CN105589935A - Social group recognition method - Google Patents
Social group recognition method Download PDFInfo
- Publication number
- CN105589935A CN105589935A CN201510920148.1A CN201510920148A CN105589935A CN 105589935 A CN105589935 A CN 105589935A CN 201510920148 A CN201510920148 A CN 201510920148A CN 105589935 A CN105589935 A CN 105589935A
- Authority
- CN
- China
- Prior art keywords
- user
- group
- session
- node
- text
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000001419 dependent effect Effects 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 7
- 238000012804 iterative process Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 230000003252 repetitive effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000032683 aging Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000854350 Enicospilus group Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 238000013264 cohort analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013481 data capture Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a social group recognition method, comprising counting conversation contents and relationships among user nodes, and recognizing the specific social group based on the counting result. According to the social group recognition method provided by the invention, the recognition accuracy and timeliness of the Internet social groups are effectively improved.
Description
Technical field
The present invention relates to large data, particularly a kind of social group recognition methods.
Background technology
Along with the development of mobile Internet, the social networks in life has been moved on internet, bringThe change of information exchange system, and changed traditional interpersonal communication mode, to each neck of social lifeTerritory has profound significance. Between user, can link up widely, interaction, by writing, transfer, collectionEtc. means, text data is operated. In social networks, always exist part of nodes to connect tightr,These nodes are relatively sparse with the contact between other nodes, this part can be connected thus to joint closelyPoint is classified as same group. Group is as a kind of important social networks attribute, virtually to public sentiment control withAnd network supervision has brought huge challenge. If group's relation is not carried out to fully identification identification, withoutMethod identification group interest, recommends content of interest, more cannot find in time harm information, safeguards good netNetwork environment.
Summary of the invention
For solving the existing problem of above-mentioned prior art, the present invention proposes the recognition methods of a kind of social group,Comprise:
The internodal session content of counting user and relation, identify specific social group based on above-mentioned statisticsGroup.
Preferably, the internodal session content of described counting user and relation, further comprise:
Utilize data structure to be described conversation procedure; The user who participates in session is connected to one with relationRise, be built into the group based on individual event; Finally in social networks topology, adopt node measurement index to knowBe not related to not by force the node in group, finally with tree-like hierarchical structure, this event be stored to file; Wherein instituteState and be related to that group's specific definition is by force, if the known α of group meets: for the each user node i in the α of group,The number of nodes that all meets i and the α of group interior nodes formation is greater than the node of this node and the α of group exterior node formationQuantity, the α of group is called as the strong group that is related to;
Obtain the remark information of the sensing superior node comprising in each session topology, find certain specific nodeFather node, obtain the transfer list that every session is safeguarded, record all these information of transfer user andComment on, find thus the child node collection of this information node; On the basis of session tree, by between userRelation, is built into relational network by the node that participates in session; In the time obtaining social networks, obtain common concernList, utilizes each node L to complete the concern to participating in event session user u, if uiPay close attention to uj，Node L and ui have common concern, i.e. ujNode; Obtain in this way uiWhether pay close attention to groupOther interior nodes;
Extract the semantic information of candidate user, the user of on this basis semantic information being mated with session titleScreen as identical semantic user, more identical semantic user is carried out to social networks analysis, for meetingThe user of analysis result screens as new candidate user; Candidate user be divided into again text-dependent user andBe related to associated user; In iterative process each time, be related to that associated user produces text phase by semantic analysisClose user, then calculate text-dependent user's session title degree of association threshold value, thereby obtain target group;
Initial candidate user's set utilizes search engine to obtain, and concrete steps are as follows: obtain group characteristics word,In search engine, retrieve, the result of retrieval is captured, obtain the user who delivers content of textLink information, by analyzing above-mentioned user's link information, captures each user's social content,As initializing candidate user;
Session text to user is analyzed, and carrys out more each use by calculating the user conversation title degree of associationDegree of correlation between family and special session title, if exist the user that is related to after the i time model iteration to gather,In order to obtain the text-dependent user set of the i+1 time, to being related to that each element in user's set is eachIndividual text-dependent user, given semantic key words, calculates each text-dependent user's the session title degree of association;The session title degree of association of user i equals this user and occurs that the number of times of keyword is divided by user's text sum; ?After having obtained text-dependent user set, calculate text-dependent user's the unduplicated session title degree of associationThe number of value, and then obtain the threshold value of group nodes;
If the text-dependent user who calculates after the i time iteration has M, wherein non-repetitive user has MU;The top n user of group nodes is expressed as:
To M text-dependent user according to the descending of session title degree of association value, the top n after sequenceUser is that effectively this top n user is a member in group; Just obtaining after N user can be byThey add group nodes set as group nodes.
The present invention compared to existing technology, has the following advantages:
The present invention proposes the recognition methods of a kind of social group, effectively improve the identification standard of the social cohort in internetReally rate and ageing.
Brief description of the drawings
Fig. 1 is according to the flow chart of the social group recognition methods of the embodiment of the present invention.
Detailed description of the invention
Below with together with the accompanying drawing of the diagram principle of the invention, provide to one or more embodiment of the present invention in detailThin description. Describe the present invention in conjunction with such embodiment, but the invention is not restricted to any embodiment. ThisBright scope is only defined by the claims, and the present invention contain manyly substitute, amendment and equivalent. ?In below describing, set forth many details to provide thorough understanding of the present invention. For exemplary purposesAnd these details are provided, and also can be according to right without some or all details in these detailsClaim is realized the present invention.
An aspect of of the present present invention provides the recognition methods of a kind of social group. Fig. 1 is according to the embodiment of the present inventionSocial group recognition methods flow chart.
In order to complete the cohort analysis to social networks, model data collecting system is to social network sites serviceData on device gather, and wherein data type comprises: user profile is as ID, user name, textData are as session id, session text, and relation data is as paid close attention to list and follower's list. This system bagContaining with lower module: user profile is obtained, text data obtains, social networks generation, de-redundancy, multithreading,Data storage, priority are selected, token obtains in batches. Master control thread in data collecting system carries out authorityCertification, program initialization, kind child node read, filtration, database manipulation; Data acquisition thread is by APIOpen interface carries out data acquisition, and gatherer process comprises that interface requests, json Data Analysis, pointer upgrade,Return to eventually master control total number of threads according to list. De-redundancy calculate selection on, the present invention adopt binary system toAmount and a series of random mapping function. For capturing seed ID list, ID list, relation list, meetingWords ID has added respectively de-redundancy function, and seed list captures user list, social list all unique with itMark ID carries out, and the form of relation is grouped together two users' ID, and distinguishes both elder generationsRear order, the former is for being concerned, the follower that the latter is the former. System has been added corresponding behaviour in multiple modulesDo: while extracting seed ID, multithreading adds mutual exclusion lock to the operation of database; For distributing, each thread capturesTask, as obtaining of 1 responsible text of thread; Thread 2 obtains userspersonal information; For each thread orderBoard resources bank is distinguished formula permutation and combination. And for each thread, a breakpoint file being set separately, record is grabbedThe position of getting. DBM by database connect, close, inquire about, increase, deletion action unifyManagement, first the ID that captures object inputs to file by manual type, starts all to add before crawl task at every turnCarry a priority file. In processing, point task capturing on object, for each thread is formulated a set of specificCrawl task, from user profile obtain, text obtains, one or more processing of choosing Relation acquisitionTarget. From the control of speed, system has proposed two kinds of regulative modes altogether, and the one, the quantity of control thread, twoTo adjust the data volume of obtaining after API request.
Individual subscriber attribute can reflect user's characteristic, and this specific character provides institute of identification group justThe strong feature needing. First the present invention is described group to be identified by manual type, and according to theseGroup's characteristic takes out one group of lists of keywords, i.e. group characteristics word. Secondly, utilize filtering user information mouldPiece is identified the user who detects, finds to belong to the user node of this group. In filter process, adoptCharacter string canonical coupling is mated individual subscriber attribute with group characteristics word, if at individual subscriber attributeOr comprise these Feature Words in the text data such as user's name, this user is divided to group to be identified.
User behavior filtering module is processed the text data being produced by the subjective desire of user in social networks,Utilize the similarity between following process computation user and group.
One of the model N gt U based on group characteristics word, expression specific as follows:
U＝[Tl,T2，T3，...，TN]
The wherein T representative frequency vector that certain Feature Words occurs in group, the subscript of N representation feature word.
Secondly, utilize the full text P of text segmentation to user AAProcess.
PA＝[key1，key2，...，keyN]
sim(A，U)＝(PA·U)/||(PA||||U||)
The key value is here the frequency vector that in user conversation text, each Feature Words occurs, relatively user's literary compositionWhether the behavioural characteristic between notebook data and group is close, if similarity sim (A, U) exceedes predetermined threshold value,This user node A is divided in the U of group. When this node adds after group, group characteristics word can be along withIn group, user gathers the text data dynamic change producing, and identifies the potential Feature Words in current group.
In social networks filtering module, the present invention has applied the unknown joint of attribute of a relation identification in social networksWhether point belongs to group. If the known α of group meets following requirement, the α of group is called as the strong group that is related to:For the each user node i in the α of group, the number of nodes that all meets i and the α of group interior nodes formation is greater than thisThe number of nodes that node and the α of group exterior node form.
Adopt following methods to carry out the strong group identification that is related to, first conversation procedure is reduced, tie with dataStructure is described; Secondly the user who participates in session is linked together with real relation, be built into based on listThe group of individual event; Finally in social networks topology, adopt corresponding node measurement index to identify the strong group of relationNode in group.
The present invention analyzes for the conversational axiom of information in social networks, and by transfer the registration of Party membership, etc. from one unit to another reductionReal event evolution, is finally stored to file with tree-like hierarchical structure by this event.
In each session topology, can comprise a remark information that points to superior node, can find accordingly certainThe father node of specific node. Every session also all can be safeguarded a transfer list, records this information of all transfersUser and comment, can find accordingly the child node collection of this information node. On the basis of session tree,By the true relation between user, the node that participates in session is built into relational network. Obtain real societyFriendship relation. Adopt API and webpage parsing to combine and jointly close injecting method, set up the topology of social networks, profitComplete the concern to participating in event session user u with each node L, if hence one can see that uiPay close attention to uj，Node L and uiThere is common concern, i.e. ujNode. Obtain in this way uiWhether pay close attention to groupOther interior nodes.
Carry out, in the process of group identification, first extracting candidate user at utilization semanteme, relation, user dataSemantic information, on this basis the user of semantic information and session title coupling is screened as identicalSemantic user, more identical semantic user is carried out to social networks analysis, for the use before relationship analysis rankFamily screens as new candidate user. Candidate user is divided into again text-dependent user and is related to associated user.In iterative process each time, be related to that associated user produces text-dependent user by semantic analysis, then calculateText-dependent user's session title degree of association threshold value, thus target group obtained.
Candidate user set is used symbol us to represent, utilizes search engine to obtain initial candidate user set, toolBody step is as follows: obtain group characteristics word, in search engine, retrieve, the result of retrieval is grabbedGet, obtain the user's who delivers content of text link information, by analyzing above-mentioned user's link information, rightEach user's social content captures, as initializing candidate user.
The candidate user set us producing in the i time iterative processiRepresent its candidate user uijRepresent,usiWith uijBetween relation can be expressed as:
usi＝(ui1，…uij)j＜Ni
NiRepresent the number of the candidate user producing in the i time iterative process.
Candidate user is conventionally divided into text-dependent user, is related to phase according to different generative processes and particular communityClose user and group nodes.
Correlation candidate user is carried out to the first step that semantic analysis is model iteration. Candidate user is repeatedly lastGeneration be related to associated user. Session text to user is analyzed, by calculating the association of user conversation titleDegree carrys out the degree of correlation between more each user and special session title. If exist after the i time model iterationBe related to user set, in order to obtain the text-dependent user set of the i+1 time, to be related in user's set oftenAn element is each text-dependent user, and given semantic key words, calculates each text-dependent user'sThe session title degree of association. The session title degree of association of user i equals number of times that keyword appears in this user divided by useThe text sum at family, the session title degree of association value of a user i is higher, and user i and this session title are describedBetween the degree of association higher. By calculating the user conversation title degree of association, tell which user and this sessionTitle is closely associated.
After having obtained text-dependent user set, determine which text-dependent user is effectively, obtainsGroup nodes. By calculating text-dependent user's the number of unduplicated session title degree of association value, and thenObtain the TopN threshold value of group nodes.
If the text-dependent user who calculates after the i time iteration has M, wherein non-repetitive user has MU., the top n user of group nodes is expressed as:
To M text-dependent user according to the descending of session title degree of association value, the top n after sequenceUser is that effectively this top n user is a member in group. Just obtaining after N user can be byThey add group nodes set as group nodes.
After obtaining group nodes, by increasing sample, expand hunting zone. Analyze by social networksFrom the network of personal connections of group nodes, identify the candidate user of deep layer. Social networks analysis comprises step:
Obtain the directed networks figure that follower and the person of being concerned in group nodes gather formation. Every in computing networkIndividual user's common attention rate, i.e. in the follower of user i set, every two followers form the inferior of mutual concernNumber. Common attention rate is greater than the user of predefined threshold value, is the needed user of relation.
After obtaining being related to user, can continue iteration to model, continue to capture by data capture programBe related to user's Social behaviors, thereby it is carried out to semantic analysis.
In sum, the present invention proposes the recognition methods of a kind of social group, effectively improve internet social groupsGroup's recognition accuracy and ageing.
Obviously, it should be appreciated by those skilled in the art, above-mentioned of the present invention each module or each step are passableRealize with general computing system, they can concentrate on single computing system, or are distributed in manyOn the network that individual computing system forms, alternatively, they can use the executable program code of computing systemRealize, thereby, they can be stored in storage system and be carried out by computing system. Like this, thisBrightly be not restricted to any specific hardware and software combination.
Should be understood that, above-mentioned detailed description of the invention of the present invention is only for exemplary illustration or explanation basisThe principle of invention, and be not construed as limiting the invention. Therefore, without departing from the spirit and scope of the present inventionSituation under make any amendment, be equal to replacement, improvement etc., all should be included in protection scope of the present inventionWithin. In addition, claims of the present invention be intended to contain fall into claims scope and border orWhole variations and modification in the equivalents on this scope of person and border.
Claims (2)
1. a social group recognition methods, is characterized in that, comprising:
The internodal session content of counting user and relation, identify specific social group based on above-mentioned statisticsGroup.
2. method according to claim 1, is characterized in that, the internodal session of described counting userContent and relation, further comprise:
Utilize data structure to be described conversation procedure; The user who participates in session is connected to one with relationRise, be built into the group based on individual event; Finally in social networks topology, adopt node measurement index to knowBe not related to not by force the node in group, finally with tree-like hierarchical structure, this event be stored to file; Wherein instituteState and be related to that group's specific definition is by force, if the known α of group meets: for the each user node i in the α of group,The number of nodes that all meets i and the α of group interior nodes formation is greater than the node of this node and the α of group exterior node formationQuantity, the α of group is called as the strong group that is related to;
Obtain the remark information of the sensing superior node comprising in each session topology, find certain specific nodeFather node, obtain the transfer list that every session is safeguarded, record all these information of transfer user andComment on, find thus the child node collection of this information node; On the basis of session tree, by between userRelation, is built into relational network by the node that participates in session; In the time obtaining social networks, obtain common concernList, utilizes each node L to complete the concern to participating in event session user u, if uiPay close attention to uj，Node L and uiThere is common concern, i.e. ujNode; Obtain in this way uiWhether pay close attention to groupOther interior nodes;
Extract the semantic information of candidate user, the user of on this basis semantic information being mated with session titleScreen as identical semantic user, more identical semantic user is carried out to social networks analysis, for meetingThe user of analysis result screens as new candidate user; Candidate user be divided into again text-dependent user andBe related to associated user; In iterative process each time, be related to that associated user produces text phase by semantic analysisClose user, then calculate text-dependent user's session title degree of association threshold value, thereby obtain target group;
Initial candidate user's set utilizes search engine to obtain, and concrete steps are as follows: obtain group characteristics word,In search engine, retrieve, the result of retrieval is captured, obtain the user who delivers content of textLink information, by analyzing above-mentioned user's link information, captures each user's social content,As initializing candidate user;
Session text to user is analyzed, and carrys out more each use by calculating the user conversation title degree of associationDegree of correlation between family and special session title, if exist the user that is related to after the i time model iteration to gather,In order to obtain the text-dependent user set of the i+1 time, to being related to that each element in user's set is eachIndividual text-dependent user, given semantic key words, calculates each text-dependent user's the session title degree of association;The session title degree of association of user i equals this user and occurs that the number of times of keyword is divided by user's text sum; ?After having obtained text-dependent user set, calculate text-dependent user's the unduplicated session title degree of associationThe number of value, and then obtain the threshold value of group nodes;
If the text-dependent user who calculates after the i time iteration has M, wherein non-repetitive user has MU;The top n user of group nodes is expressed as:
To M text-dependent user according to the descending of session title degree of association value, the top n after sequenceUser is that effectively this top n user is a member in group; Just obtaining after N user can be byThey add group nodes set as group nodes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510920148.1A CN105589935A (en) | 2015-12-11 | 2015-12-11 | Social group recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510920148.1A CN105589935A (en) | 2015-12-11 | 2015-12-11 | Social group recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105589935A true CN105589935A (en) | 2016-05-18 |
Family
ID=55929514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510920148.1A Pending CN105589935A (en) | 2015-12-11 | 2015-12-11 | Social group recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105589935A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182639A (en) * | 2017-12-29 | 2018-06-19 | 中国人民解放军火箭军工程大学 | A kind of network forum microcommunity determines method and system |
| CN109560981A (en) * | 2018-07-04 | 2019-04-02 | 蔚来汽车有限公司 | Determine method and apparatus, the computer storage medium of the node degree of association |
| CN110555081A (en) * | 2019-04-18 | 2019-12-10 | 国家计算机网络与信息安全管理中心 | Social interaction user classification method and device, electronic equipment and medium |
| US10885131B2 (en) | 2016-09-12 | 2021-01-05 | Ebrahim Bagheri | System and method for temporal identification of latent user communities using electronic content |
| CN113495941A (en) * | 2020-03-18 | 2021-10-12 | 北京京东尚科信息技术有限公司 | Method and apparatus for retrieving content items |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120303606A1 (en) * | 2011-05-24 | 2012-11-29 | Microsoft Corporation | Resource Download Policies Based On User Browsing Statistics |
| CN103793460A (en) * | 2013-11-22 | 2014-05-14 | 清华大学 | Method and system for sensing specific community on line on basis of social network |
| CN103793489A (en) * | 2014-01-16 | 2014-05-14 | 西北工业大学 | Method for discovering topics of communities in on-line social network |
-
2015
- 2015-12-11 CN CN201510920148.1A patent/CN105589935A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120303606A1 (en) * | 2011-05-24 | 2012-11-29 | Microsoft Corporation | Resource Download Policies Based On User Browsing Statistics |
| CN103793460A (en) * | 2013-11-22 | 2014-05-14 | 清华大学 | Method and system for sensing specific community on line on basis of social network |
| CN103793489A (en) * | 2014-01-16 | 2014-05-14 | 西北工业大学 | Method for discovering topics of communities in on-line social network |
Non-Patent Citations (2)
| Title |
|---|
| 姜京池: "社交网络的团体感知与挖掘方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 李蕾: "微博特定群体发现模型研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10885131B2 (en) | 2016-09-12 | 2021-01-05 | Ebrahim Bagheri | System and method for temporal identification of latent user communities using electronic content |
| CN108182639A (en) * | 2017-12-29 | 2018-06-19 | 中国人民解放军火箭军工程大学 | A kind of network forum microcommunity determines method and system |
| CN108182639B (en) * | 2017-12-29 | 2021-04-09 | 中国人民解放军火箭军工程大学 | Method and system for determining small group of internet forum |
| CN109560981A (en) * | 2018-07-04 | 2019-04-02 | 蔚来汽车有限公司 | Determine method and apparatus, the computer storage medium of the node degree of association |
| CN110555081A (en) * | 2019-04-18 | 2019-12-10 | 国家计算机网络与信息安全管理中心 | Social interaction user classification method and device, electronic equipment and medium |
| CN110555081B (en) * | 2019-04-18 | 2022-05-31 | 国家计算机网络与信息安全管理中心 | Social interaction user classification method and device, electronic equipment and medium |
| CN113495941A (en) * | 2020-03-18 | 2021-10-12 | 北京京东尚科信息技术有限公司 | Method and apparatus for retrieving content items |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156127B (en) | Method and device for selecting data content to push to terminal | |
| CN106557513B (en) | Event information pushing method and event information pushing device | |
| Bartunov et al. | Joint link-attribute user identity resolution in online social networks | |
| CN105488211A (en) | Method for determining user group based on feature analysis | |
| CN110457404B (en) | Social media account classification method based on complex heterogeneous network | |
| US9405746B2 (en) | User behavior models based on source domain | |
| US20170140058A1 (en) | Systems and Methods for Identifying Influencers and Their Communities in a Social Data Network | |
| CN108874812B (en) | Data processing method, server and computer storage medium | |
| CN103218431B (en) | A kind ofly can identify the system that info web gathers automatically | |
| CN105512301A (en) | User grouping method based on social content | |
| CN105589935A (en) | Social group recognition method | |
| CN112559747B (en) | Event classification processing method, device, electronic equipment and storage medium | |
| CN103678618A (en) | Web service recommendation method based on socializing network platform | |
| CN106980651B (en) | Crawling seed list updating method and device based on knowledge graph | |
| TWI571756B (en) | Methods and systems for analyzing reading log and documents corresponding thereof | |
| CN112488716B (en) | Abnormal event detection system | |
| CN102855245A (en) | Image similarity determining method and image similarity determining equipment | |
| De Boom et al. | Semantics-driven event clustering in Twitter feeds | |
| Huang et al. | On the understanding of interdependency of mobile app usage | |
| CN102915313B (en) | Error correction relation generation method and system in web search | |
| CN106411704A (en) | Distributed junk short message recognition method | |
| López-Ramírez et al. | Geographical aggregation of microblog posts for LDA topic modeling | |
| CN115329078B (en) | Text data processing method, device, equipment and storage medium | |
| CN108280772B (en) | Story context generation method based on event association in social network | |
| Nguyen et al. | Pagerank-based approach on ranking social events: a case study with flickr |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160518 |