CN106447508A - Improved high-quality node detection system based on computer large data in social network - Google Patents
Improved high-quality node detection system based on computer large data in social network Download PDFInfo
- Publication number
- CN106447508A CN106447508A CN201610910848.7A CN201610910848A CN106447508A CN 106447508 A CN106447508 A CN 106447508A CN 201610910848 A CN201610910848 A CN 201610910848A CN 106447508 A CN106447508 A CN 106447508A
- Authority
- CN
- China
- Prior art keywords
- node
- quality
- subelement
- information
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
An improved high-quality node detection system based on computer large data in a social network comprises a monitoring participle unit, a high-quality node detection unit, an early warning unit and an accumulation unit, wherein the monitoring participle unit is used for establishing a high-quality node information propagation monitoring model; the high-quality node detection unit is used for detecting a high-quality node from an Internet social system; the early warning unit is used for using the high-quality node information propagation monitoring model to monitor information issued by the high-quality node and sending sensitive information and information of the high-quality node issuing the sensitive information to the accumulation unit when the sensitive information is monitored; and the accumulation unit is used for selecting to send the sensitive information and information of the high-quality node issuing the sensitive information to a network supervision center according to a weight of the sensitive information.
Description
Technical field
The present invention relates to computer field of cloud computer technology, particularly to a kind of modified based on the society of the big data of computer
Hand over high-quality node detection system in network.
Background technology
In recent years, owing to the research of social networks is increasingly popular, based on the detection in social network-i i-platform with find excellent
The research of matter customer problem also obtains the attention of people day by day.By the excavation to this kind of user, can be with these high-qualitys user
Set up and more directly associate to obtain the social value containing.Simultaneously because the rise of internet social tool so that these are excellent
The surrounding of matter user is poly-has played large quantities of follower so that the information that high-quality user issues easily spreads, and easily by other people
Use stroll network rumour.
Prior art lack a kind of effectively to the detection of high-quality node in internet social networks and release news
Effective monitoring means.
Content of the invention
In view of this, the present invention proposes a kind of modified and detects based on high-quality node in the social networks of the big data of computer
System.
A kind of modified is based on high-quality node detection system in the social networks of the big data of computer, and it includes as placed an order
Unit:
Monitoring participle unit, is used for setting up high-quality nodal information and propagates monitoring model;
High-quality node probe unit, for detecting high-quality node from internet social intercourse system;
Prewarning unit, supervises for the information utilizing high-quality nodal information propagation monitoring model to issue high-quality node
Sensitive information and the high-quality nodal information issuing sensitive information, when monitoring sensitive information, are sent to summing elements by control;
Summing elements, for the Weight selected according to sensitive information by sensitive information and the high-quality joint issuing sensitive information
Dot information is sent to network supervision center;
Summing elements includes:
Weight setting subelement, affects weights for prestore all kinds of sensitive information;
Cumulative subelement, for when receiving the sensitive information that prewarning unit sends, it is judged that the sensitive information of reception
Weights, and the weights of sensitive information are added up;
Threshold value sets subelement, for determining whether whether the weights after adding up exceed alarm threshold value, is exceeding warning
During threshold value, sensitive information and the high-quality nodal information issuing sensitive information are sent to network supervision center.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Monitoring participle unit includes:
First participle subelement, for carrying out participle by the netspeak information needing training according to language performance rule;
Whether the second participle subelement, can proceed first participle after being used for judging first participle subelement participle
Unit carries out participle, if participle can not be continued, then carries out fine granularity participle, otherwise jumps to first participle subelement according to language
Speech expression rule carries out participle;
Sensitive word database, for storing the sensitive information vocabulary needing monitoring.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Described high-quality node probe unit includes:
Set determines subelement, for extracting the social networks node set at the high-quality node place needing detection;
Subelement is set up in mapping, for setting up the joint of social networks to the social networks node in social networks node set
Point mapping relations;
Subelement set up by model, extracts detection high-quality node diagnostic for the mechanics according to high-quality node;According to carrying
The high-quality node diagnostic taking sets up the characterization rules model of high-quality node detection;
Training subelement, for being grouped social networks node as experiment sample, then carry out station work and
Node-classification;
Revising subelement, the result for detecting high-quality node is estimated and feedback result, and is training repeatedly
During the rule not meeting detection high-quality node diagnostic is corrected, thus reach the purpose being optimized model;
Iteration subelement, turns again to train the training of subelement interior joint to enter with classification link for the model after optimizing
Row high-quality node detects to improve detection progress, and is iterated computing until the detection progress of high-quality node exceedes setting threshold value
Thus complete high-quality node detection process in whole social networks.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State prewarning unit to include:
Data acquisition subelement, for crawling the real time data of high-quality node issue and writing data buffer storage storehouse;
Cluster subelement, for the real time data in the first predetermined amount of time being ranked up according to pre-defined algorithm, screening
Go out the information exceeding preset heat value in the first predetermined amount of time;To being made up of real time data in the second predetermined amount of time
Text carries out burst word extraction, and then carries out vectorization, clusters the text of vectorization, chooses all kinds of middle exceptional value maximum
Real time data is as the abnormal information monitoring;Show information and the exception of the preset heat value of corresponding bar number according to predetermined threshold value
Information;
Judgment sub-unit, enters row filter for the information of preset heat value and abnormal information are sent to monitoring participle unit
Judge whether sensitive word;When monitoring sensitive word, sensitive word and issue are comprised the high-quality node of sensitive word information
Information is sent to summing elements.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Described model is set up the mechanics extraction detection high-quality node diagnostic according to high-quality node in subelement and is included:
Node is set and is judged as the nodal community of outstanding node, possess the nodal community of outstanding node at a certain node
When, then this nodal community has the feature of high quality;
Arrange and between node, As time goes on just should possess interactivity frequently, referred to as interactive degree Vinter;In society
Hand in network, be connected limit as node has between the feature of core node, and they with all mid-side nodes to exist;Connect limit at these
In, regard the active of high-quality node as out-degree V alternatelyout, out-degree is self to point to the limit of other nodes, and passively sees alternately
Make in-degree Vin, in-degree is that other nodes point to the limit of self, then high-quality node often exists more than the first predetermined threshold value simultaneously
In-degree and out-degree, and out-degree in-degree ratioClose to 1;
To there is in-degree and the out-degree exceeding preset value, and out-degree in-degree ratio simultaneouslyMore than 1 and preset threshold more than second
The node of value is as non-prime node.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State model to set up the matrix of high-quality node detection process in subelement and be expressed as follows:
Mapping matrix is the mapping relations matrix between the in-degree of inspected object and out-degree;Wherein, Min×outRepresenting matrix
Title, In represents the in-degree set of node, and Out represents the out-degree set of node;Vi,in, i=1...n and Vj,out, j=1...m
Represent the in-degree of node i and the out-degree of node j respectively;I=1...n, j=1...m represent node i in-degree and joint
Point j out-degree ratio;As i=j, high-quality node and non-prime node can be detected, the now P of high-quality nodeijTrend towards
1, and the P of non-prime nodeijMore than 1 and more than the second predetermined threshold value or less than 1 and less than the 3rd predetermined threshold value;And work as i ≠ j
When, if Pij=0 shows there is not interactive relation between different node, otherwise exists for interactive relation between node.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State and revise recall rate and the accuracy rate also including formulating result of detection in subelement, and threshold value setting is carried out to accuracy rate, with certainly
Determine whether jump to iteration subelement and be iterated calculating process.
Implement the present invention provide modified based on high-quality node detection system in the social networks of the big data of computer with
Prior art is compared and is had the advantages that:Can be used in that discovery social networks has higher compatible degree with user's request
Core node, is monitored by the information utilizing high-quality nodal information propagation monitoring model to issue high-quality node, in monitoring
During to sensitive information, sensitive information and the high-quality nodal information issuing sensitive information are sent to network supervision center, can
The information effectively issued high-quality node is monitored, and prevents the diffusion of information being harmful to.
Brief description
Fig. 1 is that the modified of the embodiment of the present invention is based on high-quality node detection system in the social networks of the big data of computer
Structured flowchart.
Detailed description of the invention
As it is shown in figure 1, it is excellent in the social networks that a kind of modified of embodiment of the present invention proposition is based on the big data of computer
Matter node detection system, it includes such as lower unit:
Monitoring participle unit, is used for setting up high-quality nodal information and propagates monitoring model;
High-quality node probe unit, for detecting high-quality node from internet social intercourse system;
Prewarning unit, supervises for the information utilizing high-quality nodal information propagation monitoring model to issue high-quality node
Sensitive information and the high-quality nodal information issuing sensitive information, when monitoring sensitive information, are sent to summing elements by control;
Summing elements, for the Weight selected according to sensitive information by sensitive information and the high-quality joint issuing sensitive information
Dot information is sent to network supervision center;
Summing elements includes:
Weight setting subelement, affects weights for prestore all kinds of sensitive information;
Cumulative subelement, for when receiving the sensitive information that prewarning unit sends, it is judged that the sensitive information of reception
Weights, and the weights of sensitive information are added up;
Threshold value sets subelement, for determining whether whether the weights after adding up exceed alarm threshold value, is exceeding warning
During threshold value, sensitive information and the high-quality nodal information issuing sensitive information are sent to network supervision center.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Monitoring participle unit includes:
First participle subelement, for carrying out participle by the netspeak information needing training according to language performance rule;
Whether the second participle subelement, can proceed first participle after being used for judging first participle subelement participle
Unit carries out participle, if participle can not be continued, then carries out fine granularity participle, otherwise jumps to first participle subelement according to language
Speech expression rule carries out participle;
Sensitive word database, for storing the sensitive information vocabulary needing monitoring.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Described high-quality node probe unit includes:
Set determines subelement, for extracting the social networks node set at the high-quality node place needing detection;
Subelement is set up in mapping, for setting up the joint of social networks to the social networks node in social networks node set
Point mapping relations;
Subelement set up by model, extracts detection high-quality node diagnostic for the mechanics according to high-quality node;According to carrying
The high-quality node diagnostic taking sets up the characterization rules model of high-quality node detection;
Training subelement, for being grouped social networks node as experiment sample, then carry out station work and
Node-classification;
Revising subelement, the result for detecting high-quality node is estimated and feedback result, and is training repeatedly
During the rule not meeting detection high-quality node diagnostic is corrected, thus reach the purpose being optimized model;
Iteration subelement, turns again to train the training of subelement interior joint to enter with classification link for the model after optimizing
Row high-quality node detects to improve detection progress, and is iterated computing until the detection progress of high-quality node exceedes setting threshold value
Thus complete high-quality node detection process in whole social networks.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State prewarning unit to include:
Data acquisition subelement, for crawling the real time data of high-quality node issue and writing data buffer storage storehouse;
Cluster subelement, for the real time data in the first predetermined amount of time being ranked up according to pre-defined algorithm, screening
Go out the information exceeding preset heat value in the first predetermined amount of time;To being made up of real time data in the second predetermined amount of time
Text carries out burst word extraction, and then carries out vectorization, clusters the text of vectorization, chooses all kinds of middle exceptional value maximum
Real time data is as the abnormal information monitoring;Show information and the exception of the preset heat value of corresponding bar number according to predetermined threshold value
Information;
Judgment sub-unit, enters row filter for the information of preset heat value and abnormal information are sent to monitoring participle unit
Judge whether sensitive word;When monitoring sensitive word, sensitive word and issue are comprised the high-quality node of sensitive word information
Information is sent to summing elements.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system,
Described model is set up the mechanics extraction detection high-quality node diagnostic according to high-quality node in subelement and is included:
Node is set and is judged as the nodal community of outstanding node, possess the nodal community of outstanding node at a certain node
When, then this nodal community has the feature of high quality;
Arrange and between node, As time goes on just should possess interactivity frequently, referred to as interactive degree Vinter;In society
Hand in network, be connected limit as node has between the feature of core node, and they with all mid-side nodes to exist;Connect limit at these
In, regard the active of high-quality node as out-degree V alternatelyout, out-degree is self to point to the limit of other nodes, and passively sees alternately
Make in-degree Vin, in-degree is that other nodes point to the limit of self, then high-quality node often exists more than the first predetermined threshold value simultaneously
In-degree and out-degree, and out-degree in-degree ratioClose to 1;
To there is in-degree and the out-degree exceeding preset value, and out-degree in-degree ratio simultaneouslyMore than 1 and preset threshold more than second
The node of value is as non-prime node.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State model to set up the matrix of high-quality node detection process in subelement and be expressed as follows:
Mapping matrix is the mapping relations matrix between the in-degree of inspected object and out-degree;Wherein, Min×outRepresenting matrix
Title, In represents the in-degree set of node, and Out represents the out-degree set of node;Vi,in, i=1...n and Vj,out, j=1...m
Represent the in-degree of node i and the out-degree of node j respectively;I=1...n, j=1...m represent node i in-degree and joint
Point j out-degree ratio;As i=j, high-quality node and non-prime node can be detected, the now P of high-quality nodeijTrend towards
1, and the P of non-prime nodeijMore than 1 and more than the second predetermined threshold value or less than 1 and less than the 3rd predetermined threshold value;And work as i ≠ j
When, if Pij=0 shows there is not interactive relation between different node, otherwise exists for interactive relation between node.
In modified of the present invention is based on the social networks of the big data of computer in high-quality node detection system, institute
State and revise recall rate and the accuracy rate also including formulating result of detection in subelement, and threshold value setting is carried out to accuracy rate, with certainly
Determine whether jump to iteration subelement and be iterated calculating process.
Implement high-quality node detecting method and system in the social networks that the present invention provides compared with prior art have with
Lower beneficial effect:Can be used in the core node finding that there is in social networks higher compatible degree with user's request, by utilizing
High-quality nodal information is propagated the monitoring model information of issuing high-quality node and is monitored, when monitoring sensitive information, by quick
The high-quality nodal information of sense information and issue sensitive information is sent to network supervision center, effectively can send out high-quality node
The information of cloth is monitored, and prevents the diffusion of information being harmful to.
It is understood that for the person of ordinary skill of the art, can do according to the technology design of the present invention
Go out other various corresponding to change and deformation, and all these change all should belong to the protection model of the claims in the present invention with deformation
Enclose.
Claims (7)
1. a modified is based on high-quality node detection system in the social networks of the big data of computer, it is characterised in that its bag
Include such as lower unit:
Monitoring participle unit, is used for setting up high-quality nodal information and propagates monitoring model;
High-quality node probe unit, for detecting high-quality node from internet social intercourse system;
Prewarning unit, is monitored for the information utilizing high-quality nodal information propagation monitoring model to issue high-quality node,
When monitoring sensitive information, sensitive information and the high-quality nodal information issuing sensitive information are sent to summing elements;
Summing elements, for the Weight selected according to sensitive information by sensitive information and the high-quality node letter issuing sensitive information
Breath is sent to network supervision center;
Summing elements includes:
Weight setting subelement, affects weights for prestore all kinds of sensitive information;
Cumulative subelement, for when receiving the sensitive information that prewarning unit sends, it is judged that the weights of the sensitive information of reception,
And the weights of sensitive information are added up;
Threshold value sets subelement, for determining whether whether the weights after adding up exceed alarm threshold value, is exceeding alarm threshold value
When, sensitive information and the high-quality nodal information issuing sensitive information are sent to network supervision center.
2. modified as claimed in claim 1 is based on high-quality node detection system in the social networks of the big data of computer, its
It is characterised by,
Monitoring participle unit includes:
First participle subelement, for carrying out participle by the netspeak information needing training according to language performance rule;
Whether the second participle subelement, can proceed first participle subelement after being used for judging first participle subelement participle
Carry out participle, if participle can not be continued, then carry out fine granularity participle, otherwise jump to first participle subelement according to language table
Reach rule and carry out participle;
Sensitive word database, for storing the sensitive information vocabulary needing monitoring.
3. modified as claimed in claim 2 is based on high-quality node detection system in the social networks of the big data of computer, its
It is characterised by,
Described high-quality node probe unit includes:
Set determines subelement, for extracting the social networks node set at the high-quality node place needing detection;
Subelement is set up in mapping, and the node for setting up social networks to the social networks node in social networks node set reflects
Penetrate relation;
Subelement set up by model, extracts detection high-quality node diagnostic for the mechanics according to high-quality node;According to extract
High-quality node diagnostic sets up the characterization rules model of high-quality node detection;
Training subelement, for being grouped social networks node as experiment sample, then carries out station work and node
Classification;
Revising subelement, the result for detecting high-quality node is estimated and feedback result, and is training process repeatedly
Middle the rule not meeting detection high-quality node diagnostic is corrected, thus reaches the purpose being optimized model;
Iteration subelement, turns again to train the training of subelement interior joint to carry out excellent with classification link for the model after optimizing
The detection of matter node improving detection progress, and be iterated computing until the detection progress of high-quality node exceed setting threshold value thus
Complete high-quality node detection process in whole social networks.
4. modified as claimed in claim 3 is based on high-quality node detection system in the social networks of the big data of computer, its
Being characterised by, described prewarning unit includes:
Data acquisition subelement, for crawling the real time data of high-quality node issue and writing data buffer storage storehouse;
Cluster subelement, for being ranked up the real time data in the first predetermined amount of time according to pre-defined algorithm, filters out the
The information exceeding preset heat value in one predetermined amount of time;To the text being made up of real time data in the second predetermined amount of time
Carry out burst word extraction, and then carry out vectorization, the text of vectorization is clustered, choose all kinds of middle exceptional value maximum in real time
Data are as the abnormal information monitoring;Show the information of the preset heat value of corresponding bar number and abnormal letter according to predetermined threshold value
Breath;
Judgment sub-unit, enters row filter judgement for the information of preset heat value and abnormal information are sent to monitoring participle unit
Whether there is sensitive word;When monitoring sensitive word, sensitive word and issue are comprised the high-quality nodal information of sensitive word information
It is sent to summing elements.
5. modified as claimed in claim 4 is based on high-quality node detection system in the social networks of the big data of computer, its
It is characterised by,
Described model is set up the mechanics extraction detection high-quality node diagnostic according to high-quality node in subelement and is included:
Node is set and is judged as the nodal community of outstanding node, when a certain node possesses the nodal community of outstanding node, then
This nodal community has the feature of high quality;
Arrange and between node, As time goes on just should possess interactivity frequently, referred to as interactive degree Vinter;In social network
It in network, is connected limit as node has between the feature of core node, and they with all mid-side nodes to exist;Connect in limit at these, will
Out-degree V is regarded in the active of high-quality node alternately asout, out-degree is self to point to the limit of other nodes, and passively regards in-degree alternately as
Vin, in-degree be other nodes point to the limit of self, then high-quality node often simultaneously exist more than the first predetermined threshold value in-degree and
Out-degree, and out-degree in-degree ratioClose to 1;
To there is in-degree and the out-degree exceeding preset value, and out-degree in-degree ratio simultaneouslyMore than 1 and more than the second predetermined threshold value
Node is as non-prime node.
6. modified as claimed in claim 5 is based on high-quality node detection system in the social networks of the big data of computer, its
Being characterised by, the matrix that high-quality node detection process in subelement set up by described model is expressed as follows:
Mapping matrix is the mapping relations matrix between the in-degree of inspected object and out-degree;Wherein, Min×outRepresenting matrix name
Claiming, In represents the in-degree set of node, and Out represents the out-degree set of node;Vi,in, i=1...n and Vj,out, j=1...m divides
Biao Shi the out-degree of the in-degree of node i and node j;I=1...n, j=1...m represent node i in-degree and node j
Out-degree ratio;As i=j, high-quality node and non-prime node can be detected, the now P of high-quality nodeijTrend towards 1, and
The P of non-prime nodeijMore than 1 and more than the second predetermined threshold value or less than 1 and less than the 3rd predetermined threshold value;And as i ≠ j, if
Pij=0 shows there is not interactive relation between different node, otherwise exists for interactive relation between node.
7. modified as claimed in claim 6 is based on high-quality node detection system in the social networks of the big data of computer, its
It is characterised by, described correction subelement also includes recall rate and the accuracy rate formulating result of detection, and threshold is carried out to accuracy rate
Value sets, to decide whether that jumping to iteration subelement is iterated calculating process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610910848.7A CN106447508A (en) | 2016-10-20 | 2016-10-20 | Improved high-quality node detection system based on computer large data in social network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610910848.7A CN106447508A (en) | 2016-10-20 | 2016-10-20 | Improved high-quality node detection system based on computer large data in social network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106447508A true CN106447508A (en) | 2017-02-22 |
Family
ID=58176746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610910848.7A Pending CN106447508A (en) | 2016-10-20 | 2016-10-20 | Improved high-quality node detection system based on computer large data in social network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106447508A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108427669A (en) * | 2018-02-27 | 2018-08-21 | 华青融天(北京)技术股份有限公司 | Abnormal behaviour monitoring method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
CN104933443A (en) * | 2015-06-26 | 2015-09-23 | 北京途美科技有限公司 | Automatic identifying and classifying method for sensitive data |
CN105447128A (en) * | 2015-11-18 | 2016-03-30 | 临沂大学 | Method for predicting spread range of microblog public opinions |
CN105701097A (en) * | 2014-11-25 | 2016-06-22 | 四三九九网络股份有限公司 | Social-network-platform-based public opinion analysis method and system |
CN105786929A (en) * | 2014-12-26 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Information monitoring method and device |
-
2016
- 2016-10-20 CN CN201610910848.7A patent/CN106447508A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
CN105701097A (en) * | 2014-11-25 | 2016-06-22 | 四三九九网络股份有限公司 | Social-network-platform-based public opinion analysis method and system |
CN105786929A (en) * | 2014-12-26 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Information monitoring method and device |
CN104933443A (en) * | 2015-06-26 | 2015-09-23 | 北京途美科技有限公司 | Automatic identifying and classifying method for sensitive data |
CN105447128A (en) * | 2015-11-18 | 2016-03-30 | 临沂大学 | Method for predicting spread range of microblog public opinions |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108427669A (en) * | 2018-02-27 | 2018-08-21 | 华青融天(北京)技术股份有限公司 | Abnormal behaviour monitoring method and system |
CN108427669B (en) * | 2018-02-27 | 2021-06-11 | 华青融天(北京)软件股份有限公司 | Abnormal behavior monitoring method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10339161B2 (en) | Expanding network relationships | |
CN106504102A (en) | High-quality node detection system in a kind of social networkies based on computer big data | |
CN100479572C (en) | Method and system for monitoring suspicious user of rubbish SMS | |
CN104899267B (en) | A kind of integrated data method for digging of social network sites account similarity | |
CN105138558B (en) | The real time individual information collecting method of content is accessed based on user | |
CN107948255B (en) | The method for pushing and computer readable storage medium of APP | |
CN103886047B (en) | Towards the online recommendation method of distribution of stream data | |
CN103118111B (en) | Information push method based on data from a plurality of data interaction centers | |
CN104978314B (en) | Media content recommendations method and device | |
CN105701097A (en) | Social-network-platform-based public opinion analysis method and system | |
CN108304437A (en) | A kind of automatic question-answering method, device and storage medium | |
CN105389389B (en) | A kind of network public-opinion propagation situation medium control analysis method | |
CN104408102B (en) | For network hot word and the data processing method and device of the degree of association of object | |
US10152478B2 (en) | Apparatus, system and method for string disambiguation and entity ranking | |
CN105339936A (en) | Text matching device and method, and text classification device and method | |
CN105354305A (en) | Online-rumor identification method and apparatus | |
WO2016115944A1 (en) | Method and device for establishing webpage quality model | |
CN104978878A (en) | Microlecture teaching system and method | |
CN105787662A (en) | Mobile application software performance prediction method based on attributes | |
CN111460145A (en) | Learning resource recommendation method, device and storage medium | |
CN113158050A (en) | Suspected problem review, review and screening method and system and storage medium | |
CN102915313B (en) | Error correction relation generation method and system in web search | |
CN109376288A (en) | A kind of cloud computing platform and its equalization methods for realizing semantic search | |
CN106447508A (en) | Improved high-quality node detection system based on computer large data in social network | |
CN105323763B (en) | A kind of recognition methods of junk short message and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
RJ01 | Rejection of invention patent application after publication |