CN109829165A - One kind is from media article Valuation Method and system - Google Patents
One kind is from media article Valuation Method and system Download PDFInfo
- Publication number
- CN109829165A CN109829165A CN201910110338.5A CN201910110338A CN109829165A CN 109829165 A CN109829165 A CN 109829165A CN 201910110338 A CN201910110338 A CN 201910110338A CN 109829165 A CN109829165 A CN 109829165A
- Authority
- CN
- China
- Prior art keywords
- media article
- content
- keyword
- value
- article
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses one kind from media article Valuation Method and system.Its method is the following steps are included: extract from media article content keyword;Calculate the sensitivity coefficient from media article;Calculate content keyword authenticity reference value;It calculates and scores from the value of media article.Method and system of the invention solve and cannot assess the technical issues of being worth from media article.
Description
Technical field
The invention belongs to instant messaging fields, from media article Valuation Method and are more particularly to one kind
System.
Background technique
From Media Era, is not audited, can arbitrarily be issued from media article, cause to be flooded with low value on network
Article of pouring water or title party article, waste the reading time of people.Need a kind of technology that can be assessed and be worth from media article
Scheme proposes a kind of from media article Valuation Method and system thus.
Summary of the invention
The technical problem to be solved by the present invention is to which the problem of being worth from media article cannot be assessed, propose a kind of from media
Article Valuation Method and system.
The present invention relies on instant communication software system, and the instant communication software system, which refers to have from media article, to be issued
The app or webpage of function or any one of small routine.Method and system of the present invention can be applied to instant communication software
In background system or third party software, for being assessed or sorted from media article or screened or marked.
It is of the invention from media article Valuation Method, comprising the following steps:
It extracting from media article content keyword: identifying the content keyword from media article, keyword quantity is denoted as N,
Content keyword is numbered, i, 1≤i≤N are denoted as;The weighted value of set content keyword, is denoted as pi。
It calculates the sensitivity coefficient from media article: calculating from media article content keyword and high sensitivity set in advance
The degree of correlation for spending topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m.
The high sensitive topic refers to any one or multinomial combination of topical news hot topic or hot microblog topic.
The degree of correlation from media article content keyword and high sensitive topic set in advance refers to from media
Keyword ratio relevant to high sensitive topic, is denoted as v in article content keyword;The sensibility system from media article
Number m=gv, wherein g is that sensitivity coefficient set in advance calculates reference value.
Calculate content keyword authenticity reference value: search to from the relevant article data of media article content keyword,
The content authenticated in identification article data according to the content authenticated and should calculate content pass from the similarity degree of media article
The authenticity reference value a of keywordi。
The content authenticated refers to it is verified that the content issued for true interior perhaps official;It is described to have authenticated
Content with should refer to from the similarity degree of media article from the similar key ratio of media article and authentication content, be denoted as
bi;The authenticity reference value a of the content keywordi=sbi, wherein s is authenticity design factor set in advance.
Calculate and score from the value of media article: according to from media article sensitivity coefficient m, content keyword it is true
Property reference value aiWith weighted value piCalculate the value assessment value x from media article.
The value assessment value from media articleWherein k is value set in advance
Assessed value design factor.
It is of the invention from media article valve estimating system, characterized by comprising:
One or more processors;
Memory;
And
One or more programs wherein one or more of programs are stored in the memory, and are configured
It is executed at by one or more of processors, described program includes:
It extracts from media article content keyword module: identifying the content keyword from media article, keyword quantity note
For N, content keyword is numbered, is denoted as i, 1≤i≤N;The weighted value of set content keyword, is denoted as pi。
It calculates the sensitivity coefficient module from media article: calculating from media article content keyword and height set in advance
The degree of correlation of susceptibility topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m.
The high sensitive topic refers to any one or multinomial combination of topical news hot topic or hot microblog topic.
The degree of correlation from media article content keyword and high sensitive topic set in advance refers to from media
Keyword ratio relevant to high sensitive topic, is denoted as v in article content keyword;The sensibility system from media article
Number m=gv, wherein g is that sensitivity coefficient set in advance calculates reference value.
Calculate content keyword authenticity reference value module: search to from the relevant article number of media article content keyword
According to the content authenticated in identification article data according to the content authenticated and is somebody's turn to do from the similarity degree calculating of media article
Hold the authenticity reference value a of keywordi。
The content authenticated refers to it is verified that the content issued for true interior perhaps official;It is described to have authenticated
Content with should refer to from the similarity degree of media article from the similar key ratio of media article and authentication content, be denoted as
bi;The authenticity reference value a of the content keywordi=sbi, wherein s is authenticity design factor set in advance.
It calculates from the value grading module of media article: according to sensitivity coefficient m, the content keyword from media article
Authenticity reference value aiWith weighted value piCalculate the value assessment value x from media article.
The value assessment value from media articleWherein k is value set in advance
Assessed value design factor.
Method and system of the invention have the advantage, that
(1) by identification from the sensibility and authenticity of media article, the value from media article is effectively assessed.
(2) it assesses from the value of media article, low-quality is provided from media article to eliminate or avoiding to read
Foundation.
Detailed description of the invention
Fig. 1 is the embodiment of the present invention from media article Valuation Method flow chart;
Fig. 2 is the embodiment of the present invention from media article valve estimating system structural schematic diagram.
Specific embodiment
It elaborates below to the preferred embodiment of the present invention.
The present invention relies on instant communication software system, and the instant communication software system refers to chat conversations function
Any one of app or webpage or small routine.The present embodiment is directed to certain instant communication software such as wechat, to its public platform or subscription
Number assessed from media article, wechat system background to after being assessed from media article mark value assessment value.
The present embodiment from media article Valuation Method, realize as follows:
It extracting from media article content keyword: identifying the content keyword from media article, keyword quantity is denoted as N,
Content keyword is numbered, i, 1≤i≤N are denoted as;The weighted value of set content keyword, is denoted as pi.In the present embodiment,
Certain moment wechat system background receive certain public platform from media article, this article is identified according to existing semantics recognition algorithm
Content keyword be that content keyword is numbered in " block chain ", " merchant XX " and " investment ", N=3, be denoted as i;According to interior
The weighted value for holding the influence degree set content keyword of keyword meaning stated to article is respectively p1=0.5, p2=0.3,
p3=0.2.
It calculates the sensitivity coefficient from media article: calculating from media article content keyword and high sensitivity set in advance
The degree of correlation for spending topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m.
The high sensitive topic refers to any one or multinomial combination of topical news hot topic or hot microblog topic.
The degree of correlation from media article content keyword and high sensitive topic set in advance refers to from media
Keyword ratio relevant to high sensitive topic, is denoted as v in article content keyword;The sensibility system from media article
Number m=gv, wherein g is that sensitivity coefficient set in advance calculates reference value.In the present embodiment, current high sensitive topic is
Topical news hot topic and hot microblog topic, wherein " block chain ", " merchant XX " they are the topic that current microblogging heat is searched on list,
The degree of correlation v=2/3=0.67 from media article content keyword and high sensitive topic set in advance is then calculated, in advance
The sensitivity coefficient of setting calculates reference value g=1, then calculates sensitivity coefficient m=gv=1 × 0.67 from media article
=0.67.
Calculate content keyword authenticity reference value: search to from the relevant article data of media article content keyword,
The content authenticated in identification article data according to the content authenticated and should calculate content pass from the similarity degree of media article
The authenticity reference value a of keywordi。
The content authenticated refers to it is verified that the content issued for true interior perhaps official;It is described to have authenticated
Content with should refer to from the similarity degree of media article from the similar key ratio of media article and authentication content, be denoted as
bi;The authenticity reference value a of the content keywordi=sbi, wherein s is authenticity design factor set in advance.This reality
Apply in example, search with from the relevant article data of media article content keyword, it is related to " block chain ", " go into business XX ", " investment "
The publication of article Zhong Junyou official content (i.e. authentication content), calculate the phase that content is issued from media article and each official
Like keyword ratio b1=1, b2=1, b3=0.2;Authenticity design factor s=1 set in advance, then calculate content keyword
Authenticity reference value a1=sb1=1 × 1=1, a2=sb2=1 × 1=1, a3=sb3=1 × 0.2=0.2.
Calculate and score from the value of media article: according to from media article sensitivity coefficient m, content keyword it is true
Property reference value aiWith weighted value piCalculate the value assessment value x from media article.
The value assessment value from media articleMiddle k is that value set in advance is commented
Valuation design factor.In the present embodiment, value assessment value design factor k=1 set in advance calculates the value from media article
Assessed value
The present embodiment from media article Valuation Method flow chart, as shown in Figure 1.
The present embodiment from media article valve estimating system, characterized by comprising:
One or more processors;
Memory;
And
One or more programs wherein one or more of programs are stored in the memory, and are configured
It is executed at by one or more of processors, described program includes:
It extracts from media article content keyword module: identifying the content keyword from media article, keyword quantity note
For N, content keyword is numbered, is denoted as i, 1≤i≤N;The weighted value of set content keyword, is denoted as pi.The present embodiment
In, certain moment wechat system background receive certain public platform from media article, should according to the identification of existing semantics recognition algorithm
The content keyword of article is " block chain ", content keyword is numbered in " merchant XX " and " investment ", N=3, is denoted as i;Root
Weighted value according to the influence degree set content keyword of content keyword meaning stated to article is respectively p1=0.5, p2=
0.3, p3=0.2.
It calculates the sensitivity coefficient module from media article: calculating from media article content keyword and height set in advance
The degree of correlation of susceptibility topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m.
The high sensitive topic refers to any one or multinomial combination of topical news hot topic or hot microblog topic.
The degree of correlation from media article content keyword and high sensitive topic set in advance refers to from media
Keyword ratio relevant to high sensitive topic, is denoted as v in article content keyword;The sensibility system from media article
Number m=gv, wherein g is that sensitivity coefficient set in advance calculates reference value.In the present embodiment, current high sensitive topic is
Topical news hot topic and hot microblog topic, wherein " block chain ", " merchant XX " they are the topic that current microblogging heat is searched on list,
The degree of correlation v=2/3=0.67 from media article content keyword and high sensitive topic set in advance is then calculated, in advance
The sensitivity coefficient of setting calculates reference value g=1, then calculates sensitivity coefficient m=gv=1 × 0.67 from media article
=0.67.
Calculate content keyword authenticity reference value module: search to from the relevant article number of media article content keyword
According to the content authenticated in identification article data according to the content authenticated and is somebody's turn to do from the similarity degree calculating of media article
Hold the authenticity reference value a of keywordi。
The content authenticated refers to it is verified that the content issued for true interior perhaps official;It is described to have authenticated
Content with should refer to from the similarity degree of media article from the similar key ratio of media article and authentication content, be denoted as
bi;The authenticity reference value a of the content keywordi=sbi, wherein s is authenticity design factor set in advance.This reality
Apply in example, search with from the relevant article data of media article content keyword, it is related to " block chain ", " go into business XX ", " investment "
The publication of article Zhong Junyou official content (i.e. authentication content), calculate the phase that content is issued from media article and each official
Like keyword ratio b1=1, b2=1, b3=0.2;Authenticity design factor s=1 set in advance, then calculate content keyword
Authenticity reference value a1=sb1=1 × 1=1, a2=sb2=1 × 1=1, a3=sb3=1 × 0.2=0.2.
It calculates from the value grading module of media article: according to sensitivity coefficient m, the content keyword from media article
Authenticity reference value aiWith weighted value piCalculate the value assessment value x from media article.
The value assessment value from media articleMiddle k is that value set in advance is commented
Valuation design factor.In the present embodiment, value assessment value design factor k=1 set in advance calculates the value from media article
Assessed value
The present embodiment from media article valve estimating system structural schematic diagram, as shown in Figure 2.
Certainly, those of ordinary skill in the art is it should be appreciated that above embodiments are intended merely to illustrate this hair
It is bright, and be not intended as limitation of the invention, as long as within the scope of the invention, all to the variations of above embodiments, modification
Protection scope of the present invention will be fallen into.
Claims (10)
1. a kind of from media article Valuation Method, it is characterised in that the following steps are included:
It extracts from media article content keyword: identifying the content keyword from media article, keyword quantity is denoted as N, internally
Hold keyword to be numbered, is denoted as i, 1≤i≤N;The weighted value of set content keyword, is denoted as pi;
It calculates the sensitivity coefficient from media article: calculating and talked about from media article content keyword and high sensitive set in advance
The degree of correlation of topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m;
Calculate content keyword authenticity reference value: search is identified with from the relevant article data of media article content keyword
The content authenticated in article data according to the content authenticated and should calculate content keyword from the similarity degree of media article
Authenticity reference value, be denoted as ai;
It calculates and scores from the value of media article: being joined according to the authenticity of sensitivity coefficient m, content keyword from media article
Examine value aiWith weighted value piCalculate the value assessment value x from media article.
2. according to claim 1 from media article Valuation Method, which is characterized in that the high sensitive topic is
Refer to any one or multinomial combination of topical news hot topic or hot microblog topic.
3. according to claim 1 from media article Valuation Method, which is characterized in that described from media article content
The degree of correlation of keyword and high sensitive topic set in advance refer to from media article content keyword with high sensitive
The relevant keyword ratio of topic, is denoted as v;The sensitivity coefficient m=gv from media article, wherein g is to be arranged in advance
Sensitivity coefficient calculate reference value.
4. according to claim 1 from media article Valuation Method, which is characterized in that the content authenticated is
Refer to it is verified that the content issued for true interior perhaps official;The content authenticated to should be from the similar of media article
Degree refers to from the similar key ratio of media article and authentication content, is denoted as bi;The authenticity of the content keyword
Reference value ai=sbi, wherein s is authenticity design factor set in advance.
5. according to claim 1 from media article Valuation Method, which is characterized in that the valence from media article
It is worth assessed valueWherein k is value assessment value design factor set in advance.
6. a kind of from media article valve estimating system, characterized by comprising:
One or more processors;
Memory;
And
One or more programs, wherein one or more of programs are stored in the memory, and be configured to by
One or more of processors execute, and described program includes:
It extracting from media article content keyword module: identifying the content keyword from media article, keyword quantity is denoted as N,
Content keyword is numbered, i, 1≤i≤N are denoted as;The weighted value of set content keyword, is denoted as pi;
It calculates the sensitivity coefficient module from media article: calculating from media article content keyword and high sensitivity set in advance
The degree of correlation for spending topic calculates the sensitivity coefficient from media article according to degree of correlation, is denoted as m;
Calculate content keyword authenticity reference value module: search to from the relevant article data of media article content keyword,
It identifies the false information in article data, according to false information and content keyword should be calculated from the similarity degree of media article
Authenticity reference value ai;
Calculate from the value grading module of media article: according to from media article sensitivity coefficient m, content keyword it is true
Property reference value aiWith weighted value piCalculate the value assessment value x from media article.
7. according to claim 6 from media article valve estimating system, which is characterized in that the high sensitive topic is
Refer to any one or multinomial combination of topical news hot topic or hot microblog topic.
8. according to claim 6 from media article valve estimating system, which is characterized in that described from media article content
The degree of correlation of keyword and high sensitive topic set in advance refer to from media article content keyword with high sensitive
The relevant keyword ratio of topic, is denoted as v;The sensitivity coefficient m=gv from media article, wherein g is to be arranged in advance
Sensitivity coefficient calculate reference value.
9. according to claim 6 from media article valve estimating system, which is characterized in that the content authenticated is
Refer to it is verified that the content issued for true interior perhaps official;The content authenticated to should be from the similar of media article
Degree refers to from the similar key ratio of media article and authentication content, is denoted as bi;The authenticity of the content keyword
Reference value ai=sbi, wherein s is authenticity design factor set in advance.
10. according to claim 6 from media article valve estimating system, which is characterized in that described from media article
Value assessment valueWherein k is value assessment value design factor set in advance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910110338.5A CN109829165A (en) | 2019-02-11 | 2019-02-11 | One kind is from media article Valuation Method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910110338.5A CN109829165A (en) | 2019-02-11 | 2019-02-11 | One kind is from media article Valuation Method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109829165A true CN109829165A (en) | 2019-05-31 |
Family
ID=66863438
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910110338.5A Pending CN109829165A (en) | 2019-02-11 | 2019-02-11 | One kind is from media article Valuation Method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109829165A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334356A (en) * | 2019-07-15 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Article matter method for determination of amount, article screening technique and corresponding device |
CN111461785A (en) * | 2020-04-01 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Content value attribute evaluation method and device and copyright trading platform |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020091991A1 (en) * | 2000-05-11 | 2002-07-11 | Castro Juan Carlos | Unified real-time microprocessor computer |
CN102682120A (en) * | 2012-05-15 | 2012-09-19 | 合一网络技术(北京)有限公司 | Method,device and system for acquiring essential article commented on network |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | 中国移动通信集团浙江有限公司 | Method and terminal for recommending learning courses |
CN104216879A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津)科技有限公司 | Video quality excavation system and method |
CN107193805A (en) * | 2017-06-06 | 2017-09-22 | 北京百度网讯科技有限公司 | Article Valuation Method, device and storage medium based on artificial intelligence |
CN107491432A (en) * | 2017-06-20 | 2017-12-19 | 北京百度网讯科技有限公司 | Low quality article recognition methods and device, equipment and medium based on artificial intelligence |
CN107577688A (en) * | 2017-04-25 | 2018-01-12 | 上海市互联网信息办公室 | Original article influence power analysis system based on media information collection |
CN107918644A (en) * | 2017-10-31 | 2018-04-17 | 北京锐思爱特咨询股份有限公司 | News subject under discussion analysis method and implementation system in reputation Governance framework |
CN108241727A (en) * | 2017-09-01 | 2018-07-03 | 新华智云科技有限公司 | News reliability evaluation method and equipment |
CN108304379A (en) * | 2018-01-15 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of article recognition methods, device and storage medium |
-
2019
- 2019-02-11 CN CN201910110338.5A patent/CN109829165A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020091991A1 (en) * | 2000-05-11 | 2002-07-11 | Castro Juan Carlos | Unified real-time microprocessor computer |
CN102682120A (en) * | 2012-05-15 | 2012-09-19 | 合一网络技术(北京)有限公司 | Method,device and system for acquiring essential article commented on network |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | 中国移动通信集团浙江有限公司 | Method and terminal for recommending learning courses |
CN104216879A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津)科技有限公司 | Video quality excavation system and method |
CN107577688A (en) * | 2017-04-25 | 2018-01-12 | 上海市互联网信息办公室 | Original article influence power analysis system based on media information collection |
CN107193805A (en) * | 2017-06-06 | 2017-09-22 | 北京百度网讯科技有限公司 | Article Valuation Method, device and storage medium based on artificial intelligence |
CN107491432A (en) * | 2017-06-20 | 2017-12-19 | 北京百度网讯科技有限公司 | Low quality article recognition methods and device, equipment and medium based on artificial intelligence |
CN108241727A (en) * | 2017-09-01 | 2018-07-03 | 新华智云科技有限公司 | News reliability evaluation method and equipment |
CN107918644A (en) * | 2017-10-31 | 2018-04-17 | 北京锐思爱特咨询股份有限公司 | News subject under discussion analysis method and implementation system in reputation Governance framework |
CN108304379A (en) * | 2018-01-15 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of article recognition methods, device and storage medium |
Non-Patent Citations (1)
Title |
---|
曾佳雯: "微信信息质量评价指标体系的构建", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334356A (en) * | 2019-07-15 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Article matter method for determination of amount, article screening technique and corresponding device |
CN110334356B (en) * | 2019-07-15 | 2023-08-04 | 腾讯科技(深圳)有限公司 | Article quality determining method, article screening method and corresponding device |
CN111461785A (en) * | 2020-04-01 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Content value attribute evaluation method and device and copyright trading platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20140351109A1 (en) | Method and apparatus for automatically identifying a fraudulent order | |
CN106453061B (en) | A kind of method and system identifying network fraudulent act | |
CN104899508B (en) | A kind of multistage detection method for phishing site and system | |
CN106934275B (en) | Password strength evaluation method based on personal information | |
CN105718577B (en) | Method and system for automatically detecting phishing aiming at newly added domain name | |
CN104077396A (en) | Method and device for detecting phishing website | |
CN113743111B (en) | Financial risk prediction method and device based on text pre-training and multi-task learning | |
CN103064987A (en) | Bogus transaction information identification method | |
CN105303440A (en) | Consumer credit application evaluation system and realizing method thereof | |
CN107807941A (en) | Information processing method and device | |
TW201926170A (en) | Method and apparatus for determining target user group | |
US9124623B1 (en) | Systems and methods for detecting scam campaigns | |
CN109829165A (en) | One kind is from media article Valuation Method and system | |
WO2015062377A1 (en) | Device and method for detecting similar text, and application | |
CN113989859B (en) | Fingerprint similarity identification method and device for anti-flashing equipment | |
CN112016317A (en) | Sensitive word recognition method and device based on artificial intelligence and computer equipment | |
CN112750038B (en) | Transaction risk determination method, device and server | |
Manek et al. | Detection of fraudulent and malicious websites by analysing user reviews for online shopping websites | |
CN105808602B (en) | Method and device for detecting junk information | |
CN111861733B (en) | Fraud prevention and control system and method based on address fuzzy matching | |
CN104751234B (en) | A kind of prediction technique and device of user's assets | |
CN105653941A (en) | Heuristic detection method and system for phishing website | |
Wang et al. | Temperature forecast based on SVM optimized by PSO algorithm | |
KR101806174B1 (en) | System and method for detecting spam sms, recording medium for performing the method | |
CN114510720A (en) | Android malicious software classification method based on feature fusion and NLP technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |