Unlock instant, AI-driven research and patent intelligence for your innovation.

Feature screening method and device, terminal and medium

A feature screening and feature word technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of limited manual processing speed, poor timeliness, poor versatility, etc. Effect

Active Publication Date: 2018-05-18
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the prior art has the following problems: in the above method, due to too much dependence on manpower, the speed of manual processing is limited, and the amount of risk data is large, so the timeliness is poor; The risk data needs to select personnel from different industries to screen the data, so the versatility is poor

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
  • Feature screening method and device, terminal and medium
  • Feature screening method and device, terminal and medium
  • Feature screening method and device, terminal and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] figure 1 It is a flowchart of a feature screening method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of extracting feature words from data of at least one user, especially the case of extracting risk feature words from data of multiple risk users. The method can be executed by a feature screening device, and the device can be implemented by software and / or hardware. see figure 1 , the feature screening method provided in this embodiment includes:

[0052] S110. Acquire data of at least one user.

[0053] Wherein, the user is a user to be screened by a feature, and the feature is a feature representing commonality of at least one user, and is specifically determined by user data. For example, if the above user data is the user's interest data, then the feature is the user interest feature. The user's data can be determined as required, and optionally, it can be user behavior data or data uploaded by the user.

[0054...

Embodiment 2

[0102] figure 2 It is a flowchart of a feature screening method provided in Embodiment 2 of the present invention. This embodiment is an optional solution proposed on the basis of the foregoing embodiments. In this embodiment, the application scenario is an Internet risk identification scenario as an example for illustration. see figure 2 , the feature screening method provided in this embodiment includes:

[0103] S210. Obtain data submitted by risk users in the risk seed set from complaint feedback and / or penalty history.

[0104] Wherein, the risk seed set is a set of at least one risk user of the same category.

[0105] Typically, the above data may be risk data uploaded by risk users for promotion. The category of risk data can be gambling, pornography, violence, etc., and this category can be obtained from complaint feedback and / or penalty history.

[0106] S220. Directly determine words or phrases in the data as keywords.

[0107] S230. Perform word segmentatio...

Embodiment 3

[0129] image 3 It is a schematic structural diagram of a feature screening device provided in Embodiment 3 of the present invention. see image 3 , The feature screening device provided in this embodiment includes: an acquisition module 10 , a keyword determination module 20 and a feature word determination module 30 .

[0130] Wherein, the obtaining module 10 is used to obtain the data of at least one user; the keyword determination module 20 is used to determine at least one keyword from the data; the feature word determination module 30 is used to determine the user frequency according to the keyword , determining a feature word from at least one of the keywords, wherein the user frequency indicates the number of users whose data contains the keyword.

[0131] According to the technical solution of the embodiment of the present invention, the keywords representing the commonness of the users are determined from the user data as the characteristic words according to the u...

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 embodiment of the invention discloses a feature screening method and device, a terminal and a medium and relates to the field of Internet information processing technology. The method comprises the steps that data of at least one user is acquired; at least one keyword is determined from the data; and according to user frequency of the keywords, feature words are determined from the keywords, wherein the user frequency refers to the quantity of the users containing the keywords in the data. Through the feature screening method and device, the terminal and the medium in the embodiment, automatic feature screening on the acquired data is realized, and therefore the timeliness and universality of the screening process are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of Internet information processing, and in particular to a feature screening method, device, terminal and medium. Background technique [0002] A core issue of Internet risk control is how to quickly screen the core risk characteristics for one type of risk, so as to distinguish risky users from normal users. [0003] In the prior art, the risk data fed back by users is usually manually analyzed to screen out core risk features and use the core risk features to identify risky users. [0004] In the process of realizing the present invention, the inventor found that the prior art has the following problems: in the above method, due to too much dependence on manpower, the speed of manual processing is limited, and the amount of risk data is large, so the timeliness is poor; The risk data needs to select personnel from different industries to screen the data, so the versatility is poor. ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/334G06F40/216G06F40/284
Inventor 邰阳路远杨丽霞林惠娟
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD