WO2010102541A1 - 一种在网络中提取特征关系圈的方法及装置 - Google Patents

一种在网络中提取特征关系圈的方法及装置 Download PDF

Info

Publication number
WO2010102541A1
WO2010102541A1 PCT/CN2010/070825 CN2010070825W WO2010102541A1 WO 2010102541 A1 WO2010102541 A1 WO 2010102541A1 CN 2010070825 W CN2010070825 W CN 2010070825W WO 2010102541 A1 WO2010102541 A1 WO 2010102541A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
relationship
user
score
module
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.)
Ceased
Application number
PCT/CN2010/070825
Other languages
English (en)
French (fr)
Inventor
蔡耿平
胡海斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to RU2011140606/08A priority Critical patent/RU2510949C2/ru
Priority to MX2011009461A priority patent/MX2011009461A/es
Priority to SG2011060225A priority patent/SG173795A1/en
Priority to BRPI1009258A priority patent/BRPI1009258A2/pt
Priority to CA2753775A priority patent/CA2753775C/en
Publication of WO2010102541A1 publication Critical patent/WO2010102541A1/zh
Priority to US13/222,133 priority patent/US20110314009A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/40Business processes related to social networking or social networking services
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/40Business processes related to social networking or social networking services
    • G06Q10/42Determination of affinities or common interests between users
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/40Business processes related to social networking or social networking services
    • G06Q10/46Determination of level of influence of users within social networking services
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/40Business processes related to social networking or social networking services
    • G06Q10/48Business processes related to social networking or social networking services using social graphs

Definitions

  • the present invention relates to the field of computer technologies, and in particular, to a method and apparatus for extracting feature relationships in a network. Background of the invention
  • the social network formed by online users is no longer just a relationship between a single user and a single user, but a one-to-many and many-to-many relationship.
  • the social network contains a large number of users and massive relationship data, which has great value, can accurately search and effectively spread information, and meet the different needs of users and enterprises.
  • the massive users and massive data in the social network are not all concerned by users and enterprises, and are interested in the relationship formed by users with specified characteristics.
  • the information of the search user or the enterprise is the Web2.0-based social network service (SNS) website search function.
  • SNS websites support searching for users in a social network by keywords, and can search for users who meet specified characteristics in the network, but cannot express the relationship between these users and the relationships they form. From the perspective of understanding and grasping the social network, it is impossible to find a more valuable relationship.
  • Information SUMMARY OF THE INVENTION
  • embodiments of the present invention provide a method and apparatus for extracting feature relationships in a network. The technical solution is as follows:
  • a method for extracting feature relationships in a network comprising:
  • Specifying a feature of the feature relationship to be extracted determining a set of users whose user information matches the specified feature, and extracting the determined set of users as a feature relationship;
  • An apparatus for extracting feature relationships in a network comprising: an obtaining module, an extracting module, and a calculating module;
  • the obtaining module is configured to acquire user information.
  • the extracting module is configured to determine, according to the specified feature relationship of the feature relationship to be extracted and the user information acquired by the acquiring module, a set of users whose user information matches the specified feature, and the determined user set Extracted as a feature relationship ⁇ ;
  • the calculating module is configured to determine, according to the user information acquired by the acquiring module, a value of the influence of the user in the feature relationship extracted by the extracting module.
  • FIG. 1 is a flowchart of a method for extracting feature relationships in a social network according to Embodiment 1 of the present invention
  • FIG. 2 is a schematic diagram of extracting feature relationships from a social network according to Embodiment 1 of the present invention.
  • FIG. 3 is a schematic diagram of extracting feature relationships from a social network and calculating influence according to Embodiment 1 of the present invention
  • FIG. 4 is a schematic structural diagram of an apparatus for extracting feature relationships in a social network according to Embodiment 2 of the present invention.
  • FIG. 5 is a schematic structural diagram of an apparatus for extracting and calculating influence of a feature relationship in a social network according to Embodiment 2 of the present invention.
  • the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.
  • an embodiment of the present invention provides a method for extracting feature relationships in a social network, where the method includes:
  • Step 101 Obtain user information.
  • the user information may include relationship data and feature data, and the relationship data of each user may be extracted from the user profile database and saved to the social network system relationship of Table 1.
  • the user profile database can store user profile information of the Instant Messaging (IM) platform or store user profile data based on the Web2.0 SNS website.
  • IM Instant Messaging
  • Each user has a unique ID, which defines the type of relationship between users.
  • Each user's relationship with other users can be expressed as (ID 1 , type), (IDn, type), or other representation types. .
  • the types of relationships in the embodiments of the present invention include but are not limited to: friends, recognition, strangeness, etc., if the ID of user A is 10001, the ID of user B is 10002, the ID of user C is 10003, and the ID of user D is 10004, A. With B as a friend, A and C know, A does not know D, then A's relationship information is described as (B, buddy), (C, acquaintance), (D, strange);
  • the feature data of each user may also be extracted according to the user profile database and saved in Table 1.
  • the feature data is a description of a certain attribute or behavior of the user, and the representation manner may be: (type, value).
  • User A's career information (Unit, XX), (Professional, Computer), (Occupation, Programming).
  • the relationship information and feature data of user A are stored in Table 1 as follows:
  • Step 102 Specify a feature of the feature relationship to be extracted, and extract a user whose user information is matched with the specified feature as a feature relationship.
  • the characteristics of the feature relationship can be specified as: (professional, computer), (occupation, programming), and then the feature data in the user information of each user in Table 1 and the specified special
  • the matching is performed, and the user having the specified feature in Table 1 is extracted as the feature relationship ⁇ ;
  • the domain of the feature relationship ⁇ can also be specified, and then the specified feature is obtained according to the corresponding feature of the domain, for example, the domain of the specified feature relationship ⁇
  • the corresponding characteristics of the IT industry may be computer, network, programming, etc.
  • the feature is the characteristic of the specified feature relationship, and the corresponding feature of a certain domain may be pre-stored in the machine and automatically parsed by the machine. Can also be artificially set.
  • the user 10001 is extracted, and it is assumed that the user with the ID 10003 and the user with the ID 10004 also match the IT ,.
  • the user 10003 and the user 10004 are also extracted, and the extracted user is regarded as a feature relationship.
  • the feature of a certain feature relationship ⁇ can be specified as A, and the user with feature A is extracted as the feature relationship ⁇ A from the social network;
  • another feature relationship ⁇ can be specified as B.
  • the user having the feature B is extracted as the feature relationship ⁇ B from the social network, and so on, and multiple feature relationships can be extracted from the social network.
  • Step 103 Determine a relationship between users in the feature relationship ⁇ according to the user information.
  • the relationship between the users in the feature relationship ⁇ can be determined based on the relationship data in the user information.
  • Table 2 Feature Relationship ⁇
  • the relationship type is only defined as a friend, (user ID1, user ID2) by default means that the user of ID1 and the user of ID2 are friends; if the relationship type is defined
  • the relationship between the users may be friends, or may be recognized, or may be unfamiliar.
  • the relationship between the user ID1 and the user ID2 may be determined according to the relationship information in Table 1. More preferably, the relationship between the users in the feature relationship can be expressed as (user ID1, user ID2, type), for example, (10001, 10003, buddy) represents a user with an ID of 10001 and a user with an ID of 10003. As a friend.
  • the method further includes: calculating the influence value of the user in the feature relationship ⁇ according to the user information.
  • the calculating the influence value of the user in the feature relationship ⁇ according to the user information includes: classifying the matching degree of the user's feature data and the specified feature in the feature relationship ,, and obtaining the feature score of the user.
  • the feature scoring function for users belonging to a certain feature relationship can be designed. For:
  • User ID ⁇ Analysis of the user's feature data, extra points according to the scoring rules ⁇ For example, after playing the feature relationship of the Dungeon Warrior game, you can play the information of the dungeon warrior game according to the user, including the time and level. To convert the corresponding game scores, so as the score of the feature, the longer the time, the higher the level, the higher the feature score, and the higher the feature score, the more consistent the feature of the user with the feature, the more influence it has. Big.
  • the calculating the influence value of the user in the feature relationship ⁇ according to the user information includes: calculating a relationship score of the user according to the relationship between the users in the feature relationship determined by the relationship data.
  • the relationship scoring function for users belonging to a certain feature relationship can be designed as:
  • the calculating the influence value of the user in the feature relationship ⁇ according to the user information includes: classifying the matching degree of the user's feature data and the specified feature in the feature relationship ,, and obtaining the feature score of the user;
  • the relationship score of the user is calculated based on the relationship between the users in the feature relationship determined by the relationship data.
  • the user's influence score is calculated based on the feature score and the relationship score.
  • the feature score and the relationship score can be weighted and added to obtain the user's influence score, and then sorted according to the influence score, and the most influential feature relationship is found. Force users.
  • the influence scoring function for users belonging to a certain feature relationship can be designed as:
  • f is the weight, the default is 0.5, which can be adjusted according to actual needs.
  • feature relationships are extracted from a socialized network with massive data, and the relationships among users in the extracted feature relationships are determined, and the most influential users are calculated.
  • the beneficial effects of the embodiment of the present invention are: by specifying the feature relationship ⁇ to be extracted, extracting the feature relationship ⁇ according to the determined relationship data and feature data of each user, and influencing the user in the feature relationship ⁇ The calculation enables all users to understand the feature relationship more specifically, so as to effectively utilize the social network relationship chain information to achieve the goal of effective information dissemination and accurate search.
  • an embodiment of the present invention provides a social network relationship extraction device, which includes: an acquisition module 201, an extraction module 202, and a determination module 203;
  • the obtaining module 201 is configured to obtain user information, and send the obtained user information to the extracting module 202;
  • the user information may include relationship data and feature data, and the relationship data of each user may be extracted from the user profile database and saved in the social network system relationship information table of Table 3.
  • the user data database may store the user of the IM platform. Data information or user data stored on the Web 2.0 SNS website. Each user has a unique ID. Define a type for the relationship between users. The relationship between each user and other users can be expressed as
  • the relationship type is defined as a friend, a knowledge, a stranger, the ID of user A is 10001, the ID of user B is 10002, the ID of user C is 10003, the ID of user D is 10004, A and B are friends, and A and C know , A does not know D, then A's relationship information is described as (B, buddy), (C, acquaintance), (D, strange);
  • the feature data of each user may also be extracted according to the user profile database and saved in Table 3.
  • the feature data is a description of a certain attribute or behavior of the user, and the representation manner may be: (type, value).
  • User A's career information (Unit, XX), (Professional, Computer), (Occupation, Programming).
  • the relationship information and feature data of user A are stored in Table 3 as follows:
  • the extraction module 202 is configured to: after receiving the user information sent by the obtaining module 201, extract the user information matching the specified feature as a feature relationship according to the specified feature relationship to be extracted;
  • the characteristics of the feature relationship can be specified as: (professional, computer), (occupation, programming), and then the feature data in the user information of each user in Table 1 is matched with the specified feature, in Table 1.
  • the user having the specified feature is extracted as a feature relationship ⁇ ; the domain of the feature relationship ⁇ can also be specified, and then the specified feature is obtained according to the corresponding feature of the domain.
  • the domain of the specified feature relationship is the IT industry.
  • the corresponding feature of the IT industry may be a computer, a network, a programming, etc.
  • the feature is a feature of a specified feature relationship, and a corresponding feature of a certain domain may be advanced. In the storage machine, it is automatically parsed by the machine, or it can be set manually.
  • the user 10001 is extracted, and it is assumed that the user with the ID 10003 and the user with the ID 10004 also match the IT ,.
  • the user 10003 and the user 10004 are also extracted, and the extracted user is regarded as a feature relationship.
  • the feature of a certain feature relationship ⁇ can be specified as A, and the user with feature A is extracted as the feature relationship ⁇ A from the social network;
  • another feature relationship ⁇ can be specified as B.
  • the user having the feature B is extracted as the feature relationship ⁇ B from the social network, and so on, and multiple feature relationships can be extracted from the social network.
  • the determining module 203 is configured to determine, according to the user information sent by the obtaining module 201, the relationship between the users in the feature relationship extracted by the extracting module 202.
  • Table 4 Feature Relationships ⁇
  • the types of relationships in the embodiments of the present invention include but are not limited to: friends, knowledge, strangers, and the like. If the relationship type is only defined as a friend, B'j (user ID1, user ID2) by default means that the user of ID1 and the user of ID2 are friends; if the relationship type defines a friend, know, strange, o
  • the device further includes: a calculation module 204.
  • the calculation module 204 is configured to calculate, according to the user information acquired by the acquisition module 201, a value of the influence of the user in the feature relationship extracted by the extraction module 202.
  • the calculation module 204 is specifically configured to score the matching degree of the user's feature data and the specified feature in the feature relationship extracted by the extraction module 202, and obtain the user's feature score.
  • the calculating module 204 is specifically configured to calculate a relationship score of the user by the relationship between the users in the feature relationship ⁇ determined by the determining module 203 according to the relationship data.
  • the relationship scoring function for users belonging to a certain feature relationship can be designed as:
  • the calculation module 204 includes: a first calculation unit and a second calculation unit; the first calculation unit is configured to calculate, according to the feature data in the user information acquired by the acquisition module 201, the feature of the user in the feature relationship extracted by the extraction module 202 Scoring; and calculating a relationship score by the determining module 203 based on the relationship between the users determined by the relationship data;
  • the second calculating unit is configured to calculate, according to the feature score and the relationship score calculated by the first calculating unit, the influence score of the user in the feature relationship extracted by the extracting module 202.
  • the feature score and the relationship score can be weighted and added to obtain the influence score of each user, and then sorted according to the influence score to find the most influential user.
  • f is the weight, the default is 0.5, which can be adjusted according to actual needs.
  • feature relationships are extracted from a socialized network with massive data, and the relationships among users in the extracted feature relationships are determined, and the most influential users are calculated.
  • the beneficial effects of the embodiment of the present invention are: by specifying the feature relationship ⁇ to be extracted, extracting the feature relationship ⁇ according to the determined relationship data and feature data of each user, and influencing the user in the feature relationship ⁇ The calculation enables all users to understand the feature relationship more specifically, so as to effectively utilize the social network relationship chain information to achieve the goal of effective information dissemination and accurate search.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Description

一种在网络中提取特征关系圏的方法及装置 技术领域 本发明涉及计算机技术领域, 特别涉及一种在网络中提取特征关系 圏的方法及装置。 发明背景
的休闲娱乐中, 而且在用户的工作中都得到广泛的使用。 如今, 网络即 时通讯工具提供的功能越来越多, 功能也日趋完善。 与此同时, 在线用 户形成的社会化网络不再仅仅是单个用户与单个用户的关系, 而是单对 多以及多对多的关系。 社会化网络包含了海量用户及海量关系数据, 具 有非常巨大的价值, 可以实现信息的精确搜索及有效传播, 满足用户和 企业的不同需求。
但是社会化网络中的海量用户和海量数据并不是全部为用户和企 业所关注, 感兴趣的是具有指定特征的用户所形成的关系圏。 现有技术 中搜索用户或企业关注的信息是基于 Web2.0 的社交网络服务(Social Network Service, SNS ) 网站搜索功能。 大多数 SNS网站支持通过关键 词对社会化网络中的用户进行搜索,可以搜索出网络中满足指定特征的 用户, 但无法表达这些用户之间的关系及其所形成的关系圏, 没有从整 体的角度去理解和把握社会化网络, 因此也就不能发现更有价值的关系 信息。 发明内容 为了提取特征关系圏, 实现信息在社会化网络中有效传播和精确搜 索, 本发明实施例提供了一种在网络中提取特征关系圏的方法及装置。 所述技术方案如下:
一种在网络中提取特征关系圏的方法, 所述方法包括:
获取用户信息;
指定待提取的特征关系圏的特征, 确定出用户信息与所述指定特征 匹配的用户的集合, 将确定出的该用户集合提取为特征关系圏;
根据所述用户信息确定所述特征关系圏中用户的影响力值。
一种在网络中提取特征关系圏的装置, 所述装置包括: 获取模块、 提取模块和计算模块;
所述获取模块, 用于获取用户信息;
所述提取模块, 用于根据指定的待提取的特征关系圏的特征以及所 述获取模块获取的用户信息,确定出用户信息与所述指定特征匹配的用 户的集合, 将确定出的该用户集合提取为特征关系圏;
所述计算模块, 用于根据所述获取模块获取的用户信息, 确定所述 提取模块提取出来的特征关系圏中用户的影响力值。
本发明实施例提供的技术方案的有益效果是: 通过提取社会化网络 中特征关系圏, 能够有效利用社会化网络关系链信息, 实现信息有效传 播和精确搜索的目标。 附图简要说明 图 1是本发明实施例 1提供的一种社会化网络中特征关系圏的提取 方法流程图;
图 2是本发明实施例 1提供的从社会化网络中提取特征关系圏的示 意图;
图 3是本发明实施例 1提供的从社会化网络中提取特征关系圏并计 算影响力的示意图;
图 4是本发明实施例 2提供的一种社会化网络中特征关系圏的提取 装置结构示意图;
图 5是本发明实施例 2提供的一种社会化网络中特征关系圏的提取 并计算影响力的装置结构示意图。 实施本发明的方式 为使本发明的目的、 技术方案和优点更加清楚, 下面将结合附图对 本发明实施方式作进一步地详细描述。
实施例 1
参见图 1 , 本发明实施例提供了一种社会化网络中特征关系圏的提 取方法, 该方法包括:
步骤 101: 获取用户信息;
其中, 用户信息可以包括关系数据和特征数据, 可以从用户资料数 据库提取每个用户的关系数据,并保存到表 1社会化网络系统关系圏信 息表中, 用户资料数据库中可以存放即时通讯( InstantMessaging , IM ) 平台的用户资料信息或者存放基于 Web2.0 SNS网站的用户资料数据。 每个用户都有一个唯一标识 ID, 对用户之间的关系定义类型, 每个用 户与其他用户的关系可以表示为 (ID 1 , type), (IDn, type), 也可以 有其它的表示类型。
本发明实施例中关系类型包括但不限于: 好友, 认识, 陌生等等, 如果用户 A的 ID是 10001 ,用户 B的 ID是 10002,用户 C的 ID是 10003 , 用户 D的 ID是 10004, A与 B为好友, A与 C认识, A不认识 D, 那 么 A的关系信息描述为 (B , 好友), (C, 认识), (D, 陌生);
还可以根据用户资料数据库提取每个用户的特征数据, 并保存到表 1中,特征数据是对用户某一个属性或者行为的描述,表示方式可以是: (类型, 值)。 例如, 用户 A的职业信息: (单位, XX), (专业, 计算机), (职业, 编程)。 则用户 A的关系信息和特征数据存储在表 1中为:
Figure imgf000006_0001
表 1 : 社会化网络系统关系圏信息表
步骤 102: 指定待提取的特征关系圏的特征, 将用户信息与该指定 特征匹配的用户提取为特征关系圏;
例如, 可以指定该特征关系圏的特征为: (专业, 计算机), (职业, 编程), 然后将表 1 中各个用户的用户信息中的特征数据与该指定的特 征进行匹配, 将表 1中具有该指定特征的用户提取为特征关系圏; 也可 以指定特征关系圏的所属领域,然后根据该领域对应的特征得到指定特 征, 例如, 指定特征关系圏的所属领域为 IT行业, 该 IT行业对应的特 征可以是计算机, 网络,编程等,该特征即为指定的特征关系圏的特征, 某领域对应的特征, 可以预先存储在机器中, 由机器自动解析出, 也可 以人为设定。
例如, 从表 1可以看出, ID为 10001的用户与该 IT圏匹配, 则将 该用户 10001提取出来,假设还有 ID为 10003的用户和 ID为 10004的 用户也与该 IT圏匹配, 则也将用户 10003和用户 10004提取出来, 将 提取出来的用户作为一个特征关系圏。
参见图 2, 从具有海量数据的社会化网络中提取特征关系圏, 可以 指定某个特征关系圏的特征为 A,则从社会化网络中将具有特征 A的用 户提取为特征关系圏 A; 同样, 也可以指定另外一个特征关系圏的特征 为 B, 则从社会化网络中将具有特征 B的用户提取为特征关系圏 B, 依 次类推, 可以从社会化网络中提取多个特征关系圏。
步骤 103: 根据用户信息确定特征关系圏中用户之间的关系。
具体地, 可以根据用户信息中的关系数据确定特征关系圏中用户之 间的关系。
继续上述的例子, 从表 1中的关系数据可以得知, 该提取出来的 IT 关系圏的用户中, ID为 10001的用户与 ID为 10003的用户认识, ID为 10001的用户与 ID为 10004的用户陌生, 则该 IT关系圏的用户之间的 关系也添加到该 IT关系圏中, 如表 2所示: 关 关系 关系圏指定 关系圏 用户之间 系 圏 圏名称 特征 里的用户 的关系
ID
1 IT (专业,计算机), 10001 , ( 10001 , 10003 ),
(职业, 编程) ( 10001 , 10004 )
2 表 2: 特征关系圏 本发明实施例中, 如果关系类型只定义为好友, 则 (用户 ID1 , 用 户 ID2 )默认表示 ID1的用户和 ID2的用 o户是好友; 如果关系类型定义
o
了好友, 认识, 陌生, 则(用户 ID1 , 用户 ID2 )表示 ID1的用户和 ID2 o
的用户之间的关系可能是好友, 也可能是认识, 也 o有可能是陌生的, 这 时可以根据表 1中的关系信息再确定用户 ID1和用户 ID2之间关系。 更优地,可以将该特征关系圏里的用户之间关系表示为(用户 ID1 , 用户 ID2, 类型), 例如, ( 10001 , 10003, 好友)就表示 ID为 10001 的用户和 ID为 10003的用户为好友。 其中, 为了在提取出来的特征关系圏中找出最有影响力的用户, 使 信息的传递更加有效和精确, 该方法还包括: 根据用户信息计算特征关系圏中用户的影响力值。 其中, 根据用户信息计算特征关系圏中用户的影响力值, 包括: 对特征关系圏中用户的特征数据和指定特征的匹配程度进行评分, 得到用户的特征评分。 其中, 对于属于某一特征关系圏的用户的特征评分函数可以设计 为:
用户 ID={对于用户的特征数据进行分析, 根据评分规则进行加分} 例如, 在玩地下城勇士游戏的特征关系圏, 可以根据该用户玩地下 城勇士游戏的信息, 包括时间, 等级的情况来转换相应的游戏积分, 从 而作为该特征的评分, 时间越长, 等级越高则特征评分就越高, 特征评 分越高表明该用户与该特征关系圏的特征越吻合, 其影响力就越大。
其中, 根据用户信息计算特征关系圏中用户的影响力值, 包括: 根据关系数据确定的特征关系圏中用户之间的关系, 计算用户的关 系评分。
其中, 对于属于某一特征关系圏的用户的关系评分函数可以设计 为:
用户 ID={对于用户的每个关系,如果是好友加 10分,一般加 5分, 陌生加 1分} , 关系评分越大表明该用户与该特征关系圏中的其他用户 关系越紧密, 其影响力就越大。
其中, 根据用户信息计算特征关系圏中用户的影响力值, 包括: 对特征关系圏中用户的特征数据和指定特征的匹配程度进行评分, 得到用户的特征评分;
根据关系数据确定的特征关系圏中用户之间的关系, 计算用户的关 系评分。
根据该特征评分和关系评分计算用户的影响力评分。
具体地, 可以将特征评分和关系评分进行加权相加, 得到用户的影 响力评分, 然后根据影响力评分进行排序, 找到特征关系圏中最有影响 力的用户。
例如, 对于属于某一特征关系圏的用户的影响力评分函数可以设计 为:
用户 10=特征评分 *f+关系评分 *(l-f)
f为权重, 默认为 0.5, 可根据实际需要调整。
参见图 3, 从具有海量数据的社会化网络中提取特征关系圏, 确定 提取出来的特征关系圏中用户之间的关系, 并计算出最有影响力的用 户。
本发明实施例的有益效果是: 通过指定待提取的特征关系圏的特 征, 根据确定的每个用户的关系数据和特征数据, 提取特征关系圏, 并 对该特征关系圏中的用户进行影响力计算,使所有用户能够更加具体的 了解该特征关系圏, 从而有效的利用社会化网络关系链信息, 实现信息 有效传播和精确搜索的目标。
实施例 2
参见图 4, 本发明实施例提供了一种社会化网络关系圏提取装置, 该装置包括: 获取模块 201 , 提取模块 202和确定模块 203;
获取模块 201 , 用于获取用户信息, 并将获取的用户信息发送给提 取模块 202;
其中, 用户信息可以包括关系数据和特征数据, 可以从用户资料数 据库提取每个用户的关系数据,并保存到表 3社会化网络系统关系圏信 息表中, 用户资料数据库中可以存放 IM平台的用户资料信息或者存放 基于 Web2.0 SNS网站的用户资料数据。每个用户都有一个唯一标识 ID, 对用户之间的关系定义类型, 每个用户与其他用户的关系可以表示为
(ID1 , type), (IDn, type), 也可以有其它的表示类型。
例如关系类型定义为好友, 认识, 陌生人, 用户 A的 ID是 10001 , 用户 B的 ID是 10002, 用户 C的 ID是 10003 , 用户 D的 ID是 10004, A与 B为好友, A与 C认识, A不认识 D, 那么 A的关系信息描述为 (B , 好友), (C, 认识), (D, 陌生);
还可以根据用户资料数据库提取每个用户的特征数据, 并保存到表 3中,特征数据是对用户某一个属性或者行为的描述,表示方式可以是: (类型, 值)。 例如, 用户 A的职业信息: (单位, XX), (专业, 计算机), (职业, 编程)。 则用户 A的关系信息和特征数据存储在表 3中为:
Figure imgf000011_0001
表 3: 社会化网络系统关系圏信息表
提取模块 202, 用于收到获取模块 201发来的用户信息后, 根据指 定的待提取的特征关系圏的特征,将用户信息与该指定特征匹配的用户 提取为特征关系圏;
例如, 可以指定该特征关系圏的特征为: (专业, 计算机), (职业, 编程), 然后将表 1 中各个用户的用户信息中的特征数据与该指定的特 征进行匹配, 将表 1中具有该指定特征的用户提取为特征关系圏; 也可 以指定特征关系圏的所属领域,然后根据该领域对应的特征得到指定特 征, 例如, 指定特征关系圏的所属领域为 IT行业, 该 IT行业对应的特 征可以是计算机, 网络,编程等,该特征即为指定的特征关系圏的特征, 某领域对应的特征, 可以预先存储机器中, 由机器自动解析出, 也可以 人为设定。
例如, 从表 1可以看出, ID为 10001的用户与该 IT圏匹配, 则将 该用户 10001提取出来,假设还有 ID为 10003的用户和 ID为 10004的 用户也与该 IT圏匹配, 则也将用户 10003和用户 10004提取出来, 将 提取出来的用户作为一个特征关系圏。
参见图 2, 从具有海量数据的社会化网络中提取特征关系圏, 可以 指定某个特征关系圏的特征为 A,则从社会化网络中将具有特征 A的用 户提取为特征关系圏 A; 同样, 也可以指定另外一个特征关系圏的特征 为 B, 则从社会化网络中将具有特征 B的用户提取为特征关系圏 B, 依 次类推, 可以从社会化网络中提取多个特征关系圏。
确定模块 203, 用于根据获取模块 201发来的用户信息, 确定提取 模块 202提取出来的特征关系圏中用户之间的关系。
继续上述的例子, 从表 3中的关系数据可以得知, 该提取出来的 IT 关系圏的用户中, ID为 10001的用户与 ID为 10003的用户认识, ID为 10001的用户与 ID为 10004的用户陌生, 则该 IT关系圏的用户之间的 关系也添加到该 IT关系圏中, 如表 4所示:
Figure imgf000012_0001
1 IT (专业,计算机), 10001 , ( 10001 ,
(职业, 编程) 10003 ), ( 10001 ,
10004 )
2 表 4: 特征关系圏 本发明实施例中关系类型包括但不限于: 好友, 认识, 陌生等等。 如果关系类型只定义为好友, 贝' j (用户 ID1 , 用户 ID2 ) 默认表示 ID1 的用户和 ID2的用户是好友; 如果关系类型定义了好友, 认识, 陌生, o
则 (用户 ID1 , 用户 ID2 )表示 ID1的用户和 ID2的用户之间的关系可 能是好友, 也可能是认识, 也有可能是陌生的, 这时可以根据表 3中的 关系信息再确定用户 ID1和用户 ID2之间关系。 更优地,可以将该特征关系圏里的用户之间关系表示为(用户 ID1 , 用户 ID2, 类型), 例如, ( 10001 , 10003, 好友)就表示 ID为 10001 的用户和 ID为 10003的用户为好友。 其中, 参见图 5, 该装置还包括: 计算模块 204; 计算模块 204, 用于根据获取模块 201获取的用户信息, 计算提取 模块 202提取出来的特征关系圏中用户的影响力值。 其中, 计算模块 204具体用于, 将提取模块 202提取出来的特征关 系圏中用户的特征数据和指定特征的匹配程度进行评分,得到用户的特 征评分。 其中, 对于属于某一特征关系圏的用户的特征评分函数可以设计 为: 用户 ID={对于用户的特征数据进行分析, 根据评分规则进行加分} 例如, 在玩地下城勇士游戏的特征关系圏, 可以根据该用户玩地下 城勇士游戏的信息, 包括时间, 等级的情况来转换相应的游戏积分, 从 而作为该特征的评分, 时间越长, 等级越高则特征评分就越高, 特征评 分越高表明该用户与该特征关系圏的特征越吻合, 其影响力就越大。
或者, 计算模块 204具体用于, 由确定模块 203根据关系数据确定 的特征关系圏中用户之间的关系, 计算用户的关系评分。
其中, 对于属于某一特征关系圏的用户的关系评分函数可以设计 为:
用户 ID={对于用户的每个关系,如果是好友加 10分,一般加 5分, 陌生加 1分} , 关系评分越大表明该用户与该特征关系圏中的其他用户 关系越紧密, 其影响力就越大。
或者, 计算模块 204包括: 第一计算单元和第二计算单元; 第一计算单元, 用于根据获取模块 201获取的用户信息中的特征数 据, 计算提取模块 202提取的特征关系圏中用户的特征评分; 并由确定 模块 203根据关系数据确定的用户之间的关系计算关系评分;
第二计算单元, 用于根据第一计算单元计算的特征评分和关系评 分, 计算提取模块 202提取出来的特征关系圏中用户的影响力评分。
具体地, 可以将特征评分和关系评分进行加权相加, 得到每个用户 的影响力评分,然后^ ^据影响力评分进行排序,找到最有影响力的用户。
例如, 对于属于某一特征关系圏的用户的影响力评分函数可以设计 为: 用户 10=特征评分 *f+关系评分 *(l-f)
f为权重, 默认为 0.5, 可根据实际需要调整。
参见图 3, 从具有海量数据的社会化网络中提取特征关系圏, 确定 提取出来的特征关系圏中用户之间的关系, 并计算出最有影响力的用 户。
本发明实施例的有益效果是: 通过指定待提取的特征关系圏的特 征, 根据确定的每个用户的关系数据和特征数据, 提取特征关系圏, 并 对该特征关系圏中的用户进行影响力计算,使所有用户能够更加具体地 了解该特征关系圏, 从而有效的利用社会化网络关系链信息, 实现信息 有效传播和精确搜索的目标。
以上所述仅为本发明的较佳实施例, 并不用以限制本发明, 凡在本 发明的精神和原则之内, 所作的任何修改、 等同替换、 改进等, 均应包 含在本发明的保护范围之内。

Claims

权利要求书
1. 一种在网络中提取特征关系圏的方法, 其特征在于, 所述方法包括: 获取用户信息;
指定待提取的特征关系圏的特征,确定出用户信息与所述指定特征匹配的 用户的集合, 将确定出的该用户集合提取为特征关系圏;
根据所述用户信息确定所述特征关系圏中用户的影响力值。
2. 根据权利要求 1所述的方法, 其特征在于, 所述待提取的特征关系圏 的特征包括:
该待提取的特征关系圏的领域对应的特征。
3. 根据权利要求 1所述的方法, 其特征在于, 所述用户信息包括特征数 据; 根据所述用户信息确定所述特征关系圏中用户的影响力值包括:
对所述特征关系圏中用户的特征数据和所述指定特征的匹配程度进行评 分, 得到用户的特征评分, 根据该特征评分确定该用户在该特征关系圏中的 影响力值。
4. 根据权利要求 1所述的方法, 其特征在于, 所述用户信息包括关系数 据; 根据所述用户信息确定所述特征关系圏中用户的影响力值包括:
根据所述关系数据确定的所述特征关系圏中用户之间的关系,计算用户的 关系评分, 根据该关系评分确定该用户在该特征关系圏中的影响力值。
5. 根据权利要求 1所述的方法, 其特征在于, 所述用户信息包括特征数 据和关系数据; 根据所述用户信息确定所述特征关系圏中用户的影响力值包 括:
对所述特征关系圏中用户的特征数据和所述指定特征的匹配程度进行评 分, 得到用户的特征评分;
根据所述关系数据确定的所述特征关系圏中用户之间的关系,计算用户的 关系评分; 将所述特征评分和关系评分进行加权相加,将加权结果确定为相应用户在 该特征关系圏中的影响力值。
6、 根据权利要求 1至 5任一权项所述的方法, 其特征在于, 确定所述特 征关系圏中用户的影响力值之前, 该方法还包括:
根据所述用户信息确定所述特征关系圏中用户之间的关系。
7、 一种在网络中提取特征关系圏的装置, 其特征在于, 所述装置包括: 获取模块、 提取模块和计算模块;
所述获取模块, 用于获取用户信息;
所述提取模块,用于根据指定的待提取的特征关系圏的特征以及所述获取 模块获取的用户信息, 确定出用户信息与所述指定特征匹配的用户的集合, 将确定出的该用户集合提取为特征关系圏;
所述计算模块,用于根据所述获取模块获取的用户信息,确定所述提取模 块提取出来的特征关系圏中用户的影响力值。
8、根据权利要求 7所述装置, 其特征在于, 所述用户信息包括特征数据; 所述计算模块,用于将所述提取模块提取出来的特征关系圏中用户的特征 数据和指定特征的匹配程度进行评分, 得到用户的特征评分, 根据该特征评 分确定该用户在该特征关系圏中的影响力值。
9、根据权利要求 7所述装置, 其特征在于, 所述用户信息包括关系数据; 所述计算模块, 用于根据所述特征关系圏中用户之间的关系, 计算用户的关 系评分, 根据该关系评分确定该用户在该特征关系圏中的影响力值。
10、 根据权利要求 7所述装置, 其特征在于, 所述用户信息包括特征数据 和关系数据; 所述计算模块包括第一计算单元和第二计算单元;
所述第一计算单元,用于将所述提取模块提取出来的特征关系圏中用户的 特征数据和指定特征的匹配程度进行评分, 得到用户的特征评分;
并根据所述特征关系圏中用户之间的关系, 计算用户的关系评分; 所述第二计算单元,用于将所述第一计算单元计算的特征评分和关系评分 进行加权相加, 将加权结果确定为相应用户在该特征关系圏中的影响力值。
11、 根据权利要求 7至 10任一权项所述的装置, 其特征在于, 该装置进 一步包括确定模块;
所述确定模块,用于根据所述获取模块获取的用户信息,确定所述提取模 块提取出来的特征关系圏中用户之间的关系。
PCT/CN2010/070825 2009-03-10 2010-03-02 一种在网络中提取特征关系圈的方法及装置 Ceased WO2010102541A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
RU2011140606/08A RU2510949C2 (ru) 2009-03-10 2010-03-02 Способ и устройство для извлечения характеристического реляционного круга из сети
MX2011009461A MX2011009461A (es) 2009-03-10 2010-03-02 Metodo y dispositivo para extraer un circulo de relaciones caracteristico de una red.
SG2011060225A SG173795A1 (en) 2009-03-10 2010-03-02 Method and apparatus for extracting characteristic relation circle in network
BRPI1009258A BRPI1009258A2 (pt) 2009-03-10 2010-03-02 método e dispositivo para extrair círculo de relações característico a partir da rede.
CA2753775A CA2753775C (en) 2009-03-10 2010-03-02 Method and device for extracting characteristic relation circle from network
US13/222,133 US20110314009A1 (en) 2009-03-10 2011-08-31 Method and Device for Extracting Characteristic Relation Circle From Network

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CNA2009101273823A CN101499101A (zh) 2009-03-10 2009-03-10 一种社会化网络中特征关系圈的提取方法及装置
CN200910127382.3 2009-03-10

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/222,133 Continuation US20110314009A1 (en) 2009-03-10 2011-08-31 Method and Device for Extracting Characteristic Relation Circle From Network

Publications (1)

Publication Number Publication Date
WO2010102541A1 true WO2010102541A1 (zh) 2010-09-16

Family

ID=40946172

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2010/070825 Ceased WO2010102541A1 (zh) 2009-03-10 2010-03-02 一种在网络中提取特征关系圈的方法及装置

Country Status (8)

Country Link
US (1) US20110314009A1 (zh)
CN (1) CN101499101A (zh)
BR (1) BRPI1009258A2 (zh)
CA (1) CA2753775C (zh)
MX (1) MX2011009461A (zh)
RU (1) RU2510949C2 (zh)
SG (1) SG173795A1 (zh)
WO (1) WO2010102541A1 (zh)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101499101A (zh) * 2009-03-10 2009-08-05 腾讯科技(深圳)有限公司 一种社会化网络中特征关系圈的提取方法及装置
CN102880608A (zh) * 2011-07-13 2013-01-16 阿里巴巴集团控股有限公司 基于人际距离的排名、搜索方法和装置
CN103164416B (zh) * 2011-12-12 2016-08-03 阿里巴巴集团控股有限公司 一种用户关系的识别方法及设备
CN103514215A (zh) * 2012-06-28 2014-01-15 北京奇虎科技有限公司 生成用户社交影响力信息的方法及装置
WO2015135600A1 (en) * 2014-03-10 2015-09-17 Wyrwoll Claudia Method and computer product for automatically generating a sorted list from user generated input and / or metadata derived form social media platforms
CN105740299B (zh) * 2014-12-12 2019-06-21 阿里巴巴集团控股有限公司 识别网络关系的方法、装置及服务器
CN106570699A (zh) * 2015-10-08 2017-04-19 平安科技(深圳)有限公司 客户联系信息挖掘方法及服务器
CN106126576A (zh) * 2016-06-19 2016-11-16 叶元庆 一种树型架构用户跨节点自组织系统及其使用方法
CN106204108B (zh) * 2016-06-29 2018-09-25 腾讯科技(深圳)有限公司 广告反作弊方法及广告反作弊装置
CN109345125A (zh) * 2018-10-11 2019-02-15 北京深度制耀科技有限公司 一种确定关键意见领袖的影响力的方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021098A2 (en) * 2006-08-11 2008-02-21 Facebook, Inc. Systems and methods for generating dynamic relationship-based content personalized for members of a web-based social network
US20080120411A1 (en) * 2006-11-21 2008-05-22 Oliver Eberle Methods and System for Social OnLine Association and Relationship Scoring
US20080250322A1 (en) * 2007-04-03 2008-10-09 Szeto Christopher T Expanding a social network by the action of a single user
US20090030932A1 (en) * 2007-07-27 2009-01-29 Ralph Harik Methods for detecting and remedying missed opportunities in a social network
CN101499101A (zh) * 2009-03-10 2009-08-05 腾讯科技(深圳)有限公司 一种社会化网络中特征关系圈的提取方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003001413A1 (en) * 2001-06-22 2003-01-03 Nosa Omoigui System and method for knowledge retrieval, management, delivery and presentation
EA015549B1 (ru) * 2003-06-05 2011-08-30 Интертраст Текнолоджис Корпорейшн Переносимая система и способ для приложений одноранговой компоновки услуг
US7677970B2 (en) * 2004-12-08 2010-03-16 Microsoft Corporation System and method for social matching of game players on-line
US7711684B2 (en) * 2006-12-28 2010-05-04 Ebay Inc. Collaborative content evaluation
US8266671B2 (en) * 2007-08-02 2012-09-11 Alcatel Lucent Policy-enabled aggregation of IM user communities

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021098A2 (en) * 2006-08-11 2008-02-21 Facebook, Inc. Systems and methods for generating dynamic relationship-based content personalized for members of a web-based social network
US20080120411A1 (en) * 2006-11-21 2008-05-22 Oliver Eberle Methods and System for Social OnLine Association and Relationship Scoring
US20080250322A1 (en) * 2007-04-03 2008-10-09 Szeto Christopher T Expanding a social network by the action of a single user
US20090030932A1 (en) * 2007-07-27 2009-01-29 Ralph Harik Methods for detecting and remedying missed opportunities in a social network
CN101499101A (zh) * 2009-03-10 2009-08-05 腾讯科技(深圳)有限公司 一种社会化网络中特征关系圈的提取方法及装置

Also Published As

Publication number Publication date
CN101499101A (zh) 2009-08-05
RU2011140606A (ru) 2013-04-20
CA2753775A1 (en) 2010-09-16
CA2753775C (en) 2014-06-03
US20110314009A1 (en) 2011-12-22
MX2011009461A (es) 2011-10-03
BRPI1009258A2 (pt) 2018-02-06
RU2510949C2 (ru) 2014-04-10
SG173795A1 (en) 2011-09-29

Similar Documents

Publication Publication Date Title
WO2010102541A1 (zh) 一种在网络中提取特征关系圈的方法及装置
CN104281882B (zh) 基于用户特征的预测社交网络信息流行度的方法及系统
CN106354845A (zh) 基于传播结构的微博谣言识别方法和系统
CN103324745B (zh) 基于贝叶斯模型的文本垃圾识别方法和系统
US20160335425A1 (en) Classifier training method and apparatus, identity authentication method and system
CN110956210B (zh) 一种基于ap聚类的半监督网络水军识别方法及系统
CN103581270A (zh) 用户推荐方法和系统
CN103914494A (zh) 一种微博用户身份识别方法及系统
WO2010102527A1 (zh) 一种sns网络中成员关系圈的提取方法和装置
CN106489146A (zh) 使用会话信息的查询重写
KR20140068942A (ko) 검색 방법, 장치 및 시스템
CN104035941A (zh) 一种信息筛选方法及装置
CN103279504B (zh) 一种基于歧义消解的搜索方法及装置
CN106649849A (zh) 文本信息库建立方法和装置、以及搜索方法、装置和系统
WO2014029314A1 (zh) 信息聚合归类的显示方法及系统
CN101957845A (zh) 一种在线应用系统及其实现方法
CN102999521B (zh) 一种识别搜索需求的方法和装置
US9032044B2 (en) Information processing system, information processing method, program, and non-transitory information storage medium
WO2019107396A1 (ja) データ分析装置及びデータ分析プログラム
US20130031118A1 (en) Information processing system, information processing method, program, and non-transitory information storage medium
CN111882224A (zh) 对消费场景进行分类的方法和装置
CN105138572B (zh) 获取用户标签的关联度权值的方法和装置
CN103593397B (zh) 一种采集微博内容的方法及设备
CN114036395B (zh) 内容推荐方法、装置、计算机设备及计算机可读存储介质
WO2019056502A1 (zh) 综艺比赛结果预测方法、装置及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10750337

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2753775

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: MX/A/2011/009461

Country of ref document: MX

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 6717/CHENP/2011

Country of ref document: IN

ENP Entry into the national phase

Ref document number: 2011140606

Country of ref document: RU

Kind code of ref document: A

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.02.12)

122 Ep: pct application non-entry in european phase

Ref document number: 10750337

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: PI1009258

Country of ref document: BR

ENP Entry into the national phase

Ref document number: PI1009258

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20110909