CN106991133B - It is a kind of based on any active ues group recommending method for restarting random walk model - Google Patents
It is a kind of based on any active ues group recommending method for restarting random walk model Download PDFInfo
- Publication number
- CN106991133B CN106991133B CN201710145033.9A CN201710145033A CN106991133B CN 106991133 B CN106991133 B CN 106991133B CN 201710145033 A CN201710145033 A CN 201710145033A CN 106991133 B CN106991133 B CN 106991133B
- Authority
- CN
- China
- Prior art keywords
- group
- active ues
- project
- user
- gmg
- 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.)
- Active
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
Abstract
The invention discloses a kind of based on any active ues group recommending method for restarting random walk, mainly for the problems such as covering of fringe sport in group's recommendation process, propose a kind of group recommending method, main includes proposing any active ues group, user's propensity value, project coverage rate, group is inclined to deviation, each related coefficient for enlivening group about project is obtained by restarting random walk model, and the recommendation comprising fringe sport is generated to groups of users, the problem that user volume is excessive in group's recommendation is reduced, while the recommendation generated contains fringe sport.
Description
Technical field
It is especially a kind of based on any active ues group for restarting random walk model the present invention relates to recommender system technical field
Group recommended method.
Background technique
With the rapid development of Internet technology, quantity of service on network also therewith sharp increase however, this growth
The scope that can receive, handle and efficiently use considerably beyond personal or system.In such a case, different user can be directed to
The recommender system of demand is come into being, and theoretical and its relevant technologies is recommended to have become a popular research of academia and industry
Project.
Traditional service recommendation system such as collaborative filtering, which is generally laid particular emphasis on to single user, to be recommended, but in reality
In many daily routines of life, user is that occur in the form of group, such as trip tourism, purchase by group on the net.Therefore, group
Recommender system needs while considering the tendency of all users recommend on the other hand, recommends for certain sole user
It is easy to produce the undesirable situation of effect, and needs to put it into group, recommends to tend to obtain good effect by group
Fruit, and the recommender system research towards group at present of cold start-up problem caused by new user can be effectively relieved by more and more
Concern, 2011 the conference of ACM recommender system (RecSys2011) with " for group, family recommend film " be the theme, held
Hereafter perception film recommends challenge match (CAMRa2011), promotes group's recommendation in the popularization in the fields such as film, food and drink, tourism
The prerequisite steps recommended as group are found with application group, and group division result plays an important role group to recommendation effect
Inherent similarity determine the accuracy that group is recommended, the recommendation effect of high similarity group can meet or exceed individually
The precision that user recommends, and it is also with good stability when group size increases.
During existing group is recommended, often as the increase computational efficiency of group size sharply declines, the overwhelming majority is calculated
Consumption is also a problem to be solved from sluggish user, and for the recommendation of fringe sport.Group recommend in
Being increasing for group size, one by one analyze single user greatly waste time and resource, and not can guarantee completely
Cover all items and fringe sport cannot get appropriate recommendation.
Summary of the invention
One kind is provided the technical problem to be solved by the present invention is to overcome the deficiencies in the prior art to be based on restarting random trip
Any active ues group recommending method for walking model using any active ues as group's recommended, and restarts mould by random walk
Type recommends suitable items for it.
The present invention uses following technical scheme to solve above-mentioned technical problem:
What is proposed according to the present invention is a kind of based on any active ues group recommending method for restarting random walk model, including with
Lower step:
Step 1: being inclined to deviation by calculating project coverage rate and group obtains any active ues group: will have simultaneously most
The subset group of large project coverage rate and minimum group tendency deviation is as any active ues group；
Step 2: building correlation matrix SGMG, wherein SGMGContain the degree of correlation square between any active ues group and project
Battle array SGM, each any active ues group includes the phase of the selection tendency and each any active ues group and each user to project
Guan Du, and each user equally has the selection propensity value to project；Then by correlation matrix SGMGIt is regular to turn to NGMG, make
For the probability transfer matrix for restarting random walk model；
Step 3: random walk model is restarted in starting, the related coefficient of any active ues group and project is obtained, with NGMGFor
Probability transfer matrix restarts random walk process to the execution that iterates of each any active ues group, passes through and define termination condition
Random walk is restarted in termination；Its steady probability matrix is calculated to each any active ues group againUntil convergence, to obtain
The correlation coefficient of any active ues group and project is obtained, finally uses the highest preceding K project recommendation of correlation coefficient to active
Family group.
As of the present invention a kind of further based on any active ues group recommending method for restarting random walk model
Prioritization scheme, the detailed process that any active ues group is obtained in step 1 are as follows:
Step 1.1 calculates scoring quantization matrix, defines user's set U:U={ ui, 0≤i≤| U |, project set P:P
={ pj, 0≤j≤| P |, the interactive information between user and project is quantified with rating matrix R, then has:
R={ rij}|U|×|P|,rij≥0
Wherein, uiFor i-th of user and i is integer, pjFor j-th of project and j is integer, rijIt is the i-th of rating matrix R
The element and r of row j columnijIt is i-th of user to the interactive information score data of j-th of project, if rij=0 represents uiAnd pjNo
Interaction, i.e. uiActivity do not cover pj；
Step 1.2 calculates project coverage rate, covers collection P for the project of given the subset U', U' of user's set UU' fixed
Justice are as follows:
The project coverage rate Cov (U') of U' is the subset P of PU' ratio shared in P, it may be assumed that
Step 1.3 calculates group's tendency deviation, and user's subset and all use are indicated with subset error score Err (U')
Tendency deviation between family:
Wherein, avg (pj, U') and indicate user's subset U' to j-th of project pjAverage score；
Step 1.4 obtains project coverage rate and tendency deviation acquisition any active ues group, group according to step 1.2 and 1.3,
Any active ues group CUG is a subset of user's set U, and the size of any active ues group is k, which meets following two
Condition has in the subset that all sizes of user's set U are k:
As of the present invention a kind of further based on any active ues group recommending method for restarting random walk model
Prioritization scheme constructs correlation matrix S in step 2GMGThe specific method is as follows:
Correlation matrix SGMGTo indicate the related coefficient between two intermediate items:
Wherein, SGMFor the correlation matrix between any active ues group and project, SMUGBy SMUAnd SUGMultiplication obtains, SMUFor item
The correlation matrix of mesh and any active ues group, SUGFor the correlation matrix of user and any active ues group；
NGMGIt obtains by the following method:
Markov transition matrix N between any active ues group and projectGMG=col_norm (SGMG), wherein col_norm
(SGMG) indicate normalized SGMG, so matrix SGMGEach column and be 1, then normalization SGMAnd SMUG, then:
Wherein, NGMGS as after normalizationGMG, NGMIndicate the probability transfer matrix from any active ues group to project,
NMUGProbability transfer matrix of the expression project to any active ues group.
As of the present invention a kind of further based on any active ues group recommending method for restarting random walk model
Prioritization scheme, the termination condition are as follows: work as λ2It is terminated when≤ε and restarts walk process immediately, ε is preset threshold value；
λ2Refer in step 3 and random walk process is restarted to the execution that iterates of each any active ues group, it is obtained
The resultful variance of institute, λ2It is calculated by following formula:
Wherein, G is any active ues group quantity, and M is the number of entry, and μ is statistical variable, is terminated since 1 to (G+M),Indicate the v of the μ nodethIt is secondary to any active ues group or project migration,(v+1) of the μ nodethIt is secondary to
Any active ues group or project migration, node are the abstract representation of any active ues group and project；
Steady probability vectorIt is obtained by following equation:
Wherein,Indicate the vector of first any active ues group,Indicate last
A object vector, for i-th of any active ues group gi, formula (1) is executed up to convergence, when formula (1) convergence, formula
(1) the result is that one about gi(G+M) × 1 vector.
As of the present invention a kind of further based on any active ues group recommending method for restarting random walk model
Prioritization scheme, the ε are 0.28.
The invention adopts the above technical scheme compared with prior art, has following technical effect that
(1) suitable group's recommendation results are provided for user: in group is recommended, since the long tail effect of user's selection is led
It causes fringe sport to be covered by popular project, is excavated including fringe sport by using random walk model is restarted, user,
Correlativity between group and project provides group's recommendation results comprising fringe sport for any active ues group.
(2) reduce group and recommend computation complexity: since number of users sharply increases in network, group recommend in user
Scale also increases with it, and replaces original group by defining any active ues group, effectively shields inactive user's bring
Consumption is calculated, in the case where guaranteeing project coverage rate, computational efficiency is improved and has saved calculating time and resource.
Detailed description of the invention
Fig. 1 is the process for excavating any active ues group.
Fig. 2 is the process for restarting random walk.
Fig. 3 is overall flow figure of the present invention.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing:
In order to illustrate group recommending method of the present invention, we provide following preferred example, detailed to elaborate
A kind of realization process based on any active ues group recommending method for restarting random walk model.
Be given below a kind of related notion based in any active ues group recommending method for restarting random walk model and
It specifically describes:
(1) groups of users: the set that the user with similar selection tendency is formed.Such as in online film comment community
Film circles.
(2) propensity value: the quantized value that user is inclined to a certain purpose is selected, different application scene quantification manner is not
Together.
(3) project coverage rate: recommender system is a kind of using between user and the content information and user items of project
Interactive information, recommend the information filtering system of suitable project to suitable user.
(4) it any active ues group: since the tendency preference of total user can sufficiently be reflected in expectation any active ues group, uses
Subset error score Err (U') indicates the tendency deviation between user's subset and total user:
Wherein avg (pj, U') and indicate user's subset U' to project pjAverage score, it is clear that Err (U') is smaller, subset U'
It more can sufficiently reflect the preference tendency of total user group.But if Cov (U') is smaller, user's subset U' cannot sufficiently be covered
All projects.Therefore, any active ues group (Active User Group, AUG) is a subset of user's set U, and size is
K, it meets two following conditions simultaneously, in the subset that all sizes of user's set U are k, has:
(5) restart random walk model: random walk (random walk) is a kind of mathematical statistical model, earliest by
Pearson is proposed.Random walk is made of a series of track, the movement of each step be all it is random, this random process can
It is indicated with Markov Chain, is moved to the transition probability that another is put from a point and is unrelated with the time.Restart random walk
(random walk with restart, RWR) model is proposed by Grady, is used for image segmentation earliest.Restarting random walk is
A kind of random walk of specific type, when next moved further will be carried out there are two types of selection: one is with certain probability according to
State-transition matrix is randomly chosen next state, and another kind is to start random walk with certain probability selection arbitrary point,
It is mainly used for the structure sexual intercourse in calculating figure between any two points.
The process of RWR is defined as:
Wherein c (0≤c≤1) is to return to probability,The unit vector for being 1 for i-th dimension,For the node of graph after normalization
Weighted adjacent matrix, j, [r when initiali,j] it is related coefficient of the node i relative to j.Then:
(6) scoring fusion: the prediction scoring or recommended project list of scoring fusion method fusion user obtains the pre- of group
Assessment point or group's recommendation list.According to user u when the fusion process that scoresxIn group giIn relative weight w (ux,gi) and use
Family uxTo project itemjPrediction score pred (ux,itemj) calculate group giTo project itemjPrediction score pred
(gi,itemj):
Specific steps are expressed as follows:
Fig. 1 is the process for excavating any active ues group, and step 1) is inclined to deviation by calculating project coverage rate and is lived
Jump groups of users, and detailed process is as follows:
Step 1.1) calculates scoring quantization matrix, in general, defining user's set U:U={ ui, 0≤i≤| U |, wherein ui
For single user and i is integer, project set P:P={ pj, 0≤j≤| P |, wherein pjFor single project and j is integer；User
Interactive information between project is quantified with rating matrix R, then is had:
R={ rij}|U|×|P|,rij≥0 (6)
Wherein, uiFor i-th of user and i is integer, pjFor j-th of project and j is integer, rijIt is the i-th of rating matrix R
The element and r of row j columnijIt is i-th of user to the interactive information score data of j-th of project, if rij=0 represents uiAnd pjNo
Interaction, i.e. uiActivity do not cover pj；
Step 1.2) calculates project coverage rate, covers collection P for the project of given the subset U', U' of user's set UU' fixed
Justice are as follows:
The project coverage rate Cov (U') of U' is the subset P of PU' ratio shared in P, it may be assumed that
Step 1.3) calculates group and is inclined to deviation, and due to expectation, inclining for total user can sufficiently be reflected in any active ues group
To preference, the tendency deviation between user's subset and total user is indicated with subset error score Err (U'):
Wherein, avg (pj, U') and indicate user's subset U' to j-th of project pjAverage score；
Step 1.4) obtains any active ues group, obtains project coverage rate according to step 1.2 and 1.3 and group is inclined to partially
Difference, any active ues group (Active User Group) are a subsets of user's set U, and the size of any active ues group is
K, the subset meet two following conditions, in the subset that all sizes of user's set U are k, have:
Fig. 2 restarts the process of random walk, and step 2) constructs the correlation probabilities matrix for enlivening group and project, specific side
Method is as follows:
Correlation matrix S is constructed firstGMG, the correlation matrix is to the related coefficient between indicating two intermediate items:
Wherein, SGMFor the correlation matrix between any active ues group and project, SMUGBy SMUAnd SUGMultiplication obtains, SMUFor item
The correlation matrix of mesh and any active ues group, SUGFor the correlation matrix of user and group；
Markov transition matrix N between any active ues group and projectGMG=col_norm (SGMG), wherein col_norm
(SGMG) indicate normalized SGMG, so matrix SGMGEach column and be 1, then normalization SGMAnd SMUG, then:
Wherein, NGMGS as after normalizationGMG, NGMIndicate the probability transfer matrix from any active ues group to project,
NMUGProbability transfer matrix of the expression project to any active ues group.
Random walk model is restarted in step 3) starting, obtains the related coefficient for enlivening group and project, the specific method is as follows:
It is general to restart random walk process and iterate execution, until reaching a stable state, Wo Menke
To restart random walk by defining termination condition termination, to obtain the accurate estimation to node of graph related coefficient.Restart with
The resultful variance of machine migration institute is calculated by following formula:
Wherein, G is any active ues group quantity, and M is the number of entry, and μ is statistical variable, is terminated since 1 to (G+M),Indicate the v of the μ nodethIt is secondary to any active ues group or project migration,(v+1) of the μ nodethIt is secondary to
Any active ues group or project migration, node are the abstract representation of any active ues group and project；
The termination condition are as follows: work as λ2It is terminated when≤ε and restarts walk process immediately, ε is preset threshold value；
In order to obtain related coefficient between any active ues group and project by restarting random walk model, we shift in application
Matrix NGMG, therefore steady probability vectorIt is obtained by following equation:
Cost and memory space, modified equation are calculated in order to save are as follows:
Wherein, g andRespectively indicate first group's any active ues to the last one project to
Amount.For each any active ues group gi, formula (15) are executed up to convergence, when formula (15) convergence, the knot of equation (15)
Fruit is one about gi(G+M) × 1 vector.Any active ues group giWith project mjBetween related coefficient it is higher, then group pair
The preference of the project is higher.
Fig. 3 gives a kind of overall flow based on any active ues group recommending method for restarting random walk model.It is false
It include 6020 users and 5763 films equipped with a film score data system, wherein containing group's letter of user
Breath, score information, scoring quantity, film and film quantity.Specific step is as follows:
Step 1: the scoring according to user to film project, constructs the scoring quantization matrix of user and project.
Step 2: project coverage rate is calculated, scoring item and project set involved in the subset by groups of users
The project coverage rate of ratio calculation user's subset.
Step 3: calculating group is inclined to deviation, by calculating average score and group of the subset groups of users to projects
Deviation is inclined to as group to the ratio of the average score of respective item.
Step 4: the project coverage rate and group's tendency deviation that are obtained according to second step and third step obtain any active ues group
Group, while the group's subset met is any active ues group.
Step 5: the correlation matrix between building any active ues group and project, is deposited to improve computational efficiency and saving
Cost is stored up, normalization is carried out to correlation matrix.
Step 6: random walk is restarted in starting.It is straight to be iterated operation to each any active ues group nodes for given threshold
To convergence.
Step 7: by the correlation coefficient for restarting any active ues group and project that obtain after random walk, it will be related
Any active ues group g is given in the degree highest preceding K film project recommendation of coefficient.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, several simple deductions or substitution can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (4)
1. a kind of based on any active ues group recommending method for restarting random walk model, which comprises the following steps:
Step 1: being inclined to deviation by calculating project coverage rate and group obtains any active ues group: will have maximal term simultaneously
The subset group of mesh coverage rate and minimum group tendency deviation is as any active ues group；
Step 2: building correlation matrix SGMG, wherein SGMGContain the correlation matrix between any active ues group and project
SGM, each any active ues group is inclined to comprising the selection to project and each any active ues group is related to each user's
Degree, and each user equally has the selection propensity value to project；Then by correlation matrix SGMGIt is regular to turn to NGMG, as
Restart the probability transfer matrix of random walk model；
Step 3: random walk model is restarted in starting, the related coefficient of any active ues group and project is obtained, with NGMGFor probability
Transfer matrix restarts random walk process to the execution that iterates of each any active ues group, passes through and defines termination condition and terminate
Restart random walk；Its steady probability matrix is calculated to each any active ues group againUntil convergence, to be enlivened
The correlation coefficient of groups of users and project finally gives the highest preceding K project recommendation of correlation coefficient to any active ues group；
The detailed process that any active ues group is obtained in step 1 is as follows:
Step 1.1 calculates scoring quantization matrix, defines user's set U:U={ ui, 0≤i≤| U |, project set P:P=
{pj, 0≤j≤| P |, the interactive information between user and project is quantified with rating matrix R, then has:
R={ rij}|U|×|P|,rij≥0
Wherein, uiFor i-th of user and i is integer, pjFor j-th of project and j is integer, rijIt is arranged for the i-th row j of rating matrix R
Element and rijIt is i-th of user to the interactive information score data of j-th of project, if rij=0 represents uiAnd pjDo not interact,
That is uiActivity do not cover pj；
Step 1.2 calculates project coverage rate, covers collection P for the project of given the subset U', U' of user's set UU'Is defined as:
The project coverage rate Cov (U') of U' is the subset P of PU'The shared ratio in P, it may be assumed that
Step 1.3 calculates group and is inclined to deviation, indicated with subset error score Err (U') user's subset and total user it
Between tendency deviation:
Wherein, avg (pj, U') and indicate user's subset U' to j-th of project pjAverage score；
Step 1.4 obtains project coverage rate and tendency deviation acquisition any active ues group, group according to step 1.2 and 1.3, active
Groups of users CUG is a subset of user's set U, and the size of any active ues group is k, which meets following two items
Part has in the subset that all sizes of user's set U are k:
Wherein, Err (CUG) indicates the tendency deviation between user's subset and total user, and minErr (CUG) is to seek all Err
(CUG) minimum value in, Cov (CUG) indicate the project coverage rate of CUG, and maxCov (CUG) is the maximum value for seeking Cov (CUG).
2. it is according to claim 1 a kind of based on any active ues group recommending method for restarting random walk model, it is special
Sign is, correlation matrix S is constructed in step 2GMGThe specific method is as follows:
Correlation matrix SGMGTo indicate the related coefficient between two intermediate items:
Wherein, SGMFor the correlation matrix between any active ues group and project, SMUGBy SMUAnd SUGMultiplication obtains, SMUFor project with
The correlation matrix of any active ues group, SUGFor the correlation matrix of user and any active ues group；
NGMGIt obtains by the following method:
Markov transition matrix N between any active ues group and projectGMG=col_norm (SGMG),
Wherein col_norm (SGMG) indicate normalized SGMG, so matrix SGMGEach column and be 1, then normalization SGMWith
SMUG, then:
Wherein, NGMGS as after normalizationGMG, NGMIndicate the probability transfer matrix from any active ues group to project, NMUGTable
Probability transfer matrix of the aspect mesh to any active ues group.
3. it is according to claim 2 a kind of based on any active ues group recommending method for restarting random walk model, it is special
Sign is, the termination condition are as follows: work as λ2It is terminated when≤ε and restarts walk process immediately, ε is preset threshold value；
λ2Refer in step 3 and random walk process restarted to the execution that iterates of each any active ues group, it is obtained all
As a result variance, λ2It is calculated by following formula:
Wherein, G is any active ues group quantity, and M is the number of entry, and μ is statistical variable, is terminated since 1 to (G+M),Table
Show the v times of the μ node to any active ues group or project migration,(v+1) of the μ node is secondary to any active ues
Group or project migration, node are the abstract representation of any active ues group and project；
Steady probability vector cgiMIt is obtained by following equation:
Wherein,Indicate the vector of first any active ues group,Indicate the last one
Object vector, for i-th of any active ues group gi, formula (1) is executed up to convergence, when formula (1) convergence, formula (1)
The result is that one about gi(G+M) × 1 vector.
4. it is according to claim 3 a kind of based on any active ues group recommending method for restarting random walk model, it is special
Sign is that the ε is 0.28.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710145033.9A CN106991133B (en) | 2017-03-13 | 2017-03-13 | It is a kind of based on any active ues group recommending method for restarting random walk model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710145033.9A CN106991133B (en) | 2017-03-13 | 2017-03-13 | It is a kind of based on any active ues group recommending method for restarting random walk model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106991133A CN106991133A (en) | 2017-07-28 |
| CN106991133B true CN106991133B (en) | 2019-08-06 |
Family
ID=59413212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710145033.9A Active CN106991133B (en) | 2017-03-13 | 2017-03-13 | It is a kind of based on any active ues group recommending method for restarting random walk model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106991133B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590243B (en) * | 2017-09-14 | 2019-09-06 | 中国人民解放军信息工程大学 | The personalized service recommendation method to be sorted based on random walk and diversity figure |
| CN110019975B (en) * | 2017-10-10 | 2020-10-16 | 创新先进技术有限公司 | Random walk, random walk method based on cluster, random walk device and equipment |
| CN109658094B (en) | 2017-10-10 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Random walk, random walk method based on cluster, random walk device and equipment |
| CN108628967B (en) * | 2018-04-23 | 2020-07-28 | 西安交通大学 | Network learning group division method based on learning generated network similarity |
| CN111209745B (en) * | 2018-11-02 | 2022-04-22 | 北京好啦科技有限公司 | Information reliability evaluation method, equipment and storage medium |
| CN111062800B (en) * | 2019-11-27 | 2023-09-08 | 同盾控股有限公司 | Data processing method, device, electronic equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101437220A (en) * | 2008-09-18 | 2009-05-20 | 广州五度信息技术有限公司 | System and method for implementing mutual comment and color bell recommendation between users |
| CN102663128A (en) * | 2012-04-24 | 2012-09-12 | 南京师范大学 | Recommending system of large-scale collaborative filtering |
| CN105677647A (en) * | 2014-11-17 | 2016-06-15 | 中国移动通信集团广东有限公司 | Individual recommend method and system |
-
2017
- 2017-03-13 CN CN201710145033.9A patent/CN106991133B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101437220A (en) * | 2008-09-18 | 2009-05-20 | 广州五度信息技术有限公司 | System and method for implementing mutual comment and color bell recommendation between users |
| CN102663128A (en) * | 2012-04-24 | 2012-09-12 | 南京师范大学 | Recommending system of large-scale collaborative filtering |
| CN105677647A (en) * | 2014-11-17 | 2016-06-15 | 中国移动通信集团广东有限公司 | Individual recommend method and system |
Non-Patent Citations (1)
| Title |
|---|
| 一种在信任网络中随机游走的推荐算法;原福永等;《现代图书情报技术》;20141031(第10期);第70-74页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106991133A (en) | 2017-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106991133B (en) | It is a kind of based on any active ues group recommending method for restarting random walk model | |
| Pham et al. | A general graph-based model for recommendation in event-based social networks | |
| CN104199896B (en) | The video similarity of feature based classification is determined and video recommendation method | |
| Kim et al. | Viscors: A visual-content recommender for the mobile web | |
| CN107688605B (en) | Cross-platform data matching process, device, computer equipment and storage medium | |
| CN106372101B (en) | A kind of video recommendation method and device | |
| CN109274987A (en) | A kind of video collection sort method, server and readable storage medium storing program for executing | |
| CN102625940A (en) | Internet preference learning facility | |
| CN111581516B (en) | Investment product recommending method and related device | |
| CN107657034A (en) | A kind of event social networks proposed algorithm of social information enhancing | |
| Jeong et al. | HGGC: A hybrid group recommendation model considering group cohesion | |
| CN109711871A (en) | A kind of potential customers determine method, apparatus, server and readable storage medium storing program for executing | |
| CN110322053A (en) | A kind of score in predicting method constructing local matrix based on figure random walk | |
| Zhao et al. | A generative model approach for geo-social group recommendation | |
| Ji et al. | STARec: Adaptive learning with spatiotemporal and activity influence for POI recommendation | |
| CN109360058A (en) | Method for pushing, device, computer equipment and storage medium based on trust network | |
| CN112989211B (en) | Method and system for determining information similarity | |
| Sitkrongwong et al. | Latent probabilistic model for context-aware recommendations | |
| CN110188123A (en) | User matching method and equipment | |
| CN112231579B (en) | Social video recommendation system and method based on implicit community discovery | |
| Hafiene et al. | A new structural and semantic approach for identifying influential nodes in social networks | |
| CN106469163A (en) | A kind of public number recommends method and system | |
| CN112507245A (en) | Social network friend recommendation method based on graph neural network | |
| CN110209704B (en) | User matching method and device | |
| CN108334645A (en) | One kind feeding back newer activity recommendation method based on graph model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170728 Assignee: NUPT INSTITUTE OF BIG DATA RESEARCH AT YANCHENG Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2020980007071 Denomination of invention: An active user group recommendation method based on restart random walk model Granted publication date: 20190806 License type: Common License Record date: 20201026 |