CN106095987A - Community network-based content personalized pushing method and system - Google Patents
Community network-based content personalized pushing method and system Download PDFInfo
- Publication number
- CN106095987A CN106095987A CN201610451961.3A CN201610451961A CN106095987A CN 106095987 A CN106095987 A CN 106095987A CN 201610451961 A CN201610451961 A CN 201610451961A CN 106095987 A CN106095987 A CN 106095987A
- Authority
- CN
- China
- Prior art keywords
- user
- cluster
- user profile
- degree
- membership
- 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 31
- 238000001914 filtration Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000007 visual effect 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a content personalized pushing method and a system based on a community network, wherein the method comprises the following steps: acquiring user information accessing a community network, and clustering the user information to acquire a user information clustering result; acquiring the membership degree among all users in the cluster according to the user information clustering result; obtaining interest similarity among the users in the cluster according to membership degrees among the users in the cluster; and carrying out content personalized pushing on the target user according to the interest similarity among the users in the cluster. In the embodiment of the invention, the personalized recommendation of the information content is realized for the user through the community network, so that the user can obtain better use experience.
Description
Technical field
Planned network commending contents technical field of the present invention, particularly relates to a kind of content personalization based on community network and pushes away
Delivery method and system.
Background technology
In community network, user is in the face of numerous numerous and diverse information and resource, obtains oneself the most quickly and easily interested
Information be very important;But in the case of present community network technology high-speed development, user is difficult to get community
The accurate information pushing that user is carried out by network, community network is not the most that user is interested to the information major part that user pushes
Or the information wanted.
Community network analyze (social network analysis, SNA) be used for measuring actor individual and they residing for
Community network member between intricate relation, to becoming the communication pattern between group members to carry out visual modeling, and have
It is beneficial to the understanding to large-scale community network structure.SNA method can allow researcher " have an X-rayed " as see user in community network
Between interaction, it is seen that they create interconnective form.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, the invention provides a kind of content based on community network
Personalized push method and system, realize user is carried out information content personalized recommendation by community network, make user obtain
Preferably experience sense.
In order to solve above-mentioned technical problem, the invention provides a kind of content personalization propelling movement side based on community network
Method, described method includes:
Obtain the user profile accessing community network, described user profile is carried out clustering processing, obtain user profile and gather
Class result;
According to described user profile cluster result, obtain the degree of membership between each user in described cluster;
According to the degree of membership between user each in described cluster, obtain in described cluster Interest Similarity between each user;
Content personalization propelling movement is carried out to targeted customer according to Interest Similarity between user each in described cluster.
Preferably, the described user obtaining access community network, including:
Obtain the user profile of all users accessing described community network;Described user profile at least includes that user accesses
Any one in daily record or user interest content;
In the way of the restriction of access time, described user profile is filtered, obtain nearest 1 year and access described community network
The user profile of network.
Preferably, described described user profile is carried out clustering processing, including:
Described user profile is carried out information retrieval process, obtains and user profile at least includes user name, Yong Hufang
Ask daily record and user interest;
Carry out clustering processing according to the user name in described user profile, user access logs and user interest, obtain and use
Family information cluster result.
Preferably, described according to described user profile cluster result, obtain the degree of membership between each user in described cluster,
Including:
Determine the cluster centre of described user profile cluster result, obtain the user assembled around described cluster centre;
Use user's Subject Matrix that the user assembled around described cluster centre is processed, obtain each user in cluster
The degree of membership at center.
Preferably, according to the degree of membership between user each in described cluster, obtain in described cluster interest between each user
Similarity, including:
Obtain in described cluster degree of membership weight between each user, use in cluster described in described degree of membership weight calculation each
Interest Similarity between user.
It addition, the embodiment of the present invention additionally provides a kind of content personalization supplying system based on community network, described system
System includes:
Cluster module: for obtaining the user profile accessing community network, described user profile is carried out clustering processing, obtains
Take family information cluster result;
Degree of membership acquisition module: for according to described user profile cluster result, obtains in described cluster between each user
Degree of membership;
Interest Similarity acquisition module: for according to the degree of membership between user each in described cluster, obtain described cluster
In Interest Similarity between each user;
Pushing module: for carrying out content individual character according to Interest Similarity between user each in described cluster to targeted customer
Change and push.
Preferably, described cluster module includes:
Information acquisition unit: for obtaining the user profile of all users accessing described community network;Described user believes
Breath at least includes any one in user access logs or user interest content;
Information filtering unit: for described user profile being filtered in the way of the restriction of access time, obtain recently
The user profile accessing described community network in 1 year.
Preferably, described cluster module also includes:
Information extraction unit: for described user profile being carried out information retrieval process, in acquisition user profile at least
Including user name, user access logs and user interest;
Cluster cell: for gathering according to the user name in described user profile, user access logs and user interest
Class processes, and obtains user profile cluster result.
Preferably, described degree of membership acquisition module includes:
Cluster centre determines unit: for determining the cluster centre of described user profile cluster result, obtain described cluster
The user assembled around center;
Degree of membership acquiring unit: for using at user's Subject Matrix user to assembling around described cluster centre
Reason, obtains each user degree of membership at cluster centre.
Preferably, described Interest Similarity acquisition module includes:
Computing unit: be used for obtaining in described cluster degree of membership weight between each user, use described degree of membership weight meter
Calculate in described cluster Interest Similarity between each user.
In embodiments of the present invention, by modes such as user clusterings, calculate in this cluster the interest between user similar
Degree, carries out information pushing according to Interest Similarity between user in this cluster to user;Community network can realize to
Family carries out information content personalized recommendation, makes user obtain preferable experience sense.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it is clear that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is the method flow signal of the content personalization method for pushing based on community network in the embodiment of the present invention
Figure;
Fig. 2 is that the system structure composition of the content personalization supplying system based on community network in the embodiment of the present invention shows
It is intended to.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, those of ordinary skill in the art obtained under not making creative work premise all other
Embodiment, broadly falls into the scope of protection of the invention.
Fig. 1 is the method flow signal of the content personalization method for pushing based on community network in the embodiment of the present invention
Figure, as it is shown in figure 1, the method includes:
S11: obtain the user profile accessing community network, carries out clustering processing to this user profile, obtains user profile
Cluster result;
S123: according to this user profile cluster result, obtains the degree of membership between each user in this cluster;
S13: according to the degree of membership between user each in this cluster, obtains in this cluster Interest Similarity between each user;
S14: carry out content personalization propelling movement to targeted customer according to Interest Similarity between user each in this cluster.
S11 is further illustrated:
Obtain the user profile of all users accessing this community network;This user profile at least includes user access logs
Or any one in user interest content;In the way of the restriction of access time, this user profile is filtered, obtain recently
The user profile accessing described community network in 1 year.
This user profile is carried out information retrieval process, obtains and user profile at least includes that user name, user access
Daily record and user interest;Carry out clustering processing according to the user name in this user profile, user access logs and user interest, obtain
Take family information cluster result.
Further, by the way of administrator right or other, data base in community network is processed, obtain
Access the user profile of all users of this community network;In this user profile at least includes user access logs or user interest
Any one in appearance;After obtaining the user profile of all users accessing this community network, these user profile are entered
These users, to access the time sorted lists for order, are carried out in the way of the restriction of access time by row according to this sorted lists
Filtering user information, accessing limiting time can set according to the demand of user, uses in embodiments of the present invention 1 year
Interval time carries out filtering user information as filtration time, thus gets the nearest user's letter accessing this community network for a year
Breath.
Carry out information separation to filtering the user profile got, user profile is at least separated into user name, Yong Hufang
Ask the information such as daily record and user interest, then these user profile are carried out extraction process, obtain at least bag in user profile
Include user name, user access logs and user interest.Finally according to the user name in this user profile, user access logs and use
Family interest carries out clustering processing, obtains user clustering result;Because clustering algorithm is more, including K-MEANS, K-MEDOIDS,
The clustering algorithms such as Clara and Clarans, in the present embodiment, use K-MEANS clustering algorithm, the base of K-MEANS clustering algorithm
This thought is: sort out as center with k object in space, in object space near each center object respectively
It is classified as a class, by the way of successive ignition, the value of each cluster barycenter is gradually calculated renewal, until clustering barycenter the most not
Become.
S12 is described further:
Determine the cluster centre of this user profile cluster result, obtain the user assembled around this cluster centre;Use and use
The user assembled around described cluster centre is processed by family Subject Matrix, obtains each user degree of membership at cluster centre.
Further, higher according to user access logs, user interest similarity each other after having clustered
User as cluster centre, and according to this cluster centre centered by, the situation of user around, thus obtain in this cluster
The user assembled around the heart;Initialising subscriber Subject Matrix, uses the random number between 0 to 1 to carry out initialising subscriber and is subordinate to square
Battle array U={ul,u2,…,un, wherein uj=(u1j,u2j..., ucj) T, uijRepresent certain user j degree of membership at the i-th apoplexy due to endogenous wind, thus
Obtain a user mutual degree of membership at cluster centre.
S13 is described further:
According to the degree of membership between user each in this cluster, obtain in this cluster between each user Interest Similarity specifically
Obtain in this cluster degree of membership weight between each user, use in this this cluster of degree of membership weight calculation interest phase between each user
Like degree.
Further, it is converted in this cluster degree of membership weight between each user according to degree of membership and then uses this degree of membership
Interest Similarity between user in this cluster of weight calculation, the mode using degree of membership to be multiplied by a coefficient calculates this cluster
In Interest Similarity between user;Depending on this coefficient can be according to user's actual need.
S14 is described further:
By analyzing in targeted customer and cluster the Interest Similarity between each user, will be in targeted customer's Interest Similarity
Information or web content that higher user is interested carry out personalized push to targeted customer.
Fig. 2 is that the system structure composition of the content personalization supplying system based on community network in the embodiment of the present invention shows
It is intended to, as in figure 2 it is shown, this system includes:
Cluster module 11: for obtaining the user profile accessing community network, this user profile is carried out clustering processing, obtains
Take family information cluster result;
Degree of membership acquisition module 12: for according to this user profile cluster result, obtains in this cluster between each user
Degree of membership;
Interest Similarity acquisition module 13: for according to the degree of membership between user each in this cluster, obtain in this cluster
Interest Similarity between each user;
Pushing module 14: for carrying out content individual character according to Interest Similarity between user each in this cluster to targeted customer
Change and push.
Preferably, this cluster module 11 includes:
Information acquisition unit: for obtaining the user profile of all users accessing this community network;This user profile is extremely
Include any one in user access logs or user interest content less;
Information filtering unit: for this user profile being filtered in the way of the restriction of access time, obtain nearest one
Year accesses the user profile of this community network.
Preferably, this cluster module 11 also includes:
Information extraction unit: for this user profile being carried out information retrieval process, obtain at least bag in user profile
Include user name, user access logs and user interest;
Cluster cell: for clustering according to the user name in this user profile, user access logs and user interest
Process, obtain user profile cluster result.
Preferably, this degree of membership acquisition module 12 includes:
Cluster centre determines unit: for determining the cluster centre of this user profile cluster result, obtain this cluster centre
The user around assembled;
Degree of membership acquiring unit: for using at user's Subject Matrix user to assembling around this cluster centre
Reason, obtains each user degree of membership at cluster centre.
Preferably, this Interest Similarity acquisition module 13 includes:
Computing unit: be used for obtaining in this cluster degree of membership weight between each user, uses this degree of membership weight calculation should
Interest Similarity between each user in cluster.
Specifically, the operation principle of the system related functions module of the embodiment of the present invention can be found in the relevant of embodiment of the method
Describe, repeat no more here.
In embodiments of the present invention, by modes such as user clusterings, calculate in this cluster the interest between user similar
Degree, carries out information pushing according to Interest Similarity between user in this cluster to user;Community network can realize to
Family carries out information content personalized recommendation, makes user obtain preferable experience sense.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
Completing instructing relevant hardware by program, this program can be stored in a computer-readable recording medium, storage
Medium may include that read only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
It addition, above a kind of based on community network the content personalization method for pushing that the embodiment of the present invention is provided and
System is described in detail, and should have employed specific case herein and be set forth principle and the embodiment of the present invention,
The explanation of above example is only intended to help to understand method and the core concept thereof of the present invention;Simultaneously for this area one
As technical staff, according to the thought of the present invention, the most all will change, to sum up institute
Stating, this specification content should not be construed as limitation of the present invention.
Claims (10)
1. a content personalization method for pushing based on community network, it is characterised in that described method includes:
Obtain the user profile accessing community network, described user profile is carried out clustering processing, obtain user profile cluster knot
Really;
According to described user profile cluster result, obtain the degree of membership between each user in described cluster;
According to the degree of membership between user each in described cluster, obtain in described cluster Interest Similarity between each user;
Content personalization propelling movement is carried out to targeted customer according to Interest Similarity between user each in described cluster.
Content personalization method for pushing the most according to claim 1, it is characterised in that described acquisition accesses community network
User, including:
Obtain the user profile of all users accessing described community network;Described user profile at least includes user access logs
Or any one in user interest content;
In the way of the restriction of access time, described user profile is filtered, obtain nearest 1 year and access described community network
User profile.
Content personalization method for pushing the most according to claim 1, it is characterised in that described described user profile is carried out
Clustering processing, including:
Described user profile is carried out information retrieval process, obtains and user profile at least includes that user name, user access day
Will and user interest;
Carry out clustering processing according to the user name in described user profile, user access logs and user interest, obtain user's letter
Breath cluster result.
Content personalization method for pushing the most according to claim 1, it is characterised in that described poly-according to described user profile
Class result, obtains the degree of membership between each user in described cluster, including:
Determine the cluster centre of described user profile cluster result, obtain the user assembled around described cluster centre;
Use user's Subject Matrix that the user assembled around described cluster centre is processed, obtain each user at cluster centre
Degree of membership.
Content personalization method for pushing the most according to claim 1, it is characterised in that according to user each in described cluster it
Between degree of membership, obtain in described cluster Interest Similarity between each user, including:
Obtain in described cluster degree of membership weight between each user, use each user in cluster described in described degree of membership weight calculation
Between Interest Similarity.
6. a content personalization supplying system based on community network, it is characterised in that described system includes:
Cluster module: for obtaining the user profile accessing community network, described user profile is carried out clustering processing, obtain and use
Family information cluster result;
Degree of membership acquisition module: for according to described user profile cluster result, obtain the person in servitude between each user in described cluster
Genus degree;
Interest Similarity acquisition module: for according to the degree of membership between user each in described cluster, obtain in described cluster each
Interest Similarity between user;
Pushing module: push away for carrying out content personalization according to Interest Similarity between user each in described cluster to targeted customer
Send.
Content personalization supplying system the most according to claim 6, it is characterised in that described cluster module includes:
Information acquisition unit: for obtaining the user profile of all users accessing described community network;Described user profile is extremely
Include any one in user access logs or user interest content less;
Information filtering unit: for described user profile being filtered in the way of the restriction of access time, obtain nearest 1 year
Access the user profile of described community network.
Content personalization supplying system the most according to claim 6, it is characterised in that described cluster module also includes:
Information extraction unit: for described user profile being carried out information retrieval process, obtain at least including in user profile
User name, user access logs and user interest;
Cluster cell: for carrying out at cluster according to the user name in described user profile, user access logs and user interest
Reason, obtains user profile cluster result.
Content personalization supplying system the most according to claim 6, it is characterised in that described degree of membership acquisition module bag
Include:
Cluster centre determines unit: for determining the cluster centre of described user profile cluster result, obtain described cluster centre
The user around assembled;
Degree of membership acquiring unit: for using user's Subject Matrix that the user assembled around described cluster centre is processed,
Obtain each user degree of membership at cluster centre.
Content personalization supplying system the most according to claim 6, it is characterised in that described Interest Similarity obtains mould
Block includes:
Computing unit: be used for obtaining in described cluster degree of membership weight between each user, use described degree of membership weight calculation institute
State in cluster Interest Similarity between each user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610451961.3A CN106095987A (en) | 2016-06-20 | 2016-06-20 | Community network-based content personalized pushing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610451961.3A CN106095987A (en) | 2016-06-20 | 2016-06-20 | Community network-based content personalized pushing method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106095987A true CN106095987A (en) | 2016-11-09 |
Family
ID=57238085
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610451961.3A Pending CN106095987A (en) | 2016-06-20 | 2016-06-20 | Community network-based content personalized pushing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106095987A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109408733A (en) * | 2018-09-26 | 2019-03-01 | 西安理工大学 | A kind of diversified interest community method for building up based on VR environment |
CN109978075A (en) * | 2019-04-04 | 2019-07-05 | 江苏满运软件科技有限公司 | Vehicle dummy location information identifying method, device, electronic equipment, storage medium |
CN110209931A (en) * | 2019-05-17 | 2019-09-06 | 腾讯科技(深圳)有限公司 | Method for pushing and device, storage medium, the electronic device of media content |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN104462383A (en) * | 2014-12-10 | 2015-03-25 | 山东科技大学 | Movie recommendation method based on feedback of users' various behaviors |
-
2016
- 2016-06-20 CN CN201610451961.3A patent/CN106095987A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN104462383A (en) * | 2014-12-10 | 2015-03-25 | 山东科技大学 | Movie recommendation method based on feedback of users' various behaviors |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109408733A (en) * | 2018-09-26 | 2019-03-01 | 西安理工大学 | A kind of diversified interest community method for building up based on VR environment |
CN109978075A (en) * | 2019-04-04 | 2019-07-05 | 江苏满运软件科技有限公司 | Vehicle dummy location information identifying method, device, electronic equipment, storage medium |
CN109978075B (en) * | 2019-04-04 | 2021-09-28 | 江苏满运软件科技有限公司 | Vehicle false position information identification method and device, electronic equipment and storage medium |
CN110209931A (en) * | 2019-05-17 | 2019-09-06 | 腾讯科技(深圳)有限公司 | Method for pushing and device, storage medium, the electronic device of media content |
CN110209931B (en) * | 2019-05-17 | 2023-08-25 | 腾讯科技(深圳)有限公司 | Media content pushing method and device, storage medium and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Detecting community structure in complex networks using simulated annealing with k-means algorithms | |
CN105005589B (en) | A kind of method and apparatus of text classification | |
CN108595585A (en) | Sample data sorting technique, model training method, electronic equipment and storage medium | |
CN103049496B (en) | A kind of multiple users are carried out the method for customer group division, device and equipment | |
CN105874753A (en) | Systems and methods for behavioral segmentation of users in a social data network | |
CN102880719A (en) | User trajectory similarity mining method for location-based social network | |
CN109376610B (en) | Pedestrian unsafe behavior detection method based on image concept network in video monitoring | |
CN111866196B (en) | Domain name traffic characteristic extraction method, device and equipment and readable storage medium | |
CN113904872B (en) | Feature extraction method and system for anonymous service website fingerprint attack | |
CN106776928A (en) | Recommend method in position based on internal memory Computational frame, fusion social environment and space-time data | |
CN109871504A (en) | A kind of Course Recommendation System based on Heterogeneous Information network and deep learning | |
CN106095987A (en) | Community network-based content personalized pushing method and system | |
CN110348494A (en) | A kind of human motion recognition method based on binary channels residual error neural network | |
CN110516533A (en) | A kind of pedestrian based on depth measure discrimination method again | |
CN109949174A (en) | A kind of isomery social network user entity anchor chain connects recognition methods | |
Han et al. | Linking social network accounts by modeling user spatiotemporal habits | |
Zhang et al. | Multi-view clustering of microbiome samples by robust similarity network fusion and spectral clustering | |
CN108830106A (en) | A kind of private data providing method and device | |
CN106649380A (en) | Hot spot recommendation method and system based on tag | |
Zhou et al. | Using global t-SNE to preserve intercluster data structure | |
CN113704373A (en) | User identification method and device based on movement track data and storage medium | |
Wang et al. | Action recognition using linear dynamic systems | |
CN108647739A (en) | A kind of myspace discovery method based on improved density peaks cluster | |
CN105975897A (en) | Image human face gender recognition method and system | |
CN114970684A (en) | Community detection method for extracting network core structure by combining VAE |
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: 20161109 |