CN102902744A - Book recommendation method - Google Patents

Book recommendation method Download PDF

Info

Publication number
CN102902744A
CN102902744A CN2012103432633A CN201210343263A CN102902744A CN 102902744 A CN102902744 A CN 102902744A CN 2012103432633 A CN2012103432633 A CN 2012103432633A CN 201210343263 A CN201210343263 A CN 201210343263A CN 102902744 A CN102902744 A CN 102902744A
Authority
CN
China
Prior art keywords
books
user
vector
author
level
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2012103432633A
Other languages
Chinese (zh)
Other versions
CN102902744B (en
Inventor
廖建新
李萍
周立娟
崔晓茹
赵贝尔
张雷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xinxun Digital Technology (Hangzhou) Co.,Ltd.
Original Assignee
Hangzhou Dongxin Beiyou Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Dongxin Beiyou Information Technology Co Ltd filed Critical Hangzhou Dongxin Beiyou Information Technology Co Ltd
Priority to CN201210343263.3A priority Critical patent/CN102902744B/en
Publication of CN102902744A publication Critical patent/CN102902744A/en
Application granted granted Critical
Publication of CN102902744B publication Critical patent/CN102902744B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to a book recommendation method. The book recommendation method comprises the following steps: step A. establishing a book label vector of each book in a library according to the author, three-level classification, four-level classification and universal label of the book; step B. establishing the text label vector of each user according to the authors, three-level classifications, four-level classifications, universal labels of all deeply read books in the book reading records of the user and corresponding weighted values of the authors, the three-level classifications, the four-level classifications, the universal labels of all deeply read books in the book reading records of the user respectively; and step C. calculating the label scores of all books in the library corresponding to each user according to the corresponding weighted values of the authors, the three-level classifications, the four-level classifications, the universal labels in the book label vectors of the books respectively in the text label vectors of the users. The book recommendation method belongs to the technical field of network application, books can be individually recommended for the users according to the contents of the books and the reading habits of the users, and books meeting the user habits are recommended for the users; and therefore, the degree of satisfaction is increased, and the user experience is improved.

Description

A kind of book recommendation method
Technical field
The present invention relates to a kind of book recommendation method, belong to the network application technical field.
Background technology
Along with the develop rapidly of movement, Internet technology, being digitized into of books is an inexorable trend.Increasing books reading platform has been subject to showing great attention to of user, and has obtained fast development, has become the important channel of people's obtaining information and knowledge.
Usually the digital book resource that has magnanimity on the books reading platform, how to effectively utilize these abundant and valuable resources, allow the user can find more quickly and utilize fully them just to seem extremely important, so the Personalized Intelligent Recommendation of books be very important functions of books reading platform.
At present the books reading platform in book recommendation institute extensively the mode of employing include:
1, based on the recommend method of book classification or type, by book classification, will recommend to the user with classification or books of the same type with user read book, this method is not considered content topic and the keyword of books;
2, based on the recommend method of book content, adopt TF-IDF(word frequency-anti-document frequency, being term frequency – inverse document frequency) formula etc. carries out the recommendation based on the books content of text, because many books are to fabricate or original class books in the books reading platform, the hero who wherein relates to and event etc. are all fabricated, thereby bad based on the applicability of the recommend method of content of text, can not be for the user recommend out more to meet the books of user preferences with raising user's satisfaction, its performance and user experience not good.
Therefore, how according to the content of books and user's reading hobby, carry out the personalized recommendation of books to the user, be still the technical barrier that a urgent need will solve.
Summary of the invention
In view of this, the purpose of this invention is to provide a kind of book recommendation method, can according to the content of books and user's reading hobby, carry out the personalized recommendation of books to the user.
In order to achieve the above object, the invention provides a kind of book recommendation method, described method includes:
Steps A, the author according to books, reclassify, level Four classification and universal tag, the book labels of every books vector in the design of graphics stack room;
Step B, according to all author, reclassify, level Four classification, universal tag and corresponding weighted values respectively thereof of degree of depth read books in user's the books reading record, set up each user's text label vector;
Step C, according to author in the book labels vector of books, reclassify, level Four classification, universal tag corresponding weighted value in user's text label vector respectively, all books are corresponding to every user's label score in the calculating chart stack room.
Compared with prior art, the invention has the beneficial effects as follows: the present invention is according to the characteristics of books reading platform, utilize user's books degree of depth browing record to estimate it to the fancy grade of books author, reclassify, level Four classification and universal tag for the basis, and form accordingly corresponding author, reclassify, level Four classification and universal tag weight vectors, thereby set up all users' text label vector; In order between books and user, to set up corresponding contact, according to author, reclassify, level Four classification, these essential informations of universal tag of books, set up the book labels vector of all books in the Library; The matching degree of the text label vector of the book labels vector sum user by books is calculated, and weight setting, obtain at last all books with respect to the label score of user preferences, be the priority of Recommended Books, the books that the label score is the highest are recommended to the user, thereby recommend out more to meet the books of user preferences for the user, improve user's satisfaction, improve user's experience.
Description of drawings
Fig. 1 is a kind of book recommendation method process flow diagram of the present invention.
Fig. 2 is among Fig. 1 step C, calculates these books of i corresponding to the concrete operations process flow diagram of j position user's label score.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, the present invention is described in further detail below in conjunction with drawings and Examples.
As shown in Figure 1, a kind of book recommendation method of the present invention includes:
Steps A, the author according to books, reclassify, level Four classification and universal tag, the book labels of every books vector in the design of graphics stack room;
Step B, according to all author, reclassify, level Four classification, universal tag and corresponding weighted values respectively thereof of degree of depth read books in user's the books reading record, set up each user's text label vector;
Step C, according to author in the book labels vector of books, reclassify, level Four classification, universal tag corresponding weighted value in user's text label vector respectively, all books are corresponding to every user's label score in the calculating chart stack room;
All books are corresponding to every user's label score in step D, the comparison diagram stack room, and according to user's books reading record filtering user read books, some the books that the label score is the highest are recommended to described user at last.
In Fig. 1 steps A, the book labels of every books vector:
Figure 2012103432633100002DEST_PATH_IMAGE001
=＜
Figure 2012103432633100002DEST_PATH_IMAGE002
,
Figure 2012103432633100002DEST_PATH_IMAGE003
, ,
Figure 2012103432633100002DEST_PATH_IMAGE005
.Wherein,
Figure 2012103432633100002DEST_PATH_IMAGE006
The book labels vector of these books of i in the Library,
Figure 446670DEST_PATH_IMAGE002
The author of these books of i,
Figure 560119DEST_PATH_IMAGE003
The reclassify of these books of i,
Figure 2012103432633100002DEST_PATH_IMAGE007
Be the level Four classification of these books of i, because may there be a plurality of universal tags in every books, described a plurality of universal tags consisted of the universal tag vector representation,
Figure 485350DEST_PATH_IMAGE005
It is the universal tag vector of these books of i.
Books have the essential informations such as author, reclassify, level Four classification, universal tag.Wherein, reclassify and level Four classification are to be specified according to classifying rules and the book content of books platform by editor, and universal tag is the keyword that can be represented the books content characteristic by editor according to every selected part of book content.Take books " clothes made of brocade is extremely bright " as example, its author is " Latin sea 13 youths ", reclassify is " history ", and level Four is categorized as sky, and universal tag is " play the part of pig and eat tiger ", " change ", " vengeance ", " refreshing literary composition ", " iron blood ", " the little text of an annotated book ", " conspiracy ", " unit is bright ".
Among Fig. 1 step B, each user's text label vector:
, wherein,
Figure 2012103432633100002DEST_PATH_IMAGE009
J position user's text label vector,
Figure 2012103432633100002DEST_PATH_IMAGE010
Be j position user all the author vector that consists of of the author of degree of depth read books (for example:
Figure 522707DEST_PATH_IMAGE010
=＜residence pig, vast stretch of wooded country listens great waves, heptan is new, Latin sea 11 youths 〉),
Figure 2012103432633100002DEST_PATH_IMAGE011
Be corresponding to
Figure 646521DEST_PATH_IMAGE010
In author's weight vectors of consisting of of each author's weighted value;
Figure 920060DEST_PATH_IMAGE011
Be j position user all the reclassify vector that consists of of the reclassify of degree of depth read books (for example:
Figure 2012103432633100002DEST_PATH_IMAGE012
=＜history, celestial chivalrous, fantasy, officialdom, military affairs, sports 〉),
Figure 2012103432633100002DEST_PATH_IMAGE013
Be corresponding to
Figure 245386DEST_PATH_IMAGE012
In the reclassify weight vectors that consists of of the weighted value of each reclassify;
Figure 2012103432633100002DEST_PATH_IMAGE014
Be j position user all the level Four class vector that consists of of the level Four classification of degree of depth read books (for example:
Figure 657913DEST_PATH_IMAGE014
=＜classic is celestial chivalrous, the The Romance of the Three Kingdoms, the illusion of celestial road 〉),
Figure 2012103432633100002DEST_PATH_IMAGE015
Be corresponding to In the level Four classification weight vectors that consists of of the weighted value of each level Four classification;
Figure 2012103432633100002DEST_PATH_IMAGE016
Be j position user all the universal tag vector that consists of of the universal tag of degree of depth read books (for example:
Figure 2012103432633100002DEST_PATH_IMAGE017
=＜old the text of an annotated book, upgrading stream is played the part of pig and is eaten tiger, non-human is made laughs, fat person, the stream of living again 〉),
Figure 2012103432633100002DEST_PATH_IMAGE018
Be corresponding to
Figure 929811DEST_PATH_IMAGE017
In the universal tag weight vectors that consists of of the weighted value of each universal tag.
Among the described step B, parameter in each user's the text label vector can be carried out analytical calculation based on the books degree of depth browing record of user within recently a period of time (such as 6 months), namely at first pick out the books reading record in nearest a period of time of user, and according to the criterion that the books degree of depth is read, from the books reading record of picking out, further filter out user's books degree of depth browing record.Dissimilar according to books, the criterion that can adopt the different books degree of depth to read.For example, the degree of depth read books (wherein, reading the degree of depth=reading chapters and sections number/general rules joint number) that one of meets the following conditions and to be the user:
A. books general rules joint number＜=10, (reading chapters and sections number-free chapters and sections number)〉0, nearly 6 month to dates read the degree of depth=70%;
B. books general rules joint number〉10, (reading chapters and sections number-free chapters and sections number) 0, nearly 6 month to dates read the degree of depth=40%;
C. publish in instalments books general rules joint number〉184, (reading chapters and sections number-free chapters and sections number) 0, nearly 6 month to dates read the chapters and sections number=74.
It is worth mentioning that,
Figure 2012103432633100002DEST_PATH_IMAGE019
In weighted value with
Figure 932533DEST_PATH_IMAGE010
In the author be one to one, for example:
Figure 832356DEST_PATH_IMAGE010
=＜residence pig, vast stretch of wooded country listens great waves, and heptan is new, Latin sea 11 youths ...,
Figure 398467DEST_PATH_IMAGE019
=＜0.11,0.21,0.29,0.18 ..., represent that then weighted value corresponding to author " residence pig " is 0.11, weighted value corresponding to author's " vast stretch of wooded country listens great waves " is 0.21, and weighted value corresponding to author's " heptan is new " is 0.29, and weighted value corresponding to author " Latin sea 11 youths " is 0.18.Equally,
Figure 2012103432633100002DEST_PATH_IMAGE020
In weighted value with
Figure 762452DEST_PATH_IMAGE012
In reclassify, In weighted value with
Figure 123026DEST_PATH_IMAGE014
In level Four classification,
Figure 2012103432633100002DEST_PATH_IMAGE022
In weighted value with
Figure 2012103432633100002DEST_PATH_IMAGE023
In universal tag homogeneous one correspondence.
Further,
Figure 821729DEST_PATH_IMAGE019
,
Figure 191531DEST_PATH_IMAGE020
,
Figure 82127DEST_PATH_IMAGE015
Or
Figure 941498DEST_PATH_IMAGE018
In weighted value can calculate according to the frequency that the corresponding author of this weighted value, reclassify, level Four classification or universal tag occur in j position user degree of depth read books, namely in j position user degree of depth read books, the author that this weighted value is corresponding, reclassify, level Four are classified or the frequency of universal tag appearance and the ratio of the total degree that all authors, reclassify, level Four classification or universal tag occur.
Among Fig. 1 step C, all books are corresponding to every user's label score in the Library: , wherein,
Figure 2012103432633100002DEST_PATH_IMAGE025
Be these books of i for j position user's label score,
Figure 2012103432633100002DEST_PATH_IMAGE026
The weighted value of reclassify correspondence in j position user's text label vector of these books of i,
Figure 2012103432633100002DEST_PATH_IMAGE027
That the level Four of these books of i is sorted in corresponding weighted value in j position user's the text label vector, The author of these books of i corresponding weighted value in j position user's text label vector, because that the universal tag of these books of i may have is a plurality of,
Figure 2012103432633100002DEST_PATH_IMAGE029
The weighted value sum of all universal tags correspondence in j position user's text label vector of these books of i,
Figure 2012103432633100002DEST_PATH_IMAGE030
Be respectively the recommendation weight of reclassify, level Four classification, author, universal tag vector, its value can be rule of thumb definite by the technician, for example:
Figure 2012103432633100002DEST_PATH_IMAGE031
As shown in Figure 2, calculate these books of i among Fig. 1 step C corresponding to j position user's label score, can further include:
Author in the book labels vector of step C1, these books of judgement i
Figure 2012103432633100002DEST_PATH_IMAGE032
Empty? if not, then extract the author
Figure 2012103432633100002DEST_PATH_IMAGE033
, continue next step; If so, then
Figure 734355DEST_PATH_IMAGE028
=0, turn to step C3.
Step C2, judge all author's vectors of degree of depth read books of j position user
Figure 907847DEST_PATH_IMAGE010
In whether have described author
Figure 918529DEST_PATH_IMAGE033
If so, then
Figure 886485DEST_PATH_IMAGE028
It is author's weight vectors
Figure 44934DEST_PATH_IMAGE019
In with described author
Figure 756538DEST_PATH_IMAGE032
Corresponding weighted value continues next step; If not, then
Figure 621725DEST_PATH_IMAGE028
=0, continue next step.
Because
Figure 2012103432633100002DEST_PATH_IMAGE034
In the author with
Figure 2012103432633100002DEST_PATH_IMAGE035
In weighted value corresponding one by one, namely
Figure 573632DEST_PATH_IMAGE034
The ordering of middle weighted value with
Figure DEST_PATH_IMAGE036
Middle author's ordering is identical, therefore can exist by the author
Figure 157060DEST_PATH_IMAGE034
In ordering, find
Figure 406776DEST_PATH_IMAGE036
In the weighted value corresponding with described author.
Reclassify in the book labels vector of step C3, these books of judgement i Empty? if not, then extract reclassify
Figure DEST_PATH_IMAGE037
, continue next step; If so, then
Figure DEST_PATH_IMAGE038
=0, turn to step C5.
Step C4, judge all reclassify vectors of degree of depth read books of j position user
Figure 764125DEST_PATH_IMAGE012
In whether have described reclassify
Figure DEST_PATH_IMAGE039
If so, then It is the reclassify weight vectors
Figure 199840DEST_PATH_IMAGE013
In with described reclassify
Figure DEST_PATH_IMAGE040
Corresponding weighted value continues next step; If not, then =0, continue next step.
Level Four classification in the book labels vector of step C5, these books of judgement i
Figure DEST_PATH_IMAGE041
Empty? if not, then extract the level Four classification , continue next step; If so, then
Figure 834794DEST_PATH_IMAGE027
=0, turn to step C7.
Step C6, judge all level Four class vectors of degree of depth read books of j position user
Figure 940285DEST_PATH_IMAGE014
In whether have the classification of described level Four
Figure DEST_PATH_IMAGE043
If so, then
Figure 797382DEST_PATH_IMAGE027
It is level Four classification weight vectors
Figure 553986DEST_PATH_IMAGE015
In with the classification of described level Four
Figure DEST_PATH_IMAGE044
Corresponding weighted value continues next step; If not, then
Figure 205547DEST_PATH_IMAGE027
=0, continue next step.
Universal tag vector in the book labels vector of step C7, these books of judgement i
Figure 250863DEST_PATH_IMAGE005
Empty? if not, then extract the universal tag vector
Figure 957657DEST_PATH_IMAGE005
, continue next step; If so, then
Figure 506450DEST_PATH_IMAGE029
=0, this flow process finishes.
Step C8, extract the universal tag vector one by one In each universal tag, and judge successively all universal tag vectors of degree of depth read books of j position user
Figure 861525DEST_PATH_IMAGE023
In whether have described universal tag, if exist, then from the universal tag weight vectors
Figure 122742DEST_PATH_IMAGE018
In obtain the weighted value corresponding with described universal tag, last It is the universal tag vector
Figure 784985DEST_PATH_IMAGE005
In all universal tags at the universal tag weight vectors
Figure DEST_PATH_IMAGE045
In corresponding weighted value sum.For example, universal tag vector =
Figure DEST_PATH_IMAGE046
,
Figure DEST_PATH_IMAGE047
...,
Figure DEST_PATH_IMAGE048
, wherein
Figure 89375DEST_PATH_IMAGE046
, ...,
Figure DEST_PATH_IMAGE049
It is the universal tag vector
Figure 104922DEST_PATH_IMAGE005
The universal tag that comprises, m are the universal tag vectors
Figure 80968DEST_PATH_IMAGE005
Universal tag sum, then
Figure DEST_PATH_IMAGE050
,
Figure DEST_PATH_IMAGE051
It is the universal tag weight vectors
Figure DEST_PATH_IMAGE052
In with universal tag
Figure DEST_PATH_IMAGE053
Corresponding weighted value.
Can also adopt multiple allotment strategy among the present invention, to the recommendation weight of reclassify, level Four classification, author, universal tag vector
Figure 992642DEST_PATH_IMAGE030
Value be optimized adjustment, described allotment strategy includes: according to the click effect of user to Recommended Books, distinguish the different time period (such as working day and weekend), or for different users or customer group different values is set.
Clearer for what set forth, the below is further explained in detail the present invention as an example of the label score computation process of books " clothes made of brocade kills the people " example:
1, makes up the book labels vector of books " clothes made of brocade kills the people "
Figure DEST_PATH_IMAGE054
=＜
Figure DEST_PATH_IMAGE055
,
Figure DEST_PATH_IMAGE056
,
Figure DEST_PATH_IMAGE057
, , author wherein
Figure DEST_PATH_IMAGE059
=Latin sea 11 youths, reclassify
Figure 449163DEST_PATH_IMAGE056
=history, the level Four classification
Figure DEST_PATH_IMAGE060
Be sky, the universal tag vector
Figure 846646DEST_PATH_IMAGE058
=＜play the part of, pig ate tiger, and change is revenged, refreshing literary composition, and iron blood, the little text of an annotated book, conspiracy, unit is bright 〉;
2, according to certain user's books reading record, set up this user's text label vector
Figure 575568DEST_PATH_IMAGE054
Wherein,
Table 1 shows this user all author, author's frequency of occurrence and frequencies of degree of depth read books:
Table 1
The author Author's frequency of occurrence Author's frequency of occurrences
The residence pig 2 2/48=0.041667
Vast stretch of wooded country listens great waves 2 2/48=0.041667
Heptan is new 2 2/48=0.041667
Latin sea 11 youths 1 1/48=0.020833
… … …
Draw all author vectors of degree of depth read books of this user from table 1 =＜residence pig, vast stretch of wooded country listens great waves, and heptan is new, Latin sea 11 youths ..., author's weight vectors
Figure DEST_PATH_IMAGE062
=＜0.041667,0.041667,0.041667,0.020833 ....
Table 2 shows this user all reclassify, reclassify frequency of occurrence and frequencies of degree of depth read books:
Table 2
Reclassify The reclassify frequency of occurrence The reclassify frequency of occurrences
Historical 22 22/48=0.458333
Celestial chivalrous 21 21/48=0.4375
Fantasy 2 2/48=0.041667
Officialdom 1 1/48=0.020833
Military 1 0.020833
Sports 1 0.020833
Draw all reclassify vectors of degree of depth read books of this user from table 2
Figure DEST_PATH_IMAGE063
=＜history, celestial chivalrous, fantasy, officialdom, military affairs, sports 〉, the reclassify weight vectors
Figure DEST_PATH_IMAGE064
=＜0.458333,0.4375,0.041667,0.020833,0.020833,0.020833 〉.
Table 3 shows this user all universal tag and frequencies of occurrences thereof of degree of depth read books:
Table 3
Universal tag The universal tag frequency of occurrences
Play the part of pig and eat tiger 0.0152284
Refreshing literary composition 0.071066
The little text of an annotated book 0.0761421
Unit is bright 0.0050761
Draw all universal tag vectors of degree of depth read books of this user from table 3 =＜play the part of, pig ate tiger, and change is revenged, refreshing literary composition, and iron blood, the little text of an annotated book, conspiracy, unit is bright 〉, the universal tag weight vectors
Figure DEST_PATH_IMAGE066
=＜0.0152284,0,0,0.071066,0,0.0761421,0,0.0050761 〉.
3, calculate books " clothes made of brocade kills the people " for this user's label score: 1*0.458333+2*0+3*0.020833+4*(0.0152284+0.071066+0.076142 1+0.0050761)=1.1700494.Wherein
Figure DEST_PATH_IMAGE067
, the weighted value of the reclassify of these books " history " correspondence in user's text label vector
Figure DEST_PATH_IMAGE068
=0.458333, the level Four of these books is categorized as sky, the weighted value of correspondence in user's text label vector
Figure DEST_PATH_IMAGE069
=0, the author of these books " Latin sea 11 youths " weighted value of correspondence in user's text label vector
Figure DEST_PATH_IMAGE070
=0.020833, all universal tags of these books " are played the part of pig and are eaten tiger ", " change ", " vengeance ", " refreshing literary composition ", " iron blood ", " the little text of an annotated book ", " conspiracy ", " unit is bright " corresponding weighted value sum in j position user's text label vector
Figure DEST_PATH_IMAGE071
=0.0152284+0+0+0.071066+0+0.0761421+0+0.0050761.
Identical with the computation process of books " clothes made of brocade kills the people ", continue the label score of other books in the calculating chart stack room, at last user read books is filtered, and the books that filter out some by the label score are recommended to this user.
The above only is preferred embodiment of the present invention, and is in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of making, is equal to replacement, improvement etc., all should be included within the scope of protection of the invention.

Claims (12)

1. a book recommendation method is characterized in that, described method includes:
Steps A, the author according to books, reclassify, level Four classification and universal tag, the book labels of every books vector in the design of graphics stack room;
Step B, according to all author, reclassify, level Four classification, universal tag and corresponding weighted values respectively thereof of degree of depth read books in user's the books reading record, set up each user's text label vector;
Step C, according to author in the book labels vector of books, reclassify, level Four classification, universal tag corresponding weighted value in user's text label vector respectively, all books are corresponding to every user's label score in the calculating chart stack room.
2. method according to claim 1 is characterized in that, also includes:
All books are corresponding to every user's label score in step D, the comparison diagram stack room, and according to user's books reading record filtering user read books, some the books that the label score is the highest are recommended to described user at last.
3. method according to claim 1 is characterized in that, in the described steps A, and the book labels of every books vector:
Figure 2012103432633100001DEST_PATH_IMAGE001
=＜
Figure 2012103432633100001DEST_PATH_IMAGE002
,
Figure 2012103432633100001DEST_PATH_IMAGE003
,
Figure 2012103432633100001DEST_PATH_IMAGE004
,
Figure 2012103432633100001DEST_PATH_IMAGE005
, wherein,
Figure 2012103432633100001DEST_PATH_IMAGE006
The book labels vector of these books of i in the Library, The author of these books of i,
Figure 551765DEST_PATH_IMAGE003
The reclassify of these books of i,
Figure 2012103432633100001DEST_PATH_IMAGE007
The level Four classification of these books of i, It is the universal tag vector of these books of i.
4. method according to claim 1 is characterized in that, among the described step B, and each user's text label vector:
Figure DEST_PATH_IMAGE008
, wherein,
Figure 2012103432633100001DEST_PATH_IMAGE009
J position user's text label vector,
Figure DEST_PATH_IMAGE010
All author vectors of consisting of of the author of degree of depth read books of j position user,
Figure DEST_PATH_IMAGE011
Be corresponding to In author's weight vectors of consisting of of each author's weighted value;
Figure DEST_PATH_IMAGE012
All reclassify vectors of consisting of of the reclassify of degree of depth read books of j position user,
Figure DEST_PATH_IMAGE013
Be corresponding to
Figure 668647DEST_PATH_IMAGE012
In the reclassify weight vectors that consists of of the weighted value of each reclassify;
Figure DEST_PATH_IMAGE014
All level Four class vectors of consisting of of the level Four classification of degree of depth read books of j position user,
Figure DEST_PATH_IMAGE015
Be corresponding to
Figure 943640DEST_PATH_IMAGE014
In the level Four classification weight vectors that consists of of the weighted value of each level Four classification;
Figure DEST_PATH_IMAGE016
All universal tag vectors of consisting of of the universal tag of degree of depth read books of j position user,
Figure DEST_PATH_IMAGE017
Be corresponding to
Figure DEST_PATH_IMAGE018
In the universal tag weight vectors that consists of of the weighted value of each universal tag.
5. method according to claim 4 is characterized in that, among the described step B,
Figure 69727DEST_PATH_IMAGE011
In weighted value with
Figure 268628DEST_PATH_IMAGE010
In the author,
Figure DEST_PATH_IMAGE019
In weighted value with In reclassify, In weighted value with
Figure 622883DEST_PATH_IMAGE014
In level Four classification,
Figure 359895DEST_PATH_IMAGE017
In weighted value with In universal tag homogeneous one correspondence.
6. method according to claim 4 is characterized in that, among the described step B,
Figure 70230DEST_PATH_IMAGE011
,
Figure DEST_PATH_IMAGE021
,
Figure DEST_PATH_IMAGE022
Or
Figure 500075DEST_PATH_IMAGE017
In weighted value calculate according to the frequency that the corresponding author of this weighted value, reclassify, level Four classification or universal tag occur in j position user degree of depth read books.
7. method according to claim 1 is characterized in that, among the described step C, all books are corresponding to every user's label score in the Library:
Figure DEST_PATH_IMAGE023
, wherein, Be these books of i for j position user's label score,
Figure DEST_PATH_IMAGE025
The weighted value of reclassify correspondence in j position user's text label vector of these books of i,
Figure DEST_PATH_IMAGE026
That the level Four of these books of i is sorted in corresponding weighted value in j position user's the text label vector,
Figure DEST_PATH_IMAGE027
The weighted value of author's correspondence in j position user's text label vector of these books of i, The weighted value sum of all universal tags correspondence in j position user's text label vector of these books of i,
Figure DEST_PATH_IMAGE029
Be respectively the recommendation weight of reclassify, level Four classification, author, universal tag vector.
8. method according to claim 7 is characterized in that, among the described step C, calculates these books of i corresponding to j position user's label score, further includes:
Extract the author in the book labels vector of these books of i
Figure DEST_PATH_IMAGE030
Whether all have described author among the author of degree of depth read books to judge j position user
Figure DEST_PATH_IMAGE031
, if so, then
Figure 801087DEST_PATH_IMAGE027
Be in user's the text label vector with described author
Figure 76211DEST_PATH_IMAGE002
Corresponding weighted value; If not, then
Figure 719682DEST_PATH_IMAGE027
=0.
9. method according to claim 7 is characterized in that, among the described step C, calculates these books of i corresponding to j position user's label score, further includes:
Extract the reclassify in the book labels vector of these books of i
Figure 507378DEST_PATH_IMAGE003
Whether all have described reclassify in the reclassify of degree of depth read books to judge j position user
Figure DEST_PATH_IMAGE032
, if so, then
Figure DEST_PATH_IMAGE033
Be in user's the text label vector with described reclassify
Figure 236300DEST_PATH_IMAGE003
Corresponding weighted value; If not, then
Figure 987218DEST_PATH_IMAGE033
=0.
10. method according to claim 7 is characterized in that, among the described step C, calculates these books of i corresponding to j position user's label score, further includes:
Extract the level Four classification in the book labels vector of these books of i
Figure 485196DEST_PATH_IMAGE004
Whether all have described level Four classification in the level Four classification of degree of depth read books to judge j position user
Figure DEST_PATH_IMAGE034
, if so, then
Figure 256842DEST_PATH_IMAGE026
Be in user's the text label vector with described level Four classification
Figure 394432DEST_PATH_IMAGE004
Corresponding weighted value; If not, then
Figure 276937DEST_PATH_IMAGE026
=0.
11. method according to claim 7 is characterized in that, among the described step C, calculates these books of i corresponding to j position user's label score, further includes:
Extract the universal tag vector in the book labels vector of these books of i
Figure 629421DEST_PATH_IMAGE005
Extract one by one the universal tag vector
Figure 571969DEST_PATH_IMAGE005
In each universal tag, and whether all have described universal tag in the universal tag of degree of depth read books to judge successively j position user, if exist, then from user's text label vector, obtain the weighted value corresponding with described universal tag, last
Figure 947587DEST_PATH_IMAGE028
It is the universal tag vector
Figure 368204DEST_PATH_IMAGE005
In all universal tags corresponding weighted value sum in user's text label vector.
12. method according to claim 7 is characterized in that, also includes:
Adopt multiple allotment strategy, to the recommendation weight of reclassify, level Four classification, author, universal tag vector
Figure DEST_PATH_IMAGE035
Value be optimized adjustment, described allotment strategy includes: according to the click effect of user to Recommended Books, distinguish the different time periods, or for different users or customer group different values is set.
CN201210343263.3A 2012-09-17 2012-09-17 Book recommendation method Active CN102902744B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210343263.3A CN102902744B (en) 2012-09-17 2012-09-17 Book recommendation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210343263.3A CN102902744B (en) 2012-09-17 2012-09-17 Book recommendation method

Publications (2)

Publication Number Publication Date
CN102902744A true CN102902744A (en) 2013-01-30
CN102902744B CN102902744B (en) 2015-02-11

Family

ID=47574976

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210343263.3A Active CN102902744B (en) 2012-09-17 2012-09-17 Book recommendation method

Country Status (1)

Country Link
CN (1) CN102902744B (en)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103488714A (en) * 2013-09-11 2014-01-01 杭州东信北邮信息技术有限公司 Book recommendation method and system based on social networking
CN104021153A (en) * 2014-05-19 2014-09-03 江苏金智教育信息技术有限公司 Personalized recommendation method for campus books
CN104111939A (en) * 2013-04-18 2014-10-22 中国移动通信集团浙江有限公司 Book recommending method and device
CN104156366A (en) * 2013-05-13 2014-11-19 中国移动通信集团浙江有限公司 Method and network server for recommending network applications to mobile terminal
CN104536989A (en) * 2014-12-10 2015-04-22 百度在线网络技术（北京）有限公司 Electronic publication recommendation method and device
CN104679835A (en) * 2015-02-09 2015-06-03 浙江大学 Book recommending method based on multi-view hash
CN105045867A (en) * 2015-07-14 2015-11-11 杭州东信北邮信息技术有限公司 Book scoring based book writer recommendation method
CN105956904A (en) * 2016-04-26 2016-09-21 武汉理工数字传播工程有限公司 Digital reading appending package method, digital reading appending package system, and editing terminal
CN106294502A (en) * 2015-06-09 2017-01-04 北京搜狗科技发展有限公司 A kind of e-book information processing method and processing device
CN103886067B (en) * 2014-03-20 2017-01-18 浙江大学 Method for recommending books through label implied topic
CN103714118B (en) * 2013-11-22 2017-02-08 浙江大学 Book cross-reading method
CN106601041A (en) * 2016-12-15 2017-04-26 邵宏锋 Reading information grading analysis processing system
CN106656861A (en) * 2016-12-15 2017-05-10 咪咕数字传媒有限公司 Electronic book pushing method and device
WO2017124263A1 (en) * 2016-01-18 2017-07-27 杨瑛 Information pushing method when book is recommended and book recommendation system
WO2017124264A1 (en) * 2016-01-18 2017-07-27 杨瑛 Information collection method when book is recommended and book recommendation system
WO2017124262A1 (en) * 2016-01-18 2017-07-27 杨瑛 Method for recommending book by swiping and obtaining identity card information and book recommendation system
CN107153850A (en) * 2016-03-04 2017-09-12 上海阿法迪智能标签系统技术有限公司 The acquisition methods and system of books relevant information
CN107437215A (en) * 2017-08-02 2017-12-05 杭州东信北邮信息技术有限公司 A kind of book recommendation method based on label
CN107506398A (en) * 2017-08-02 2017-12-22 杭州东信北邮信息技术有限公司 A kind of method that tag attributes are added for books
CN107562881A (en) * 2017-09-04 2018-01-09 网易无尾熊（杭州）科技有限公司 Interference method, medium, system and the computing device of commending system
CN108319713A (en) * 2018-02-08 2018-07-24 邵睿锋 E-book processing method Internet-based
CN109597934A (en) * 2018-11-23 2019-04-09 北京字节跳动网络技术有限公司 Determine method, apparatus, storage medium and the electronic equipment clicked and recommend word
CN109885766A (en) * 2019-02-11 2019-06-14 武汉理工大学 A kind of books recommended method and system based on book review
CN112650429A (en) * 2020-12-18 2021-04-13 掌阅科技股份有限公司 Book recommendation method for bookshelf pages, computing device and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108427723B (en) * 2018-02-09 2021-08-06 哈尔滨工业大学深圳研究生院 Author recommendation method and system based on clustering algorithm and local perception reconstruction model

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320375A (en) * 2008-07-04 2008-12-10 浙江大学 Digital book search method based on user click action
EP2095219A2 (en) * 2006-11-22 2009-09-02 Boorah, Inc Method and system for analyzing user-generated content
US20090254543A1 (en) * 2008-04-03 2009-10-08 Ofer Ber System and method for matching search requests and relevant data
CN101719145A (en) * 2009-11-17 2010-06-02 北京大学 Individuation searching method based on book domain ontology

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2095219A2 (en) * 2006-11-22 2009-09-02 Boorah, Inc Method and system for analyzing user-generated content
US20090254543A1 (en) * 2008-04-03 2009-10-08 Ofer Ber System and method for matching search requests and relevant data
CN101320375A (en) * 2008-07-04 2008-12-10 浙江大学 Digital book search method based on user click action
CN101719145A (en) * 2009-11-17 2010-06-02 北京大学 Individuation searching method based on book domain ontology

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
田莹颖: "基于社会化标签系统的个性化信息推荐探讨", 《图书馆学理论研究》 *

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104111939B (en) * 2013-04-18 2018-08-17 中国移动通信集团浙江有限公司 A kind of book recommendation method and device
CN104111939A (en) * 2013-04-18 2014-10-22 中国移动通信集团浙江有限公司 Book recommending method and device
CN104156366B (en) * 2013-05-13 2017-11-21 中国移动通信集团浙江有限公司 A kind of method applied to mobile terminal recommendation network and the webserver
CN104156366A (en) * 2013-05-13 2014-11-19 中国移动通信集团浙江有限公司 Method and network server for recommending network applications to mobile terminal
CN103488714B (en) * 2013-09-11 2017-01-18 杭州东信北邮信息技术有限公司 Book recommendation method and system based on social networking
CN103488714A (en) * 2013-09-11 2014-01-01 杭州东信北邮信息技术有限公司 Book recommendation method and system based on social networking
CN103714118B (en) * 2013-11-22 2017-02-08 浙江大学 Book cross-reading method
CN103886067B (en) * 2014-03-20 2017-01-18 浙江大学 Method for recommending books through label implied topic
CN104021153A (en) * 2014-05-19 2014-09-03 江苏金智教育信息技术有限公司 Personalized recommendation method for campus books
CN104021153B (en) * 2014-05-19 2017-06-06 江苏金智教育信息技术有限公司 A kind of personalized recommendation method of campus books
CN104536989A (en) * 2014-12-10 2015-04-22 百度在线网络技术（北京）有限公司 Electronic publication recommendation method and device
CN104679835A (en) * 2015-02-09 2015-06-03 浙江大学 Book recommending method based on multi-view hash
CN104679835B (en) * 2015-02-09 2017-10-31 浙江大学 A kind of book recommendation method based on multi views Hash
CN106294502B (en) * 2015-06-09 2020-06-23 北京搜狗科技发展有限公司 Electronic book information processing method and device
CN106294502A (en) * 2015-06-09 2017-01-04 北京搜狗科技发展有限公司 A kind of e-book information processing method and processing device
CN105045867B (en) * 2015-07-14 2018-02-13 杭州东信北邮信息技术有限公司 A kind of books writer based on books scoring recommends method
CN105045867A (en) * 2015-07-14 2015-11-11 杭州东信北邮信息技术有限公司 Book scoring based book writer recommendation method
WO2017124264A1 (en) * 2016-01-18 2017-07-27 杨瑛 Information collection method when book is recommended and book recommendation system
WO2017124262A1 (en) * 2016-01-18 2017-07-27 杨瑛 Method for recommending book by swiping and obtaining identity card information and book recommendation system
WO2017124263A1 (en) * 2016-01-18 2017-07-27 杨瑛 Information pushing method when book is recommended and book recommendation system
CN107153850A (en) * 2016-03-04 2017-09-12 上海阿法迪智能标签系统技术有限公司 The acquisition methods and system of books relevant information
CN105956904A (en) * 2016-04-26 2016-09-21 武汉理工数字传播工程有限公司 Digital reading appending package method, digital reading appending package system, and editing terminal
CN106601041A (en) * 2016-12-15 2017-04-26 邵宏锋 Reading information grading analysis processing system
CN106656861B (en) * 2016-12-15 2019-03-01 咪咕数字传媒有限公司 A kind of e-book method for pushing and device
CN106656861A (en) * 2016-12-15 2017-05-10 咪咕数字传媒有限公司 Electronic book pushing method and device
CN107506398A (en) * 2017-08-02 2017-12-22 杭州东信北邮信息技术有限公司 A kind of method that tag attributes are added for books
CN107437215A (en) * 2017-08-02 2017-12-05 杭州东信北邮信息技术有限公司 A kind of book recommendation method based on label
CN107506398B (en) * 2017-08-02 2020-01-24 杭州东信北邮信息技术有限公司 Method for adding label attribute to book
CN107437215B (en) * 2017-08-02 2020-07-24 杭州东信北邮信息技术有限公司 Book recommendation method based on labels
CN107562881A (en) * 2017-09-04 2018-01-09 网易无尾熊（杭州）科技有限公司 Interference method, medium, system and the computing device of commending system
CN108319713A (en) * 2018-02-08 2018-07-24 邵睿锋 E-book processing method Internet-based
CN109597934A (en) * 2018-11-23 2019-04-09 北京字节跳动网络技术有限公司 Determine method, apparatus, storage medium and the electronic equipment clicked and recommend word
CN109885766A (en) * 2019-02-11 2019-06-14 武汉理工大学 A kind of books recommended method and system based on book review
CN112650429A (en) * 2020-12-18 2021-04-13 掌阅科技股份有限公司 Book recommendation method for bookshelf pages, computing device and storage medium
CN112650429B (en) * 2020-12-18 2021-09-24 掌阅科技股份有限公司 Book recommendation method for bookshelf pages, computing device and storage medium

Also Published As

Publication number Publication date
CN102902744B (en) 2015-02-11

Similar Documents

Publication Publication Date Title
CN102902744B (en) Book recommendation method
Matysiak et al. Finding their way? female employment patterns in West Germany, East Germany, and Poland
CN105095219B (en) Micro-blog recommendation method and terminal
CN108256119A (en) A kind of construction method of resource recommendation model and the resource recommendation method based on the model
CN107818105A (en) The recommendation method and server of application program
CN102609523A (en) Collaborative filtering recommendation algorithm based on article sorting and user sorting
CN105512326A (en) Picture recommending method and system
CN107045533B (en) Educational resource based on label recommends method and system
CN108460082A (en) A kind of recommendation method and device, electronic equipment
CN102625940A (en) Internet preference learning facility
CN102662975A (en) Bidirectional and clustering mixed friend recommendation method
CN106874355A (en) The collaborative filtering method of social networks and user's similarity is incorporated simultaneously
CN103870972A (en) Data recommendation method and data recommendation system
CN109840702A (en) A kind of new projects' collaborative recommendation method based on multi-core integration
CN106548006A (en) A kind of meals based on user's typical case's taste recommend method
CN109241451A (en) A kind of content combined recommendation method, apparatus and readable storage medium storing program for executing
CN108509499A (en) A kind of searching method and device, electronic equipment
CN108629010A (en) It is a kind of to recommend method based on the web services of theme and service combination information
CN108280124A (en) Product classification method and device, ranking list generation method and device, electronic equipment
CN110275980A (en) One kind having an X-rayed music recommended method based on group
CN112116380A (en) Dynamic satisfaction-based intelligent interactive information terminal visualization method
CN109408726A (en) Question answering person's recommended method in question and answer website
Kang et al. How do cultural classes emerge from assimilation and distinction? An extension of the Cucker-Smale flocking model
CN109325171A (en) User interest analysis method and system based on domain knowledge
Bengtsson Digital distinctions: Mechanisms of difference in digital media use

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CP02 Change in the address of a patent holder
CP02 Change in the address of a patent holder

Address after: 310013, Zhejiang, Xihu District, Wensanlu Road, No. 398, 4 floor, Hangzhou

Patentee after: EB Information Technology Ltd.

Address before: 100191 Beijing, Zhichun Road, No. 9, hearing the building on the floor of the 7 floor,

Patentee before: EB Information Technology Ltd.

CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: 310013 4th floor, No.398 Wensan Road, Xihu District, Hangzhou City, Zhejiang Province

Patentee after: Xinxun Digital Technology (Hangzhou) Co.,Ltd.

Address before: 310013 4th floor, No.398 Wensan Road, Xihu District, Hangzhou City, Zhejiang Province

Patentee before: EB Information Technology Ltd.