Identification method and device for false search behavior of search engine

A recognition method and search engine technology, applied in the field of information search and retrieval, can solve problems such as difficulty in identifying false search behaviors, recognition lag, and inability to automatically identify false search behaviors of full query words

Active Publication Date: 2016-05-11
ALIBABA (CHINA) CO LTD
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (2) False search behaviors of search engines are generally concealed
This also brings difficulties to the identification of false search behavior by search engines
[0007] (4) Generally, the identification of false search behavior by search engines is lagging and passive
This identification method may be effective for false search behaviors that search for multimedia resources but do not click on multimedia resources, but may not be effective for false search behaviors that click on multimedia resources but do not play multimedia resources
Moreover, with the development of current crawler technology, the crawler behavior of forged IP addresses makes it more difficult to identify fake search behaviors
In addition, it is currently impossible to automatically identify false search behaviors of full query words

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
  • Identification method and device for false search behavior of search engine
  • Identification method and device for false search behavior of search engine
  • Identification method and device for false search behavior of search engine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] figure 1 A flowchart showing a method for identifying false search behavior of a search engine according to an embodiment of the present invention. Such as figure 1 As shown, the identification method can mainly include:

[0063] In step S100, user viewing behavior data of a single query word and user conversion behavior data of a single query word may be acquired from user logs.

[0064] Specifically, the quadruple {query, vids, percs, δ} can be used to characterize the user's viewing behavior for each query word. This process may include preprocessing and noise removal processing on the user log data. The noise of the user log data may come from many aspects such as illegal input, system abnormality, and record abnormality.

[0065] Wherein, query is a query word, that is, each search input by the user on the search engine, for example, the query word query of the user can be obtained from a user log of the search engine.

[0066] vids is a collection of clicked...

Embodiment 2

[0126] figure 2 A flowchart showing a method for identifying false search behavior of a search engine according to Embodiment 2 of the present invention. figure 2 Winning mark and figure 1 The same steps have the same functions, and detailed descriptions of these steps are omitted for brevity.

[0127] Such as figure 2 as shown, figure 2 The identification method of the false search behavior of the search engine shown and figure 1 The main difference of the identification method of the false search behavior of the search engine shown is that, in addition to step S100 and step S120 in the first embodiment above, the user conversion behavior data includes the conversion rate of the direct area and the identification data includes the multimedia resource click divergence In the case of degree, step S140 may specifically include:

[0128] Step S200, it may be judged whether the conversion rate of the direct area of ​​the current query word is less than the first thresho...

Embodiment 3

[0150] Figure 4 A flowchart showing a method for identifying false search behavior of a search engine according to Embodiment 3 of the present invention. Figure 4 Winning mark and figure 1 The same steps have the same functions, and detailed descriptions of these steps are omitted for brevity.

[0151] Such as Figure 4 as shown, Figure 4 The identification method of the false search behavior of the search engine shown and figure 1 The main difference of the identification method of the false search behavior of the search engine is that, in addition to step S100 and step S120 in the first embodiment above, the user conversion behavior data includes the conversion rate of the direct area and the identification data includes the average playback of multimedia resources. In the case of completion ratio, step S140 may specifically include:

[0152] Step S300, it may be judged whether the conversion rate of the direct area of ​​the current query word is less than the firs...

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 an identification method and device for a false search behavior of a search engine. The search engine is used for searching for a multimedia resource. The identification method comprises the steps of obtaining user watching behavior data of a single query word and user transformation behavior data of the single query word from a user log; according to the user watching behavior data and / or the user transformation behavior data, determining identification data used for identifying the false search behavior, wherein the identification data includes at least one of an independent multimedia resource playing amount, a multimedia resource average playing completion percentage, multimedia resource clicking divergence degree and multimedia resource set playing residue degree; and according to the identification data, identifying the false search behavior. According to the identification method and device, the accuracy of identifying the false search behavior can be improved and the false search behavior of a total-amount query word can be automatically identified.

Description

technical field [0001] The invention relates to the field of information search and retrieval, in particular to a method and device for identifying false search behavior of a search engine. Background technique [0002] At present, there is no uniform and mature method to identify false search behaviors of search engines used to search multimedia resources. In general, only when it is necessary to identify the false search behavior of the search engine, the search engine will carry out the identification of false search behavior according to its own business needs. As the business system of the search engine matures and the processing capability and robustness of the search engine improve, the false search behavior of the search engine can basically be tolerated, that is, there is basically no need to identify the false search behavior of the search engine. For example, only when individual false search behaviors affect the system service quality of search engines, engineer...

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): G06F17/30
CPCG06F16/95
Inventor 魏博齐志兵李力行魏强马堰夫姚键顾思斌潘柏宇王冀
Owner ALIBABA (CHINA) 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