User identifier recognition method and apparatus

A technology of user identification and identification method, which is applied in the field of user identification identification method and a user identification device, and can solve the problems of high time cost of manual labeling, difficulty in obtaining training data, and low applicability, etc.

Inactive Publication Date: 2016-11-09
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since there is no public IIP navy data set, it is difficult to obtain training data based on machine learning methods, and the time cost of relying solely on manual labeling is too high
In addition, the method based on machine learning requires more user information to determine whether the current user is a troll, and has higher requirements for data integrity.
Therefore, the efficiency of machine learning methods is also low, and the applicability is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • User identifier recognition method and apparatus
  • User identifier recognition method and apparatus
  • User identifier recognition method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0114] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a method for identifying a user ID according to an embodiment of the present invention, which may specifically include the following steps:

[0115] Step 110, acquiring multiple user IDs.

[0116] In this embodiment of the present invention, the user ID may refer to a name that identifies the user identity in the IIP, for example, user nickname, user name, user account, etc. all belong to the user ID. In practical applications, the user ID is composed of a series of characters recognizable by the IIP system, such as letters, Chinese characters, Arabic numerals, special symbols, and so on. Such as Figure 1A Examples for some user IDs. It can be seen that the 1st to 4th user IDs are composed of Chinese characters, underscores and letters, while the subsequent 5th to 8th and 12th to 16th are composed of Chinese characters and letters, and the other 9th to 11th are completely composed of Chine...

Embodiment 2

[0193] refer to figure 2 , which shows a flow chart of the steps of an embodiment of a method for identifying a user ID according to an embodiment of the present invention, which may specifically include the following steps:

[0194] Step 210, acquiring multiple user IDs.

[0195] Step 220, converting each user ID among the plurality of user IDs into a block policy set; the block policy set includes slices of corresponding user IDs.

[0196] Step 230, using N first hash functions to calculate the hash signatures of the elements included in the block policy set of each user ID; the N first hash functions are different.

[0197] In practical applications, if according to the method of Embodiment 1, the similarity between each user's nickname is directly compared in turn, the time complexity is O(n 2 ), where O(f(n)) is a time complexity function, which can quantitatively describe the running time of the algorithm f(n), n is the number of user IDs that need to be identified, u...

Embodiment 3

[0279] refer to image 3 , which shows a flow chart of the steps of an embodiment of a method for identifying a user ID according to an embodiment of the present invention, which may specifically include the following steps:

[0280] Step 310, acquiring multiple user identifiers.

[0281] Step 320: Transform each user ID among the plurality of user IDs into a block policy set; the block policy set includes slices of corresponding user IDs.

[0282] Step 330: Construct a first matrix according to the relationship between each user ID among the plurality of user IDs and each element in the block strategy set of each user ID; wherein, the columns of the first matrix correspond to each user ID ID; the row of the first matrix corresponds to each element in the block policy set of each user ID; if the user ID contains any element in the element, then the corresponding value in the first matrix is The second value; if the element is not included in the user identifier, then the cor...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a user identifier recognition method and apparatus, and relates to the technical field of computers. The method comprises the steps of obtaining a plurality of user identifiers; calculating the similarity between the user identifiers in the plurality of the user identifiers; for any user identifier in the plurality of the user identifiers, judging whether the similarity between the current user identifier and other user identifier with the value exceeding a first numerical value exceeds a first threshold or not; and if the similarity between the current user identifier and other user identifier with the value exceeding the first numerical value exceeds the first threshold, confirming that the current user identifier is a user identifier of an online water army. Therefore, the problems of relatively numerous manual interventions and low applicability of an existing rule-based qualitative recognition method, excessively high time cost, relatively high data completeness requirement and relatively low efficiency of a machine learning method, and the like are solved and the beneficial effects of reducing the time cost, lowering the data completeness requirement and improving the efficiency and applicability of user recognition are achieved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a user identification identification method and a user identification identification device. Background technique [0002] With the continuous development of network technology, the Internet information interaction platform has gradually become the main channel for people to obtain information. The so-called Internet information interaction platform, referred to as information interaction platform IIP (Information Interaction Platform) refers to: all information systems and platforms that can perform information release, expression, interaction (including reply, reprint) and other operations, in the form of communities, forums, social networks, etc. , media, portals, and more. However, with the popularity of IIP marketing, the number of trolls on the IIP platform has also increased dramatically. Internet trolls can create a lot of meaningless or untrue spam, which not...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/30G06Q50/00
CPCG06F16/951G06Q50/01
Inventor 沈一鲍新平
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products