CN103324636B - The system and method for commending friends in social networks - Google Patents
The system and method for commending friends in social networks Download PDFInfo
- Publication number
- CN103324636B CN103324636B CN201210079045.3A CN201210079045A CN103324636B CN 103324636 B CN103324636 B CN 103324636B CN 201210079045 A CN201210079045 A CN 201210079045A CN 103324636 B CN103324636 B CN 103324636B
- Authority
- CN
- China
- Prior art keywords
- user
- face characteristic
- data
- face
- photograph album
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 110
- 238000013523 data management Methods 0.000 claims abstract description 27
- 239000000284 extract Substances 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 69
- 230000008878 coupling Effects 0.000 claims description 67
- 238000010168 coupling process Methods 0.000 claims description 67
- 238000005859 coupling reaction Methods 0.000 claims description 67
- 238000000605 extraction Methods 0.000 claims description 54
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 13
- 238000012217 deletion Methods 0.000 claims description 6
- 230000037430 deletion Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 8
- 230000013011 mating Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
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
- 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
- G06Q50/10—Services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of system and method for commending friends in social networks is provided.Described system comprises data management module, Face datection and characteristic extracting module, face matching module, user's head portrait confirms module, friend recommendation computing module and friend recommendation control module, wherein, friend recommendation control module extracts the album data of each user from data management module, control Face datection and characteristic extracting module detect each photo in album data and extract face characteristic data, for each user builds the photograph album face characteristic table comprised from the whole face characteristic data extracted, control user head portrait confirm module determine described each user user's head portrait feature and by user's head portrait characteristic item in the user profile of described each user of user's head portrait characteristic storage of determining, and control the photograph album face characteristic table of friend recommendation computing module based on each user built, user profile in data management module and friend information generate good friend's recommending data.
Description
Technical field
The application relates to a kind of system and method for commending friends in social networks, particularly relates to a kind of photo by uploading user and carries out human face detection and recognition and the described system and method mating the non-good friend user recommending to mate with the head portrait of all users of social networks.
Background technology
Network technology melts the resource that internet disperses for organic aggregate, realizes the overall sharing of resource and organic cooperation, enables people use the whole capability of resource pellucidly and obtaining information as required.Everybody social circle has been enriched in the appearance of social networks greatly, can share and obtain more information and resource.Each user can have oneself sub-network, the friend relation figure namely centered by me in social networks, and friend recommendation technology is also arisen at the historic moment.
Current friend recommendation technology is normally based on the individual ground literal descriptor of user on social networks, comprise school, hobby, or recommend the good friend of this user good friend, or other users near zone are recommended in the online position current according to this user, the accuracy of recommendation depends on the accuracy of user's input information to a certain extent.
These friend recommendation technology have certain limitation.User wants to find the user associated by other means and just compares and difficult for.Such as, user A has and magnifies group photo, but user A not with take a group photo greatly in other people information of associating, these people just cannot be recommended as the good friend of user A by existing friend recommendation technology.
Summary of the invention
The object of the present invention is to provide a kind of photo (as photograph album photo) by uploading user in social networks to carry out Face datection and coupling carrys out the system and method for commending friends, thus other users not yet becoming good friend appeared in photo that user uploads are recommended described user.
Another object of the present invention is to provide a kind of photo (as photograph album photo) by uploading user in social networks to carry out Face datection and mate to come the system and method for commending friends, if thus same person appears in the photo of the different user not yet becoming good friend, then described different user is recommended the other side.
According to an aspect of the present invention, a kind of system for commending friends in social networks is provided, described system comprises data management module, Face datection and characteristic extracting module, face matching module, the confirmation of user's head portrait module, friend recommendation computing module and friend recommendation control module, wherein: data management module, for managing the user profile of each user of social networks, friend information and album data, described user profile comprises user ID and user's head portrait feature, and described friend information comprises at least one user ID as good friend, Face datection and characteristic extracting module, analyze for the photo provided friend recommendation control module, detects the human face region in photo, and from each face extracted region face characteristic data detected, face matching module, mates for the first face characteristic of being provided by friend recommendation computing module and the second face characteristic data, and coupling or unmatched matching result is returned to friend recommendation computing module, friend recommendation control module, for the friend recommendation instruction according to reception, the album data of each user is extracted from data management module, control Face datection and characteristic extracting module to detect each photo in the album data of each user extracted and the extraction of face characteristic data builds the photograph album face characteristic table comprising the whole face characteristic data extracted from the album data of described user for each user, control user head portrait confirm module be based upon photograph album face characteristic table that each user builds to determine described each user user's head portrait feature and by user's head portrait characteristic item in the user profile of described each user of user's head portrait characteristic storage of determining, and control the photograph album face characteristic table of friend recommendation computing module based on each user built, user profile in data management module and friend information generate good friend's recommending data, user's head portrait confirms module, face characteristic data for being extracted by the head portrait photo of specifying from user in the photograph album face characteristic table built for each user are defined as the head portrait feature of described user, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined, with friend recommendation computing module, for the photograph album face characteristic table for each user, carry out following first process: the user profile of usage data administration module and friend information, by face matching module, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever face matching module returns the matching result of coupling, and user's head portrait feature of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, the user of friend recommendation computing module belonging to user's head portrait feature of described user and coupling generates the friend recommendation data of mutually recommending.
Preferably, friend recommendation control module stores the photograph album face characteristic table of each user by data management module.
Preferably, friend recommendation control module is when building photograph album face characteristic table for each user, each face characteristic in the photograph album face characteristic table of each user is counted, and from the photograph album face characteristic list deletion repeater face characteristic of each user.
Preferably, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user, when carrying out the first process to the photograph album face characteristic table of each user, are deleted by friend recommendation computing module from described photograph album face characteristic table.
Preferably, friend recommendation computing module is after carrying out the first process to the photograph album face characteristic table of each user, photograph album face characteristic table for each user carries out the second process, described second process comprises: each face characteristic in the photograph album face characteristic table of described user mated one by one with each face characteristic in the face characteristic table of other users each by face matching module, and when face matching module returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending.
Preferably, the friend recommendation packet generated by the first process and the second process containing different content, wherein, by the friend recommendation packet of the second process generation containing the information of photo of face head portrait characteristic extracting coupling.
Preferably, if user's head portrait confirms that module determines the head portrait photo of Non-precondition in the album data of arbitrary user, then user's head portrait confirms that module is using the user head portrait feature of face characteristic data the highest for the counting that extracts in the photograph album face characteristic table of described user as described user.
Preferably, when friend recommendation control module receive add the instruction of photograph album photo for user time, friend recommendation control module control data administration module adds described photograph album photo in the album data of described user, control Face datection and characteristic extracting module extract the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and controls friend recommendation computing module generation good friend recommending data.Wherein, friend recommendation computing module carries out the first process and the second process for face characteristic data of adding new in the photograph album face characteristic table of described user.
Preferably, friend recommendation control module is when receiving the user for specifying and adding the instruction of good friend, in the friend information of the user specified, the user ID of described good friend is added by data management module, by face matching module, the face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data returning the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
Preferably, described system also comprises safety control module, mark for selecting to allow to carry out analyzing the photo detected in its album data to user, and when friend recommendation control module extracts the album data of each user from data management module, safety control module only allows the photo carrying out analyzing detection to be supplied to Face datection user's selection and characteristic extracting module carries out analysis detection and feature extraction.
Face datection and characteristic extracting module can use carries out Face datection with at least one in drag: Template matching model, complexion model, active appearance models, supporting vector machine model and Adaboost model, and uses one of following methods to carry out the extraction of face characteristic data: the feature extraction based on template, the feature extraction based on algebraic method, the feature extraction based on Elastic Matching method, the feature extraction based on neural network and the feature extraction based on Wavelet Multiresolution Decomposition; And face matching module can use principal component analytical method to carry out the coupling of face characteristic data.
According to a further aspect in the invention, a kind of method of commending friends in social networks is provided, in described social networks, for each user stores the user profile of user, friend information and album data, described user profile comprises user ID and user's head portrait feature, described friend information comprises at least one user ID as good friend, described method comprises: analyze the photo in the photograph album of user each in social networks, detect the human face region in photo, from each face extracted region face characteristic data, and for each user builds the photograph album face characteristic table comprising the whole face characteristic data extracted from the photo of its photograph album, the face characteristic data that the head portrait photo of specifying from user in the photograph album face characteristic table built for each user extracts are defined as the head portrait feature of described user, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined, with the photograph album face characteristic table for each user, carry out the first process, described first process comprises: the user profile and the friend information that use each user stored, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever described coupling returns the matching result of coupling, and user's head portrait of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, user belonging to user's head portrait of described user and coupling generates the friend recommendation data of mutually recommending.
Preferably, the photograph album face characteristic table of each user is stored in a database.
Preferably, when building photograph album face characteristic table for each user, each face characteristic in the photograph album face characteristic table of each user is counted, and repeat face characteristic data from the photograph album face characteristic list deletion of each user.
Preferably, when carrying out the first process to the photograph album face characteristic table of each user, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user are deleted from described photograph album face characteristic table.
Preferably, after the first process is carried out to the photograph album face characteristic table of each user, photograph album face characteristic table for each user carries out the second process, described second process comprises: each face characteristic in the photograph album face characteristic table of described user mated one by one with each face characteristic in the face characteristic table of other users each, and when face matching module returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending.
Preferably, the friend recommendation packet generated by the first process and the second process containing different content, wherein, by the friend recommendation packet of the second process generation containing the information of photo of face head portrait characteristic extracting coupling.
Preferably, if determine the head portrait photo of not specifying in the album data of arbitrary user, then using the user head portrait feature of face characteristic data the highest for the counting extracted in the photograph album face characteristic table of described user as described user.
Preferably, when receive add the instruction of photograph album photo for user time, described photograph album photo is added in the album data of described user, extract the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and carries out the first process and the second process for face characteristic data of adding new in the photograph album face characteristic table of described user.
Preferably, when receiving the user for specifying and adding the instruction of good friend, the user ID of described good friend is added in the friend information of the user specified, face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data returning the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
Preferably, also in its album data, select the photo allowing to carry out analyzing detection to mark to user, and when extracting the album data of each user, only user being selected to allow to carry out analyzing the photo detected and carrying out analysis detection and feature extraction.
Can use and carry out Face datection with at least one in drag: Template matching model, complexion model, active appearance models, supporting vector machine model and Adaboost model, and use one of following methods to carry out the extraction of face characteristic data: the feature extraction based on template, the feature extraction based on algebraic method, the feature extraction based on Elastic Matching method, the feature extraction based on neural network and the feature extraction based on Wavelet Multiresolution Decomposition; With the coupling that principal component analytical method can be used to carry out face characteristic data.
Accompanying drawing explanation
By the description carried out below in conjunction with accompanying drawing, above and other object of the present invention and feature will become clearly, wherein:
Fig. 1 is the logic diagram of the structure of the system for commending friends illustrated according to exemplary embodiment of the present invention;
Fig. 2 is the process flow diagram of the process of the method for commending friends illustrated according to exemplary embodiment of the present invention; With
Fig. 3 is the process flow diagram of the process for generating photograph album face characteristic table illustrated according to exemplary embodiment of the present invention.
Embodiment
Below, embodiments of the invention are described in detail with reference to accompanying drawing.
The module divided in the system of the commending friends of the present invention's proposition and limit is not restrictive, these modules can be reconfigured and become less module, or further these Module Division can be become more module to realize their function yet.In addition, can be equipped with in one or more computer/processor of social networking service device end and run these modules.Equally, the step limited the method for the commending friends that the present invention proposes neither be restrictive, these steps can be reconfigured and become less step, or also further these steps can be divided into more step to complete their function.
The server end of social networks can be installed, operate in the form of plug-in unit or module to the system and method for commending friends that the present invention proposes.Present general inventive concept of the present invention is: in social networks, photo in each user's photograph album is analyzed, detect human face region, extract face characteristic data wherein, for each user creates the photograph album face characteristic table comprising whole face characteristic data of described extraction, user's head portrait feature of each user determined by photograph album face characteristic table based on each user, then, each face characteristic in the photograph album face characteristic table of each user is mated with user's head portrait feature of other users each in social networks, if determine that user's head portrait feature of mating does not belong to user, any good friend of described user is not belonged to yet, user then belonging to user's head portrait feature of coupling and the user of face characteristic data extracting coupling generate the friend recommendation data of mutually recommending, like this can by the photo appearing at other users but the user not yet becoming other user good friends described recommends other users described.In addition, each face characteristic in the photograph album face characteristic table of each user can be mated with each face characteristic in the photograph album face characteristic table of other users each, thus generate the friend recommendation data of mutually recommending for the user not yet becoming good friend of the face characteristic data with coupling.
Various existing algorithm and model can be used to extract to realize analysis that in the present invention, comparison film carries out, detection and face characteristic data, and the coupling between face characteristic data, between face characteristic data and user's head portrait feature.Such as, existing Face datection can use Template matching model, complexion model, active appearance models (AAM), support vector machine (SVM) model, Adaboost model etc., their accuracy of detection and speed are had nothing in common with each other, and the extraction of face characteristic data comprises the feature extraction based on template, the feature extraction based on algebraic method, the feature extraction based on Elastic Matching method, the feature extraction based on neural network, feature extraction etc. based on Wavelet Multiresolution Decomposition.The description of face characteristic data also has multiple, such as principal component analytical method (PCA).Face coupling is in fact calculate face characteristic, obtains similar value, is mated by machine learning to face characteristic.Described Face datection, face characteristic data are extracted and the technology of face coupling is not limited to above-mentioned technology, those of ordinary skill in the art can use other various algorithm and models to realize as required, therefore, in order to clear and simple and clear, concrete description will do not given to these aspects in this application.
Fig. 1 is the logic diagram of the structure of the system for commending friends illustrated according to exemplary embodiment of the present invention.
With reference to Fig. 1, the system for commending friends of the present invention comprises face matching module 110, Face datection and characteristic extracting module 120, user's head portrait confirms module 160, friend recommendation computing module 130, friend recommendation control module 140 and data management module 150.
Data management module 150 is for managing the user profile of each user in social networks, friend information and album data.In social networks, use exclusive user ID to identify each user.In the present invention, the user profile of each user at least comprises user ID and user's head portrait feature, can also comprise other social relevant information, as the user name, sex, age, residence, personal like etc. of user.Described user's head portrait feature is initially sky, and described user profile can also comprise other information relevant to user's head portrait feature.The friend information of each user at least comprises the user ID of at least one user of the good friend as described user.Usually, user in social networks can classify to the good friend of oneself, and organize the good friend of oneself according to tag along sort (such as " household ", " classmate ", " colleague " etc.), under the good friend be not assigned under any one tag along sort can be placed in the tag along sort (as " do not divide into groups good friend ") of acquiescence.The album data of each user comprises the photo that user described at least one uploads.
Data management module 150 is in its database managed, can set up separately for each user the table comprising user profile, friend information and album data, the user message table also can setting up the user profile comprising whole user respectively, comprise whole user friend information friend information table and comprise the photograph album information table of album data of whole user.In storage organization below, the record in each table must comprise the user ID of described record owning user, and described user ID is as one of the main index entry of described table.Certainly, the storage of described user profile, friend information and album data is not limited to above-mentioned two kinds of storage organizations, other data structures can be adopted as required to organize described information, as long as the user profile of described user, friend information and album data can be retrieved by given user ID.
According to a preferred embodiment of the invention, data management module 150 is under the control of friend recommendation control module 140, the also photograph album face characteristic table of each user of store and management, described photograph album face characteristic table comprises the face characteristic data extracted from the album data of photograph album face characteristic table owning user.
Face datection and characteristic extracting module 120 are analyzed for the photo provided friend recommendation control module 140, detect the human face region in photo, and from each face extracted region face characteristic data detected.
Face matching module 110 mates for the first face characteristic of being provided by friend recommendation computing module 130 and the second face characteristic data, and coupling or unmatched matching result are returned to friend recommendation computing module 130.
In the systems described in the present invention, the module that friend recommendation control module 140 controls other operates accordingly according to the instruction received, and described operation comprises: manage according to the user management instruction received, good friend's supervisory instruction and photograph album supervisory instruction control data administration module 150 pairs of user profile, friend information and album datas; According to the friend recommendation instruction received, extract the album data of each user from data management module 150; Control Face datection and characteristic extracting module 120 to detect each photo in the album data of each user extracted and the extraction of face characteristic data, thus build the photograph album face characteristic table comprising the whole face characteristic data extracted from the album data of described user for each user; Control user head portrait confirm module 160 be based upon photograph album face characteristic table that each user builds to determine described each user user's head portrait feature and by user's head portrait characteristic item in the user profile of described each user of user's head portrait characteristic storage of determining; Then control friend recommendation computing module 130 and generate good friend's recommending data based on the user profile in the photograph album face characteristic table of each user built, data management module 150 and friend information.
According to a preferred embodiment of the invention, friend recommendation control module 140 is when building photograph album face characteristic table for each user, each face characteristic in the photograph album face characteristic table of each user is counted, the number of times namely occurred in the photograph album face characteristic table of described each user for each face characteristic is added up, and repeats face characteristic data from the photograph album face characteristic list deletion of each user.Friend recommendation control module 140 can store the photograph album face characteristic table of each user by data management module 150, thus when user uploads new photo, described system can generate good friend's recommending data cumulatively on the basis of the photograph album face characteristic table of each user previously built.
User's head portrait confirms that the face characteristic data of the head portrait photo extraction of specifying from user in the photograph album face characteristic table built for each user are defined as the head portrait feature of described user by module 160, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined.If determine that user does not specify head portrait photo, then user's head portrait confirms that face characteristic data the highest for the counting extracted in the photograph album face characteristic table of described user can be defined as user's head portrait feature of described user by module 160.
Friend recommendation computing module 130 is for the photograph album face characteristic table for each user, carry out following first process: the user profile that usage data administration module 150 manages and friend information, by face matching module 110, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever face matching module returns the matching result of coupling, and user's head portrait feature of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, the user of friend recommendation computing module 130 belonging to user's head portrait feature of described user and coupling generates the friend recommendation data of mutually recommending, namely recommend the recommending data of the user belonging to user's head portrait feature of mating to described user and recommend the recommending data of described user to the user belonging to user's head portrait feature of mating.In order to make friend recommendation more directly perceived, the photo extracting user's head portrait feature can be included in the recommending data of generation in the album data of recommended user.
Friend recommendation computing module 130, when carrying out the first process to the photograph album face characteristic table of each user, can identify the face characteristic data with user's head portrait characteristic matching of arbitrary good friend of user oneself or described user in the photograph album face characteristic table of described user by above-mentioned process.Therefore, according to a preferred embodiment of the invention, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user, when carrying out the first process to the photograph album face characteristic table of each user, can be deleted by friend recommendation computing module 130 from described photograph album face characteristic table.
According to a preferred embodiment of the invention, friend recommendation computing module 130 is after carrying out the first process to the photograph album face characteristic table of each user, photograph album face characteristic table for each user carries out the second process, described second process comprises: each face characteristic in the photograph album face characteristic table of described user mated one by one with each face characteristic in the face characteristic table of other each users by face matching module 110, and when face matching module 110 returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending, namely recommend the recommending data of other users described in coupling to described user and recommend the recommending data of described user to other users described in coupling.In order to make friend recommendation more directly perceived, can be included in extracting one of photo of the face characteristic data of coupling in the recommending data of generation.
Friend recommendation computing module 130 can store by data management module 150 the friend recommendation data generated according to the present invention, so as relevant user refresh the given page or on once log in time be shown as the friend recommendation data that this relevant user generates.
When friend recommendation control module 140 receive add the instruction of photograph album photo for user time, friend recommendation control module 140 control data administration module 150 adds described photograph album photo in the album data of described user, control Face datection and characteristic extracting module 120 extract the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and controls friend recommendation computing module 130 and generate good friend's recommending data.Now, friend recommendation computing module 130 carries out the first process for face characteristic data of adding new in the photograph album face characteristic table of described user, and preferably carries out the second process.
Friend recommendation control module 140 is when receiving the user for specifying and adding the instruction of good friend, in the friend information of the user specified, the user ID of described good friend is added by data management module 150, by face matching module 110, the face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data returning the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
According to a preferred embodiment of the invention, described system also comprises safety control module (not shown), safety control module is used in its album data, selecting to allow to carry out analyzing the photo detected to user and marks, and friend recommendation control module 140 is when extracting the album data of each user from data management module 150, safety control module only allows the photo carrying out analyzing detection to be supplied to Face datection user's selection and characteristic extracting module 120 carries out analysis detection and feature extraction.
From the above-mentioned description carried out with reference to Fig. 1, system according to commending friends in social networks of the present invention can carry out Face datection and feature extraction by the photo (as photograph album photo) uploaded user in social networks, and carries out mating with user's head portrait feature of other users the user not yet becoming good friend recommending to appear in the other side's photo by the face characteristic extracted by the photo uploaded from user.In addition, the system of commending friends of the present invention also will occur that in the photograph album of user not yet becoming good friend two users of same person recommend the other side mutually by extraction is carried out coupling one by one from the face characteristic data of the photograph album photo of all users.
The method according to commending friends in social networks of the present invention is described in detail below in conjunction with Fig. 2 and Fig. 3.Described method is realized in the system of the social networking service device end shown in Fig. 1.As mentioned above, in the system of the present invention, each user for social networks stores the user profile of described user, friend information and album data, and described user profile comprises user ID and user's head portrait feature, and described friend information comprises at least one user ID as good friend.
Fig. 2 is the process flow diagram of the process of the method for commending friends illustrated according to exemplary embodiment of the present invention.
With reference to Fig. 2, in step S210, described system carries out Face datection and analysis to the photo in the album data of user each in social networks, detect the human face region in photo, extract face characteristic data from each human face region detected, and be that each user builds the photograph album face characteristic table comprising the whole face characteristic data extracted from the photo of its photograph album.Fig. 3 shows the process given photo of arbitrary user being carried out to Face datection and analysis and extraction face characteristic data in step S210.In step S212, described given photo is analyzed and Face datection, determine whether human face region detected in described given photo.If determine human face region to be detected, then in step S215, described system extracts face characteristic data according to predetermined algorithm from the human face region detected.Then, in step S218, the face characteristic data of extraction are inserted in the photograph album face characteristic table of described user by described system.On the contrary, if in step S210 by analyzing described given photo, human face region do not detected, then the process to described given photo is terminated.Process shown in Fig. 3 is performed to the photo of often opening in user's album data each in social networks.
According to a preferred embodiment of the invention, in the process of photograph album face characteristic table building each user, (that is described system counts to each face characteristic in the photograph album face characteristic table of each user, the number of times occurred in the photograph album face characteristic table of described each user for each face characteristic is added up), and from the photograph album face characteristic list deletion repeater face characteristic of each user.In addition, described system stores the photograph album face characteristic table of each user on non-volatile memory medium.
In step S220, the face characteristic data that the head portrait photo of specifying from user in the photograph album face characteristic table built for each user extracts are defined as the head portrait feature of described user by described system, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined.If determine that user does not specify head portrait photo, then face characteristic data the highest for the counting extracted in the photograph album face characteristic table of described user can be defined as the head portrait feature of described user, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined.
Then, in step S230, described system carries out the first process for the photograph album face characteristic table of each user, described first process comprises: the user profile and the friend information that use each user stored, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever described coupling returns the matching result of coupling, and user's head portrait feature of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, user belonging to user's head portrait feature of described user and coupling generates the friend recommendation data of mutually recommending, namely recommend the recommending data of the user belonging to user's head portrait feature of mating to described user and recommend the recommending data of described user to the user belonging to user's head portrait feature of mating.In order to make friend recommendation more directly perceived, the photo extracting user's head portrait feature can be included in the recommending data of generation in the album data of recommended user.So, according to the method for commending friends of the present invention, can introduce other users not yet becoming good friend appeared in the photograph album of arbitrary user in social networks to described user, vice versa.
Preferably, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user, when carrying out the first process to the photograph album face characteristic table of each user, can be deleted by described system from described photograph album face characteristic table.
On this basis, according to another preferred embodiment of the invention, described system is after carrying out the first process to the photograph album face characteristic table of each user, photograph album face characteristic table also for each user carries out the second process (step S240), described second process comprises: each face characteristic in the photograph album face characteristic table of described user mated one by one with each face characteristic in the face characteristic table of other each users, and when described coupling returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending, namely recommend the recommending data of other users described in coupling to described user and recommend the recommending data of described user to other users described in coupling.In order to make friend recommendation more directly perceived, can be included in extracting one of photo of the face characteristic data of coupling in the recommending data of generation.Like this, can will there is the user-association of same person in photograph album, and mutually recommend.
According to another exemplary embodiment of the present invention, when receive add the instruction of photograph album photo for user time, described system adds described photograph album photo in the album data of described user, extraction module extracts the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and carry out the first process for face characteristic data of adding new in the photograph album face characteristic table of described user, and preferably carry out the second process.
According to another exemplary embodiment of the present invention, when receiving the user for specifying and adding the instruction of good friend, described system adds the user ID of described good friend in the friend information of the user specified, face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data described coupling being returned the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
According to a preferred embodiment of the invention, described system is also selected to allow to carry out analyzing the photo detected to user and is marked in its album data, and when extracting the album data of each user, only user being selected to allow to carry out analyzing the photo detected and carrying out analysis detection and feature extraction.
From the above-mentioned description carried out with reference to Fig. 1 ~ Fig. 3, system and method according to commending friends in social networks of the present invention can carry out Face datection and feature extraction by the photo (as photograph album photo) uploaded user in social networks, and carries out mating with user's head portrait feature of other users the user not yet becoming good friend recommending to appear in the other side's photo by the face characteristic extracted by the photo uploaded from user.In addition, the system of commending friends of the present invention also will occur that in the photograph album of user not yet becoming good friend two users of same person recommend the other side mutually by extraction is carried out coupling one by one from the face characteristic data of the photograph album photo of all users, improves the correlativity between user further.
Although show and describe the present invention with reference to preferred embodiment, it should be appreciated by those skilled in the art that when not departing from the spirit and scope of the present invention be defined by the claims, various amendment and conversion can be carried out to these embodiments.
Claims (18)
1. the system for commending friends in social networks, described system comprises data management module, Face datection and characteristic extracting module, face matching module, the confirmation of user's head portrait module, friend recommendation computing module and friend recommendation control module, wherein:
Data management module, for managing the user profile of each user of social networks, friend information and album data, described user profile comprises user ID and user's head portrait feature, and described friend information comprises at least one user ID as good friend;
Face datection and characteristic extracting module, analyze for the photo provided friend recommendation control module, detects the human face region in photo, and from each face extracted region face characteristic data detected;
Face matching module, mates for the first face characteristic of being provided by friend recommendation computing module and the second face characteristic data, and coupling or unmatched matching result is returned to friend recommendation computing module;
Friend recommendation control module, for the friend recommendation instruction according to reception, the album data of each user is extracted from data management module, control Face datection and characteristic extracting module to detect each photo in the album data of each user extracted and the extraction of face characteristic data builds the photograph album face characteristic table comprising the whole face characteristic data extracted from the album data of described user for each user, control user head portrait confirm module be based upon photograph album face characteristic table that each user builds to determine described each user user's head portrait feature and by user's head portrait characteristic item in the user profile of described each user of user's head portrait characteristic storage of determining, and control the photograph album face characteristic table of friend recommendation computing module based on each user built, user profile in data management module and friend information generate good friend's recommending data, wherein, friend recommendation control module stores the photograph album face characteristic table of each user by data management module, wherein, friend recommendation control module is when building photograph album face characteristic table for each user, each face characteristic in the photograph album face characteristic table of each user is counted, and from the photograph album face characteristic list deletion repeater face characteristic of each user,
User's head portrait confirms module, face characteristic data for being extracted by the head portrait photo of specifying from user in the photograph album face characteristic table built for each user are defined as the head portrait feature of described user, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined; With
Friend recommendation computing module, for the photograph album face characteristic table for each user, carry out following first process: the user profile of usage data administration module and friend information, by face matching module, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever face matching module returns the matching result of coupling, and user's head portrait feature of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, the user of friend recommendation computing module belonging to user's head portrait feature of described user and coupling generates the friend recommendation data of mutually recommending.
2. the system as claimed in claim 1, wherein, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user, when carrying out the first process to the photograph album face characteristic table of each user, are deleted by friend recommendation computing module from described photograph album face characteristic table.
3. system as claimed in claim 2, wherein, friend recommendation computing module is after carrying out the first process to the photograph album face characteristic table of each user, and the photograph album face characteristic table for each user carries out the second process, and described second process comprises:
By face matching module, each face characteristic in the photograph album face characteristic table of described user is mated one by one with each face characteristic in the face characteristic table of other users each, and when face matching module returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending.
4. system as claimed in claim 3, wherein, the friend recommendation packet generated by the first process and the second process containing different content, wherein, by the friend recommendation packet of the second process generation containing the information of photo of face head portrait characteristic extracting coupling.
5. the system as claimed in claim 1, wherein, if user's head portrait confirms that module determines the head portrait photo of Non-precondition in the album data of arbitrary user, then user's head portrait confirms that module is using the user head portrait feature of face characteristic data the highest for the counting that extracts in the photograph album face characteristic table of described user as described user.
6. system as claimed in claim 3, wherein, when friend recommendation control module receive add the instruction of photograph album photo for user time, friend recommendation control module control data administration module adds described photograph album photo in the album data of described user, control Face datection and characteristic extracting module extract the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and control friend recommendation computing module and generate good friend's recommending data
Wherein, friend recommendation computing module carries out the first process and the second process for face characteristic data of adding new in the photograph album face characteristic table of described user.
7. the system as claimed in claim 1, wherein, friend recommendation control module is when receiving the user for specifying and adding the instruction of good friend, in the friend information of the user specified, the user ID of described good friend is added by data management module, by face matching module, the face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data returning the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
8. the system as claimed in claim 1, also comprise: safety control module, mark for selecting to allow to carry out analyzing the photo detected in its album data to user, and when friend recommendation control module extracts the album data of each user from data management module, safety control module only allows the photo carrying out analyzing detection to be supplied to Face datection user's selection and characteristic extracting module carries out analysis detection and feature extraction.
9. the system according to any one of claim 1 ~ 8,
Wherein, Face datection and characteristic extracting module use carries out Face datection with at least one in drag: Template matching model, complexion model, active appearance models, supporting vector machine model and Adaboost model, and uses one of following methods to carry out the extraction of face characteristic data: the feature extraction based on template, the feature extraction based on algebraic method, the feature extraction based on Elastic Matching method, the feature extraction based on neural network and the feature extraction based on Wavelet Multiresolution Decomposition; With
Wherein, face matching module uses principal component analytical method to carry out the coupling of face characteristic data.
10. the method for a commending friends in social networks, in described social networks, for each user stores the user profile of user, friend information and album data, described user profile comprises user ID and user's head portrait feature, described friend information comprises at least one user ID as good friend, and described method comprises:
Photo in the photograph album of user each in social networks is analyzed, detect the human face region in photo, from each face extracted region face characteristic data, and for each user builds the photograph album face characteristic table comprising the whole face characteristic data extracted from the photo of its photograph album, wherein, store the photograph album face characteristic table of each user in a database, wherein, when building photograph album face characteristic table for each user, each face characteristic in the photograph album face characteristic table of each user is counted, and repeat face characteristic data from the photograph album face characteristic list deletion of each user,
The face characteristic data that the head portrait photo of specifying from user in the photograph album face characteristic table built for each user extracts are defined as the head portrait feature of described user, and by user's head portrait characteristic item in the user profile of described user of the head portrait characteristic storage determined; With
For the photograph album face characteristic table of each user, carry out the first process, described first process comprises: the user profile and the friend information that use each user stored, each face characteristic in the photograph album face characteristic table of described user is mated one by one with user's head portrait feature of each user, whenever described coupling returns the matching result of coupling, and user's head portrait of coupling neither belongs to described user oneself when also not belonging to any good friend of described user, user belonging to user's head portrait of described user and coupling generates the friend recommendation data of mutually recommending.
11. methods as claimed in claim 10, wherein, when carrying out the first process to the photograph album face characteristic table of each user, the face characteristic data of user's head portrait characteristic matching of any good friend with described user or described user are deleted from described photograph album face characteristic table.
12. methods as claimed in claim 11, wherein, after carrying out the first process to the photograph album face characteristic table of each user, the photograph album face characteristic table for each user carries out the second process, and described second process comprises:
Each face characteristic in the photograph album face characteristic table of described user is mated one by one with each face characteristic in the face characteristic table of other users each, and when face matching module returns the matching result of coupling, for other users described in described user and coupling generate the friend recommendation data of mutually recommending.
13. methods as claimed in claim 12, wherein, the friend recommendation packet generated by the first process and the second process containing different content, wherein, by the friend recommendation packet of the second process generation containing the information of photo of face head portrait characteristic extracting coupling.
14. methods as claimed in claim 10, wherein, if determine the head portrait photo of not specifying in the album data of arbitrary user, then using the user head portrait feature of face characteristic data the highest for the counting extracted in the photograph album face characteristic table of described user as described user.
15. methods as claimed in claim 12, wherein, when receive add the instruction of photograph album photo for user time, described photograph album photo is added in the album data of described user, extract the face characteristic data in described photo, the face characteristic data of extraction are added in the photograph album face characteristic table of described user, and carries out the first process and the second process for face characteristic data of adding new in the photograph album face characteristic table of described user.
16. methods as claimed in claim 10, wherein, when receiving the user for specifying and adding the instruction of good friend, the user ID of described good friend is added in the friend information of the user specified, face characteristic data in user's head portrait feature of described good friend and the photograph album face characteristic table of the user specified are mated one by one, and the face characteristic data returning the matching result of coupling are deleted from the photograph album face characteristic table of the user specified.
17. methods as claimed in claim 10, also comprise: user is selected to allow to carry out analyzing the photo detected in its album data and marks, and when extracting the album data of each user, only user being selected to allow to carry out analyzing the photo detected and carrying out analysis detection and feature extraction.
18. methods according to any one of claim 10 ~ 17,
Wherein, use and carry out Face datection with at least one in drag: Template matching model, complexion model, active appearance models, supporting vector machine model and Adaboost model, and use one of following methods to carry out the extraction of face characteristic data: the feature extraction based on template, the feature extraction based on algebraic method, the feature extraction based on Elastic Matching method, the feature extraction based on neural network and the feature extraction based on Wavelet Multiresolution Decomposition; With
Wherein, principal component analytical method is used to carry out the coupling of face characteristic data.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210079045.3A CN103324636B (en) | 2012-03-22 | 2012-03-22 | The system and method for commending friends in social networks |
| KR1020130026675A KR20130108125A (en) | 2012-03-22 | 2013-03-13 | System and method for recommending buddies in social network |
| US13/848,302 US20130251201A1 (en) | 2012-03-22 | 2013-03-21 | System and method for recommending buddies in social network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210079045.3A CN103324636B (en) | 2012-03-22 | 2012-03-22 | The system and method for commending friends in social networks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103324636A CN103324636A (en) | 2013-09-25 |
| CN103324636B true CN103324636B (en) | 2016-04-06 |
Family
ID=49193383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210079045.3A Active CN103324636B (en) | 2012-03-22 | 2012-03-22 | The system and method for commending friends in social networks |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR20130108125A (en) |
| CN (1) | CN103324636B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514286A (en) * | 2013-09-30 | 2014-01-15 | 鸿富锦精密工业（深圳）有限公司 | Friend recommending system and method |
| CN105302812B (en) * | 2014-06-16 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Image information processing method and device |
| CN105763581A (en) * | 2014-12-15 | 2016-07-13 | 北京奇虎科技有限公司 | Method for pushing exhibition information, equipment and system |
| CN106330658A (en) * | 2015-06-23 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Internet-based information association method, terminal, server and system |
| CN106559317B (en) * | 2015-09-30 | 2021-05-18 | 北京奇虎科技有限公司 | Method and device for sending account information based on instant messaging |
| CN105429848B (en) * | 2015-10-23 | 2019-07-12 | 广东小天才科技有限公司 | Pass through the method for adding good friend of taking pictures, system and the social intercourse system of social interaction server device |
| KR102278017B1 (en) * | 2015-11-19 | 2021-07-15 | 주식회사 웹웨어 | Method for social networking service based on photos |
| KR102071661B1 (en) * | 2015-11-19 | 2020-01-30 | 주식회사 웹웨어 | Method for social networking service based on photos |
| CN107154890B (en) * | 2016-03-02 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Method, device and system for adding contact persons in social network |
| CN106777030B (en) * | 2016-12-08 | 2020-12-25 | 北京小米移动软件有限公司 | Information pushing method and device |
| CN107517274A (en) * | 2017-09-26 | 2017-12-26 | 北京小米移动软件有限公司 | Recommend method and device |
| CN110147486B (en) * | 2017-10-16 | 2021-10-29 | 中国电信股份有限公司 | Friend recommendation method and device |
| CN110084709A (en) * | 2018-01-23 | 2019-08-02 | 百度在线网络技术（北京）有限公司 | Good friend's processing method, server and computer-readable medium based on facial characteristics |
| CN108573054A (en) * | 2018-04-24 | 2018-09-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109033149B (en) * | 2018-06-12 | 2020-11-13 | 北京奇艺世纪科技有限公司 | Information recommendation method and device, server and storage medium |
| CN110174923B (en) * | 2018-09-30 | 2021-06-01 | 广东小天才科技有限公司 | Friend making method based on wearable device and wearable device |
| CN109753605A (en) * | 2018-12-22 | 2019-05-14 | 深圳市珍爱捷云信息技术有限公司 | User's recommended method, device, computer equipment and computer readable storage medium |
| CN110414455A (en) * | 2019-08-01 | 2019-11-05 | 珠海格力电器股份有限公司 | The sequence of face value and matching degree judgment method, computer readable storage medium and terminal based on image recognition |
| CN110569758A (en) * | 2019-08-26 | 2019-12-13 | 深圳市云歌人工智能技术有限公司 | method, device and storage medium for determining user category |
| CN111178124A (en) * | 2019-09-26 | 2020-05-19 | 重庆市链盟联智能科技有限责任公司 | Marriage and love dating system and data processing method thereof |
| KR102402472B1 (en) * | 2020-01-10 | 2022-05-26 | 주식회사 웹웨어 | Method for social networking service based on photos |
| CN114900554B (en) * | 2022-04-28 | 2023-07-21 | 河南省中视新科文化产业有限公司 | Accurate pushing system and equipment of social media information based on big data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446961A (en) * | 2008-12-24 | 2009-06-03 | 腾讯科技（深圳）有限公司 | Method and system for carrying out association on users and friends thereof in network community |
| CN101770459B (en) * | 2008-12-31 | 2013-10-09 | 华为技术有限公司 | Method and device for commending friends |
| US20120030587A1 (en) * | 2010-07-30 | 2012-02-02 | Neel Ketkar | Systems and methods for sharing media using social media guidance applications |
| CN102035891A (en) * | 2010-12-17 | 2011-04-27 | 百度在线网络技术（北京）有限公司 | Method and device for recommending friends in network friend making platform |
| CN102118510B (en) * | 2011-03-17 | 2013-12-25 | 宇龙计算机通信科技(深圳)有限公司 | Contact correlation method, server and mobile terminal |
-
2012
- 2012-03-22 CN CN201210079045.3A patent/CN103324636B/en active Active
-
2013
- 2013-03-13 KR KR1020130026675A patent/KR20130108125A/en not_active Application Discontinuation
Also Published As
| Publication number | Publication date |
|---|---|
| CN103324636A (en) | 2013-09-25 |
| KR20130108125A (en) | 2013-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103324636B (en) | The system and method for commending friends in social networks | |
| Bi et al. | Modelling customer satisfaction from online reviews using ensemble neural network and effect-based Kano model | |
| US11593894B2 (en) | Interest recommendation method, computer device, and storage medium | |
| US20220138431A1 (en) | Method and system for securely storing private data in a semantic analysis system | |
| Zhang et al. | CAP: Community activity prediction based on big data analysis | |
| CN105612514B (en) | System and method for image classification by associating contextual cues with images | |
| CN107894998B (en) | Video recommendation method and device | |
| CN103984775A (en) | Friend recommending method and equipment | |
| EP2741473A1 (en) | Human-machine interaction data processing method and apparatus | |
| CN109472305A (en) | Answer quality determines model training method, answer quality determination method and device | |
| CN108959323B (en) | Video classification method and device | |
| CN104077723A (en) | Social network recommending system and social network recommending method | |
| US20170091584A1 (en) | Classifying and Grouping Electronic Images | |
| CN113127633A (en) | Intelligent conference management method and device, computer equipment and storage medium | |
| CN107809370B (en) | User recommendation method and device | |
| CN111191039A (en) | Knowledge graph creation method, knowledge graph creation device and computer readable storage medium | |
| Xu et al. | A novel matrix factorization recommendation algorithm fusing social trust and behaviors in micro-blogs | |
| CN108268762B (en) | Mobile social network user identity identification method based on behavior modeling | |
| US20130054687A1 (en) | Online communities | |
| KR102053980B1 (en) | Providing Social Network Service And Providing Contents For The Same | |
| Li et al. | Cgmf: Coupled group-based matrix factorization for recommender system | |
| CN110472057B (en) | Topic label generation method and device | |
| Srivastava et al. | Importance of User's Profile Attributes in Identity Matching Across Multiple Online Social Networking Sites | |
| US20210166331A1 (en) | Method and system for risk determination | |
| KR20150087891A (en) | Experts Matching System Using Social Network Analysis and Ontologies |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |