CN105894254A - Social recommendation system based on degree distribution and user rating - Google Patents
Social recommendation system based on degree distribution and user rating Download PDFInfo
- Publication number
- CN105894254A CN105894254A CN201610488068.8A CN201610488068A CN105894254A CN 105894254 A CN105894254 A CN 105894254A CN 201610488068 A CN201610488068 A CN 201610488068A CN 105894254 A CN105894254 A CN 105894254A
- Authority
- CN
- China
- Prior art keywords
- user
- degrees
- social
- scoring
- recommendation system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- 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
-
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention provides a social recommendation system based on degree distribution and user rating. The system is characterized by comprising the following steps of: (I) calculating the degrees of all current users of a social network; (II) finding all pairs of users not friends now according to preset conditions, and entering all selected pairs of users in a recommendation candidate table; and (III) recommending friends based on the degree of any user.
Description
Technical field
The present invention relates to social recommendation system, particularly relate to a kind of based on the number of degrees distribution with user scoring
Social recommendation system.
Background technology
In existing commending system, such as Amazon, Taobao etc. is to use the business bought according to user
Product label recommends similar commodity to user, and user then has certain probability to pay a return visit this businessman
And the sales volume that improves businessman with this and visit capacity.But this way of recommendation is the most accurate,
Consumer's Experience is not fine yet.
In order to solve this problem, there is researcher to it is also proposed use social networks itself in recent years and had
Some information carries out commodity or friend recommendation.User more can be confident that the people close with oneself interest
Selection made.The most so-called activity is similar with social trust.Have many based on this aspect
The social recommendation system of design.Use the commending system with social information that recommendation can be made to become more
Accurate user is also more prone to accept.
" the social network friend recommendation system trusted based on moving phase Sihe social activity and method " (application number:
CN201410462802.4) following scheme of the invention is proposed: utilize user social contact trust value and activity preference
Similarity realizes based on friend recommendation in the social networks of position, owing to activity can embody user interest
Preference, therefore passes through the good friend that between user, movable similarities discovery is similar to its preference;Owing to social activity is believed
Appoint and can reflect mutual tightness degree between user, therefore carry out friend recommendation according to trusting relationship in various degree
There is more reasonably interpretability.Have employed user social contact trust value and activity preference similarity.Increase
Effectiveness during friend recommendation also carries out friend recommendation to trusting relationship in various degree and has more reasonably
Interpretability.The method is suitable for for tradition social networks, but in similar Yelp and popular comment etc.
In the social recommendation system that commodity are combined with friend recommendation, if simply making can not make in this way
The diffuser efficiency of social networks self.
Summary of the invention
The present invention is carried out to solve the problems referred to above, it is therefore intended that provide one to reduce social network
When hitting of network, the one of the propagation efficiency optimizing whole social networks is commented with user based on number of degrees distribution
The social recommendation system divided.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, has this
The feature of sample, comprises the following steps:
Step one, calculates the number of degrees of all users of current social networks;
Step 2, finds out all a pair users being currently not good friend according to predetermined condition, selects
All in user is listed a recommended candidate table;And
Step 3, number of degrees size based on any one user carries out the recommendation of good friend.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature: wherein, the number of degrees are the quantity of good friend.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature: wherein, predetermined condition is that a pair user carried out comment and commented same businessman
Split-phase is same.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature: wherein, number of degrees size is the number of good friend.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature, comprises the following steps:
Step zero, arranges a minimum number of degrees parameter alpha and needs the number of times EdgeNum recommended.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature: wherein, parameter alpha is that the overall number of degrees distribution according to social networks is arranged.
A kind of social recommendation system marked with user based on number of degrees distribution that the present invention provides, also has
Such feature: wherein, number of times EdgeNum is to arrange according to system requirements.
Invention effect and effect
According to involved in the present invention a kind of based on the number of degrees distribution with user scoring social recommendation system,
Consider when hitting of network entirety while carrying out friend recommendation, thus ensure with moving phase Sihe social
Trust and carry out friend recommendation, the most largely reduce when hitting of social networks, optimize whole social network
The propagation efficiency of network;Businessman can quickly put out a new product, and user also is able to receive as early as possible new commodity
Information;First user's similarity and activity preference similarity are navigated to that same businessman is had phase
With scoring on, and find out all of can recommended case;On this basis, when recommending
Consider good friend's quantity of user, in the case of the number recommended is limited, pay the utmost attention to good friend fewer in number
User;This can make the number of degrees distribution of whole social networks more averagely, and the channel of diffusion of information is more
It is many, so that the propagation efficiency of social networks increases.
Accompanying drawing explanation
Fig. 1 is a kind of based on number of degrees distribution with user's scoring the social recommendation system in the embodiment of the present invention
The flow chart of system.
Detailed description of the invention
Referring to the drawings and embodiment to one involved in the present invention based on the number of degrees distribution comment with user
The social recommendation system divided is explained in detail.
Embodiment
Fig. 1 is a kind of based on number of degrees distribution with user's scoring the social recommendation system in the embodiment of the present invention
The flow chart of system.
As it is shown in figure 1, a kind of social recommendation system based on number of degrees distribution with user's scoring has following
Step:
Step zero: a minimum number of degrees parameter alpha is set and needs the number of times EdgeNum (net recommended
The required limit number increased of network), enter step one.Parameter alpha is that the overall number of degrees according to social networks divide
Cloth is arranged, and number of times EdgeNum is to arrange according to system requirements.
Step one: calculate the number of degrees (quantity of good friend) of all users of current social networks, enters step
Rapid two.
Step 2: find out all a pair users being currently not good friend according to predetermined condition, enters step
Rapid three.Predetermined condition is that a pair user carried out comment and marked identical same businessman.
Travel through all of businessman finding out these businessmans were carried out the ID of user of comment and they
Scoring.All for same businessman k carry out commenting on and mark identical two user vi with
Vj selects, and puts into recommended candidate table L<vi, vj>in.When all of businessman all travel through complete after,
The preparatory stage of whole commending system completes.
Step 3, number of degrees size based on any one user (number of good friend) carries out pushing away of good friend
Recommend.
From recommended candidate table L<vi, vj>in select a pair user<vi, vj>randomly.And to user vi
The number of degrees judge, if meeting degree (vi)≤α,<vi, vj>as a new limit
Join in this social networks, namely carried out a friend recommendation.Otherwise, constantly select
Select until finding qualified<vi, vj>.The number of times set at the beginning is met when needing the number of times recommended
EdgeNum or when the most there is not the limit meeting condition degree (vi)≤α inside table L,
This recommendation terminates.
The present invention takes into full account the two indices evaluating a social recommendation systematic function: user level
Difference value and when hitting of whole social networks aspect (Hitting time).Because using social activity
When commending system is to user's Recommendations or good friend, the structure of whole social networks can change,
So change when hitting can be brought, this change also brings whole social networks to propagate expanding efficiency
Change, therefore, it must also be noted that network structure while using social recommendation system to recommend
Change and it needs to the scope that accounts for when hitting of network.Present invention solves the technical problem that and be
When hitting of network entirety is considered, it is ensured that trust with moving phase Sihe social activity while carrying out friend recommendation
Carry out friend recommendation, reduce when hitting of social networks, optimize the propagation efficiency of whole social networks.
The effect of embodiment and effect
According to social recommendation system based on number of degrees distribution with user's scoring a kind of involved by the present embodiment,
While carrying out friend recommendation, consider when hitting of network entirety, thus ensure with moving phase Sihe society
Hand over trust to carry out friend recommendation, the most largely reduce when hitting of social networks, optimize whole social activity
The propagation efficiency of network;Businessman can quickly put out a new product, and user also is able to receive new business as early as possible
The information of product;First user's similarity and activity preference similarity are navigated to same businessman is had
In identical scoring, and find out all of can recommended case;On this basis, recommend
Time consider user good friend's quantity, recommend number limited in the case of pay the utmost attention to good friend's number relatively
Few user;This can make the number of degrees distribution of whole social networks more averagely, the channel of diffusion of information
It is more, so that the propagation efficiency of social networks increases.
Above-mentioned embodiment is the preferred case of the present invention, is not intended to limit protection scope of the present invention.
Claims (7)
1. one kind based on the number of degrees distribution with user scoring social recommendation system, it is characterised in that include with
Lower step:
Step one, calculates the number of degrees of all users of current social networks;
Step 2, finds out user described in all be currently not good friend a pair according to predetermined condition,
That selects all lists a recommended candidate table in described user;And
Step 3, number of degrees size based on any one of user carries out the recommendation of described good friend.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 1
System, it is characterised in that:
Wherein, the described number of degrees are the quantity of described good friend.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 1
System, it is characterised in that:
Wherein, described predetermined condition is that user described in a pair carried out comment and commented same businessman
Split-phase is same.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 1
System, it is characterised in that:
Wherein, described number of degrees size is the number of described good friend.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 1
System, it is characterised in that further comprising the steps of:
Step zero, arranges a minimum number of degrees parameter alpha and needs the number of times EdgeNum recommended.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 5
System, it is characterised in that:
Wherein, described parameter alpha is that the distribution of the described number of degrees of the entirety according to social networks is arranged.
A kind of social recommendation system based on number of degrees distribution with user's scoring the most according to claim 5
System, it is characterised in that:
Wherein, described number of times EdgeNum is to arrange according to system requirements.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610488068.8A CN105894254A (en) | 2016-06-28 | 2016-06-28 | Social recommendation system based on degree distribution and user rating |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610488068.8A CN105894254A (en) | 2016-06-28 | 2016-06-28 | Social recommendation system based on degree distribution and user rating |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105894254A true CN105894254A (en) | 2016-08-24 |
Family
ID=56718379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610488068.8A Pending CN105894254A (en) | 2016-06-28 | 2016-06-28 | Social recommendation system based on degree distribution and user rating |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105894254A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110740088A (en) * | 2018-07-19 | 2020-01-31 | 上海掌门科技有限公司 | Method, device, terminal and medium for recommending and adding social resources |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102495864A (en) * | 2011-11-25 | 2012-06-13 | 清华大学 | Collaborative filtering recommending method and system based on grading |
CN104268171A (en) * | 2014-09-11 | 2015-01-07 | 东北大学 | Activity similarity and social trust based social networking website friend recommendation system and method |
CN104615775A (en) * | 2015-02-26 | 2015-05-13 | 北京奇艺世纪科技有限公司 | User recommendation method and device |
CN104850579A (en) * | 2015-03-20 | 2015-08-19 | 南京邮电大学 | Food and beverage recommendation algorithm based on rating and feature similarity in social network |
-
2016
- 2016-06-28 CN CN201610488068.8A patent/CN105894254A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102495864A (en) * | 2011-11-25 | 2012-06-13 | 清华大学 | Collaborative filtering recommending method and system based on grading |
CN104268171A (en) * | 2014-09-11 | 2015-01-07 | 东北大学 | Activity similarity and social trust based social networking website friend recommendation system and method |
CN104615775A (en) * | 2015-02-26 | 2015-05-13 | 北京奇艺世纪科技有限公司 | User recommendation method and device |
CN104850579A (en) * | 2015-03-20 | 2015-08-19 | 南京邮电大学 | Food and beverage recommendation algorithm based on rating and feature similarity in social network |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110740088A (en) * | 2018-07-19 | 2020-01-31 | 上海掌门科技有限公司 | Method, device, terminal and medium for recommending and adding social resources |
CN110740088B (en) * | 2018-07-19 | 2023-06-23 | 上海掌门科技有限公司 | Method, device, terminal and medium for recommending and adding social resources |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10529004B2 (en) | Systems and methods for generating location-based group recommendations | |
CN103514204B (en) | Information recommendation method and device | |
CN108197330B (en) | Data digging method and device based on social platform | |
CN103455515B (en) | User recommendation method and system in SNS (social networking services) community | |
WO2020037931A1 (en) | Item recommendation method and apparatus, computer device and storage medium | |
US11113731B2 (en) | Systems and methods for customer valuation and merchant bidding | |
RU2617921C2 (en) | Category path recognition method and system | |
CN106960044B (en) | Time perception personalized POI recommendation method based on tensor decomposition and weighted HITS | |
CN109118336A (en) | Information recommendation method, device, computer equipment and storage medium | |
US20130097182A1 (en) | Method for calculating distances between users in a social graph | |
US20130110835A1 (en) | Method for calculating proximities between nodes in multiple social graphs | |
CN105373619B (en) | A kind of user group's analysis method and system based on user's big data | |
CN103150667B (en) | A kind of personalized recommendation method based on body construction | |
CN110110244A (en) | A kind of point of interest recommended method merging multi-source information | |
CN110335123A (en) | Method of Commodity Recommendation, system, computer-readable medium and device based on social electric business platform | |
CN107092609A (en) | A kind of information-pushing method and device | |
CN107220334A (en) | Similarity calculating method, device and the equipment of name of firm | |
CN109284449A (en) | The recommended method and device of point of interest | |
CN107256224B (en) | A kind of generation method of the element structure of knowledge, searching method, apparatus and system | |
CN107506488A (en) | A kind of intelligent music commending system | |
CN105119743B (en) | Acquisition method of user behavior intention and apparatus | |
CN105894254A (en) | Social recommendation system based on degree distribution and user rating | |
CN112069416B (en) | Cross-social network user identity recognition method based on community discovery | |
Fang et al. | Trip recommendation with multiple user constraints by integrating point-of-interests and travel packages | |
Mahdian et al. | Algorithmic cartography: Placing points of interest and ads on maps |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160824 |
|
RJ01 | Rejection of invention patent application after publication |