CN107609173A - A kind of method for information content violation quantitative analysis - Google Patents
A kind of method for information content violation quantitative analysis Download PDFInfo
- Publication number
- CN107609173A CN107609173A CN201710901623.XA CN201710901623A CN107609173A CN 107609173 A CN107609173 A CN 107609173A CN 201710901623 A CN201710901623 A CN 201710901623A CN 107609173 A CN107609173 A CN 107609173A
- Authority
- CN
- China
- Prior art keywords
- violation
- information content
- sentence fragment
- database
- index
- 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 provides a kind of method for information content violation quantitative analysis, including：A, each information is monitored in real time；When B, judging certain the violation sentence fragment for occurring storing in presetting database in each information content, the index of the violation sentence fragment and the information content where it is established, and is stored in the database；C, the frequency that each violation sentence fragment occurs in the information content of different specified time sections in the database is obtained, and obtains the violation ranking of each violation sentence fragment of different time sections accordingly.By upper, it is possible to achieve the violation quantitative analysis to information content.
Description
Technical field
The present invention relates to information analysis field, more particularly to a kind of method for information content violation quantitative analysis.
Background technology
At present, the analysis of information content violation is primarily based on the filter method of Keywords matching and divided in the prior art
Analysis, its principle are：Prepare a keywords database first, some keywords selected in advance are recorded in storehouse.When to an information content
When being judged, this information content is matched one by one with the word in keywords database, closed if there is one or more
Keyword can match with the content of text in information content, that is, have keyword to occur in the text, then judge that this webpage is
It is no to belong to the information for needing management and control, if it is, being filtered to this information content；Otherwise, then illustrate that this webpage is not
Need the target filtered.Therefore, the shortcomings that being currently based on key word matching method be：Violation information content can not be quantified
Analysis.
Therefore, a kind of method for information content violation quantitative analysis is needed badly at present.
The content of the invention
In view of this, the application provides a kind of method for information content violation quantitative analysis, is advantageous to provide violation
Interrogate content and carry out quantitative analysis.
The application provides a kind of method for information content violation quantitative analysis, including：
A, each information content is monitored in real time；
When B, there is each violation sentence fragment stored in presetting database in monitoring each information content, establish
The index of the violation sentence fragment and the information content where it, and be stored in the database；
C, current violation sentence fragment and each violation sentence fragment are obtained in the database in different specified time sections
Information content in the frequency that occurs, and obtain the violation ranking of each violation sentence fragment of different time sections accordingly.
By upper, the application is further carried out by being monitored to the violation sentence fragment in information content to it
Quantitative analysis, the violation ranking of each violation sentence fragment of different time sections is obtained, be advantageous to intuitively show to user in violation of rules and regulations
The violation situation of sentence fragment.The ranking is also corresponding with relative information content, is advantageous to facilitate user to click directly on and looks into
Read.For example, can intuitively show daily, weekly, monthly, every year or other periods scheduled date each violation sentence piece
The violation ranking of section.Meanwhile for sensitive word determination methods, due to the different implications that it may be represented of linguistic context residing for sensitive word
It is different.Such as：Equally it is " murder " one word, it both possibly be present in the news of positive strike violence, it is also possible to appear in
Among some violence news contents, and both news are entirely different in nature.Therefore, it is if simple using crucial
Word monitors, and can cause to judge inaccuracy.And by being monitored to violation sentence fragment aspect, be advantageous to what enhancing monitored in violation of rules and regulations
Accuracy.
Preferably, also include after the step C：
D, disobeying for violation sentence fragment is obtained according to the violation ranking of each violation sentence fragment of the different time sections
Rule trend.
By upper, above-mentioned violation trend can be represented with line illustration, can intuitively be checked at one week by the violation trend
Within or 1 year within or the different time sections such as different year in the violation trend that occurs of each violation sentence fragment be to rise
High or reduction.
Preferably, the step B also includes：
When there is the sensitive word stored in presetting database in B1, monitoring each information content：
B11, the linguistic context occurred respectively in each information content with reference to each sensitive word, by various dimensions to its point
Analyse the violation index of each sensitive word；Wherein, the violation index by each sensitive word of multi dimensional analysis includes：Pass through knot
Close main body involved by the sensitive word, personage, time, place, the violation index of each sensitive word described in time series analysis；
B12, sensitive word of the violation index more than the first specified threshold be labeled as violation sensitive word, by the violation
Sentence fragment where sensitive word is labeled as violation sentence fragment, establishes the violation sentence fragment and the information content where it
Index, and be stored in the database.
By upper, the application determines the violation index of each sensitive word by the analysis of various dimensions, such as with reference to the sensitive word
Involved main body, personage, time, place, the violation index of each sensitive word described in time series analysis and further by its institute
Sentence fragment be labeled as violation sentence fragment so that follow-up can judge whether it disobeys when judging according to the violation sentence fragment
Rule, for example, sensitive word " human rights crisis ", when it is " human rights crisis is got deeply stuck in by India ", then the sentence fragment not in violation of rules and regulations, when it is
When " human rights crisis is got deeply stuck in by China ", then sentence fragment violation.
Preferably, the step C also includes：
The frequency that each violation sentence fragment occurs in its current information content in C1, the acquisition database, and according to
This obtains each violation sentence fragment violation frequency in its current information content.
By upper, by violation situation of each violation sentence fragment of violation frequency quantization in its current information content, with
Intuitively shown to user.
Preferably, also include after the step C1：
D1, violation frequency and violation rank, acquisition in its current information content according to each violation sentence fragment
The information content violation index of each information content；And by information of the information content violation index more than the second specified threshold
Content-label is violation information content, and the violation information content and its storage of corresponding violation index are arrived into the database
In.
By upper, violation frequency and violation rank of the application according to each violation sentence fragment in its current information content
Obtain the information content violation index of each information content；Wherein, can be true according to the violation rank of different violation sentence fragments
Its fixed shared violation weight, for example, it is assumed that the violation sentence fragment for being related to country is first level, its shared violation weight then compared with
Weight；Assuming that the violation sentence fragment for being related to law is second level, its shared violation weight is then in centre；Assuming that it is related to morals
Violation sentence fragment be third level, its shared violation weight is then in lighter.Then the information content obtained accordingly is disobeyed
Rule index is labeled as violation information content more than the information content of the second specified threshold.By the above method to violation information content
Judgement it is more accurate.
Preferably, also include after the step D1：
E1, referred in violation of rules and regulations according to the information content of each violation information content of the different time sections stored in the database
Number, obtain the information content violation ranking of each violation information content of different time sections.
By upper, by the way that to different time sections information content violation ranking each violation sentence piece directly can be shown to user
Violation situation in the current information contents of Duan Qi.For example, to user's displaying daily, weekly, monthly, every year or other are specified
The violation ranking of the information content of date-time section.The ranking is also corresponding with relative information content, is advantageous to conveniently use
Family clicks directly on access.
Preferably, also include after the step D1：
E2, each author corresponding to each violation information content of the different time sections stored in the database is obtained,
And author's violation degree ranking of each author of different time sections is obtained according to each information content violation degree ranking.
By upper, each author's violation situation directly can be shown to user by author's violation degree ranking.The ranking is also right
There should be relative information content, be advantageous to facilitate user to click directly on access.
Preferably, also include after the step D1：
E3, each matchmaker for issuing each violation information content for obtaining the different time sections stored in the database
Body, and the violation degree ranking of the information content included according to each media, obtain each media of different time sections
Media violation degree ranking.
By upper, the violation situation of each media can be directly shown to user by media violation degree ranking.The ranking is also
Relative information content is corresponding with, is advantageous to facilitate user to click directly on access.
Preferably, also include after the step D1：
E4, when the violation information content violation index is more than three specified thresholds, carry out violation alert, and this provided
Content push is interrogated to user.
By upper, by carry out violation alert can user understand the information content of violation in real time.
Preferably, the step B also includes：
When B21, monitoring each information content are the information content reprinted, information content and its turn after reprinting are judged
When occurring each violation sentence fragment stored in presetting database in the difference content of the information content in load source, the violation is established
The index of sentence fragment and the information content where it, and be stored in the database；Or
When B22, monitoring each information content are the information content reprinted, information content and its turn after reprinting are judged
When there is the sensitive word stored in presetting database in the difference content of the information content in load source：
The linguistic context occurred respectively in each information content with reference to each sensitive word, by multi dimensional analysis to its point
Analysis；Wherein, it is described it is analyzed by various dimensions including：By the main body with reference to involved by the sensitive word, personage, the time,
The violation index of each sensitive word described in point, time series analysis；
Sensitive word of the violation index more than the first specified threshold is labeled as violation sensitive word, the violation is sensitive
Sentence fragment where word is labeled as violation sentence fragment, establishes the rope of the violation sentence fragment and the information content where it
Draw, and be stored in the database.
By upper, the application is monitored to the information content of reprinting by above-mentioned violation, overcomes traditional violation system only to right
Violation keyword, news sources etc. are caused when a qualified news sources when being monitored, and are reprinted by other sources, and add separated
Advise fragment after, because news sources are qualified, be ignored in violation of rules and regulations, not up to monitor violation effect the defects of.
In summary, the application is to the violation sentence fragment in information content by being monitored, and further to it
Quantitative analysis is carried out, for example, obtaining the violation ranking and violation sentence fragment of each violation sentence fragment of different time sections
It is related corresponding to violation trend, information content violation degree ranking, media violation ranking, author's violation ranking etc. and above-mentioned ranking
Information content, be advantageous to intuitively show the violation situation of information content to user by above-mentioned quantitative analysis.And the application is led to
Cross carry out violation alert can be so that user understands the information content of violation in real time.By upper, the application passes through to violation sentence piece
Section aspect is monitored, and is advantageous to the accuracy that enhancing monitors in violation of rules and regulations.And the application by its quantitative analysis is advantageous to
Family intuitively shows the violation situation of information content.The application carries out violation monitoring to the information content of reprinting, overcomes tradition and disobeys
It is caused when a qualified news sources when rule system to violation keyword, news sources etc. only to being monitored, turned by other sources
Carry, and after adding violation fragment, because news sources are qualified, be ignored in violation of rules and regulations, the defects of not up to monitoring the effect of violation.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet of method for information content violation quantitative analysis of the embodiment of the present application.
Embodiment
The application is illustrated below in conjunction with the accompanying drawing in the embodiment of the present application.
Embodiment one
The application provides a kind of method for information content violation quantitative analysis, including：
S101, build database.Wherein, history violation sentence fragment and its corresponding difference are included in the database
Time, different media, the information content of different authors, and comprising different grades of violation sensitive word and its it is corresponding different when
Between, the information content of different media, different authors.And different sensitive word.Wherein on the grade, for example, it is assumed that relating to
And the violation sentence fragment of country is first level, its shared violation weight is then heavier；Assuming that it is related to the violation sentence piece of law
Section is second level, and its shared violation weight is then in centre；Assuming that the violation sentence fragment for being related to morals is third level, its
Shared violation weight is then in lighter.
S102, each information content is monitored in real time；Including but not limited to：Each webpage, news media, APP are monitored in real time
And the information content of the issue of other channels or forwarding.
S103, monitor when there is each violation sentence fragment stored in presetting database in each information content,
The index of the violation sentence fragment and the information content where it is established, and is stored in the database；
Wherein, the S103 also includes：
Monitor when there is the sensitive word stored in presetting database in each information content：
The linguistic context occurred respectively in each information content with reference to each sensitive word, it is analyzed respectively by various dimensions
The violation index of individual sensitive word；Wherein, the violation index by each sensitive word of multi dimensional analysis includes：Should by combining
The violation index of each sensitive word described in main body, personage, time, these dimensional analysis of place involved by sensitive word；
Wherein, for different dimensions, different weights can be set to refer to percentage to calculate the violation index, example
Such as：
Total violation index=a1X1+a2X2+ ... .anXn.
Wherein Xn is the violation index of the n-th dimension, and an is the weight percentage of the n-th dimension, and the weight percentage can be carried out
Adjustment.For example, when judging closer to the event of certain history specific date generation, then corresponding time dimension index weight more increases
Greatly.
Sensitive word of the violation index more than the first specified threshold is labeled as violation sensitive word, the violation is sensitive
Sentence fragment where word is labeled as violation sentence fragment, establishes the rope of the violation sentence fragment and the information content where it
Draw, and be stored in the database.
Thus, the violation index of each sensitive word is determined by the analysis of various dimensions, such as with reference to involved by the sensitive word
Main body, personage, the time, place, the violation index of each sensitive word described in time series analysis and further by the sentence where it
Sub-piece is labeled as violation sentence fragment, so as to it can be judged when subsequently judging according to the violation sentence fragment whether in violation of rules and regulations, example
Such as, sensitive word " human rights crisis ", when it is " human rights crisis is got deeply stuck in by India ", then the sentence fragment not in violation of rules and regulations, when it is " China
Get deeply stuck in human rights crisis " when, then sentence fragment violation.
Wherein, the S103 also includes：
During the information content for monitoring each information content to reprint, the information content after reprinting and its reprinting source are judged
Information content difference content in when there is each violation sentence fragment stored in presetting database, establish the violation sentence
Fragment and the index of the information content where it, and be stored in the database；Or
During the information content for monitoring each information content to reprint, the information content after reprinting and its reprinting source are judged
Information content difference content in when there is the sensitive word stored in presetting database：
The linguistic context occurred respectively in each information content with reference to each sensitive word, by multi dimensional analysis to its point
Analysis；Wherein, it is described it is analyzed by various dimensions including：By the main body with reference to involved by the sensitive word, personage, the time,
The violation index of each sensitive word described in point, time series analysis；
Sensitive word of the violation index more than the first specified threshold is labeled as violation sensitive word, the violation is sensitive
Sentence fragment where word is labeled as violation sentence fragment, establishes the rope of the violation sentence fragment and the information content where it
Draw, and be stored in the database.
Thus, the application is monitored to the information content of reprinting by above-mentioned violation, overcomes traditional violation system only to right
Violation keyword, news sources etc. are caused when a qualified news sources when being monitored, and are reprinted by other sources, and add separated
Advise fragment after, because news sources are qualified, be ignored in violation of rules and regulations, not up to monitor violation effect the defects of.
S104, current violation sentence fragment and each violation sentence fragment are obtained in the database in different specified times
The frequency occurred in the information content of section, and the violation ranking of each violation sentence fragment of different time sections is obtained accordingly.By
This, the violation ranking of each violation sentence fragment by obtaining different time sections, is advantageous to intuitively show violation sentence to user
The violation situation of sub-piece.For example, can intuitively it show daily, weekly, monthly, every year or other periods scheduled date
The violation ranking of each violation sentence fragment.
Wherein described step S104 also includes：
The frequency that each violation sentence fragment occurs in its current information content in the database is obtained, and is obtained accordingly
Take each violation sentence fragment violation frequency in its current information content.Thus, each violation sentence of violation frequency quantization is passed through
Violation situation of the sub-piece in its current information content, intuitively to be shown to user.
S105, violation sentence fragment is obtained according to the violation ranking of each violation sentence fragment of the different time sections
Violation trend.Wherein, above-mentioned violation trend can be represented with line illustration, can intuitively be checked at one week by the violation trend
Within or 1 year within or the different time sections such as different year in the violation trend that occurs of each violation sentence fragment be to rise
High or reduction.
Wherein, the S105 also includes：
According to each violation sentence fragment, violation frequency and violation rank, acquisition are each in its current information content
The information content violation index of information content；And by information content of the information content violation index more than the second specified threshold
Labeled as violation information content, and by the violation information content and its storage of corresponding violation index into the database.
Thus, the application obtains each according to violation frequency of each violation sentence fragment in its current information content and violation rank
The information content violation index of information content；Wherein, according to shared by the violation rank of different violation sentence fragments can determine it
Violation weight, for example, it is assumed that the violation sentence fragment for being related to country is first level, its shared violation weight is then heavier；Assuming that
The violation sentence fragment for being related to law is second level, and its shared violation weight is then in centre；Assuming that it is related to the violation of morals
Sentence fragment is third level, and its shared violation weight is then in lighter.Then the information content violation index that will be obtained accordingly
Information content more than the second specified threshold is labeled as violation information content.Pass through judgement of the above method to violation information content
It is more accurate.
S106, according to the information content of each violation information content of the different time sections stored in the database in violation of rules and regulations
Index, obtain the information content violation ranking of each violation information content of different time sections.Thus, by different time sections
Information content violation ranking directly can show violation feelings of each violation sentence fragment in its current information content to user
Condition.For example, to user displaying daily, weekly, monthly, every year or the information content of other periods scheduled date violation row
Name.The ranking is also corresponding with relative information content, is advantageous to facilitate user to click directly on access.
Wherein, the S106 also includes：
Obtain each author corresponding to each violation information content of the different time sections stored in the database, and root
Author's violation degree ranking of each author of different time sections is obtained according to each information content violation degree ranking.By
This, directly each author's violation situation can be shown by author's violation degree ranking to user.The ranking is also corresponding with and its phase
The information content of pass, be advantageous to facilitate user to click directly on access.
Wherein, the S106 also includes：
Each media of issue each violation information content of the different time sections stored in the database are obtained,
And the violation degree ranking of the information content included according to each media, obtain the media of each media of different time sections
Violation degree ranking.Thus, the violation situation of each media can be directly shown to user by media violation degree ranking.The ranking
Relative information content is also corresponding with, is advantageous to facilitate user to click directly on access.
Wherein, the S106 also includes：
When the violation information content violation index is more than three specified thresholds, violation alert is carried out, and by the information
Content push is to user.Thus, by carry out violation alert can user understand the information content of violation in real time.
In summary, the application is to the violation sentence fragment in information content by being monitored, and further to it
Quantitative analysis is carried out, for example, obtaining the violation ranking and violation sentence fragment of each violation sentence fragment of different time sections
It is related corresponding to violation trend, information content violation degree ranking, media violation ranking, author's violation ranking etc. and above-mentioned ranking
Information content, be advantageous to intuitively show the violation situation of information content to user by above-mentioned quantitative analysis.And the application is led to
Cross carry out violation alert can be so that user understands the information content of violation in real time.By upper, the application passes through to violation sentence piece
Section aspect is monitored, and is advantageous to the accuracy that enhancing monitors in violation of rules and regulations.And the application by its quantitative analysis is advantageous to
Family intuitively shows the violation situation of information content.The application carries out violation monitoring to the information content of reprinting, overcomes tradition and disobeys
It is caused when a qualified news sources when rule system to violation keyword, news sources etc. only to being monitored, turned by other sources
Carry, and after adding violation fragment, because news sources are qualified, be ignored in violation of rules and regulations, the defects of not up to monitoring the effect of violation.
Wherein, for each dimension ranking beneficial effect, except being advantageous to intuitively show information content to user
Violation situation and outside being alarmed more than specified threshold, also include for also being had the advantage that in terms of specific system administration：
Some features of information content in itself are shown according to user's request, help user to examine information content, including money closely from multiple angles
Interrogate the informational capacity of content, information point enriches degree, title and relevance degree etc..In addition, system can also provide singleton
Test function, user can be helped to go to judge history information content according to newest violation content rule.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention.In a word, it is all in the present invention
Spirit and principle within, any modification, equivalent substitution and improvements made etc., should be included in protection scope of the present invention it
It is interior.
Claims (9)
- A kind of 1. method for information content violation quantitative analysis, it is characterised in that including：A, each information is monitored in real time；When B, judging certain the violation sentence fragment for occurring storing in presetting database in each information content, the violation is established The index of sentence fragment and the information content where it, and be stored in the database；C, the frequency that each violation sentence fragment occurs in the information content of different specified time sections in the database is obtained, And the violation ranking of each violation sentence fragment of different time sections is obtained accordingly.
- 2. according to the method for claim 1, it is characterised in that also include after the step C：D, the violation that violation sentence fragment is obtained according to the violation ranking of each violation sentence fragment of the different time sections becomes Gesture.
- 3. according to the method for claim 1, it is characterised in that the step B also includes：B11, when judging certain sensitive word stored in presetting database occur in each information content：The linguistic context occurred respectively in each information content with reference to each sensitive word, it is analyzed by various dimensions；B12, sensitive word of the violation index more than the first specified threshold be labeled as violation sensitive word, the violation is sensitive Sentence fragment where word is labeled as violation sentence fragment, establishes the rope of the violation sentence fragment and the information content where it Draw, and be stored in the database.
- 4. according to the method for claim 3, it is characterised in that in the step B11 by various dimensions to its analysis bag Include：Referred to by the violation of each sensitive word described in the main body with reference to involved by the sensitive word, personage, time, place dimensional analysis Number；Wherein, for different dimensions, different weights can be set to refer to percentage to calculate the violation index, it calculates public Formula is：Violation index=a1X1+a2X2+ ... .anXn.Wherein, Xn is the violation index of the n-th dimension, and an is the weight percentage of the n-th dimension.
- 5. according to the method described in claim any one of 1-4, it is characterised in that the step C also includes：C1, the frequency that each violation sentence fragment occurs in its current information content in the database is obtained, and obtained accordingly Take each violation sentence fragment violation frequency in its current information content.
- 6. according to the method for claim 5, it is characterised in that also include after the step C1：D1, according to each violation sentence fragment, violation frequency and violation rank, acquisition are each in its current information content The information content violation index of information content；And by information content of the information content violation index more than the second specified threshold Labeled as violation information content, and by the violation information content and its storage of corresponding violation index into the database.
- 7. according to the method for claim 6, it is characterised in that also include at least following one after the step D1：E1, the information content violation index according to each violation information contents of the different time sections stored in the database, Obtain the information content violation ranking of each violation information content of different time sections；OrE2, obtain each author corresponding to each violation information content of the different time sections stored in the database, and root Author's violation degree ranking of each author of different time sections is obtained according to each information content violation degree ranking；OrE3, each media for issuing each violation information content for obtaining the different time sections stored in the database, And the violation degree ranking of the information content included according to each media, obtain the media of each media of different time sections Violation degree ranking.
- 8. according to the method for claim 6, it is characterised in that also include after the step D1：E4, when the violation information content violation index is more than three specified thresholds, violation alert is carried out, and by the information Appearance is pushed to user.
- 9. according to the method for claim 1, it is characterised in that when the information is the information reprinted, the information content For the information content after reprinting and the difference content of the information content in its reprinting source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710901623.XA CN107609173A (en) | 2017-09-28 | 2017-09-28 | A kind of method for information content violation quantitative analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710901623.XA CN107609173A (en) | 2017-09-28 | 2017-09-28 | A kind of method for information content violation quantitative analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107609173A true CN107609173A (en) | 2018-01-19 |
Family
ID=61057953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710901623.XA Pending CN107609173A (en) | 2017-09-28 | 2017-09-28 | A kind of method for information content violation quantitative analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609173A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163706A (en) * | 2018-02-13 | 2019-08-23 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296128A (en) * | 2007-04-24 | 2008-10-29 | 北京大学 | Method for monitoring abnormal state of internet information |
| CN102096703A (en) * | 2010-12-29 | 2011-06-15 | 北京新媒传信科技有限公司 | Filtering method and equipment of short messages |
| CN102184188A (en) * | 2011-04-15 | 2011-09-14 | 百度在线网络技术（北京）有限公司 | Method and equipment for determining sensitivity of target text |
| CN104270372A (en) * | 2014-10-11 | 2015-01-07 | 国家电网公司 | Parameter self-adaption network security posture quantitative evaluation method |
| CN105069107A (en) * | 2015-08-07 | 2015-11-18 | 北京百度网讯科技有限公司 | Method and device for monitoring website |
| CN106445998A (en) * | 2016-05-26 | 2017-02-22 | 达而观信息科技（上海）有限公司 | Text content auditing method and system based on sensitive word |
-
2017
- 2017-09-28 CN CN201710901623.XA patent/CN107609173A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296128A (en) * | 2007-04-24 | 2008-10-29 | 北京大学 | Method for monitoring abnormal state of internet information |
| CN102096703A (en) * | 2010-12-29 | 2011-06-15 | 北京新媒传信科技有限公司 | Filtering method and equipment of short messages |
| CN102184188A (en) * | 2011-04-15 | 2011-09-14 | 百度在线网络技术（北京）有限公司 | Method and equipment for determining sensitivity of target text |
| CN104270372A (en) * | 2014-10-11 | 2015-01-07 | 国家电网公司 | Parameter self-adaption network security posture quantitative evaluation method |
| CN105069107A (en) * | 2015-08-07 | 2015-11-18 | 北京百度网讯科技有限公司 | Method and device for monitoring website |
| CN106445998A (en) * | 2016-05-26 | 2017-02-22 | 达而观信息科技（上海）有限公司 | Text content auditing method and system based on sensitive word |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163706A (en) * | 2018-02-13 | 2019-08-23 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110163706B (en) * | 2018-02-13 | 2024-04-19 | 北京京东尚科信息技术有限公司 | Method and device for generating information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Galárraga et al. | Canonicalizing open knowledge bases | |
| Hansmann et al. | Big data-characterizing an emerging research field using topic models | |
| Zhang et al. | The diffusion of H-related literature | |
| Carretero-Campos et al. | Improving statistical keyword detection in short texts: Entropic and clustering approaches | |
| Liu et al. | Gene ontology enrichment improves performances of functional similarity of genes | |
| KR20150057322A (en) | System and Method for Deducting about Weak Signal Using Big Data Analysis | |
| Shourick et al. | Assessing rare diseases prevalence using literature quantification | |
| Lavertu et al. | RedMed: Extending drug lexicons for social media applications | |
| O'Brien et al. | What is the value of adding Medicare data in estimating VA hospital readmission rates? | |
| CN107609173A (en) | A kind of method for information content violation quantitative analysis | |
| Sigalo et al. | Using COVID-19 vaccine attitudes on Twitter to improve vaccine uptake forecast models in the United States: infodemiology study of Tweets | |
| Cohen et al. | CSI-OMIM-Clinical synopsis search in OMIM | |
| Cui et al. | Multidimensional scholarly citations: Characterizing and understanding scholars' citation behaviors | |
| Yoon et al. | Methods of knowledge discovery in tweets | |
| Lagisetty et al. | Opioid prescribing after opioid-related inpatient hospitalizations by diagnosis: a cohort study | |
| Bolton | We need science to be useful too | |
| Chen et al. | Drug abuse-related accidents leading to emergency department visits at two medical centers | |
| Fan et al. | Disorder concept identification from clinical notes an experience with the ShARe/CLEF 2013 challenge | |
| Dietrich et al. | Extending the query language of a data warehouse for patient recruitment | |
| Mendis et al. | Tracking Australian health and medical research expenditure with a PubMed bibliometric method | |
| KR102504891B1 (en) | Methods and Computer-Readable Medium for Providing Information on Bills of Law | |
| Sen et al. | Differential DNA methylation patterns in patients with epilepsy due to malformations of cortical development: A pilot study | |
| Manohar | Whole system research and ayurveda | |
| Jankowski-Lorek et al. | Document controversy classification based on the wikipedia category structure | |
| Gouda et al. | Why my disease is important: metrics of disease occurrence used in the introductory sections of papers in three leading general medical journals in 1993 and 2003 |
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: 20180119 |
|
| RJ01 | Rejection of invention patent application after publication |