CN106909637A - The influence power analysis method and system of wechat public number - Google Patents

The influence power analysis method and system of wechat public number Download PDF

Info

Publication number
CN106909637A
CN106909637A CN201710079050.7A CN201710079050A CN106909637A CN 106909637 A CN106909637 A CN 106909637A CN 201710079050 A CN201710079050 A CN 201710079050A CN 106909637 A CN106909637 A CN 106909637A
Authority
CN
China
Prior art keywords
article
wechat public
public number
account
thumb
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
Application number
CN201710079050.7A
Other languages
Chinese (zh)
Inventor
刘春阳
张旭
李雄
王萌
梁汝锋
张成壮
王松
刘巨安
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Blue Ebizal Network Technology Co Ltd
National Computer Network and Information Security Management Center
Original Assignee
Beijing Blue Ebizal Network Technology Co Ltd
National Computer Network and Information Security Management Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Blue Ebizal Network Technology Co Ltd, National Computer Network and Information Security Management Center filed Critical Beijing Blue Ebizal Network Technology Co Ltd
Priority to CN201710079050.7A priority Critical patent/CN106909637A/en
Publication of CN106909637A publication Critical patent/CN106909637A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a kind of influence power analysis method of wechat public number, comprise the following steps:Every reading number α of article in the m article issued in setting time under step one, a certain wechat public number of collectioniWith thumb up number βi, and calculate the conversion ratio k=readings sum/thumb up sum for reading number and thumb up number;Step 2, when certain reading number of article is 100000+ under wechat public number, using αx=k* βxIt is calculated the reading number of article, wherein αxFor piece article reads number, βxIt is article thumb up number, single article is set and reads number 1 × 107It is the upper limit;Step 3, the influence power weight that wechat public number is calculated according to equation below:η is the authoritative weight of wechat public number;The analysis of the influence power for the management released news to wechat public number and to wechat public number.The invention also discloses a kind of influence power analysis system of wechat public number.The present invention dramatically saves on cost of labor, increase substantially the analysis efficiency of public number influence power.

Description

The influence power analysis method and system of wechat public number
Technical field
The invention belongs to computer information technology field, more particularly to a kind of influence power analysis method of wechat public number and System.
Background technology
With the fast development and the popularization of intelligent mobile client of internet communication, the social software such as wechat into It is one of modern's communication exchange and the Main Means for obtaining information.Because wechat has huge user group, wechat is public Many numbers have become the Important Platform that numerous media and individual release news, and this also causes wechat public number in news information service Communication sphere and social event Information Communication proliferation turn into that influence power is maximum, one of most potential media.
At home, the traditional media such as People's Daily, Sohu, Tengxun, Netease and large-scale portal website all register the corresponding public Number, information is regularly published, these accounts release news, and authority is strong, and public credibility is high, by substantial amounts of forwarding, to information and event Propagation have very big impetus.But also it is no lack of some and some information is issued by wechat public number from media, it is rapid to pass Broadcast, continuing fermentation, finally as the major issue for making a strong impact.
The management and the influence power of public number that current supervision department releases news to wechat public number are analyzed mainly by people Work is completed.In the big data epoch that information index increases, there is obvious office obtaining the influence power of public number in this way It is sex-limited.This mode of operation there is a problem of as follows:
1. efficiency is low:Artificial operation is fully relied on, it is artificial to search and the reading needs regular hour.
2. accuracy rate is low:Artificial speed of searching is slow, and the scope for covering is small, and information is not comprehensive.
3. cannot quantify:Cannot judge that a public number specifically has great influence power, qualitatively can only faintly draw The size of its influence power.
4. cannot lateral comparison:The influence power size of the influence power and other public numbers that cannot weigh certain public number is closed System, it is impossible to give people accurate intuitively comparing result.
The content of the invention
It is an object of the invention to solve at least the above and/or defect, and provide at least will be described later excellent Point.
In view of this, it is a still further object of the present invention to provide a kind of influence power analysis method of wechat public number.
A further object of the present invention is to provide a kind of influence power analysis system of wechat public number;Purpose is to replace people Work is operated, and helps supervision department rapidly, accurately to obtain the influence power of the quantization of a certain wechat public number.
Therefore, the technical scheme that the present invention is provided is:
A kind of influence power analysis method of wechat public number, comprises the following steps:
Every reading number of article in the m article issued in setting time under step one, a certain wechat public number of collection αiWith thumb up number βi, and calculate the conversion ratio k=readings sum/thumb up sum for reading number and thumb up number;
Step 2, when certain reading number of article is 100000+ under the wechat public number, using αx=k* βxCalculate To the reading number of this article, wherein αxFor this article reads number, βxIt is this article thumb up number, single article reading number 1 of setting × 107It is the upper limit;
Step 3, the influence power weight that the wechat public number is calculated according to equation below:
Wherein, η is the authoritative weight of the wechat public number, sets the authoritative weight η of the official media of State-level It is 1, the other official media's authority weight η of provincial, and municipal level is 0.8, and the authoritative weight η of other accounts is 0.6;
The analysis of the influence power for the management released news to wechat public number and to the wechat public number.
Preferably, in the influence power analysis method of described wechat public number, in the step one, a certain wechat is gathered Every reading number α of article in the m article issued in setting time under public numberiWith thumb up number βiSpecific method include:
(1) wechat public number account is gathered:It is acquired for wechat public number account, if collection gets new wechat Public number account, is stored in account information storehouse;
(2) wechat public number article information is gathered:Wechat public number information is gathered comprehensively, Real-time Collection wechat is public The many numbers all of history articles announced, record all specifying informations for returning;
(3) judge whether memory database has stored text
The wechat public number article specifying information of collection is parsed, and is assigned each unique ID of one, article, profit It is compared with unique ID and the article ID of storage in memory database of new collection article, if the ID is existing, shows this article Chapter is acquired to be incorporated to storehouse, if the ID does not exist, shows that this article is not yet stored in text database;
(4) wechat public number article is stored in text database
Judged by memory database, if text information is not stored in text database, together with this article only One ID is together stored in text database;
(5) update and gathered article reading number and thumb up number
The all issue articles under each wechat public number account are extracted from text database, this article is obtained from internet The reading number and thumb up number of chapter, reading number and thumb up number to article are updated and are stored in text database;
(6) all articles in the range of particular account number setting time are extracted
The all texts in the range of the setting time of influence power wechat public account to be measured are extracted using Text Feature Extraction device Chapter;
(7) the corresponding account information of text message is extracted
For all articles that cluster is screened, every the reading number and thumb up number of article are extracted.
Preferably, in the influence power analysis method of described wechat public number, in step (1) and (2), climbed using network Worm algorithm obtains wechat public number account and wechat public number article information respectively.
Preferably, in the influence power analysis method of described wechat public number, in step (3), by wechat public number account Number ID, issuing time and exercise question as this article described unique ID.
Preferably, in the influence power analysis method of described wechat public number, in the step one, the setting time It is 100 days.
A kind of influence power analysis system of wechat public number, including:
Wechat public number account acquisition module, it is used to gather wechat public number account specifying information, and stores;
Wechat public number article acquisition module, its all article for being used to capture wechat public number are parsed to article, Every unique ID of one, article is assigned, and is stored;
Gather article and read number thumb up number update module, it has been used to extract every article under each wechat public number, Collection each the reading number and thumb up number of article, update each the reading number and thumb up number of article, then store;
Wechat public number influence power analysis module, its wechat public number for obtaining influence power to be calculated first, then from institute All articles that issue in account setting time section is extracted in wechat public number article acquisition module are stated, has been gathered using described Article reads number thumb up number update module and gets each the reading number and thumb up number of article, finally using all of the account The influence power for reading number and the thumb up number weighted calculation wechat public number account of article, is stored in the wechat public number account and adopts Collection module wherein, the wechat public number influence power analysis module be stored with claim 1 the step of.
Preferably, in the influence power analysis system of described wechat public number, the wechat public number account gathers mould Block includes:
Wechat public number harvester, it, using web crawlers algorithm, is obtained using the keyword being previously set from internet Take wechat public number specifying information;
Account memory database, it is used to store wechat public number account ID;
Account is sentenced refitting and is put, the data in the wechat public number account that it will be collected and the account memory database Compare, it is determined that whether the wechat public number for collecting is new account;
Account information storehouse, its specifying information for being used to store wechat public number account, the weight for wechat public number is true It is fixed.
Preferably, in the influence power analysis system of described wechat public number, the wechat public number article acquisition mould Block:
Wechat article acquisition device, it utilizes web crawlers algorithm, obtains the article of all wechat public number issues;
Content text extraction element, it is used to parse wechat article specifying information, obtains unique ID and the content text of article This;
Text memory database, its unique ID for being used to store the article for having gathered and being put in storage;
Content text is sentenced refitting and is put, and it is used to judge the article for gathering, and determines whether this article is acquired simultaneously It is stored in text database;
Text database, it is used to store freshly harvested wechat public number article data.
Preferably, in the influence power analysis system of described wechat public number, the article that gathered reads number thumb up Number update module includes;
Wechat public number storage device, it is connected with account information storehouse communication, travels through the account information storehouse, one by one Extract the wechat public number account in the account information storehouse;
Wechat public number Text Feature Extraction device, it is connected with text database communication, from the text database Extract all articles of a certain wechat public number account issue;
Text reading thumb up number harvester, it utilizes web crawlers algorithm to gather wechat public number article, and parsing is obtained The reading number and thumb up number of this article are taken, as the master data of wechat public number influence power analytical calculation.
Preferably, in the influence power analysis system of described wechat public number, the wechat public number influence power analysis Module includes:
Text reading thumb up number extraction element, it is used to obtain every the reading number and thumb up number of article, to calculate wechat Public number account influence power;
Account influence power computing device, it is added using the reading number and thumb up number of wechat public number to be measured issue article Power is calculated, to obtain the influence power of the wechat public number.
The present invention at least includes following beneficial effect:
1st, the various information issued using computer-automatic collection wechat public number, can be obtained comprehensively within a short period of time Wechat public number article data, for next step carry out public number influence power analysis accurate data basis are provided.
2nd, according to the method for present invention design, read number using the article of collection and thumb up number is weighted, so that The influence power for being quantified.
3rd, it is weighted according to the method for the present invention, is greatly saved cost of labor, increases substantially public number influence The analysis efficiency of power.So as to improve the operating efficiency and accuracy rate of supervision department.
Further advantage of the invention, target and feature embody part by following explanation, and part will also be by this The research and practice of invention and be understood by the person skilled in the art.
Brief description of the drawings
Fig. 1 is the functional structure chart of wechat public number influence power analysis system in one of embodiment of the invention;
Fig. 2 is middle public number influence power analysis system flow chart in one of embodiment of the invention;
Fig. 3 is wechat public number influence power analysis system wechat public number account collection in one of embodiment of the invention Module account data flow graph;
Fig. 4 is the data of wechat public number influence power analysis system article acquisition module in one of embodiment of the invention Flow graph;
Fig. 5 is that wechat public number influence power analysis system text reading number thumb up number is more in one of embodiment of the invention The DFD of new module;
Fig. 6 is wechat public number influence power analysis system wechat public number influence power point in one of embodiment of the invention Analyse the DFD of module.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings, to make those skilled in the art with reference to specification text Word can be implemented according to this.
It should be appreciated that it is used herein such as " have ", "comprising" and " including " term do not allot one or many The presence or addition of individual other elements or its combination.
Some specific wechat public numbers are monitored present invention is mainly applied to public sentiment supervision department, according to its influence power It is analyzed and supervises, safeguards the healthy and orderly of public opinion environment, and then ensure the long-term stability of society.
As shown in figs. 1 to 6, the present invention provides a kind of influence power analysis method of wechat public number, comprises the following steps:
Every reading number of article in the m article issued in setting time under step one, a certain wechat public number of collection αiWith thumb up number βi, and calculate the conversion ratio k=readings sum/thumb up sum for reading number and thumb up number;
Step 2, when certain reading number of article is 100000+ under the wechat public number, using αx=k* βxCalculate To the reading number of this article, wherein αxFor this article reads number, βxIt is this article thumb up number, single article reading number 1 of setting × 107It is the upper limit;
Step 3, the influence power weight that the wechat public number is calculated according to equation below:
Wherein, η is the authoritative weight of the wechat public number, sets the authoritative weight η of the official media of State-level It is 1, the other official media's authority weight η of provincial, and municipal level is 0.8, and the authoritative weight η of other accounts is 0.6;
The analysis of the influence power for the management released news to wechat public number and to the wechat public number.
In one of embodiment of the invention, preferably, in the influence power analysis method of the wechat public number, institute In stating step one, every reading number α of article in m article of issue is gathered under a certain wechat public number in setting timeiWith Thumb up number βiSpecific method include:
(1)S61:Collection wechat public number account:Be acquired for wechat public number account, if collection get it is new Wechat public number account, is stored in account information storehouse;
(2)S62:Collection wechat public number article information:Wechat public number information is gathered comprehensively, Real-time Collection is micro- The all of history article that letter public number is announced, records all specifying informations for returning;
(3)S63:Judge whether memory database has stored text
The wechat public number article specifying information of collection is parsed, and is assigned each unique ID of one, article, profit It is compared with unique ID and the article ID of storage in memory database of new collection article, if the ID is existing, shows this article Chapter is acquired to be incorporated to storehouse, if the ID does not exist, shows that this article is not yet stored in text database;
(4)S64:Wechat public number article is stored in text database
Judged by memory database, if text information is not stored in text database, together with this article only One ID is together stored in text database;
(5)S65:Renewal has gathered article and has read number and thumb up number
The all issue articles under each wechat public number account are extracted from text database, this article is obtained from internet The reading number and thumb up number of chapter, reading number and thumb up number to article are updated and are stored in text database;
(6)S66:Extract all articles in the range of particular account number setting time
The all texts in the range of the setting time of influence power wechat public account to be measured are extracted using Text Feature Extraction device Chapter;
(7)S67:Extract the corresponding account information of text message
For all articles that cluster is screened, every the reading number and thumb up number of article are extracted.
In such scheme, preferably, in the influence power analysis method of the wechat public number, in step (1) and (2), Wechat public number account and wechat public number article information are obtained respectively using web crawlers algorithm.
In one of embodiment of the invention, preferably, in the influence power analysis method of the wechat public number, step Suddenly in (3), using wechat public number account ID, issuing time and exercise question as this article described unique ID.
In one of embodiment of the invention, preferably, in the influence power analysis method of the wechat public number, institute State in step one, the setting time is 100 days.
As shown in figure 1, the present invention also provides a kind of influence power analysis system of wechat public number, including:
Wechat public number account acquisition module, it is used to gather wechat public number account specifying information, and stores;
Wechat public number article acquisition module, its all article for being used to capture wechat public number are parsed to article, Every unique ID of one, article is assigned, and is stored;
Gather article and read number thumb up number update module, it has been used to extract every article under each wechat public number, Collection each the reading number and thumb up number of article, update each the reading number and thumb up number of article, then store;
Wechat public number influence power analysis module, its wechat public number for obtaining influence power to be calculated first, then from institute All articles that issue in account setting time section is extracted in wechat public number article acquisition module are stated, has been gathered using described Article reads number thumb up number update module and gets each the reading number and thumb up number of article, finally using all of the account The influence power for reading number and the thumb up number weighted calculation wechat public number account of article, is stored in the wechat public number account and adopts Collection module wherein, the wechat public number influence power analysis module be stored with claim 1 the step of.
In one of embodiment of the invention, preferably, in the influence power analysis system of the wechat public number, institute Stating wechat public number account acquisition module includes:
Wechat public number harvester 101, it utilizes the keyword being previously set, using web crawlers algorithm, from interconnection Net obtains wechat public number specifying information;
Account memory database 103, it is used to store wechat public number account ID;
Account sentences refitting and puts 102, in the wechat public number account that it will be collected and the account memory database Data are compared, it is determined that whether the wechat public number for collecting is new account;
Account information storehouse 104, its specifying information for being used to store wechat public number account, for the weight of wechat public number It is determined that.
In one of embodiment of the invention, preferably, in the influence power analysis system of the wechat public number, institute State wechat public number article acquisition module:
Wechat article acquisition device 201, it utilizes web crawlers algorithm, obtains the article of all wechat public number issues;
Content text extraction element 201, it is used to parse wechat article specifying information, obtains unique ID and content of article Text;
Text memory database 204, its unique ID for being used to store the article for having gathered and being put in storage;
Content text sentences refitting and puts 203, and it is used to judge the article for gathering, and determines whether this article is acquired And it is stored in text database;
Text database 205, it is used to store freshly harvested wechat public number article data.
In one of embodiment of the invention, preferably, in the influence power analysis system of the wechat public number, institute State gathered article read number thumb up number update module include;
Wechat public number storage device 301, it is connected with account information storehouse communication, travels through the account information storehouse, The wechat public number account in the account information storehouse is extracted one by one;
Wechat public number Text Feature Extraction device 302, it is connected with text database communication, from the text database The middle all articles for extracting a certain wechat public number account issue;
Text reading thumb up number harvester 303, it utilizes web crawlers algorithm to gather wechat public number article, and parses The reading number and thumb up number of this article are obtained, as the master data of wechat public number influence power analytical calculation.
In one of embodiment of the invention, preferably, in the influence power analysis system of the wechat public number, institute Stating wechat public number influence power analysis module includes:
Text reading thumb up number extraction element 401, it is used to obtain every the reading number and thumb up number of article, micro- to calculate Letter public number account influence power;
Account influence power computing device 402, it is entered using the reading number and thumb up number of wechat public number to be measured issue article Row weighted calculation, to obtain the influence power of the wechat public number.
To make those skilled in the art more fully understand the present invention, following examples are now provided and are illustrated.
Embodiment 1
As shown in figure 1, Fig. 1 represents the functional structure chart of wechat public number influence power analysis system for outline.It is of the invention System mainly includes wechat public number account acquisition module, wechat public number article acquisition module, has gathered article and read reading point Praise four parts of several update modules and wechat public number influence power analysis module.
1. wechat public number account acquisition module, using existing web crawlers algorithm, captures according to keyword from network The information of wechat public number, carries out the specifying information that parsing obtains account (including micro-signal, account name, authentication information etc.).Profit Compared with existing information in memory database with the uniqueness of micro-signal and sentence weight, if not existing the account in memory database Number, then the account is new account, is added to memory database to carry out sentencing weight later, while being stored in account information storehouse.
2. wechat public number article acquisition module:Using existing web crawlers algorithm, all of wechat public number are captured Article, the article for gathering by after HTML dissection process, setting up content text unit, is then sentenced by memory database Operate again, if content text is not held in text database, carry out in-stockroom operation, and the text is recorded in memory database ID is used to sentence weight, and the text data of storage gives over to and carries out various data analyses.
3. gather article and read number thumb up number update module:Traversal account information storehouse first, for each account, from Each article under the account is extracted in text database, readding for each article is gathered using number thumb up number harvester is read Reading and thumb up number, update the reading number and thumb up number of this article, are then stored in text database.
4. wechat public number influence power analysis module:This module obtains the wechat public number of influence power to be calculated first, so The all articles issued in the special time period of the account are extracted from text database afterwards, is obtained using text reading number thumb up number Take device and extract each the reading number and thumb up number of article, finally using the account all articles reading number and thumb up number The influence power of the weighted calculation account, is stored in account information storehouse.
Embodiment 2
As shown in Fig. 2 Fig. 2 is public number influence power analysis system flow chart in specific implementation process.The part is by many Individual thread is completed jointly, and wechat public number account collecting thread and article acquisition thread run without interruption, and wechat are included at any time public Many numbers, it is ensured that the high real-time of information data, the influence power analysis idiographic flow of wechat public number is as follows:
(1)S61:Collection wechat public number account
Using existing universal network crawler algorithm, it is acquired for public number account, if collection gets new account, Account information storehouse is stored in, other links is remained and is used.
(2)S62:Collection wechat public number article information
Using general web crawlers algorithm, wechat public number information is gathered comprehensively, the Real-time Collection wechat public Number all of history article, records all specifying informations for returning, as initial data, to carry out deep dissection process.
(3)S63:Memory database judges whether text has stored
The wechat public number article specifying information of collection is parsed, using its account ID, issuing time and exercise question as Unique ID of this article.It is compared using unique ID and the article ID of storage in memory database of new collection article, if should ID is existing, shows that this article is acquired and is incorporated to storehouse, if the ID does not exist, shows that this article is not yet stored in text database.
(4)S64:Public number article is stored in text database
Judged by memory database, if text information is not stored in text database, together with this article only One ID is together stored in text database, convenient to be inquired about and read later.
(5)S65:Update article and read number and thumb up number
The all issue articles under each account are extracted from text database, the reading number of this article is obtained from internet With thumb up number, reading number and thumb up number to article are updated and are stored in text database.
(6)S66:Extract all articles in the range of particular account number setting time
The all articles in the range of the setting time of influence power account to be measured are extracted using Text Feature Extraction device, this algorithm sets It is set to all articles in nearly 100 days.
(7)S67:Extract the corresponding account information of text message
For all articles that cluster is screened, every the reading number and thumb up number of article are extracted, influenceed using account Power statistic algorithm (see algorithmic descriptions 1.) is weighted for the account, obtains the influence power of the account.
Embodiment 3
As shown in figure 3, Fig. 3 is wechat public number account acquisition module account data flow graph, including the collection of wechat public number Device 101, account sentences refitting and puts 102, account memory database 103, account information storehouse 104.
Wechat public number harvester 101 using the keyword that is previously set, using general web crawlers algorithm, from mutual Networking obtains public number specifying information.
Account sentences refitting and puts the 102 wechat public number accounts that will be collected and compared with the data in memory database It is right, it is determined that whether what is collected is new account.
Account memory database 103 is used to store the wechat public number account ID for having gathered, using the uniqueness of account ID Can the account that collected be carried out sentencing weight, if existing in memory database, to have gathered account;If in memory database Do not exist, be then new account to be put in storage.
Account information storehouse 104 is used to store specifying information (such as log-on message, public number brief introduction of wechat public number account Deng), can be used for weight determination of wechat public number etc..
As shown in figure 4, Fig. 4 is the DFD of wechat public number article acquisition module in implementation process, including wechat text Chapter harvester 201, content text extraction element 202, content text sentence refitting put 203, memory database 204 (storage adopted Collection article ID), text database 205 (storage all wechat text datas).
Wechat article acquisition device 201 uses existing web crawlers algorithm in this part, obtains all public number issues Wechat article.
Content text extraction element 202 is used to parse wechat article specifying information, obtains the ID and content text of article.
Content text sentences refitting and puts 203 for judging the article for gathering, and determines whether this article is acquired simultaneously It is stored in text database.
The ID of the article that memory database 204 (record has gathered the ID of article) has been gathered and be put in storage for storage, is easy to Freshly harvested article is carried out to judge whether to repeat, shows article acquired storage if ID is present, if ID does not exist showing It is that freshly harvested wechat article is not put in storage.
Text database 205 is used to store freshly harvested wechat public number article data, is ensuing data analysis, text Chapter cluster provides most basic original material.
Embodiment 5
As shown in figure 5, Fig. 5 is the data of wechat public number text reading number thumb up number update module in specific implementation process Flow graph, part traversal public number account information storehouse, updates the reading number and thumb up number of all articles under each account, including Wechat public number storage device 301, public number article extraction element 302, article reads thumb up number harvester 303, account letter Breath storehouse 104, text database 205.
The traversal account information of wechat public number storage device 301 storehouse, extracts the wechat public number in account information storehouse one by one Account.
Public number article extraction element 302 can extract all articles of a certain account issue from text database.
Article reads thumb up number harvester 303 using existing universal network crawler algorithm collection wechat public number text Chapter, and the reading number and thumb up number for obtaining this article are parsed, as the master data of wechat public number influence power analytical calculation.
Account information storehouse 104 is used to store all wechat public number account specifying informations for having gathered.
Text database 205 is used to store whole wechat text messages of collection.
Embodiment 6
As shown in fig. 6, Fig. 6 is the DFD of wechat public number influence power analysis module in implementation process, including wechat Public number storage device 301, account Text Feature Extraction device 302, text database 204, text reading thumb up number extraction element 401st, account influence power computing device 402, account information storehouse 104.
Wechat public number storage device 301 is responsible for storage wechat public number to be measured.
Account Text Feature Extraction device 302 can extract what is issued in any public number special time period from text database Whole articles.
Text reading thumb up number extraction element 401 can obtain every the reading number and thumb up number of article, to be used for counting Calculate wechat public number account influence power.
Account influence power computing device 402 is added using the reading number and thumb up number of wechat public number to be measured issue article Power is calculated, to obtain the influence power of the wechat public number.
Embodiment 7
Algorithmic descriptions are 1.:
Effect:Calculate the propagating influence of particular account number.
Citing:First, all articles of timing uninterrupted sampling read number and thumb up numbers, and calculate and read number and thumb up number Conversion ratio k=reads sum/thumb up sum.Assuming that certain account is XXXX, its has issued m article in nearly 100 days altogether, and it reads number It is and thumb up number respectively α1, α2, α3... αmAnd β1, β2, β3... βm.If the official media of State-level, its authority power Weight η is set to 1;The other official media's authority weight η of provincial, and municipal level is set to 0.8;The authoritative weight η of other accounts is 0.6. Every the reading number and thumb up number of article in nearly 100 days of the account are counted, when certain the reading number of article is 100000+, profit Use αx=k* βxThe approximate reading number for obtaining this article, wherein αxFor single article reads number, βxIt is this article thumb up number, sets Single article reads number 1 × 107It is the upper limit.The influence power weight approximate representation of certain account is:
Treatment scale described herein is for simplifying explanation of the invention.Influence to wechat public number of the invention Power analysis method and systematic difference, modifications and variations will be readily apparent to persons skilled in the art.
The present invention greatly saves labour turnover, and increases substantially the analysis efficiency of public number influence power, instead of artificial Operation, helps supervision department rapidly, accurately to obtain the influence power of the quantization of a certain wechat public number.
Although embodiment of the present invention is disclosed as above, it is not restricted to listed in specification and implementation method With, it can be applied to various suitable the field of the invention completely, for those skilled in the art, can be easily Other modification is realized, therefore under the universal limited without departing substantially from claim and equivalency range, the present invention is not limited In specific details and shown here as the legend with description.

Claims (10)

1. a kind of influence power analysis method of wechat public number, it is characterised in that comprise the following steps:
Every reading number α of article in the m article issued in setting time under step one, a certain wechat public number of collectioniAnd point Praise several βi, and calculate the conversion ratio k=readings sum/thumb up sum for reading number and thumb up number;
Step 2, when certain reading number of article is 100000+ under the wechat public number, using αx=k* βxIt is calculated this The reading number of article, wherein αxFor this article reads number, βxIt is this article thumb up number, single article is set and reads number 1 × 107 It is the upper limit;
Step 3, the influence power weight that the wechat public number is calculated according to equation below:
λ = η * Σ i = 1 m x + k * β i 2 × 10 9 ,
Wherein, η is the authoritative weight of the wechat public number, and the authoritative weight η for setting the official media of State-level is 1, The other official media's authority weight η of provincial, and municipal level is 0.8, and the authoritative weight η of other accounts is 0.6;
The analysis of the influence power for the management released news to wechat public number and to the wechat public number.
2. the influence power analysis method of wechat public number as claimed in claim 1, it is characterised in that in the step one, adopt Collect under a certain wechat public number in setting time every reading number α of article in m article of issueiWith thumb up number βiIt is specific Method includes:
(1) wechat public number account is gathered:It is acquired for wechat public number account, if collection gets the new wechat public Number account, is stored in account information storehouse;
(2) wechat public number article information is gathered:Wechat public number information is gathered comprehensively, Real-time Collection wechat public number The all of history article announced, records all specifying informations for returning;
(3) judge whether memory database has stored text
The wechat public number article specifying information of collection is parsed, and is assigned each unique ID of one, article, using new The unique ID and the article ID of storage in memory database for gathering article are compared, if the ID is existing, show this article It is acquired and be put in storage, if the ID does not exist, show that this article is not yet stored in text database;
(4) wechat public number article is stored in text database
Judged by memory database, if text information is not stored in text database, together with the unique ID of this article Together it is stored in text database;
(5) update and gathered article reading number and thumb up number
The all issue articles under each wechat public number account are extracted from text database, this article is obtained from internet Number and thumb up number are read, reading number and thumb up number to article are updated and are stored in text database;
(6) all articles in the range of particular account number setting time are extracted
The all articles in the range of the setting time of influence power wechat public account to be measured are extracted using Text Feature Extraction device;
(7) the corresponding account information of text message is extracted
For all articles that cluster is screened, every the reading number and thumb up number of article are extracted.
3. the influence power analysis method of wechat public number as claimed in claim 2, it is characterised in that in step (1) and (2), Wechat public number account and wechat public number article information are obtained respectively using web crawlers algorithm.
4. the influence power analysis method of wechat public number as claimed in claim 2, it is characterised in that in step (3), by wechat Public number account ID, issuing time and exercise question as this article described unique ID.
5. the influence power analysis method of wechat public number as claimed in claim 1, it is characterised in that in the step one, institute Setting time is stated for 100 days.
6. a kind of influence power analysis system of wechat public number, it is characterised in that including:
Wechat public number account acquisition module, it is used to gather wechat public number account specifying information, and stores;
Wechat public number article acquisition module, its all article for being used to capture wechat public number are parsed to article, are assigned Every unique ID of one, article, and store;
Gather article and read number thumb up number update module, it has been used to extract every article under each wechat public number, collection Each the reading number and thumb up number of article, update each the reading number and thumb up number of article, then store;
Wechat public number influence power analysis module, its wechat public number for obtaining influence power to be calculated first, then from described micro- All articles of issue in account setting time section are extracted in letter public number article acquisition module, article has been gathered using described Read number thumb up number update module and get each the reading number and thumb up number of article, finally using all articles of the account The influence power for reading number and the thumb up number weighted calculation wechat public number account, be stored in the wechat public number account collection mould Block wherein, the wechat public number influence power analysis module be stored with claim 1 the step of.
7. the influence power analysis system of wechat public number as claimed in claim 6, it is characterised in that the wechat public number account Number acquisition module includes:
Wechat public number harvester, it, using web crawlers algorithm, obtains micro- using the keyword being previously set from internet Letter public number specifying information;
Account memory database, it is used to store wechat public number account ID;
Account is sentenced refitting and is put, and the wechat public number account that it will be collected is carried out with the data in the account memory database Compare, it is determined that whether the wechat public number for collecting is new account;
Account information storehouse, its specifying information for being used to store wechat public number account, the weight for wechat public number determines.
8. the influence power analysis system of wechat public number as claimed in claim 7, it is characterised in that the wechat public number text Chapter acquisition module:
Wechat article acquisition device, it utilizes web crawlers algorithm, obtains the article of all wechat public number issues;
Content text extraction element, it is used to parse wechat article specifying information, obtains unique ID and content text of article;
Text memory database, its unique ID for being used to store the article for having gathered and being put in storage;
Content text is sentenced refitting and is put, and it is used to judge the article for gathering, and determines whether this article is acquired and is stored in Text database;
Text database, it is used to store freshly harvested wechat public number article data.
9. the influence power analysis system of wechat public number as claimed in claim 8, it is characterised in that the article that gathered is read Reading thumb up number update module includes;
Wechat public number storage device, it is connected with account information storehouse communication, travels through the account information storehouse, extracts one by one Wechat public number account in the account information storehouse;
Wechat public number Text Feature Extraction device, it is connected with text database communication, is extracted from the text database All articles of a certain wechat public number account issue;
Text reading thumb up number harvester, its utilize web crawlers algorithm gather wechat public number article, and parse acquisition should The reading number and thumb up number of article, as the master data of wechat public number influence power analytical calculation.
10. the influence power analysis system of wechat public number as claimed in claim 9, it is characterised in that the wechat public number Influence power analysis module includes:
Text reading thumb up number extraction element, it is used to obtain every the reading number and thumb up number of article, to calculate the wechat public Number account influence power;
Account influence power computing device, it is weighted meter using the reading number and thumb up number of wechat public number to be measured issue article Calculate, to obtain the influence power of the wechat public number.
CN201710079050.7A 2017-02-14 2017-02-14 The influence power analysis method and system of wechat public number Pending CN106909637A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710079050.7A CN106909637A (en) 2017-02-14 2017-02-14 The influence power analysis method and system of wechat public number

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710079050.7A CN106909637A (en) 2017-02-14 2017-02-14 The influence power analysis method and system of wechat public number

Publications (1)

Publication Number Publication Date
CN106909637A true CN106909637A (en) 2017-06-30

Family

ID=59208167

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710079050.7A Pending CN106909637A (en) 2017-02-14 2017-02-14 The influence power analysis method and system of wechat public number

Country Status (1)

Country Link
CN (1) CN106909637A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107480297A (en) * 2017-08-30 2017-12-15 福建中金在线信息科技有限公司 A kind of article recording method and device
CN108335008A (en) * 2017-12-13 2018-07-27 腾讯科技(深圳)有限公司 Web information processing method and device, storage medium and electronic device
CN109086289A (en) * 2018-06-07 2018-12-25 杜泽壮 A kind of media data processing method, client, medium and equipment
CN109213924A (en) * 2017-07-07 2019-01-15 腾讯科技(深圳)有限公司 Promote method for allocating tasks, device and computer equipment
CN109614542A (en) * 2018-12-11 2019-04-12 平安科技(深圳)有限公司 Public platform recommended method, device, computer equipment and storage medium
CN110019780A (en) * 2017-09-15 2019-07-16 腾讯科技(深圳)有限公司 Method, the method for information processing and the relevant apparatus of text information sequence
CN110362728A (en) * 2019-06-19 2019-10-22 深圳壹账通智能科技有限公司 Information-pushing method, device, equipment and storage medium based on big data analysis
CN111931060A (en) * 2020-08-25 2020-11-13 腾讯科技(深圳)有限公司 Method for evaluating influence of publishing platform, related device and computer storage medium
CN113139124A (en) * 2021-04-16 2021-07-20 厦门飞博共创网络科技股份有限公司 Method and terminal for autonomously analyzing self-media content based on internet user interest
CN113220823A (en) * 2020-01-21 2021-08-06 北京中科闻歌科技股份有限公司 Sentiment, topic and viewpoint analysis method for social media public language
CN113409073A (en) * 2021-05-30 2021-09-17 咸宁方片互娱网络有限公司 Method and system for optimizing reading number of article

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105320740A (en) * 2015-09-22 2016-02-10 清华大学 WeChat article and official account acquisition method and acquisition system
CN106355507A (en) * 2016-09-05 2017-01-25 北京蓝色光标品牌管理顾问股份有限公司 Official account activity level ranking method and ranking system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105320740A (en) * 2015-09-22 2016-02-10 清华大学 WeChat article and official account acquisition method and acquisition system
CN106355507A (en) * 2016-09-05 2017-01-25 北京蓝色光标品牌管理顾问股份有限公司 Official account activity level ranking method and ranking system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘彬: "健康类微信公众号影响力优化规则探析"", 《中国传媒大学学报 (自然科学版)》 *
吴霖: "分布式微信公众平台爬虫系统的研究与应用", 《信息科技辑》 *
颜月明等: "一种微信公众号影响力的评估方法", 《情报杂志》 *
骏君: "《微信营销方法1+2+3 大咖教你玩转朋友圈、微信群、公众号》", 30 September 2016 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109213924A (en) * 2017-07-07 2019-01-15 腾讯科技(深圳)有限公司 Promote method for allocating tasks, device and computer equipment
CN109213924B (en) * 2017-07-07 2023-01-03 腾讯科技(深圳)有限公司 Popularization task allocation method and device and computer equipment
CN107480297A (en) * 2017-08-30 2017-12-15 福建中金在线信息科技有限公司 A kind of article recording method and device
CN110019780A (en) * 2017-09-15 2019-07-16 腾讯科技(深圳)有限公司 Method, the method for information processing and the relevant apparatus of text information sequence
CN108335008A (en) * 2017-12-13 2018-07-27 腾讯科技(深圳)有限公司 Web information processing method and device, storage medium and electronic device
CN109086289A (en) * 2018-06-07 2018-12-25 杜泽壮 A kind of media data processing method, client, medium and equipment
CN109614542A (en) * 2018-12-11 2019-04-12 平安科技(深圳)有限公司 Public platform recommended method, device, computer equipment and storage medium
CN109614542B (en) * 2018-12-11 2024-05-14 平安科技(深圳)有限公司 Public number recommendation method, device, computer equipment and storage medium
WO2020253364A1 (en) * 2019-06-19 2020-12-24 深圳壹账通智能科技有限公司 Big data analytics-based information pushing method, apparatus, and device, and storage medium
CN110362728A (en) * 2019-06-19 2019-10-22 深圳壹账通智能科技有限公司 Information-pushing method, device, equipment and storage medium based on big data analysis
CN113220823A (en) * 2020-01-21 2021-08-06 北京中科闻歌科技股份有限公司 Sentiment, topic and viewpoint analysis method for social media public language
CN113220823B (en) * 2020-01-21 2024-03-01 北京中科闻歌科技股份有限公司 Method and device for analyzing emotion, topic and viewpoint of social media public language
CN111931060A (en) * 2020-08-25 2020-11-13 腾讯科技(深圳)有限公司 Method for evaluating influence of publishing platform, related device and computer storage medium
CN111931060B (en) * 2020-08-25 2023-11-03 腾讯科技(深圳)有限公司 Evaluation method of influence of release platform, related device and computer storage medium
CN113139124A (en) * 2021-04-16 2021-07-20 厦门飞博共创网络科技股份有限公司 Method and terminal for autonomously analyzing self-media content based on internet user interest
CN113139124B (en) * 2021-04-16 2022-07-19 厦门飞博共创网络科技股份有限公司 Method and terminal for autonomously analyzing self-media content based on internet user interest
CN113409073A (en) * 2021-05-30 2021-09-17 咸宁方片互娱网络有限公司 Method and system for optimizing reading number of article

Similar Documents

Publication Publication Date Title
CN106909637A (en) The influence power analysis method and system of wechat public number
CN110610767B (en) Morbidity monitoring method, device, equipment and storage medium
Zhou et al. Real-time news cer tification system on sina weibo
CN102779190B (en) Rapid detection method for hot issues of timing sequence massive network news
CN102426610B (en) Microblog rank searching method and microblog searching engine
CN103577581B (en) Agricultural product price trend forecasting method
CN107577688A (en) Original article influence power analysis system based on media information collection
CN102567407B (en) Method and system for collecting forum reply increment
CN106021508A (en) Sudden event emergency information mining method based on social media
CN103647676B (en) Domain name system data processing method
CN103268350A (en) Internet public opinion information monitoring system and monitoring method
CN102955813B (en) A kind of information search method and system
CN103077190A (en) Hot event ranking method based on order learning technology
CN103177076A (en) Public sentiment monitoring system and method based on fixed point websites
CN109165273A (en) General Chinese address matching method facing big data environment
CN103309960A (en) Method and device for extracting multidimensional information of network public sentiment event
CN105975609A (en) Industrial design product intelligent recommendation method and system
CN101609445A (en) Crucial sub-method for extracting topic based on temporal information
JP2013061756A (en) Information processing system, information processing method, program, and information storage medium
CN104809252A (en) Internet data extraction system
Erhan et al. Analyzing objective and subjective data in social sciences: Implications for smart cities
CN115293723A (en) Network public opinion heat analysis system based on big data analysis
CN112632218A (en) Network public opinion monitoring method for enterprise crisis public customs
CN103914534B (en) Content of text sorting technique based on specialist system URL classification knowledge base
CN107845042A (en) Supervisory systems is imposed in house in a kind of state-owned land

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170630

RJ01 Rejection of invention patent application after publication