, step S3 is described in detail in the embodiment shown in reference Fig. 1, and is contained in this by reference, repeats no more.

As one of preferred version of the present embodiment, recommendation apparatus carrys out to determine the content type information corresponding with described alternative web pages content information in the following manner:

1) when described web page content information comprises link address information, the webpage classification information of the webpage pointed content type information corresponding as it using described link address information;

2), when described web page content information comprises other web page content information except link address information, recommendation apparatus is determined the content type information of described other web page content information according to following at least one information:

A) each user's of described other web page content information of retrieval user category information in the first predetermined amount of time.

Wherein, the mode of obtaining each user's of described other web page contents of retrieval user category information in the first predetermined amount of time includes but not limited to:

I) directly obtain the interior user category information of retrieving each user of described other web page contents of described the first predetermined amount of time of pre-stored.

Ii) obtain the user category information from each user of described other web page contents of retrieval in described first predetermined amount of time of other equipment.

Iii) obtain the user totem information of each user of described other web page contents of retrieval in described the first predetermined amount of time, and obtain corresponding user category information according to described user totem information.For example, three users' that the recommendation apparatus acquisition term that employing comprises the audio file title is within a predetermined period of time retrieved user totem information User_3, User_4 and User_5, and inquire about in the user category information storehouse of pre-stored according to user totem information, obtain respectively the user category information of User_3, User_4 and User_5.

Particularly, described recommendation apparatus is according to the user category information of each user of described other web page content information of retrieval in the first predetermined amount of time, determine the mode of the content type information of described other web page content information, implementation 3 with aforementioned reference step S1 embodiment illustrated in fig. 1) recommendation apparatus described in is according to the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, the mode of user category information of determining described user is same or similar, repeats no more herein.

B) retrieve the webpage classification information of each webpage that described other web page content information obtain.

Wherein, the mode of obtaining the webpage classification information of each webpage of obtaining of described other web page content information of retrieval includes but not limited to:

I) directly obtain the webpage classification information of each webpage that described other web page content information of retrieval of pre-stored obtain.

Ii) obtain the webpage classification information of each webpage obtained from described other web page content information of the retrieval of other equipment.

Iii) obtain the banner information of each webpage that described other web page contents of one or many retrieval obtain, to obtain the webpage classification information of corresponding web page according to described banner information.

Particularly, the webpage classification information of each webpage that described recommendation apparatus obtains according to described other web page content information of retrieval, determine the mode of the content type information of described other web page content information, with the user category information of recommendation apparatus described in aforementioned reference step S8 embodiment illustrated in fig. 1 according to each user of the described webpage of access in the 3rd predetermined amount of time, the mode of webpage classification information of determining described webpage is similar, repeats no more herein.

Method according to the present embodiment, but the content information in the webpage that extract real-time user accesses, and select and this user's the corresponding content information of user category information, as the recommendation information that offers this user, make the recommendation information the provided user's request of more fitting.

What Fig. 3 had illustrated one aspect of the invention provides the structural representation of the recommendation apparatus of content recommendation information to the user.Recommendation apparatus according to the present invention comprises that the first deriving means 1, the second deriving means 2 and first present device 3.

The first deriving means 1 obtains the user's of accessed web page user category information.Wherein, described user category information comprises one or more class of subscribers.

Particularly, the mode of user category information that described the first deriving means 1 obtains the user of accessed web page includes but not limited to:

1) the first deriving means 1 directly obtains the described user's of pre-stored user category information;

2) the first deriving means 1 obtains the user category information from the described user of other equipment;

3) be contained in the 3rd in the first deriving means 1 and determine the predetermined webpage classification information of device (not shown) according to each webpage of described user's access in the second predetermined amount of time, determine described user's user category information.Wherein, described predetermined webpage classification packets of information is drawn together one or more webpage classifications.

Particularly, the 3rd determines that device is in one or more webpage classifications that the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time comprises, select the class of subscriber of at least one webpage classification as described user, to generate described user's user category information.

For example, in predetermined 1 hour, in 3 webpages of user User_1 access, the predetermined webpage classification packets of information of webpage Web_1 is drawn together " news " and " amusement " two webpage classifications; The predetermined webpage classification packets of information of webpage Web_2 is drawn together " amusement ", " information " and " house property " three webpage classifications, the predetermined webpage classification packets of information of webpage Web_3 is drawn together " amusement " and " house property " two webpage classifications, the 3rd determines that device selects " amusement " that occurrence number is maximum class of subscriber as User_1, the user category information that comprises class of subscriber " amusement " with generation in each obtained webpage classification.

Preferably, the 3rd determines that device obtains the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, and, for each the webpage classification comprised in each predetermined webpage classification information, the 3rd determine device to it weight information under each predetermined webpage classification information added up and processed, with according to the statistical treatment result, select one or more webpage classifications as described class of subscriber, and obtain the weight information of selected class of subscriber, the weight information that comprises and generate based on described statistical treatment result described class of subscriber with generation, then, the 3rd determines the weight information of device according to selected one or more class of subscribers and each class of subscriber thereof, generates described user's user category information.

For example, the 3rd to determine that device obtains three webpage Web_3, Web_4, the Web_5 webpage classification information separately of user User_2 access in the second predetermined amount of time as shown in table 4 below:

Table 4

The 3rd to determine that device obtains other average weight value of each web page class as shown in table 5 below:

Table 5

The 3rd webpage classification " swordsman " of determining Array selection weight information rank front three, " military affairs " and " science fiction " are as the class of subscriber of User_2, and the weighted value using the mutual ratio of these three other average weight values of web page class as corresponding class of subscriber, to generate the user category information of User_2 as shown in table 6 below:

Table 6

Then, the second deriving means 2 obtains corresponding to described webpage and relevant with described user category information content recommendation information, wherein, and the web page content information of described content recommendation information for to this user, recommending described webpage.

Particularly, the mode that described the second deriving means 2 obtains corresponding to described webpage and relevant with described user category information content recommendation information includes but not limited to:

1) the second deriving means 2 is selected web page content information in described webpage, and, according to selected web page content information, generates for recommending the described content recommendation information of this web page content information.Wherein, corresponding content type information and the described user category information of selected web page content information is complementary.

Wherein, this implementation will be described in detail in the embodiment shown in reference Fig. 4.

2), in the predetermined recommendation information storehouse that the second deriving means 2 is correlated with at described user category information, select the web page content information of recommending to be contained in the recommendation information in described webpage, as described content recommendation information.Wherein, the recommendation information comprised in described predetermined recommendation information storehouse is for obtaining in advance.

For example, the user category information that the first deriving means 1 obtains the user of accessed web page Web_6 comprises class of subscriber " house property ", the predetermined recommendation information storehouse relevant to " house property " that recommendation apparatus obtains in advance comprises character " building ", " location ", and " http:www.abc.com "; And comprise keyword " building " in the text message of the second deriving means 2 judgement webpage Web_6, and the URL that the hyperlink that in Web_6, the anchor text is " ABC " comprises is " http:www.abc.com ", the second deriving means 2 is using character " building " as for recommending the content recommendation information of text message of Web_6, the content recommendation information using character " http:www.abc.com " as the hyperlink " ABC " that is used for recommending Web_6.

Then, first presents device 3 and presents described content recommendation information to described user.

As one of the preferred embodiments of the present invention, according to recommendation apparatus of the present invention, also comprise that second determines that device (not shown) and second presents the device (not shown).

Second determines the selection operation that device is carried out described content recommendation information according to described user, determines the web page content information that the user selects.

Particularly, second determines the selection operation of device according to the user, the web page content information that the content recommendation information that the user is selected is recommended, the web page content information of selecting as the user.

Then, second presents the web page content information that device selects described user and presents to described user.

As one of the preferred embodiments of the present invention, according to recommendation apparatus of the present invention, also comprise that the 4th determines the device (not shown).

The 4th determines the user category information of device according to each user of the described webpage of access in the 3rd predetermined amount of time, determines the webpage classification information of described webpage.Wherein, described user category information comprises one or more class of subscribers.

Wherein, the described the 4th determines the user category information of device according to each user of the described webpage of access in the 3rd predetermined amount of time, determine the mode of the webpage classification information of described webpage, with the predetermined webpage classification information of aforementioned the first deriving means 1 according to each webpage of described user's access in the second predetermined amount of time, the mode of user category information of determining described user is similar, repeats no more herein.

According to the solution of the present invention, can obtain for recommend the recommendation information of the web page content information that its webpage of accessing may be relevant to its point of interest to the user, and present to the user.So that the user can obtain the information of self being concerned about fast, reduced the time that the user searches at the page, improved the efficiency that the user obtains info web.

What Fig. 4 had illustrated a preferred embodiment of the invention provides the structural representation of the recommendation apparatus of content recommendation information to the user.According to the recommendation apparatus of the present embodiment comprise the first deriving means 1, be contained in the first selecting arrangement 201 of the second deriving means 2, the generating apparatus 202 and first that is contained in the second deriving means 2 presents device 3.

The first deriving means 1 is described in detail in the embodiment shown in reference Fig. 3, and is contained in this by reference, repeats no more.

The first selecting arrangement 201 is selected web page content information in described webpage, and wherein, the user category information that the content type information that selected web page content information is corresponding and the first deriving means 1 obtain is complementary.

As one of preferred operations scheme of this device, whether the first selecting arrangement 201 has comprised the identical classification that is greater than predetermined quantity according to described content type information and described user category information, judge whether described content type information and described user category information are complementary.

For example, the web page contents classification information content classification " Europe " of the content information that the first selecting arrangement 201 is selected in webpage, " diplomacy ", " current events ", comprise class of subscriber " amusement ", " Europe ", " current events " in the user category information that the first deriving means 1 obtains, the first selecting arrangement 201 is determined the quantity 2 of this content type information and the identical classification comprised in this user category information, and judge that 2 are greater than predetermined quantity threshold value 1, first selecting arrangement 201 these content type information of judgement and this user category information are complementary.

As one of preferred operations scheme of this device, described content type information comprises the weight information of a plurality of content types and each content type, and described user category information comprises the weight information of a plurality of class of subscribers and each class of subscriber.

The identical category that the first selecting arrangement 201 comprises according to described content type information and described user category information, and, whether described identical weight information and the weight information in described user category information of classification in described content type information meets the predefined weight condition, judges whether described content type information and described user category information are complementary.

Particularly, the first selecting arrangement 201 selects the mode of web page content information to include but not limited in described webpage:

1) the first sub-selecting arrangement (not shown) be contained in the first selecting arrangement 201 selects to meet the alternative web pages content information of being scheduled to optional condition in described webpage; Then, the second sub-selecting arrangement (not shown) be contained in the first selecting arrangement 201 selects to need the web page content information of recommending in described alternative web pages content information.Wherein, corresponding content type information and the described user category information of this web page content information is complementary.

Particularly, the first sub-selecting arrangement selects to meet the alternative web pages content information of predetermined optional condition in described webpage; Then, the second sub-selecting arrangement obtains the content type information that described alternative web pages content information is corresponding, to judge whether this content type information is complementary with the user category information of the first deriving means 1 acquisition, and when judging that this content type information and described user category information are complementary, the web page content information of recommending this alternative web pages content information as needs.

For example, the user category information that the first deriving means 1 obtains comprises class of subscriber " amusement ", " Taiwan ", " star ", the first sub-selecting arrangement is selected the text message of webpage Web_7, and comprises popular search keyword " star " and " wedding " of first 10 of current rank in definite text message, and the first sub-selecting arrangement determines that text information is the alternative web pages content information, then, the second sub-selecting arrangement is according to the title " news_taiwan " of text information, inquiry in the web page content information prestored in this locality table corresponding to content type information, and " news_taiwan " the corresponding content type information that obtains comprises content tab information " amusement ", " news " and " Taiwan ", the matched rule that the second sub-selecting arrangement comprises at least two identical classifications according to predetermined content type information and user category information, determine that the content type information of text message " news_taiwan " and the user category information that the first deriving means 1 obtains are complementary, and select text message " news_taiwan " as needing the web page content information of recommending in Web_7.

2) the first selecting arrangement 201 is selected the web page content information that one or more alternative web pages content informations are recommended as needs in the predetermined content information bank corresponding with described webpage, wherein, the described corresponding content type information of content information and the described user category information recommended of needing is complementary.Wherein, comprise the alternative web pages content information that at least one meets predetermined optional condition in described predetermined content information bank.

Wherein, the first selecting arrangement 201, according to the identification information of described webpage, is determined the predetermined content information bank corresponding with described webpage; Then, the first selecting arrangement 201 obtains the corresponding content type information of the web page content information comprised in described predetermined content information bank, to judge whether this content type information is complementary with the user category information of the first deriving means 1 acquisition, when judging that this content type information and described user category information are complementary, the web page content information of recommending this alternative web pages content information as needs.

Wherein, the first selecting arrangement 201 is according to the identification information of described webpage, the mode of determining the predetermined content information bank corresponding with described webpage includes but not limited to: a) identification information of the described webpage of inquiry in a plurality of predetermined content information banks of local pre-stored, the predetermined content information bank corresponding with described webpage with acquisition; B) identification information of described webpage is sent to network, to obtain the predetermined content information bank corresponding with described webpage in network.

Wherein, the first selecting arrangement 201 obtains content type information corresponding to web page content information comprised in described predetermined content information bank, to judge whether this content type information is complementary with the user category information of the first deriving means 1 acquisition, and when judging that this content type information and described user category information are complementary, mode using this alternative web pages content information as web page content information, with aforementioned implementation 1) described in the mode of operation of the second sub-selecting arrangement same or similar, repeat no more herein.

Then, generating apparatus 202, according to selected web page content information, generates for recommending the described content recommendation information of this web page content information.

Particularly, generating apparatus 202 obtains the part or all of information of selected web page content information, and, according to the presentation mode of predetermined content recommendation information, correspondingly generates for recommending the content recommendation information of this web page content information.

For example, the web page content information that the first deriving means 1 obtains comprises text message " news_taiwan ", the presentation mode of predetermined text message comprises the link that presents text message itself and be positioned to it, generating apparatus 202 obtains the title " news_taiwan " of text information and for the link of the webpage position that is positioned to text information, generation is with the hyperlink of " news_taiwan ", as the content recommendation information of text message " news_taiwan ".

Again for example, the web page content information that the first selecting arrangement 201 obtains comprises picture Pic_1, the presentation mode of predetermined pictorial information comprises and presents picture thumbnail and describe text, generating apparatus 202 obtains the description text of Pic_1 in current web page, and generate the thumbnail of Pic_1, using this is described to text and the thumbnail content recommendation information as Pic_1.

Then, first presents device 3 is described in detail in the embodiment shown in reference Fig. 3, and is contained in this by reference, repeats no more.

2), when described web page content information comprises other web page content information except link address information, be contained in the definite device (not shown) of first in recommendation apparatus and determine the content type information of described other web page content information according to following at least one information:

Iii) obtain the user totem information of each user of described other web page contents of retrieval in described the first predetermined amount of time, and obtain corresponding user category information according to described user totem information.For example, first determines three users' that the device acquisition term that employing comprises the audio file title is within a predetermined period of time retrieved user totem information User_3, User_4 and User_5, and inquire about in the user category information storehouse of pre-stored according to user totem information, obtain respectively the user category information of User_3, User_4 and User_5.

Particularly, described first determines the user category information of device according to each user of described other web page content information of retrieval in the first predetermined amount of time, determine the mode of the content type information of described other web page content information, with the predetermined webpage classification information of aforementioned reference the first deriving means 1 embodiment illustrated in fig. 3 according to each webpage of described user's access in the second predetermined amount of time, the mode of user category information of determining described user is same or similar, repeats no more herein.

Particularly, described first determines the webpage classification information of each webpage that device obtains according to described other web page content information of retrieval, determine the mode of the content type information of described other web page content information, in embodiment illustrated in fig. 3 with aforementioned reference, the 4th determines the user category information of device according to each user of the described webpage of access in the 3rd predetermined amount of time, the mode of webpage classification information of determining described webpage is similar, repeats no more herein.

Scheme according to the present embodiment, but the content information in the webpage that extract real-time user accesses, and select and this user's the corresponding content information of user category information, as the recommendation information that offers this user, make the recommendation information the provided user's request of more fitting.

To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned example embodiment, and in the situation that do not deviate from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore, no matter from which point, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims rather than above-mentioned explanation, therefore is intended to be included in the present invention dropping on the implication that is equal to important document of claim and all changes in scope.Any Reference numeral in claim should be considered as limit related claim.In addition, obviously other unit or step do not got rid of in " comprising " word, and odd number is not got rid of plural number.A plurality of unit of stating in the system claim or device also can be realized by software or hardware by a unit or device.The first, the second word such as grade is used for meaning title, and does not mean any specific order.

Claims

1. the computer implemented method that content recommendation information is provided to the user wherein, said method comprising the steps of:

A. obtain the user's of accessed web page user category information;

C. present described content recommendation information to described user.

2. method according to claim 1, wherein, described step b comprises the following steps:

B1 selects web page content information in described webpage, and wherein, content type information and described user category information that described web page content information is corresponding are complementary;

B2, according to selected web page content information, generates for recommending the described content recommendation information of this web page content information.

3. method according to claim 2, wherein, described step b1 comprises the following steps:

-in described webpage, selection meets the alternative web pages content information of predetermined optional condition;

-select described web page content information in described alternative web pages content information, wherein, content type information and described user category information that this web page content information is corresponding are complementary.

4. method according to claim 3, wherein, described content type information comprises the weight information of a plurality of content types and each content type, described user category information comprises the weight information of a plurality of class of subscribers and each class of subscriber.

5. according to the described method of any one in claim 2 to 4, wherein, described web page content information comprises link address information, and wherein, content type information corresponding to described link address information comprises the webpage classification information of described link address information webpage pointed.

6. according to the described method of any one in claim 2 to 4, wherein, described web page content information comprises other web page content information except link address information, and wherein, described method also comprises:

-determine the content type information of described other web page content information according to following at least one information:

-each user's of described other web page content information of retrieval user category information in the first predetermined amount of time;

-retrieve the webpage classification information of each webpage that described other web page content information obtain.

7. method according to claim 1, wherein, described step b comprises the following steps:

-at described user category information, in relevant predetermined recommendation information storehouse, select the web page content information of recommending to be contained in the recommendation information in described webpage, as described content recommendation information.

8. according to the described method of any one in claim 1 to 7, wherein, described method is further comprising the steps of:

-according to described user, the selection of described content recommendation information execution is operated, determine the web page content information that the user selects;

-web page content information of described user's selection is presented to described user.

9. according to the described method of any one in claim 1 to 8, wherein, described step a comprises the following steps:

-according to the predetermined webpage classification information of each webpage of described user's access in the second predetermined amount of time, determine described user's user category information.

10. according to the described method of any one in claim 5 or 6 or 9, wherein, described method is further comprising the steps of:

-according to the user category information of each user of the described webpage of access in the 3rd predetermined amount of time, determine the webpage classification information of described webpage.

11. one provides the recommendation apparatus of content recommendation information to the user, wherein, described recommendation apparatus comprises:

12. recommendation apparatus according to claim 11, wherein, described the second deriving means comprises:

The first selecting arrangement, for by described webpage, selecting web page content information, wherein, content type information and described user category information that described web page content information is corresponding are complementary;

Generating apparatus, for according to selected web page content information, generate for recommending the described content recommendation information of this web page content information.

13. recommendation apparatus according to claim 12, wherein, described the second deriving means comprises:

The first sub-selecting arrangement, for being selected to meet the alternative web pages content information of predetermined optional condition by described webpage;

The second sub-selecting arrangement, for by described alternative web pages content information, selecting described web page content information, wherein, content type information and described user category information that this web page content information is corresponding are complementary.

14. recommendation apparatus according to claim 13, wherein, described content type information comprises the weight information of a plurality of content types and each content type, and described user category information comprises the weight information of a plurality of class of subscribers and each class of subscriber.

15. according to claim 12 to the described recommendation apparatus of any one in 14, wherein, described web page content information comprises link address information, and wherein, content type information corresponding to described link address information comprises the webpage classification information of described link address information webpage pointed.

16., according to claim 12 to the described recommendation apparatus of any one in 14, wherein, described web page content information comprises other web page content information except link address information, wherein, described recommendation apparatus also comprises:

First determines device, for determine the content type information of described other web page content information according to following at least one information:

17. recommendation apparatus according to claim 11, wherein, described the second deriving means comprises:

The second selecting arrangement, for the predetermined recommendation information storehouse relevant to described user category information, select the web page content information of recommending to be contained in the recommendation information in described webpage, as described content recommendation information.

18., according to claim 11 to the described recommendation apparatus of any one in 17, wherein, described recommendation apparatus also comprises:

Second determines device, for the selection operation of described content recommendation information being carried out according to described user, determines the web page content information that the user selects;

Second presents device, for the web page content information that described user is selected, presents to described user.

19., according to claim 11 to the described recommendation apparatus of any one in 18, wherein, described the first deriving means also comprises:

The 3rd determines device, for the predetermined webpage classification information according to each webpage of described user's access in the second predetermined amount of time, determines described user's user category information.

20., according to the described recommendation apparatus of any one in claim 15 or 16 or 19, wherein, described recommendation apparatus also comprises:

The 4th determines device, for the user category information according to each user of the described webpage of access in the 3rd predetermined amount of time, determines the webpage classification information of described webpage.

21. a computer equipment, wherein, this computer equipment comprises as at least one described recommendation apparatus in claim 11 to 20.