CN107193984A - A kind of high-quality user's commending system - Google Patents
A kind of high-quality user's commending system Download PDFInfo
- Publication number
- CN107193984A CN107193984A CN201710388945.9A CN201710388945A CN107193984A CN 107193984 A CN107193984 A CN 107193984A CN 201710388945 A CN201710388945 A CN 201710388945A CN 107193984 A CN107193984 A CN 107193984A
- Authority
- CN
- China
- Prior art keywords
- user
- evaluation index
- network
- evaluation
- represent
- 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
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Library & Information 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 invention provides a kind of high-quality user's commending system, including instruction acquisition module, candidate list generation module, user's screening module and user's recommending module；The instruction acquisition module is used for the instruction for obtaining triggering recommended user；The candidate list generation module is used to generate Candidate Recommendation user list according to the instruction；User's screening module is used to screen the user in Candidate Recommendation user list, the user after being screened；User's recommending module is at least chosen a user in being used for the user that is filtered out from the Candidate Recommendation user list and recommended.Beneficial effects of the present invention are：High-quality user is realized to recommend.
Description
Technical field
The present invention relates to user's recommended technology field, and in particular to a kind of high-quality user's commending system.
Background technology
The development of Internet technology greatly changes the Working Life mode of people so that interpersonal communication becomes
Fast with it is various, various social networks both provide user's recommendation function.
Question and answer service in the Internet community finds help for people and exchanges viewpoint online provides very easily channel.
In the Internet community, on the one hand search obtains existing information to people, on the other hand energetically shares the experience and knowledge of oneself,
High-quality content is contributed for community.In the past, the technological core point of conventional IR class question and answer service was how to be searched for user
Rope is to the answer related to query demand and information.Now, Novel community class question answering system technological core point is changed.By
In the participation for having real user, required knowledge can not only be searched in existing knowledge base, and can also seek help rope to online user
Take.At this moment, the core missions of system are changed into how to search for directly or indirectly can potentially provide for system and high-quality known
The user of knowledge.The notice of researcher is no longer limited to content retrieval, and expands in the identification of special user.
The content of the invention
In view of the above-mentioned problems, a kind of the present invention is intended to provide high-quality user's commending system.
The purpose of the present invention is realized using following technical scheme：
There is provided a kind of high-quality user's commending system, recommend for the network user, including instruction acquisition module, candidate
List Generating Module, user's screening module and user's recommending module；
The instruction acquisition module is used for the instruction for obtaining triggering recommended user；
The candidate list generation module is used to generate Candidate Recommendation user list according to the instruction；
User's screening module is used to screen the user in Candidate Recommendation user list, the use after being screened
Family；
User's recommending module at least chooses one in being used for the user that is filtered out from the Candidate Recommendation user list
User is recommended.
Beneficial effects of the present invention are：High-quality user is realized to recommend.
Brief description of the drawings
Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not constitute any limit to the present invention
System, for one of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to the following drawings
Other accompanying drawings.
Fig. 1 is the structural representation of the present invention；
Reference：
Instruction acquisition module 1, candidate list generation module 2, user's screening module 3, user's recommending module 4.
Embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of high-quality user's commending system of the present embodiment is recommended for the network user, including instruction
Acquisition module 1, candidate list generation module 2, user's screening module 3 and user's recommending module 4；
The instruction acquisition module 1 is used for the instruction for obtaining triggering recommended user；
The candidate list generation module 2 is used to generate Candidate Recommendation user list according to the instruction；
User's screening module 3 is used to screen the user in Candidate Recommendation user list, after being screened
User；
User's recommending module 4 at least chooses one in being used for the user that is filtered out from the Candidate Recommendation user list
User is recommended.
The present embodiment, which realizes high-quality user, to be recommended.
It is preferred that, the mode of the candidate list generation module 2 generation Candidate Recommendation user list for it is following wherein extremely
Few one kind：
Operating time generation Candidate Recommendation user list according to corresponding to the operation to the network terminal, the Candidate Recommendation
User of time difference of the user list comprising the operating time in setting range；
Candidate Recommendation user list is generated according to the geographical position of the network terminal, the Candidate Recommendation user list includes ground
Reason position belongs to the user of the same area.
This preferred embodiment provides the generating mode of two kinds of Candidate Recommendation user lists, obtains Candidate Recommendation user list
It is simple and easy to apply.
It is preferred that, the Candidate Recommendation user list includes the personal data of user, and the personal data of the user include
Head image data and signed data.
This preferred embodiment can obtain intuitively Candidate Recommendation user profile, improve user discrimination degree.
It is preferred that, user's screening module 3 is screened according to the ability of the network user to user, including the first information
Submodule, the second evaluation submodule and the 3rd screening submodule are gathered, the first information collection submodule is used to believe user
Breath is acquired, and the second evaluation submodule is used to be evaluated according to user's information, obtains evaluation result, described
3rd screening submodule is used to screen user according to evaluation result；Described second, which evaluates submodule, includes the first evaluation list
Member, the second evaluation unit and the 3rd evaluation unit, first evaluation unit are used to evaluate contribution of the user to knowledge in network
Size, second evaluation unit is used to evaluate the active degree of user in a network, and the 3rd evaluation unit is used to evaluate
The influence power of user in a network.
The user is specifically weighed to the contribution of knowledge in network using the first evaluation index, the first evaluation index tool
Body is calculated using following formula：In formula, NR
(uj) represent user ujThe quantity of reply problem, NQ(uj) represent user ujThe quantity of proposition problem, QK (uj) represent user ujThe
One evaluation index, NDR(uj) represent other users to user ujThe quantity of reply problem thumb up, the first evaluation index is bigger, then uses
Contribution of the family to knowledge in network is bigger.
This preferred embodiment user commending system introduces the first evaluation index when evaluating user network Knowledge Contribution,
Consider influence of the degree of recognition of user's enquirement, the quantity for replying problem and other users to Knowledge Contribution, acquisition
Evaluation result is more accurate, so as to improve the recommendation accuracy of commending system.
It is preferred that, the active degree of the user in a network is specifically weighed using the second evaluation index, and the second evaluation refers to
Mark is specific to be calculated using following formula：
In formula, FN (uj) represent user ujSecond evaluation index, ND(uj) represent user ujOther users are replied with the thumb up of problem
Quantity, the second evaluation index is bigger, then user is more active in a network.
This preferred embodiment user commending system introduces second when active degree is evaluated in a network to user and evaluated
Index, has considered the various actions of user in a network, the evaluation result of acquisition is more accurate, so as to improve commending system
Recommendation accuracy.
It is preferred that, the influence power of the user in a network is specifically weighed using the 3rd evaluation index, the 3rd evaluation index
Obtained especially by the following manner：(1) user's interconnection is turned into by social relation network (U, G) by concern relation, wherein, U tables
Show all user's set, G represents element g (u in the set of all concern relations, Gi,uj) represent user u in social relation networki
Pay close attention to user ujBehavior, due to social relation network connection have directionality, uiReferred to as ujBean vermicelli, ujReferred to as uiGood friend；
(2) the 3rd evaluation index is calculated using following formula： In formula, NH(uj) represent user ujGood friend's quantity, NF(uj) represent user ujBean vermicelli quantity, Ei
(uj) represent user ujI-th of bean vermicelli to user ujTrust value,Wherein, SY is definite value, represents each user
Overall trust value, XiRepresent user ujI-th of bean vermicelli good friend's quantity, AY (uj) represent user uj3rd evaluation index, the
Three evaluation indexes are bigger, then the influence power of user in a network is bigger.
This preferred embodiment user commending system introduces the 3rd evaluation when the influence power of network is evaluated to user and referred to
Mark, obtains more accurate evaluation result, so as to improve the recommendation accuracy of commending system.3rd evaluation index is to being concerned
Person and the aspect of follower two are considered that from the point of view of follower, concern relation is vote of confidence behavior, follower couple
All overall trust values for being concerned user are definite value, and the user being each concerned can assign to one of overall trust value
Point, in terms of the person's of being concerned angle, concern relation is can to influence other people behavior, and the bean vermicelli user possessed is more, his influence
Power can just be radiated wider scope, with bigger influence power.
It is preferred that, the 3rd screening submodule includes combination evaluation unit and user's screening unit, the combination evaluation
Unit is used for the mixing evaluation index that user is asked for according to the first evaluation index, the second evaluation index and the 3rd evaluation index, institute
State user's screening unit to be ranked up user capability according to mixing evaluation index, the strong user of screening output capacity.
The mixing evaluation index of the user is calculated using following formula：
In formula, EU (uj) table
Show user ujMixing evaluation index, mixing evaluation index is bigger, then user capability is stronger.
Mixing evaluation index is introduced when this preferred embodiment user's commending system is evaluated user capability, is obtained complete
The reliable user capability ranking results in face, are screened with very strong applicability, the recommendation quality of user has obtained root for user
This guarantee.
Using high-quality user's commending system recommended user of the invention, when recommended user's quantity is respectively 3,4,5,6,7
When, to recommending performance and recommending efficiency to count, compared with the not use present invention, generation has the beneficial effect that shown in table：
| Recommended user's quantity | Performance is recommended to improve | Efficiency is recommended to improve |
| 3 | 10% | 18% |
| 4 | 15% | 23% |
| 5 | 20% | 25% |
| 6 | 24% | 28% |
| 7 | 31% | 32% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than to present invention guarantor
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 (8)
1. a kind of high-quality user's commending system, recommend for the network user, it is characterised in that including instruction acquisition module,
Candidate list generation module, user's screening module and user's recommending module；
The instruction acquisition module is used for the instruction for obtaining triggering recommended user；
The candidate list generation module is used to generate Candidate Recommendation user list according to the instruction；
User's screening module is used to screen the user in Candidate Recommendation user list, the user after being screened；
User's recommending module at least chooses a user in being used for the user that is filtered out from the Candidate Recommendation user list
Recommended.
2. high-quality user's commending system according to claim 1, it is characterised in that the candidate list generation module
The mode for generating Candidate Recommendation user list is following wherein at least one：
Operating time generation Candidate Recommendation user list according to corresponding to the operation to the network terminal, the Candidate Recommendation user
User of time difference of the list comprising the operating time in setting range；
Candidate Recommendation user list is generated according to the geographical position of the network terminal, the Candidate Recommendation user list includes geographical position
Put the user for belonging to the same area.
3. high-quality user's commending system according to claim 2, it is characterised in that the Candidate Recommendation user list
Personal data comprising user, the personal data of the user include head image data and signed data.
4. high-quality user's commending system according to claim 3, it is characterised in that user's screening module according to
The ability of the network user is screened to user, including first information collection submodule, the second evaluation submodule and the 3rd screening
Submodule, the first information collection submodule is used to be acquired user profile, and described second, which evaluates submodule, is used for root
Evaluated according to user's information, obtain evaluation result, it is described 3rd screening submodule be used for according to evaluation result to
Screened at family；Described second, which evaluates submodule, includes the first evaluation unit, the second evaluation unit and the 3rd evaluation unit, described
First evaluation unit is used to evaluate contribution of the user to knowledge in network, and second evaluation unit exists for evaluating user
Active degree in network, the 3rd evaluation unit is used to evaluate the influence power of user in a network.
5. high-quality user's commending system according to claim 4, it is characterised in that the user is to knowledge in network
Contribution specifically using the first evaluation index weigh, the first evaluation index specifically using following formula calculate： In formula, NR(uj) represent user ujReply problem
Quantity, NQ(uj) represent user ujThe quantity of proposition problem, QK (uj) represent user ujFirst evaluation index, NDR(uj) represent other
User to user ujThe quantity of reply problem thumb up, the first evaluation index is bigger, then contribution of the user to knowledge in network is bigger.
6. high-quality user's commending system according to claim 5, it is characterised in that the work of the user in a network
Jump degree is specifically weighed using the second evaluation index, and the second evaluation index is specifically calculated using following formula：
In formula,
FN(uj) represent user ujSecond evaluation index, ND(uj) represent user ujOther users are replied with the thumb up quantity of problem, second
Evaluation index is bigger, then user is more active in a network.
7. high-quality user's commending system according to claim 6, it is characterised in that the shadow of the user in a network
Ring power specifically to weigh using the 3rd evaluation index, the 3rd evaluation index is obtained especially by the following manner：(1) concern relation is passed through
User's interconnection is turned into social relation network (U, G), wherein, U represents all user's set, and G represents the collection of all concern relations
Close, element g (u in Gi,uj) represent user u in social relation networkiPay close attention to user ujBehavior, due to social relation network connect
Connect with directionality, uiReferred to as ujBean vermicelli, ujReferred to as uiGood friend；
(2) the 3rd evaluation index is calculated using following formula： In formula, NH(uj) represent user ujGood friend's quantity, NF(uj) represent user ujBean vermicelli quantity, Ei
(uj) represent user ujI-th of bean vermicelli to user ujTrust value,Wherein, SY is definite value, represents each user
Overall trust value, XiRepresent user ujI-th of bean vermicelli good friend's quantity, AY (uj) represent user uj3rd evaluation index, the
Three evaluation indexes are bigger, then the influence power of user in a network is bigger.
8. high-quality user's commending system according to claim 7, it is characterised in that the 3rd screening submodule bag
Combination evaluation unit and user's screening unit are included, the combination evaluation unit, which is used to evaluate according to the first evaluation index, second, to be referred to
Mark and the 3rd evaluation index ask for the mixing evaluation index of user, and user's screening unit is according to mixing evaluation index to user
Ability is ranked up, the strong user of screening output capacity；
The mixing evaluation index of the user is calculated using following formula：
In formula, EU (uj) represent to use
Family ujMixing evaluation index, mixing evaluation index is bigger, then user capability is stronger.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710388945.9A CN107193984A (en) | 2017-05-25 | 2017-05-25 | A kind of high-quality user's commending system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710388945.9A CN107193984A (en) | 2017-05-25 | 2017-05-25 | A kind of high-quality user's commending system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107193984A true CN107193984A (en) | 2017-09-22 |
Family
ID=59875135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710388945.9A Pending CN107193984A (en) | 2017-05-25 | 2017-05-25 | A kind of high-quality user's commending system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107193984A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190058A (en) * | 2018-10-15 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2156058A1 (en) * | 1993-12-17 | 1995-06-22 | Jeffery Charles Conniff | Automatic gathering and graphical display of useability test data |
| CN103138954A (en) * | 2011-12-02 | 2013-06-05 | 中国移动通信集团公司 | Recommending method, recommending system and recommending server of referenced item |
| CN103581270A (en) * | 2012-08-08 | 2014-02-12 | 腾讯科技（深圳）有限公司 | User recommendation method and system |
-
2017
- 2017-05-25 CN CN201710388945.9A patent/CN107193984A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2156058A1 (en) * | 1993-12-17 | 1995-06-22 | Jeffery Charles Conniff | Automatic gathering and graphical display of useability test data |
| CN103138954A (en) * | 2011-12-02 | 2013-06-05 | 中国移动通信集团公司 | Recommending method, recommending system and recommending server of referenced item |
| CN103581270A (en) * | 2012-08-08 | 2014-02-12 | 腾讯科技（深圳）有限公司 | User recommendation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 韩闻文: "基于社会化媒体的观点和行为挖掘研究", 《中国博士学位论文全文数据库信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109190058A (en) * | 2018-10-15 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
| WO2020078049A1 (en) * | 2018-10-15 | 2020-04-23 | 北京字节跳动网络技术有限公司 | User information processing method and device, server, and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104572889B (en) | A kind of search word recommends methods, devices and systems | |
| Vu et al. | Joint bluetooth/wifi scanning framework for characterizing and leveraging people movement in university campus | |
| CN102880691B (en) | A kind of mixing commending system based on user's cohesion and method | |
| Maier et al. | Online social networks as a source and symbol of stress: An empirical analysis | |
| US8843518B2 (en) | Method and apparatus for establishing a connection with known individuals | |
| CN105207821B (en) | A kind of network synthesis performance estimating method of service-oriented | |
| KR20140037268A (en) | Method, apparatus and storage medium for adding friends in social network | |
| CN102035891A (en) | Method and device for recommending friends in network friend making platform | |
| CN109522475A (en) | A kind of merchant recommendation method based on user's history consumption data | |
| CN104598648B (en) | A kind of microblog users interactive mode gender identification method and device | |
| CN106126586A (en) | A kind of social networks recommended models construction method trusted based on overall merit | |
| CN109905399A (en) | A kind of social media individual abnormal user detection method to be developed based on self network structure | |
| CN108280121A (en) | A method of social network opinion leader is obtained based on K- nuclear decomposition | |
| CN101136869A (en) | Method for generating search intention based contacts group of instant communication system | |
| CN106971345A (en) | A kind of location recommendation method based on position social networks | |
| CN105978729B (en) | A kind of cellphone information supplying system and method based on user's internet log and position | |
| CN109190052A (en) | A kind of space index method based on society's perception under distributed environment | |
| CN107193984A (en) | A kind of high-quality user's commending system | |
| CN107463551A (en) | The analysis method and device of social networks interpersonal relationships | |
| Li et al. | Context-based people search in labeled social networks | |
| De et al. | Differentially private link prediction with protected connections | |
| Nepal et al. | A social trust based friend recommender for online communities “invited paper” | |
| CN109801146A (en) | A kind of resource service recommended method and system based on Demand perference | |
| CN107563217A (en) | A kind of recommendation method and apparatus for protecting user privacy information | |
| CN109871493A (en) | Friend-making matching process, device, computer equipment and readable storage medium storing program for executing |
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: 20170922 |
|
| RJ01 | Rejection of invention patent application after publication |