CN107045536A - A kind of social networks arrangement method - Google Patents
A kind of social networks arrangement method Download PDFInfo
- Publication number
- CN107045536A CN107045536A CN201710064007.3A CN201710064007A CN107045536A CN 107045536 A CN107045536 A CN 107045536A CN 201710064007 A CN201710064007 A CN 201710064007A CN 107045536 A CN107045536 A CN 107045536A
- Authority
- CN
- China
- Prior art keywords
- social
- satellite information
- arrangement method
- account number
- social networks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of social networks arrangement method, it is related to the social field in internet, is included in social platform and creates social account, a theme is distributed to each social account, according to affiliated subject categories, the relational tree set up between social account；The keyword of search for obtains associated account number in social platform, uses the satellite information of crawler capturing associated account number；The satellite information of smoothing processing associated account number, the inside ranking of each satellite information is directed to hundred-mark system standardization；For different index, the classification of satellite information and the weight of each satellite information are set；Under different index, total weight of each associated account number is calculated, ranking is carried out to associated account number according to total weight；For associated account number in the top under different index, allow interactive between social account and associated account number；According to the growth pattern of satellite information of the social account after interaction, the species and weight of dynamic adjustment satellite information.
Description
Technical field
The present invention relates to the social field in internet, more particularly to a kind of social networks arrangement method.
Background technology
In internet arena, custom is browsed based on user, is very universal technical side to specific content ranking
Method.Google discloses the matter that so-called PageRank algorithms are used to deriving and measuring webpage in its patent US6285999
Amount and importance.PageRank algorithms are a link analysis technologies, and this algorithm distributes a numerical value and is weighted to hyperlink
Document sets, such as internet, the relative importance for calculating each document in this document sets.
When carrying out ranking to the content on internet using PageRank algorithms, PageRank algorithms are inevitably not
Can accurately, be fully applied to social networks, therefore, United States Patent (USP) US9311620 discloses a kind of for social networks
Rank algorithm, it is mutual between the action of this rank algorithm monitoring social network user and at least two social network users
It is dynamic, it is determined that the result based on the action quality and social networks user content importance.But this algorithm with
Single bean vermicelli relation is the basis of influence force estimation, carries out ranking to social network user, excessively simplifies.Actual social activity
Complicated people is there is in network to content, content to content, content to people etc. by a variety of interactive means to enter
Capable association.
Therefore, those skilled in the art is directed to developing a kind of social networks arrangement method, makes full use of social networks
In each account and its content each attribute, more accurately evaluate the weight of account.
The content of the invention
In view of the drawbacks described above of prior art, the technical problems to be solved by the invention are how to improve social networks
How rank algorithm, more accurately evaluate the weight of social account.
To achieve the above object, the invention provides a kind of social networks arrangement method, comprise the following steps：
Step 1, the social account of establishment in social platform, give each social account to distribute a theme, according to institute
Belong to subject categories, the relational tree set up between social account；
Step 2, in the social platform search for the keyword of the theme to obtain associated account number, use crawler capturing
The satellite information of the associated account number；
The satellite information of associated account number described in step 3, smoothing processing, each is directed to hundred-mark system standardization
The inside ranking of the satellite information；
Step 4, for different index, the classification of satellite information and the weight of each satellite information are set；
Step 5, under different index, total weight of each associated account number is calculated, according to total weight to described
Associated account number carries out ranking；
Step 6, for associated account number in the top under the different indexes, allow the social account and the association account
It is interactive between number；
Step 7, according to the social account it is described it is interactive after the satellite information growth pattern, dynamic adjustment institute
State the species and weight of the satellite information in step 4.
Further, in step 1, the relational tree refers to the father and son that multiple social accounts belong to same big theme composition
Relation, the subdivision theme that these accounts are belonging respectively under this big theme again constitutes brotherhood.
Further, in step 2, the satellite information include bean vermicelli number, post number, forwarding number, obtain praise quantity,
Referred number of times and the number of times with the theme label.
Further, in step 2, described in increasing and decreasing or change according to different social platforms and platform development period
The species of satellite information.
Further, in step 2, the association of the associated account number includes the association of association, people and the content of person to person
And the association between content and content.
Further, in step 3, the smoothing processing is to take the logarithm.
Further, in step 4, the weight sum of each satellite information is 1.
Further, in steps of 5, the index includes the satellite information of variety classes but correlation.
Further, in step 6, it is described interactive including "@", concern, forwarding and personal letter.
Further, in step 7, the dynamic adjustment includes increase, deletes and reset weight.
Compared with existing patented technology, technical solutions according to the invention are to phases such as the accounts and content in social networks
Pass element, which has been done, more accurately to be evaluated, and is supported so as to provide effective strategy for optimization social interaction and broadcasting media；Significantly
Reduce this technology in broadcasting media cost, practical application and the other bean vermicelli user of millions is obtained with zero advertisement marketing cost；
The parameter and model of technical solutions according to the invention are that, according to substantial amounts of social networks interaction test, constantly training optimization is come
, it is not a static model.Technical solutions according to the invention are based on accurate weight evaluation, predict various social interactions
The issuable effect of behavior, so as to optimize social and broadcasting media strategy, reduces user's procurement cost.Skill of the present invention
Art scheme uses for reference neutral net deep learning method according to the result of the actual generation of social interaction behavior, and account is evaluated in dynamic adjustment
Variable and parameter in number weight method.
The technique effect of the design of the present invention, concrete structure and generation is described further below with reference to accompanying drawing, with
It is fully understood from the purpose of the present invention, feature and effect.
Brief description of the drawings
Fig. 1 is the method flow diagram of the preferred embodiment of the present invention.
Embodiment
The method of a kind of social networks ranking of the present invention, as shown in figure 1, comprising the following steps：
The first step, creates thousands of social media accounts in batches, and each account is absorbed in a subdivision theme.All microblogging accounts
Number together can be with the theme of cover extensively.Gone to find the theme for having popularity as far as possible with the method for systematization.Establish theme and
Relation between theme.All thousands of themes form a huge network together, and it is various that they have father and son, brother etc.
Relation.These account numbers collectively form account number pond one vast.
Second step, for each theme, correspondence topic keyword is searched for first in social platform, is crawled with web crawlers
As a result the various information of middle account number, including bean vermicelli quantity f (follower), quantity of posting c (content), model is forwarded number
R (repost) is measured, the number of times l (like), referred number of times m (mention), the number of times with theme label of posting praised is obtained
T (tag), V={ f, c, r, l, m, t } represent the collection of these input variables and the variable in this set is according to different social flat
Platform and platform development period increase and decrease or changed.
3rd step, logarithmetics lg (x) is carried out for each variable first, and such smoothing techniques can avoid single change
Amount difference is too big and causes its dependent variable to fail, then to carrying out ranking inside each variable, with hundred-mark system standardization,
S={ sf,sc,sr,sl,sm,stRepresent standardization result.
4th step, W={ wf,wc,wr,wl,wm,wtRepresent to correspond to the weight of input variable, w need to be metf+wc+wr+wl+wm+
wt=1, its initial value can rule of thumb be set, constantly these ginsengs of dynamic adjusting and optimizing during subsequent tune ginseng
Number.
5th step, T=f*wf+c*wc+r*wr+l*wl+m*wm+t*wtThe total weight of account is represented, an account number is evaluated
Weight can carry out from different perspectives, such as the influence index of account number, interest index etc., the power of each variable of different index
It can be very different again, such as bean vermicelli quantity f, hop count r, like time l that influence index is valued, and interest index is then
The quantity c that posts more is valued, with theme label number of times t.According to different indexes, we take rejecting some and the index not phase
Close or the low parameter of the degree of correlation, setting calculates the power under different index with the method such as the high variable minimum value of correlation of indices degree
Reset name.
6th step, for n account number before under different index ranking, we using in the account number pond of first step foundation with theme
Corresponding account number takes different interactive tactics.The high account number of such as influence index is usually famous person star, and we can turn
Simultaneously '@' these account numbers are sent out, cause the concern of these account numbers, forwarding or '@' that these account numbers may be obtained in the future are big to obtain
The bean vermicelli of amount.And for the higher account number of interest index, we can directly pay attention in and send a common attentinal contents
Personal letter directly to obtain the concern of other side.
7th step, after taking these interactive tactics, examines our account number bean vermicelli quantity growth rate after a while,
The 4th step is fed back using bean vermicelli growth rate as output, then the parameter of dynamic the 4th step of adjustment circulates the 4th step
To the 7th step, optimization is constantly adjusted to parameter.
In practical application, this technology, with zero advertisement marketing cost, is successfully more than 3000 Twitter theme accounts not
Develop in the times of 2 years accumulative more than 12,000,000 beans vermicelli.
Preferred embodiment of the invention described in detail above.It should be appreciated that the ordinary skill of this area is without wound
The property made work just can make many modifications and variations according to the design of the present invention.Therefore, all technical staff in the art
Pass through the available technology of logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Scheme, all should be in the protection domain being defined in the patent claims.
Claims (10)
1. a kind of social networks arrangement method, it is characterised in that comprise the following steps：
Step 1, the social account of establishment in social platform, give each social account to distribute a theme, according to institute owner
Classification is inscribed, the relational tree set up between social account；
Step 2, in the social platform search for the keyword of the theme to obtain associated account number, using described in crawler capturing
The satellite information of associated account number；
The satellite information of associated account number described in step 3, smoothing processing, with hundred-mark system standardization for described in each
The inside ranking of satellite information；
Step 4, for different index, the classification of satellite information and the weight of each satellite information are set；
Step 5, under different index, total weight of each associated account number is calculated, according to total weight to the association
Account carries out ranking；
Step 6, for associated account number in the top under the different indexes, allow the social account and the associated account number it
Between it is interactive；
Step 7, according to the social account it is described it is interactive after the satellite information growth pattern, the dynamic adjustment step
The species and weight of the satellite information in rapid 4.
2. social networks arrangement method as claimed in claim 1, it is characterised in that in step 1, the relational tree refers to multiple
Social account belongs to the set membership that same big theme is constituted, and these accounts are belonging respectively to the subdivision master under this big theme again
Topic constitutes brotherhood.
3. social networks arrangement method as claimed in claim 1, it is characterised in that in step 2, the satellite information includes
Quantity, referred number of times and the number of times with the theme label that bean vermicelli number, number of posting, forwarding number, acquisition are praised.
4. social networks arrangement method as claimed in claim 1, it is characterised in that in step 2, according to different social platforms
And the platform development period increases and decreases or changed the species of the satellite information.
5. social networks arrangement method as claimed in claim 1, it is characterised in that in step 2, the pass of the associated account number
Join the association between the association for including association, people and the content of person to person and content and content.
6. social networks arrangement method as claimed in claim 1, it is characterised in that in step 3, the smoothing processing is to take
Logarithm.
7. social networks arrangement method as claimed in claim 1, it is characterised in that in step 4, each described attached letter
The weight sum of breath is 1.
8. social networks arrangement method as claimed in claim 1, it is characterised in that in steps of 5, the index includes difference
The satellite information of species but correlation.
9. social networks arrangement method as claimed in claim 1, it is characterised in that in step 6, it is described it is interactive include "@",
Concern, forwarding and personal letter.
10. social networks arrangement method as claimed in claim 1, it is characterised in that in step 7, the dynamic adjustment bag
Increase is included, delete and resets weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710064007.3A CN107045536A (en) | 2017-02-04 | 2017-02-04 | A kind of social networks arrangement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710064007.3A CN107045536A (en) | 2017-02-04 | 2017-02-04 | A kind of social networks arrangement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107045536A true CN107045536A (en) | 2017-08-15 |
Family
ID=59543311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710064007.3A Pending CN107045536A (en) | 2017-02-04 | 2017-02-04 | A kind of social networks arrangement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107045536A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009056A (en) * | 2019-04-15 | 2019-07-12 | 秒针信息技术有限公司 | A kind of classification method and sorter of social activity account |
| CN113055485A (en) * | 2021-03-19 | 2021-06-29 | 展讯半导体(南京)有限公司 | Remote control method and system, electronic device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016825A (en) * | 2007-08-17 | 2011-04-13 | 谷歌公司 | Ranking social network objects |
| CN105117422A (en) * | 2015-07-30 | 2015-12-02 | 中国传媒大学 | Intelligent social network recommender system |
| CN105723402A (en) * | 2013-10-25 | 2016-06-29 | 西斯摩斯公司 | Systems and methods for determining influencers in a social data network |
| CN105740366A (en) * | 2016-01-26 | 2016-07-06 | 哈尔滨工业大学深圳研究生院 | Inference method and device of MicroBlog user interests |
| CN105787025A (en) * | 2016-02-24 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Network platform public account classifying method and device |
| US20170286535A1 (en) * | 2013-09-05 | 2017-10-05 | TSG Technologies, LLC | Systems and methods for identifying issues in electronic documents |
-
2017
- 2017-02-04 CN CN201710064007.3A patent/CN107045536A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016825A (en) * | 2007-08-17 | 2011-04-13 | 谷歌公司 | Ranking social network objects |
| US20170286535A1 (en) * | 2013-09-05 | 2017-10-05 | TSG Technologies, LLC | Systems and methods for identifying issues in electronic documents |
| CN105723402A (en) * | 2013-10-25 | 2016-06-29 | 西斯摩斯公司 | Systems and methods for determining influencers in a social data network |
| CN105117422A (en) * | 2015-07-30 | 2015-12-02 | 中国传媒大学 | Intelligent social network recommender system |
| CN105740366A (en) * | 2016-01-26 | 2016-07-06 | 哈尔滨工业大学深圳研究生院 | Inference method and device of MicroBlog user interests |
| CN105787025A (en) * | 2016-02-24 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Network platform public account classifying method and device |
Non-Patent Citations (2)
| Title |
|---|
| 刘海峰: "社交网络用户交互模型及行为偏好预测研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 黄斯琪: "基于微博平台的社交网络舆情分析方法", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009056A (en) * | 2019-04-15 | 2019-07-12 | 秒针信息技术有限公司 | A kind of classification method and sorter of social activity account |
| CN110009056B (en) * | 2019-04-15 | 2021-07-30 | 秒针信息技术有限公司 | Method and device for classifying social account numbers |
| CN113055485A (en) * | 2021-03-19 | 2021-06-29 | 展讯半导体(南京)有限公司 | Remote control method and system, electronic device and storage medium |
| CN113055485B (en) * | 2021-03-19 | 2023-09-22 | 展讯半导体(南京)有限公司 | Remote control method and system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Reddy et al. | Content-based movie recommendation system using genre correlation | |
| Feng et al. | Personalized recommendations based on time-weighted overlapping community detection | |
| CN108509551B (en) | Microblog network key user mining system and method based on Spark environment | |
| CN102789462B (en) | A kind of item recommendation method and system | |
| CN109241440A (en) | It is a kind of based on deep learning towards implicit feedback recommended method | |
| CN109785062B (en) | A Hybrid Neural Network Recommendation System Based on Collaborative Filtering Model | |
| Yu et al. | Effect of infrastructure design on commons dilemmas in social− ecological system dynamics | |
| CN112487291B (en) | Big data-based personalized news recommendation method and device | |
| CN107103000A (en) | It is a kind of based on correlation rule and the integrated recommended technology of Bayesian network | |
| CN106407349A (en) | Product recommendation method and device | |
| CN108108380A (en) | Search ordering method, searching order device, searching method and searcher | |
| CN110399563A (en) | A kind of preference pattern and customized information active recommended method based on user behavior analysis | |
| CN107391582B (en) | Information recommendation method based on context ontology tree to calculate user preference similarity | |
| CN106484829A (en) | A kind of foundation of microblogging order models and microblogging diversity search method | |
| CN105678590A (en) | topN recommendation method for social network based on cloud model | |
| CN120338924A (en) | Knowledge graph construction and product recommendation method and system based on user data | |
| CN106960044A (en) | A kind of Time Perception personalization POI based on tensor resolution and Weighted H ITS recommends method | |
| CN108984555A (en) | User Status is excavated and information recommendation method, device and equipment | |
| CN107123055A (en) | A kind of social big data information maximization method based on PageRank | |
| Srisawatsakul et al. | Tourism recommender system using machine learning based on user's public instagram photos | |
| CN104123321B (en) | A kind of determining method and device for recommending picture | |
| CN107045536A (en) | A kind of social networks arrangement method | |
| Hoang et al. | Academic event recommendation based on research similarity and exploring interaction between authors | |
| CN116861078A (en) | A graph neural network recommendation method that integrates multiple user behaviors | |
| CN108491477B (en) | Neural network recommendation method based on multi-dimensional cloud and user dynamic interest |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20201030 |
|
| AD01 | Patent right deemed abandoned |