CN107492025A - A kind of method and system of book recommendation - Google Patents
A kind of method and system of book recommendation Download PDFInfo
- Publication number
- CN107492025A CN107492025A CN201710824290.5A CN201710824290A CN107492025A CN 107492025 A CN107492025 A CN 107492025A CN 201710824290 A CN201710824290 A CN 201710824290A CN 107492025 A CN107492025 A CN 107492025A
- Authority
- CN
- China
- Prior art keywords
- books
- feature
- read
- user interest
- interest profile
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method of book recommendation, including：Obtain and multiple read books feature；User interest profile is obtained according to books feature has been read；Obtain multiple target books features；The target books feature and the user interest profile are contrasted, determines Similarity value, Recommended Books information is exported according to Similarity value.The invention also discloses a kind of system of book recommendation, including:First data acquisition module, for obtaining books feature；Second data acquisition module, for obtaining user interest profile；Data analysis module, user interest profile and the Similarity value of books feature are calculated for analyzing；Information recommendation module, for the Similarity value output result according to user interest profile and books feature to user terminal.A kind of method and system of book recommendation provided by the invention, improve the accuracy rate of Recommended Books information.
Description
Technical field
The present invention relates to data analysis technique field, specifically, is related to a kind of Individual book based on interest matching
Recommend method and system.
Background technology
With the rapid development of Internet technology, network information resource is more and more, and people pass through traditional search engine
It is difficult to obtain oneself resource interested.
At present, the method for book recommendation mainly has two kinds, is briefly described below：
First method is to user, this method by frequency of reading in network-wide basis or books sales volume book recommendation in the top
Be disadvantageous in that, the interest of main flow colony can only be looked after, can not become more meticulous and personalized recommendation, and recommend accuracy rate compared with
It is low；
Second method is the essential information according to system user（Age, sex and the occupation of such as user）Determine between user
Similarity degree, the article that similar users select then is recommended into active user, is the shortcomings that this method, is related to
Than more sensitive personal information, such as age of user etc., it is larger that these user profile accurately obtain difficulty, influences consequently recommended
Effect.
The content of the invention
It is an object of the invention to provide a kind of method and system of book recommendation, lifts the accurate of Recommended Books information
Rate.
Technical scheme is used by the method and system of book recommendation disclosed by the invention：A kind of side of book recommendation
Method, including at least following steps：Obtain and multiple read books feature；User interest profile is obtained according to books feature has been read；Obtain
Take multiple target books features；The target books feature and the user interest profile are contrasted, Similarity value is determined, according to phase
Recommended Books information is exported like angle value.
Preferably, the basis has been read books feature acquisition user interest profile and included：Each institute is counted respectively
The number for having read the appearance of books feature is stated, to having read the same number progress read books feature and occurred in books in difference
Cumulative to obtain accumulated value, same books feature number accumulated value of having read is with having read books feature composition user interest profile.
Preferably, the data acquisition read books and be characterized in setting forward as initial value using current time
Section, more than the data acquisition segments data not in acquisition range.
Preferably, the contrast target books feature and the user interest profile Similarity value include：
Count the common characteristic between the target books feature and the user interest profile；To each it be shared in user interest profile
The occurrence number of feature is added up, and obtains the Similarity value of the target books feature and the user interest profile.
Preferably, it is described to be included according to Similarity value output Recommended Books information:It is not low to filter out Similarity value
In the book information of the first pre-set threshold value, be ranked up by the book information Similarity value filtered out, by Similarity value by height to
It is low to recommend to user.
Preferably, the target books feature includes novel, prose, humanity, history, music, caricature, economy；
The books feature of having read includes novel, prose, humanity, history, music, caricature, economy.
A kind of system of book recommendation, including, the first data acquisition module, books feature is read for obtaining；First number
According to analysis module, books signature analysis is read for basis and has calculated user interest profile；Second data acquisition module, for obtaining
Target books feature；Second data analysis module, for contrasting the target books feature and the user interest profile, it is determined that
Similarity value；Information recommendation module, for exporting book information to user terminal according to Similarity value.
Preferably, first data analysis module includes：First statistic submodule, it is described for counting respectively
Books feature, the first data analysis submodule have been read, the same characteristic features occurrence number for having read books to difference adds up,
Number accumulation result is with books feature collectively as user interest profile.
Preferably, second data analysis module includes：Second statistic submodule, count the target books
Same characteristic features between feature and the user interest profile；Second data analysis submodule, to identical in user interest profile
The number accumulation result of feature adds up again, obtains the Similarity value of the target books feature and the user interest profile.
A kind of computer-readable recording medium, including program, when run on a computer so that on computer performs
The method for stating book recommendation.
The beneficial effect of the method and system of book recommendation disclosed by the invention is：Interest characteristics of the invention according to user
Similarity value contrast is carried out with books feature, can be according to the interest characteristics of user, the books of interest characteristics, have corresponding to recommendation
The accuracy rate and user's acceptance of effect lifting Recommended Books.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of book recommendation method of the present invention；
Fig. 2 is the illustrative view of functional configuration of book recommendation system of the present invention；
Fig. 3 is the specific implementation structural representation of book recommendation system of the present invention.
Embodiment
The present invention is further elaborated and illustrated with reference to specific embodiment and Figure of description：It refer to Fig. 1, one
The method of kind book recommendation, the method includes the steps of：Step 1, acquisition is multiple to have read books feature.It is described to have read books
Feature includes novel, prose, humanity, history, music, caricature, economic dispatch feature；
Step 2, user interest profile is obtained according to books feature has been read.Including：Every each spy for having read books is counted respectively
The number occurred is levied, is added up to having read the number that the same feature in books occurs in difference, same feature number tires out
It is value added with read books feature collectively as user interest profile.Such as：Books are read as two, wherein a books are characterized as
History, caricature, another books are characterized as history, novel, then its user interest profile is accumulated as history * 2, novel * 1, caricature *
1。
User's read books record, is the data acquisition segments set forward as initial value using current time, exceeded
The data of the period do not gather, and because the reading interest of client is not fixed, elapses and change over time, this hair
The bright client's read books record for choosing recent certain time, can recommend corresponding according to the change of the reading interest of client
Books are a dynamic recommendation process to user.
Step 3, obtain multiple target books features.The target books feature is identical including small with having read books feature
Say, prose, humanity, history, music, caricature, economic dispatch feature.
Step 4, the target books feature and the user interest profile are contrasted, Similarity value is determined, according to similarity
Value output Recommended Books information.Including：Count the common characteristic between the target books feature and the user interest profile；
The occurrence number of each common characteristic in user interest profile is added up, obtains the target books feature and the user
The Similarity value of interest characteristics, the book information that Similarity value is not less than the first pre-set threshold value is filtered out, by the books filtered out
Information Similarity value is ranked up, and is recommended from high to low to user by Similarity value.Such as：User interest profile be history * 3,
Novel * 2, caricature * 1, the target books of the target books are characterized as history, novel, paint this, then the target books feature and user
The Similarity value of interest characteristics is 3+2=5.
Fig. 2 is refer to, specific implementation process of the present invention is as follows：Books feature 1 has been read according to user, has read books feature 2
To books feature n has been read, user interest profile is determined.Identified by computer and determine target books feature with reference to human-edited.System
After system receives books recommendation request, the user interest profile and each target books feature in system are contrasted, and confirms
The two Similarity value, its Similarity value are more than or equal to the book information of the first pre-set threshold value according to Similarity value from big to small
Order recommend the user.
The present invention determines user interest profile by the conventional browing record of user, by the interest characteristics of user and target figure
Book feature is contrasted, and is confirmed the two Similarity value according to comparing result, is effectively lifted the accuracy rate of Recommended Books and user connects
Spent, simultaneously as the present invention only chooses the browing record of the nearest certain period of time of user, dynamically can be read according to client
The change of interest and adjust the book information of recommendation, further improve recommend accuracy rate.
Fig. 3 is refer to, present invention also offers a kind of system of book recommendation, including：First data acquisition module 110,
Books feature is read for obtaining, the books feature of having read is formed by calculator combination human-edited.
First data analysis module 120, books signature analysis is read for basis and has calculated user interest profile.
Second data acquisition module 130, for obtaining target books feature, the target books feature is by set of computers
Human-edited forms.
Second data analysis module 140, for contrasting the target books feature and the user interest profile, determine phase
Like angle value.
Information recommendation module 150, for exporting book information to user terminal according to Similarity value.
Wherein, first data analysis module 120 includes：First obtains data submodule, described for counting respectively
Books feature, the first data analysis submodule are read, the same characteristic features occurrence number for having read books to difference adds up
Accumulated value is obtained, the accumulated value is with books feature collectively as user interest profile.
Second data analysis module 140 includes：Second statistic submodule, count the target books feature and described
Same characteristic features between user interest profile, the second data analysis submodule, to the number of same characteristic features in user interest profile
Accumulation result adds up again, obtains the target books feature and the similarity of the user interest profile.
Present invention also offers a kind of computer-readable recording medium, including program, when run on a computer, makes
Obtain computer and perform following methods：Obtain and multiple read books feature.
The statistics number for having read the appearance of books feature respectively, same figure is read to read in books in difference
The number that book feature occurs is added up, it is same read books feature number accumulated value with read books feature composition user it is emerging
Interesting feature.
Obtain multiple target books features.
The common characteristic between the target books feature and the user interest profile is counted, by user interest profile
The occurrence number of each common characteristic is added up, and obtains the target books feature and the similarity of the user interest profile
Value, the book information that Similarity value is not less than the first pre-set threshold value is filtered out, is carried out by the book information Similarity value filtered out
Sequence, recommend from high to low to user by Similarity value.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (10)
- A kind of 1. method of book recommendation, it is characterised in that including：Obtain and multiple read books feature；It is special according to books have been read Sign obtains user interest profile；Obtain multiple target books features；Contrast the target books feature and the user interest is special Sign, determines Similarity value, and Recommended Books information is exported according to Similarity value.
- 2. the method for book recommendation as claimed in claim 1, it is characterised in that the basis has read books feature and obtained user Interest characteristics includes：The each number for having read the appearance of books feature of statistics respectively, it is same in books to having been read in difference Read the number that books feature occurs to be added up to obtain accumulated value, the accumulated value is with having read books feature composition user interest Feature.
- 3. the method for book recommendation as claimed in claim 1 or 2, it is characterised in that the books of having read are characterized in current Time is the data acquisition segments that set forward of initial value, more than the data acquisition segments data not in acquisition range.
- 4. the method for book recommendation as claimed in claim 1, it is characterised in that described to contrast the target books feature and institute User interest profile is stated, determines that Similarity value includes：Count between the target books feature and the user interest profile Common characteristic；The corresponding number of each common characteristic in user interest profile is added up, obtains the target books feature With the Similarity value of the user interest profile.
- 5. the method for book recommendation as claimed in claim 1, it is characterised in that described that Recommended Books are exported according to Similarity value Information includes：The book information that Similarity value is not less than the first pre-set threshold value is filtered out, by the book information similarity filtered out Value is ranked up, and is recommended from high to low to user by Similarity value.
- 6. the method for the book recommendation as described in any one of claim 1,2,4,5, it is characterised in that the target books are special Sign includes novel, prose, humanity, history, music, caricature, economy；It is described read books feature include novel, prose, humanity, History, music, caricature, economy.
- 7. a kind of system of book recommendation, it is characterised in that including the first data acquisition module, books spy having been read for obtaining Sign；First data analysis module, books signature analysis is read for basis and has calculated user interest profile；Second data acquisition mould Block, for obtaining target books feature；Second data analysis module, it is emerging for contrasting the target books feature and the user Interesting feature, determines Similarity value；Information recommendation module, for exporting book information to user terminal according to Similarity value.
- 8. the system of book recommendation as claimed in claim 7, it is characterised in that first data analysis module includes：The One statistic submodule, books feature, the first data analysis submodule, for having read figure to difference are read for counting described respectively The same characteristic features occurrence number of book is added up, and number accumulation result is with books feature collectively as user interest profile.
- 9. the system of book recommendation as claimed in claim 7, it is characterised in that second data analysis module includes：The Two statistic submodules, count the same characteristic features between the target books feature and the user interest profile；Second data point Submodule is analysed, the number accumulation result of same characteristic features in user interest profile is added up again, obtains the target books feature With the Similarity value of the user interest profile.
- 10. a kind of computer-readable recording medium, including program, when run on a computer so that computer performs such as Method described in any one of claim 1,2,4,5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710824290.5A CN107492025A (en) | 2017-09-13 | 2017-09-13 | A kind of method and system of book recommendation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710824290.5A CN107492025A (en) | 2017-09-13 | 2017-09-13 | A kind of method and system of book recommendation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107492025A true CN107492025A (en) | 2017-12-19 |
Family
ID=60652526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710824290.5A Pending CN107492025A (en) | 2017-09-13 | 2017-09-13 | A kind of method and system of book recommendation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107492025A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846005A (en) * | 2018-04-23 | 2018-11-20 | 北京奇艺世纪科技有限公司 | Caricature resource recommendation method and device |
| CN109635193A (en) * | 2018-12-07 | 2019-04-16 | 孙悦桐 | A kind of books reading shared platform |
| CN110704602A (en) * | 2019-10-12 | 2020-01-17 | 苏州思必驰信息科技有限公司 | Man-machine conversation system optimization method and man-machine conversation system |
| CN110990670A (en) * | 2019-10-30 | 2020-04-10 | 华东师范大学 | Growth incentive book recommendation method and system |
| CN114218490A (en) * | 2021-12-17 | 2022-03-22 | 海信集团控股股份有限公司 | Book recommendation method and electronic equipment |
| CN116628456A (en) * | 2023-07-26 | 2023-08-22 | 北京点聚信息技术有限公司 | Layout light reading recommendation method and system based on data analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793419A (en) * | 2012-10-31 | 2014-05-14 | 深圳市世纪光速信息技术有限公司 | Information push method and device |
| CN103886067A (en) * | 2014-03-20 | 2014-06-25 | 浙江大学 | Method for recommending books through label implied topic |
| 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 |
| CN106407204A (en) * | 2015-07-29 | 2017-02-15 | 小米科技有限责任公司 | Book recommendation method and apparatus |
-
2017
- 2017-09-13 CN CN201710824290.5A patent/CN107492025A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793419A (en) * | 2012-10-31 | 2014-05-14 | 深圳市世纪光速信息技术有限公司 | Information push 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 |
| CN103886067A (en) * | 2014-03-20 | 2014-06-25 | 浙江大学 | Method for recommending books through label implied topic |
| CN106407204A (en) * | 2015-07-29 | 2017-02-15 | 小米科技有限责任公司 | Book recommendation method and apparatus |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846005A (en) * | 2018-04-23 | 2018-11-20 | 北京奇艺世纪科技有限公司 | Caricature resource recommendation method and device |
| CN109635193A (en) * | 2018-12-07 | 2019-04-16 | 孙悦桐 | A kind of books reading shared platform |
| CN110704602A (en) * | 2019-10-12 | 2020-01-17 | 苏州思必驰信息科技有限公司 | Man-machine conversation system optimization method and man-machine conversation system |
| CN110990670A (en) * | 2019-10-30 | 2020-04-10 | 华东师范大学 | Growth incentive book recommendation method and system |
| CN110990670B (en) * | 2019-10-30 | 2023-11-10 | 华东师范大学 | Growth incentive book recommendation method and recommendation system |
| CN114218490A (en) * | 2021-12-17 | 2022-03-22 | 海信集团控股股份有限公司 | Book recommendation method and electronic equipment |
| CN116628456A (en) * | 2023-07-26 | 2023-08-22 | 北京点聚信息技术有限公司 | Layout light reading recommendation method and system based on data analysis |
| CN116628456B (en) * | 2023-07-26 | 2023-10-20 | 北京点聚信息技术有限公司 | Layout light reading recommendation method and system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107492025A (en) | A kind of method and system of book recommendation | |
| CN102841946B (en) | Commodity data retrieval ordering and Method of Commodity Recommendation and system | |
| CN103761237A (en) | Collaborative filtering recommending method based on characteristics and credibility of users | |
| TW201734840A (en) | Automatic multi-threshold characteristic filtering method and apparatus | |
| US9128988B2 (en) | Search result ranking by department | |
| CN107301247B (en) | Method and device for establishing click rate estimation model, terminal and storage medium | |
| CN108897789B (en) | Cross-platform social network user identity identification method | |
| CN109460519B (en) | Browsing object recommendation method and device, storage medium and server | |
| TW201501059A (en) | Method and system for recommending information | |
| CN107194430A (en) | A kind of screening sample method and device, electronic equipment | |
| CN106021329A (en) | A user similarity-based sparse data collaborative filtering recommendation method | |
| CN103136683A (en) | Method and device for calculating product reference price and method and system for searching products | |
| CN110222790B (en) | User identity identification method and device and server | |
| CN109635200B (en) | Collaborative filtering recommendation method based on intermediary truth degree measurement and user | |
| CN106021298A (en) | Asymmetrical weighing similarity based collaborative filtering recommendation method and system | |
| CN110197404A (en) | The personalized long-tail Method of Commodity Recommendation and system of popularity deviation can be reduced | |
| CN106874943A (en) | Business object sorting technique and system | |
| CN106776859A (en) | Mobile solution App commending systems based on user preference | |
| CN114168761B (en) | Multimedia data pushing method and device, electronic equipment and storage medium | |
| CN109815987A (en) | A kind of listener clustering method and categorizing system | |
| CN116596570A (en) | Information comparison system of same product in different E-commerce platforms based on big data analysis algorithm | |
| CN110324352B (en) | Method and device for identifying batch registered account groups | |
| Li et al. | A Personalization Recommendation Algorithm for E-Commerce. | |
| Cho et al. | Mining association rules using RFM scoring method for personalized u-commerce recommendation system in emerging data | |
| Chakraborty et al. | Clustering of web sessions by FOGSAA |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171219 |