CN107967345A - A kind of social networks famous person information recommending apparatus - Google Patents
A kind of social networks famous person information recommending apparatus Download PDFInfo
- Publication number
- CN107967345A CN107967345A CN201711319468.7A CN201711319468A CN107967345A CN 107967345 A CN107967345 A CN 107967345A CN 201711319468 A CN201711319468 A CN 201711319468A CN 107967345 A CN107967345 A CN 107967345A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- cyberelite
- preference
- social networks
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of social networks famous person information recommending apparatus, including：Collecting preference information module, for collecting preference information of evaluation of the user to the information on social networks as user；Analysis module, for analyzing the preference similarity between user and cyberelite according to the preference information of user and cyberelite；Recommending module, for by the information recommendation of the satisfactory cyberelite of preference similarity to user.The behavioural analysis that apparatus of the present invention can effectively be made according to user on social networks goes out its preference information, and cyberelite similar in matching preference recommends user, and objectivity is strong, and accuracy is high.
Description
Technical field
The present invention relates to network data processing technique, particularly a kind of social networks famous person information recommending apparatus.
Background technology
With the further popularization of internet, current social networking system is quickly grown, and the one of social networking system is big
Characteristic, which is that, has concentrated substantial amounts of cyberelite, and ordinary user can very easily carry out interactive with cyberelite.With net
The expansion of network famous person troop is, it is necessary to which user cyberelite interested is pushed to user by a kind of more effective way.
It is existing to be to the method for user's recommendation famous person's information in social networking system：By way of human-edited to
User recommendation network famous person.But existing this method not only needs to expend a large amount of human costs, inefficiency；It is and main
Sight factor is too strong, can not realize and objectively targetedly be recommended for specified user, visitor of the recommendation results apart from user
It is too remote to see preference.
The content of the invention
A kind of in view of the above-mentioned problems, the present invention is intended to provide social networks famous person information recommending apparatus.
The purpose of the present invention is realized using following technical scheme：
A kind of social networks famous person information recommending apparatus, including：Collecting preference information module, for collecting user to social activity
Preference information of the evaluation of information on network as user；Analysis module, for being believed according to the preference of user and cyberelite
Preference similarity between breath analysis user and cyberelite；Recommending module, for by the satisfactory network of preference similarity
The information recommendation of famous person is to user.
Preferably, memory module is further included, for storing the user information, famous person's information, user preference information, famous person
Preference information and social network information.
Preferably, the information on the social networks is word, picture or multimedia messages；The user is to social networks
On information be evaluated as label evaluation.
Beneficial effects of the present invention are：Device provided by the invention is believed by obtaining the preference of user and cyberelite respectively
Breath, analyzes its preference similarity, the satisfactory cyberelite of similarity is recommended user, this to be matched according to preference information
The way of recommendation, the behavioural analysis that can be effectively made according to user on social networks goes out its preference information, matches preference
Similar cyberelite recommends user, and objectivity is strong, and accuracy is high；In addition, it is used as point by collecting the label of user and evaluating
The foundation of user preference information is analysed, the preference information of user can be obtained exactly, adaptable and accuracy is high.
Brief description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not form any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the frame construction drawing of the present invention.
Reference numeral：
Collecting preference information module 1, analysis module 2, recommending module 3 and memory module 4
Embodiment
With reference to following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of social networks famous person information recommending apparatus, including：
Collecting preference information module 1, for collecting preference of evaluation of the user to the information on social networks as user
Information；
Analysis module 2, it is inclined between user and cyberelite for being analyzed according to the preference information of user and cyberelite
Good similarity；
Recommending module 3, for by the information recommendation of the satisfactory cyberelite of preference similarity to user.
Preferably, memory module 4 is further included, for storing the user information, famous person's information, user preference information, name
People's preference information and social network information.
Preferably, the information on the social networks is word, picture or multimedia messages；The user is to social networks
On information be evaluated as label evaluation.
The above embodiment of the present invention, by obtaining the preference information of user and cyberelite respectively, it is similar to analyze its preference
Degree, user is recommended by the satisfactory cyberelite of similarity, this according to the matched way of recommendation of preference information, Neng Gouyou
The behavioural analysis that effect ground is made according to user on social networks goes out its preference information, matches cyberelite similar in preference and recommends
To user, objectivity is strong, and accuracy is high；In addition, by collect user label evaluate be used as analyze user preference information according to
According to the preference information of user can be obtained exactly, and adaptable and accuracy is high.
Preferably, the analysis module 2 analyzes the preference similarity between user and cyberelite, specifically includes：Obtain
Cyberelite's set on social networksWhereinFor the sum of cyberelite；According to user
Preference similarity between the preference information analysis user of cyberelite and each cyberelite, wherein the preference used is similar
Spending function is：
In formula, S (n, m) represents the preference similarity of user n and cyberelite m, and bigger represent of the value of m ∈ M, wherein S (n, m) is used
Preference between family is more similar, and H (n) and H (m) represents the label assessment item set of user n and cyberelite m, G respectivelynxTable
Show user n to the information H on social networksxLabel evaluation, P (Gnx,Gmx) represent user n to the information H on social networksx's
Label is evaluated and cyberelite m is to the information H on social networksxLabel evaluation similarity,Represent user n to social network
The most label evaluation of information access times on network.
This preferred embodiment, is obtained between user and heterogeneous networks famous person respectively using above-mentioned preference similarity function
Preference similarity, can be effectively according to user and cyberelite is obtained to the difference of the evaluation of same information on social networks
Reflect the preference similarity of user and cyberelite, objectivity is strong, and accuracy is high, be device rear line recommend most close to
The cyberelite of user preferences lays a good foundation.
Preferably, described device further includes label system module, for obtaining user with cyberelite to same social network
The similarity that network information is evaluated into row label, specifically includes：(1) judge that user and the label of cyberelite's mark evaluate whether to belong to
In same dimensional characteristics；(2) evaluated for the label of same dimensional characteristics, the label that uses evaluation similarity function for：
In formula, ZnAnd ZmRespectively user and cyberelite are to social network information HxThe label evaluation of use, P (Zn,Zm) represent
Label ZnWith label ZmSimilarity, HxRepresent x-th of social network information in social network information set H, K (Hx,Zn) table
Show social network information HxWith label ZnDegree of correlation, wherein K (Hx,Zn)=R (Hx,Zn)×T(Hx,Zn), R (Hx,Zn) represent
Social network information HxMiddle label evaluates ZnNumber account for the proportion of all labels evaluation,L(Hx,Zn)
Represent social network information HxMiddle label evaluates ZnNumber, Z represents social network information HxReceive the set of all label evaluations, T
(Hx,Zn) represent label ZnThe frequency occurred in the mark of all social network informations,
H represents the set of information in social networks, but the set of all information in social networks can not possibly be obtained in practical operation, therefore
Using the time as cut-point, the set of information in the social networks of nearest a period of time is chosen as H, K (Hx,Zm) represent society
Hand over network information HxWith label ZmDegree of correlation.
Wherein, the judgement label evaluates whether to belong to same dimensional characteristics, collects all labels by device and evaluates, builds
Day-mark label system, the label system has at least one dimensional characteristics, and the label being collected into evaluation is divided to difference
Dimensional characteristics under.
This preferred embodiment, the label marked using above-mentioned label evaluation similarity function acquisition user with cyberelite are commented
The similarity of valency, can evaluate the standard of user and cyberelite's preference similarity, adaptability is high, and objectivity is strong as after.
Preferably, in the recommending module 3, recommend for the cyberelite of new user, due to new user, there may be also
Any information is not left on social networks, therefore is specifically included for cyberelite's way of recommendation of new user：(1) build
Vertical social networks model, the node in social networks is expressed as by each user and cyberelite in system；(2) each net is obtained
Network famous person's node by reliability, wherein use by reliability iteration function for： In formula, U (m) represent cyberelite's node m by reliability, Bout(m) network is represented
The corresponding out-degree set of famous person's node m, CmnRepresent cyberelite's node m to the trust weight of node n, Bin(n) node n is represented
Corresponding in-degree set, WcnAuxiliary parameter is represented, for quantifying the prejudice value of node c to every of the node n shadow for going out side right value
Effect is rung, wherein,Ccn(1-Wcn) represent the node c after quantifying to node n's
Trust weight, k represent the number of iteration；(3) repeat step (2), until iteration tends towards stability or reaches maximum iteration,
Obtain in cyberelite's node by the highest E cyberelite information of reliability, recommend new user.
This preferred embodiment, do not left for new user on social networks also any information cause cannot according to its to
The most like cyberelite of the information matches preference that goes out, the cyberelite's information present embodiments provided specifically for new user push away
Method is recommended, recommendation apparatus effectively can be covered into all new users, improve the recommendation quality of cyberelite's recommendation apparatus
And adaptability.
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, those of ordinary skill in the art should
Work as analysis, can be to technical scheme technical scheme is modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (4)
- A kind of 1. social networks famous person information recommending apparatus, it is characterised in that including：Collecting preference information module, for collecting Preference information of evaluation of the user to the information on social networks as user；Analysis module, for according to user and network name Preference similarity between the preference information analysis user of people and cyberelite；Recommending module, for preference similarity to be met It is required that cyberelite information recommendation to user.
- 2. a kind of social networks famous person information recommending apparatus according to claim 1, it is characterised in that further include storage mould Block, for storing the user information, famous person's information, user preference information, famous person's preference information and social network information.
- A kind of 3. social networks famous person information recommending apparatus according to claim 1, it is characterised in that the social networks On information be word, picture or multimedia messages；The user is evaluated as label evaluation to the information on social networks.
- A kind of 4. social networks famous person information recommending apparatus according to claim 3, it is characterised in that the analysis module The preference similarity between user and cyberelite is analyzed, is specifically included：Obtain cyberelite's set M=on social networks {M1,M2,M3,…,Mθ, whereinθFor the sum of cyberelite；According to the preference information of user and cyberelite analysis user and often Preference similarity between a cyberelite, wherein the preference similarity function used for：In formula, S (n, m) represents the preference similarity of user n and cyberelite m, and bigger represent of the value of m ∈ M, wherein S (n, m) is used Preference between family is more similar, and H (n) and H (m) represents the label assessment item set of user n and cyberelite m, G respectivelynxTable Show user n to the information H on social networksxLabel evaluation, P (Gnx,Gmx) represent user n to the information H on social networksx's Label is evaluated and cyberelite m is to the information H on social networksxLabel evaluation similarity,Represent user n to social network The most label evaluation of information access times on network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711319468.7A CN107967345A (en) | 2017-12-12 | 2017-12-12 | A kind of social networks famous person information recommending apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711319468.7A CN107967345A (en) | 2017-12-12 | 2017-12-12 | A kind of social networks famous person information recommending apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107967345A true CN107967345A (en) | 2018-04-27 |
Family
ID=61994302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711319468.7A Pending CN107967345A (en) | 2017-12-12 | 2017-12-12 | A kind of social networks famous person information recommending apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967345A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209944A (en) * | 2019-06-10 | 2019-09-06 | 上海时廊人工智能科技有限公司 | A kind of stock analysis teacher recommended method, device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999507A (en) * | 2011-09-13 | 2013-03-27 | 腾讯科技（北京）有限公司 | Recommendation processing method and device for information of network microblog celebrities |
| CN104008163A (en) * | 2014-05-29 | 2014-08-27 | 上海师范大学 | Trust based social network maximum influence node calculation method |
| CN106126586A (en) * | 2016-06-21 | 2016-11-16 | 安徽师范大学 | A kind of social networks recommended models construction method trusted based on overall merit |
| US20170324715A1 (en) * | 2016-05-04 | 2017-11-09 | Freescale Semiconductor, Inc. | Light-weight key update mechanism with blacklisting based on secret sharing algorithm in wireless sensor networks |
-
2017
- 2017-12-12 CN CN201711319468.7A patent/CN107967345A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999507A (en) * | 2011-09-13 | 2013-03-27 | 腾讯科技（北京）有限公司 | Recommendation processing method and device for information of network microblog celebrities |
| CN104008163A (en) * | 2014-05-29 | 2014-08-27 | 上海师范大学 | Trust based social network maximum influence node calculation method |
| US20170324715A1 (en) * | 2016-05-04 | 2017-11-09 | Freescale Semiconductor, Inc. | Light-weight key update mechanism with blacklisting based on secret sharing algorithm in wireless sensor networks |
| CN106126586A (en) * | 2016-06-21 | 2016-11-16 | 安徽师范大学 | A kind of social networks recommended models construction method trusted based on overall merit |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209944A (en) * | 2019-06-10 | 2019-09-06 | 上海时廊人工智能科技有限公司 | A kind of stock analysis teacher recommended method, device, computer equipment and storage medium |
| CN110209944B (en) * | 2019-06-10 | 2023-07-28 | 上海时廊人工智能科技有限公司 | Stock analyst recommendation method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dolnicar | Market segmentation for e-tourism | |
| Coleman et al. | Limited effects of tree planting on forest canopy cover and rural livelihoods in Northern India | |
| Hegland et al. | How to monitor ecological communities cost-efficiently: The example of plant–pollinator networks | |
| JP5248915B2 (en) | GPS tracking and learning of user behavior preferences from well-known nearby destinations | |
| US8566327B2 (en) | Matching process system and method | |
| Mustajoki et al. | Use of decision analysis interviews to support the sustainable use of the forests in Finnish Upper Lapland | |
| US6904461B1 (en) | Method for making time-sensitive determinations of traffic intensity for a visitable site | |
| Bendler et al. | Taming uncertainty in big data: Evidence from social media in urban areas | |
| CN110059223A (en) | Circulation, image to video computer vision guide in machine | |
| CN105183925A (en) | Content association recommending method and content association recommending device | |
| CN109768888A (en) | A kind of network service quality evaluation method, device, equipment and readable storage medium storing program for executing | |
| CN106021455A (en) | Image characteristic relationship matching method, apparatus and system | |
| CN103905486A (en) | Mental health state evaluation method | |
| CN109635149A (en) | People search method, apparatus and electronic equipment | |
| CN105302880A (en) | Content correlation recommendation method and apparatus | |
| Lara‐Romero et al. | Direct and indirect effects of shrub encroachment on alpine grasslands mediated by plant–flower visitor interactions | |
| CN107818156A (en) | A kind of real time individual news recommends method and system | |
| CN107967345A (en) | A kind of social networks famous person information recommending apparatus | |
| CN111459657A (en) | Task allocation method based on edge-assisted data quality perception | |
| CN113469752A (en) | Content recommendation method and device, storage medium and electronic equipment | |
| KR20090014414A (en) | Method, apparatus for evaluation of internet contents and recoding media that saves program implementing the same | |
| CN117236465A (en) | Information entropy-based federal decision tree information measurement method | |
| Driskell et al. | Mapping digital divide in neighborhoods: Wi-Fi access in Baton Rouge, Louisiana | |
| CN115098792B (en) | Exhibit recommendation method and device, computer-readable storage medium and electronic device | |
| Rosenthal et al. | Hiking values and the recreation opportunity spectrum |
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 |
Application publication date: 20180427 |
|
| RJ01 | Rejection of invention patent application after publication |