CN107358533A - A kind of user of Web Community recommends method and system - Google Patents
A kind of user of Web Community recommends method and system Download PDFInfo
- Publication number
- CN107358533A CN107358533A CN201710451093.3A CN201710451093A CN107358533A CN 107358533 A CN107358533 A CN 107358533A CN 201710451093 A CN201710451093 A CN 201710451093A CN 107358533 A CN107358533 A CN 107358533A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- similarity
- candidate
- degree
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000010354 integration Effects 0.000 claims description 24
- 230000003993 interaction Effects 0.000 claims description 20
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 37
- 238000013461 design Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000011524 similarity measure Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of user of Web Community to recommend method and system, and method includes：S1, the user data to multiple users in Web Community pre-process, and obtain pretreated user data；S2, the degree of belief between any two users in multiple users is calculated, the similarity between any two users in multiple users is calculated；S3, degree of belief and similarity are integrated；S4, the starting point using the first candidate user as chain, successive ignition is carried out to degree of belief and similarity, obtains the multiple candidate users for including the first candidate user；S5, the global reputation that multiple candidate users are calculated, it is consequently recommended user to recommend the maximum user of global reputation from multiple users.The beneficial effects of the invention are as follows：The technical program combination degree of belief and similarity are recommended, and are introduced chain type and are recommended to expand recommended range, handle uncertain factor using cloud model, the reputation degree of recommended user is calculated, so as to improve recommendation precision.
Description
Technical field
The present invention relates to electronic information field, the user of more particularly to a kind of Web Community recommends method and system.
Background technology
At present, with national industry restructuring, the implementation for the policy such as accelerate transformation of the mode of economic development, numerous enterprises are outstanding
It is medium and small micro- enterprise, because economic force is weaker, constrains technology, Innovation Input and the introduction of the talent and the culture of enterprise
Development etc., designer is especially rich in innovative spirit, the designer of Specialized Quality and product development experience lacks.Due to knowing
Knowledge increasingly disperses, become increasingly complex, and causes floating of professionals to increase trend.And the economic force of many medium and small micro- enterprises compared with
Weak, technical conditions and social benefit etc. are not high, plus the development for being risk investment, large quantities of technicians is flowed to social benefit good
Unit, or go on the road of foundation.Medium and small micro- enterprise is difficult to introduce and retain staff.Product open innovation style designs, to enterprise
Extricate oneself from a plight and create opportunity.But the information of user-network access registration is typically fewer, recommend to design only according to log-on message
Expert is not necessarily accurate.
The content of the invention
The invention provides a kind of user of Web Community to recommend method and system, and the technology for solving prior art is asked
Topic.
The technical scheme that the present invention solves above-mentioned technical problem is as follows：A kind of user of Web Community recommends method, including：
S1, the user data to multiple users in Web Community pre-process, and obtain pretreated user data, institute
Stating pretreated user data includes：Interaction times, the multiple user in the multiple user between any two users
In in the product information that participates in jointly of any two users and the multiple user each user the trust for participating in product is scored letter
Breath；
S2, according to the interaction times degree of belief in the multiple user between any two users is calculated, according to
The similarity in the multiple user between any two users is calculated in the product information and the trust score information；
S3, the degree of belief and the similarity are integrated, obtain the integrated of each user in the multiple user
Value, recommend the maximum user of the integration value from the multiple user as the first candidate user；
S4, the starting point using first candidate user as chain, by the chain type proposed algorithm of cloud model to the degree of belief
Successive ignition is carried out with the similarity, obtains the multiple candidate users for including first candidate user；
S5, the global reputation of the multiple candidate user is calculated according to the trust score information, from described more
It is consequently recommended user to recommend the maximum user of the global reputation in individual user.
The beneficial effects of the invention are as follows：The technical program combination degree of belief and similarity are recommended, and are introduced chain type and are recommended
Expand recommended range, and using cloud model processing uncertain factor, calculate the reputation degree of recommended user, recommend essence so as to improve
Degree.
On the basis of above-mentioned technical proposal, the present invention can also do following improvement.
Preferably, in step S2, it is calculated according to the product information and institute's scoring information in the multiple user
The method of similarity between any two users specifically includes：
By the product information and the trust score information input Poisson similarity model, the multiple use is calculated
Similarity in family between any two users.
Preferably, in step S3, the degree of belief and the similarity are integrated, obtained every in the multiple user
The method of the integration value of individual user specifically includes：
Ratio shared by the addition regulatory factor coordination degree of belief and the similarity, obtain every in the multiple user
The integration value of individual user.
Preferably, in step S5, the global of the multiple candidate user is calculated according to the trust score information and believed
The method of degree is appointed to specifically include：
The trust score information is inputted to the reverse maker of trust cloud of the cloud model, the multiple time is calculated
Trust cloud from the global reputation at family, multiple global reputations are trusted into the cloud standard credit with the cloud model respectively
Cloud is compared, and obtains the global reputation of the multiple candidate user.
A kind of user commending system of Web Community, including：
Pretreatment module, for being pre-processed to the user data of multiple users in Web Community, after obtaining pretreatment
User data, the pretreated user data includes：Interaction times in the multiple user between any two users,
Each user is to participating in product in any two users participate in jointly in the multiple user product information and the multiple user
Trust score information；
First computing module, for being calculated according to the interaction times in the multiple user between any two users
Degree of belief, according to the product information and the trust score information be calculated in the multiple user any two users it
Between similarity；
Integration module, for being integrated to the degree of belief and the similarity, obtain each in the multiple user
The integration value of user, recommend the maximum user of the integration value from the multiple user as the first candidate user；
Iteration module, for the starting point using first candidate user as chain, pass through the chain type proposed algorithm pair of cloud model
The degree of belief and the similarity carry out successive ignition, obtain the multiple candidate users for including first candidate user；
Second computing module, believe for the global of the multiple candidate user to be calculated according to the trust score information
Ren Du, it is consequently recommended user to recommend the maximum user of the global reputation from the multiple user.
Preferably, first computing module is specifically used for：
By the product information and the trust score information input Poisson similarity model, the multiple use is calculated
Similarity in family between any two users.
Preferably, the integration module is specifically used for：
Ratio shared by the addition regulatory factor coordination degree of belief and the similarity, obtain every in the multiple user
The integration value of individual user.
Preferably, second computing module is specifically used for：
The trust score information is inputted to the reverse maker of trust cloud of the cloud model, the multiple time is calculated
Trust cloud from the global reputation at family, multiple global reputations are trusted into the cloud standard credit with the cloud model respectively
Cloud is compared, and obtains the global reputation of the multiple candidate user.
Brief description of the drawings
Fig. 1 is that a kind of user of Web Community provided in an embodiment of the present invention recommends the schematic flow sheet of method；
Fig. 2 is a kind of structural representation of the user's commending system for Web Community that another embodiment of the present invention provides.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
Embodiment 1, as shown in figure 1, a kind of user of Web Community recommends method, including：
S1, the user data to multiple users in Web Community pre-process, and obtain pretreated user data, in advance
User data after processing includes：Any two users in interaction times, multiple users in multiple users between any two users
Each user is to participating in the trust score information of product in the product information participated in jointly and multiple users；
The user data of multiple users in Web Community is pre-processed, user data includes the interaction time between user
The data such as the product information that annexation, user between number, user participate in and the scoring to product, are carried out to user data
Pretreatment, unwanted data are removed, and only retain interaction times in multiple users between any two users, in multiple users
Each user is to participating in the trust score information of product in product information that each user participates in and multiple users.
S2, according to interaction times the degree of belief in multiple users between any two users is calculated, according to product information
And the similarity in multiple users between any two users is calculated in trust score information；
Degree of belief between user u and user v is represented using trust (u, v), is calculated using formula (1).
Wherein, the number of c (u, v) interactions between user u and user v, user v are user u neighbor users, and p is use
The quantity of user in family u neighbor networks, neighbor networks refer to the network of user u all neighbor users composition.J is expressed as neighbour
Occupy j-th of user in network.
S3, degree of belief and similarity are integrated, the integration value of each user in multiple users is obtained, from multiple users
It is middle to recommend the maximum user of integration value as the first candidate user；
S4, the starting point using the first candidate user as chain, by the chain type proposed algorithm of cloud model to degree of belief and similarity
Successive ignition is carried out, obtains the multiple candidate users for including the first candidate user；
S5, the global reputations of multiple candidate users is calculated according to trusting score information, recommends from multiple users
The maximum user of global reputation is consequently recommended user.
It should be understood that existing main recommendation method has based on degree of belief, proposed algorithm of collaborative filtering etc..The former is most
Conventional method, the latter are the study hotspots just risen recent years, but the two is usually used in some service, film, good friends etc.
Property recommendation in terms of, and because " cold start-up " situation occurs in collaborative filtering method, there is very great Cheng in method based on degree of belief
Subjective trust on degree；Degree of belief can help solve " cold start-up " problem, and the Similarity Measure of collaborative filtering can certain journey
Subjective trust problem is reduced on degree.In addition, either degree of belief calculates or Similarity Measure can all be related to qualitative and quantitative
The problem of, and cloud model is adapted to carry out the conversion between qualitative and quantitative just.Therefore, the technical program will be based on degree of belief
Proposed algorithm combine with cloud model, a kind of improved chain type based on cloud model recommends to calculate under structure Web Community environment
Method, it can be used for recommended products conceptual design expert.
Embodiment 2, a kind of user of Web Community recommend method, including：
S1, the user data to multiple users in Web Community pre-process, and obtain pretreated user data, in advance
User data after processing includes：Any two users in interaction times, multiple users in multiple users between any two users
Each user is to participating in the trust score information of product in the product information participated in jointly and multiple users；
The user data of multiple users in Web Community is pre-processed, user data includes the interaction time between user
The data such as the product information that annexation, user between number, user participate in and the scoring to product, are carried out to user data
Pretreatment, unwanted data are removed, and only retain interaction times in multiple users between any two users, in multiple users
Each user is to participating in the trust score information of product in product information that each user participates in and multiple users.
S2, according to interaction times the degree of belief in multiple users between any two users is calculated, by product information and
Trust score information input Poisson similarity model, the similarity between any two users in multiple users is calculated；
Degree of belief between user u and user v is represented using trust (u, v), is calculated using formula (1).
Wherein, the number of c (u, v) interactions between user u and user v, user v are user u neighbor users, and p is use
The quantity of user in family u neighbor networks, neighbor networks refer to the network of user u all neighbor users composition.J is expressed as neighbour
Occupy j-th of user in network.
User u and user v similarity is represented using sim (u, v), using such as formula (2) Poisson Similarity Measure.
Wherein, the product quantity that S is participated in jointly for user u, v, ru、rvAll products that respectively user u, v is participated in are put down
Score.tu,qThe scoring for the Product Conceptual Design scheme that production code member is q, t are participated in for user uv,qProduct is participated in for user v to compile
Number for q Conceptual Design scoring.
Ratio shared by S3, addition regulatory factor coordination degree of belief and similarity, obtains each user in multiple users
Integration value, recommend the maximum user of integration value from multiple users as the first candidate user；
Regulatory factor is introduced in integrated degree of belief and similarityEnsure that it can efficiently recommend, can by adjust because
Son coordinates degree of belief and similarity proportion, then integrates degree of belief and similarity and represented with ω (u, v), use formula (3) to count
Calculate.
Regulatory factor is introduced between degree of belief and similarity, the global trusting of recommended node is calculated using cloud model
Degree is reputation degree to improve the precision of recommendation.
S4, the starting point using the first candidate user as chain, by the chain type proposed algorithm of cloud model to degree of belief and similarity
Successive ignition is carried out, obtains the multiple candidate users for including the first candidate user；
S5, the reverse maker of trust cloud that will trust score information input cloud model, are calculated multiple candidate users
Global reputation trusts cloud, and multiple global reputations are trusted into cloud respectively compared with the standard credit cloud of cloud model, obtained
The global reputation of multiple candidate users, it is consequently recommended user to recommend the maximum user of global reputation from multiple users.
If the trust scoring of product is rule of thumb divided into it in 5 subintervals in [0,10]：[0,1.5] (pole can not
Letter), [1.5,3.5] (insincere), [3.5,6.5] (low credible), [6.5,8.5] (general credible), [8.5,10] (high credible).
If shared Y of certain product trusts scoring interval division, wherein it is [R to trust scoring section for i-thi min,Ri max], then
The trust score value in the section is designated as α and is calculated as follows with formula (4).
α=Ri min+θ*(Ri max-Ri min) (4)
Wherein, as i >=Y/2, θ is that the evaluation number for trusting greater than or equal to i-th scoring section of scoring accounts for general comment valence mumber
Weighted percentage；Work as i<During Y/2, θ is that the evaluation number for trusting less than or equal to i-th scoring section of scoring accounts for general comment valence mumber
Weighted percentage.
Standard credit cloud is generated by standard credit cloud maker, detailed process is as follows.
Input：N is trusted scoring demarcation interval.
Output：Standard credit cloud STCi(Exi,Eni,Hei), wherein i=1,2 ..., n.
Algorithm steps are as follows:
Step1：According to the upper lower limit value in each section, calculate and it is expected Exi:
Step2：According to Step1, entropy En is calculatedi：
Step3：Calculate super entropy Hei, Hei=η, η reflect the randomness that product trusts scoring, and its value is unsuitable excessive, because
Error for the more big then Ex of He is bigger, the randomness increase of degree of belief, trusts result and is difficult to determine.So utilize standard credit cloud
Each cloud numerical characteristic STC for trusting scoring section can be obtainedi(Exi,Eni,Hei)。
The Computing Principle for trusting the reverse maker of cloud is as follows.
Input：The trust scoring sample point set X of producti(xi1,xi2,…,xin), i=1,2 ..., m (temporally inverted orders
Arrangement)
Output：M is trusted cloud (TPC1,…,TPCm) numerical characteristic (Ex1,…,Exm,En1,…,Enm,He1,…,Hem)
Algorithm steps are as follows：
Step1:Calculate and trust degree of membership μij:
Step2：According to Xi(xi1,xi2,…,xin) calculate sample mean：
Step3：Calculate and it is expected：
Step4：Calculate entropy:
Step5：Assuming that it is (x each to trust cloudij, μij), calculate
Step6:Calculate each En'miStandard deviation, obtaining super entropy He, (standard credit cloud is to determine reliability rating
The division of amount, and caused by the reverse maker of trust cloud here it is the actual trust cloud of user, including its specific super entropy, use
Trust the reverse maker of cloud and calculate the m sub- cloud of trust of the recommended candidate person, and integrated using formula (11), obtain global letter
Appoint cloud numerical characteristic TPC (Ex, En, He), then relatively established trust subinterval with STC, recycle formula (4) to obtain the recommended candidate
The global reputation of person.
Wherein, m be product classification number, ki(∑ki=1) it is product weight of all categories.
The step of chain type proposed algorithm based on cloud model, is as follows：
Step1:Gathered data, and pre-processed.Initializing variable k, array candidateNames [3],
Reputation [3], k=0；
Step2:In user's u neighbor networks using formula (3) traversal calculate with each neighbor user v integrated degree of belief and
Similarity value ω (u, v), ω (u, v) value of maximum being selected, its corresponding user is the candidate for recommending design specialist,
CandidateNames [k]=v；
Step3:The m sub- cloud of trust of the recommended candidate person is calculated using the reverse maker of cloud is trusted, and utilizes formula (11)
Integrated to obtain it is comprehensive trust cloud, then relatively established trust subinterval with STC, recycle formula (4) to obtain the recommended candidate person
Global reputation, and the value is assigned to reputation [K], K++；
Step4:If k is less than 3, using candidateNames [k-1] as initial user u, and step2 is jumped to, it is no
Then, step5 is jumped to；
Step5:The subscript pair of maximum in array reputation [0], reputation [1], reputation [2]
Should be the design specialist that this is recommended in the value in array candidateNames.
Step6:Algorithm terminates.
Embodiment 3, as shown in Fig. 2 a kind of user's commending system of Web Community, including：
Pretreatment module 1, for being pre-processed to the user data of multiple users in Web Community, after obtaining pretreatment
User data, pretreated user data includes：Interaction times, multiple users in multiple users between any two users
In in the product information that participates in jointly of any two users and multiple users each user to participating in the trust score information of product；
First computing module 2, for the trust in multiple users between any two users to be calculated according to interaction times
Degree, the similarity in multiple users between any two users is calculated according to product information and trust score information；
Integration module 3, for being integrated to degree of belief and similarity, obtain the integrated of each user in multiple users
Value, recommend the maximum user of integration value from multiple users as the first candidate user；
Iteration module 4, for the starting point using the first candidate user as chain, by the chain type proposed algorithm of cloud model to trusting
Degree and similarity carry out successive ignition, obtain the multiple candidate users for including the first candidate user；
Second computing module 5, for the global reputation of multiple candidate users to be calculated according to trust score information, from
It is consequently recommended user to recommend the maximum user of global reputation in multiple users.
Specifically, the first computing module 2 is specifically used for：
By product information and trust score information input Poisson similarity model, any two in multiple users are calculated and use
Similarity between family.
Specifically, integration module 3 is specifically used for：
Add regulatory factor and coordinate degree of belief and the ratio shared by similarity, obtain integrating for each user in multiple users
Value.
Specifically, the second computing module 5 is specifically used for：
The reverse maker of trust cloud of score information input cloud model will be trusted, the overall situation of multiple candidate users is calculated
Degree of belief trusts cloud, and multiple global reputations are trusted into cloud respectively compared with the standard credit cloud of cloud model, obtained multiple
The global reputation of candidate user.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (8)
1. a kind of user of Web Community recommends method, it is characterised in that including：
S1, the user data to multiple users in Web Community pre-process, and obtain pretreated user data, described pre-
User data after processing includes：Appoint in interaction times, the multiple user in the multiple user between any two users
Each user is to participating in the trust score information of product in product information that two users participate in jointly and the multiple user；
S2, according to the interaction times degree of belief in the multiple user between any two users is calculated, according to described
The similarity in the multiple user between any two users is calculated in product information and the trust score information；
S3, the degree of belief and the similarity are integrated, obtain the integration value of each user in the multiple user, from
Recommend the maximum user of the integration value in the multiple user as the first candidate user；
S4, the starting point using first candidate user as chain, by the chain type proposed algorithm of cloud model to the degree of belief and institute
State similarity and carry out successive ignition, obtain the multiple candidate users for including first candidate user；
S5, the global reputation of the multiple candidate user is calculated according to the trust score information, from the multiple use
It is consequently recommended user to recommend the maximum user of the global reputation in family.
2. a kind of user of Web Community according to claim 1 recommends method, it is characterised in that in step S2, according to
The method that the similarity in the multiple user between any two users is calculated in the product information and institute's scoring information
Specifically include：
The product information and the trust score information input Poisson similarity model are calculated in the multiple user
Similarity between any two users.
3. a kind of user of Web Community according to claim 2 recommends method, it is characterised in that in step S3, to institute
State degree of belief and the similarity is integrated, the method for obtaining the integration value of each user in the multiple user is specifically wrapped
Include：
Ratio shared by the addition regulatory factor coordination degree of belief and the similarity, obtains each using in the multiple user
The integration value at family.
4. a kind of user of Web Community according to claim any one of 1-3 recommends method, it is characterised in that step S5
In, the method for the global reputation that the multiple candidate user is calculated according to the trust score information specifically includes：
The trust score information is inputted to the reverse maker of trust cloud of the cloud model, the multiple candidate is calculated and uses
The global reputation at family trusts cloud, and multiple global reputations are trusted into standard credit cloud of the cloud respectively with the cloud model and entered
Row compares, and obtains the global reputation of the multiple candidate user.
A kind of 5. user's commending system of Web Community, it is characterised in that including：
Pretreatment module, for being pre-processed to the user data of multiple users in Web Community, obtain pretreated use
User data, the pretreated user data include：It is interaction times in the multiple user between any two users, described
Each user is to participating in the letter of product in any two users participate in jointly in multiple users product information and the multiple user
Appoint score information；
First computing module, for the letter in the multiple user between any two users to be calculated according to the interaction times
Ren Du, it is calculated according to the product information and the trust score information in the multiple user between any two users
Similarity；
Integration module, for being integrated to the degree of belief and the similarity, obtain each user in the multiple user
Integration value, recommend the maximum user of the integration value from the multiple user as the first candidate user；
Iteration module, for the starting point using first candidate user as chain, by the chain type proposed algorithm of cloud model to described
Degree of belief and the similarity carry out successive ignition, obtain the multiple candidate users for including first candidate user；
Second computing module, for the global trusting of the multiple candidate user to be calculated according to the trust score information
Degree, it is consequently recommended user to recommend the maximum user of the global reputation from the multiple user.
6. user's commending system of a kind of Web Community according to claim 5, it is characterised in that described first calculates mould
Block is specifically used for：
The product information and the trust score information input Poisson similarity model are calculated in the multiple user
Similarity between any two users.
A kind of 7. user's commending system of Web Community according to claim 6, it is characterised in that the integration module tool
Body is used for：
Ratio shared by the addition regulatory factor coordination degree of belief and the similarity, obtains each using in the multiple user
The integration value at family.
8. user's commending system of a kind of Web Community according to claim any one of 5-7, it is characterised in that described
Two computing modules are specifically used for：
The trust score information is inputted to the reverse maker of trust cloud of the cloud model, the multiple candidate is calculated and uses
The global reputation at family trusts cloud, and multiple global reputations are trusted into standard credit cloud of the cloud respectively with the cloud model and entered
Row compares, and obtains the global reputation of the multiple candidate user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710451093.3A CN107358533A (en) | 2017-06-15 | 2017-06-15 | A kind of user of Web Community recommends method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710451093.3A CN107358533A (en) | 2017-06-15 | 2017-06-15 | A kind of user of Web Community recommends method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107358533A true CN107358533A (en) | 2017-11-17 |
Family
ID=60272332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710451093.3A Pending CN107358533A (en) | 2017-06-15 | 2017-06-15 | A kind of user of Web Community recommends method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358533A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109656541A (en) * | 2018-11-20 | 2019-04-19 | 东软集团股份有限公司 | Exploitative recommended method, device, storage medium and electronic equipment |
| CN111597220A (en) * | 2019-02-21 | 2020-08-28 | 北京沃东天骏信息技术有限公司 | Data mining method and device |
| CN111814067A (en) * | 2020-06-30 | 2020-10-23 | 北京百度网讯科技有限公司 | Friend recommendation method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152436A (en) * | 2013-04-01 | 2013-06-12 | 无锡南理工科技发展有限公司 | P2P (peer-to-peer) internet trust cloud model computing method based on interest group |
| CN103995823A (en) * | 2014-03-25 | 2014-08-20 | 南京邮电大学 | Information recommending method based on social network |
-
2017
- 2017-06-15 CN CN201710451093.3A patent/CN107358533A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152436A (en) * | 2013-04-01 | 2013-06-12 | 无锡南理工科技发展有限公司 | P2P (peer-to-peer) internet trust cloud model computing method based on interest group |
| CN103995823A (en) * | 2014-03-25 | 2014-08-20 | 南京邮电大学 | Information recommending method based on social network |
Non-Patent Citations (1)
| Title |
|---|
| 刘电霆 等: "《一种改进的基于云模型的链式推荐算法》", 《广西大学学报( 自然科学版)》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109656541A (en) * | 2018-11-20 | 2019-04-19 | 东软集团股份有限公司 | Exploitative recommended method, device, storage medium and electronic equipment |
| CN111597220A (en) * | 2019-02-21 | 2020-08-28 | 北京沃东天骏信息技术有限公司 | Data mining method and device |
| CN111597220B (en) * | 2019-02-21 | 2024-03-05 | 北京沃东天骏信息技术有限公司 | Data mining method and device |
| CN111814067A (en) * | 2020-06-30 | 2020-10-23 | 北京百度网讯科技有限公司 | Friend recommendation method, device, equipment and storage medium |
| CN111814067B (en) * | 2020-06-30 | 2024-03-15 | 北京百度网讯科技有限公司 | Friend recommendation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shen et al. | An outranking sorting method for multi-criteria group decision making using intuitionistic fuzzy sets | |
| Lazzeroni et al. | Towards the entrepreneurial university | |
| Yang et al. | Question recommendation with constraints for massive open online courses | |
| CN103577888B (en) | Method for optimization of product design schemes | |
| Apostolakis et al. | Deliberation: integrating analytical results into environmental decisions involving multiple stakeholders | |
| CN105976207A (en) | Information search result generation method and system based on multi-attribute dynamic weight distribution | |
| CN107358533A (en) | A kind of user of Web Community recommends method and system | |
| CN105893637A (en) | Link prediction method in large-scale microblog heterogeneous information network | |
| Xiong et al. | AHP fuzzy comprehensive method of supplier evaluation in social manufacturing mode | |
| Xiao et al. | Dynamic multi-attribute evaluation of digital economy development in China: A perspective from interaction effect | |
| Dong et al. | An improved MULTIMOORA method with combined weights and its application in assessing the innovative ability of universities | |
| Wu et al. | Selection of Cooperative Enterprises in Vocational Education Based on ANP. | |
| Guo et al. | Enabling Team of Teams: A Trust Inference and Propagation (TIP) Model in Multi-Human Multi-Robot Teams | |
| Zhang et al. | A LSGDM method based on social network and IVIFN’s geometric characteristics for evaluating the collaborative innovation problem | |
| Ji et al. | Decayed Trust Propagation Method in Multiple Overlapping Communities for Improving Consensus Under Social Network Group Decision Making | |
| Zhong et al. | Sustainable supply chain partner selection and order allocation: A hybrid fuzzy PL-TODIM based MCGDM approach | |
| Chen et al. | Study of stock prediction based on social network | |
| Pope | Developmental risk associated with mutual dislike in elementary school children | |
| CN109118122A (en) | Outsourcing supplier's evaluation method based on mixing PSO-Adam neural network | |
| Mohammadi et al. | Identifying and prioritizing criteria for selecting sustainable façade materials of high-rise buildings | |
| Wang et al. | MABAC method based on cumulative prospect theory for MCGDM with dual probabilistic linguistic term set and applications to sustainable supplier selection | |
| Gong et al. | The consistency improvement of probabilistic linguistic hesitant fuzzy preference relations and their application in venture capital group decision making | |
| Yu et al. | The configurational effects of centrifugal and centripetal forces on firms' breakthrough innovation and strategic performance in the artificial intelligence context | |
| Zou et al. | An improved grey Markov chain model with ANN error correction and its application in gross domestic product forecasting | |
| Li et al. | A Network Public Opinion Trend Estimation Model Using a Scale‐Free Network Algorithm |
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: 20171117 |