An advertisement ranking mechanism generation method and a generation system

A mechanism and advertisement technology, applied in the field of advertisement sorting mechanism generation method and generation system, which can solve problems such as non-support

Active Publication Date: 2019-02-22
苏州创旅天下信息技术有限公司
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] It can be seen from the above literature that there are relatively complete technical solutions for increasing advertiser revenue and platform revenue based on improving the efficiency of advertisement display and the click-through rate of advertisements. However, the number of advertisement display positions in the prior art is a static value N (N≥1), there is no consideration for the scenario where the number of advertising display positions can be 0. For example, the number of advertising display positions may be a positive number N greater than 0, or it may be 0. In the tying service scenario, often There will be a situation where the number of advertising display positions is 0, but the existing technology does not support it. Therefore, this application proposes a new solution

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
  • An advertisement ranking mechanism generation method and a generation system
  • An advertisement ranking mechanism generation method and a generation system
  • An advertisement ranking mechanism generation method and a generation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] refer to figure 1 , is a method for generating an advertisement sorting mechanism disclosed in the present invention, which includes the following steps:

[0075] Step S1. Configure a type of feature parameter range that allows displaying services, filter services with a type of feature parameter outside the range of a type of feature parameter, and put the remaining services into a recall pool. Specifically, in this embodiment, one type of feature parameter range is the price range of services, and services within the price range are put into a recall pool to ensure user experience.

[0076] Although this application uses price as an example to introduce the application scenario of this application, those skilled in the art can understand that the technical solution of this application is also applicable to various parameter scenarios, such as advertising placement ratio, advertising The push time, etc., are not specifically limited in this application.

[0077] Step...

Embodiment 2

[0083] refer to figure 2 , based on Embodiment 1, the difference between this embodiment and Embodiment 1 is that step S1 includes the following sub-steps:

[0084] S11. Configure the upper limit parameters of a class of features that allow the display of services, filter services with a class of feature parameters greater than or equal to the upper limit parameters of a class of features, and put the remaining services into a recall pool.

[0085] S12. Detect the number of services in the recall pool. If the number of services in the recall pool is 0, add a service with the smallest characteristic parameter among the filtered services and put it into the recall pool again.

[0086] Specifically, refer to image 3 , after entering the service id, judge whether the service price / primary demand price is greater than or equal to the set upper limit parameter. If the service price / main demand price of some services is greater than or equal to the set upper limit parameter, filt...

Embodiment 3

[0106] refer to Figure 7 , is an advertisement ranking mechanism generation system disclosed in the present invention, which includes a service restriction module 10 , an estimation module 20 and a ranking mechanism generation module 30 .

[0107] refer to Figure 7 The service restriction module 10 is configured to configure a type of feature parameter range that allows displaying services, filter services with a type of feature parameter outside the type of feature parameter range, and put the remaining services into a recall pool. Specifically, in this embodiment, one type of feature parameter range is the service price range, and services within the price range will be put into a recall pool to ensure user experience.

[0108] Although this application uses price as an example to introduce the application scenario of this application, those skilled in the art can understand that the technical solution of this application is also applicable to various parameter scenarios,...

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 advertisement ranking mechanism generation method and a generation system, which relate to the technical field of computing advertisement ranking mechanism, and aim at solving the problem that the existing advertisement ranking mechanism can not support the scene that the number of advertisement display bits is zero. The key points of the technical scheme comprise 11) configuring a characteristic parameter interval of one class and filtering that service of a characteristic parameter outside the characteristic parameter interval of one class; S2 constructing a prediction sample, and obtaining the purchase rate of the service and the conversion rate of the main demand of the user through the classification decision algorithm and the prediction sample; S3 generating a list of non-display proportions of display times in total display times with the number of advertisement display bits being 0, calculating the corresponding service revenue increment according tothe non-display proportions, and generating a sorting index calculation formula in which the main demand conversion unit quantity increment / service revenue increment reaches a set value. The technicalsolution of the present application has the effect of adapting to a scene in which the number of advertisement display bits is zero.

Description

technical field [0001] The invention relates to the technical field of computing advertisement ranking mechanism, in particular to a method and system for generating an advertisement ranking mechanism. Background technique [0002] At present, the ranking mechanism that uses platform revenue as the ranking index of advertisements is more and more taken out as a separate study of the Strategy module. For example, Taobao designs OCPC sorting from the two ranking indicators of advertiser revenue + α × platform revenue and platform revenue. The mechanism is used to sort the candidate services, which has achieved the purpose of increasing the revenue of advertisers and the revenue of the platform. [0003] Based on the above-mentioned purpose of increasing advertiser revenue and platform revenue, some Internet platforms and Internet companies have also launched different online advertising solutions, such as: [0004] D1: Beijing Qihoo Technology Co., Ltd. applied for a Chinese ...

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): G06Q30/02
CPCG06Q30/0244
Inventor 汤友花
Owner 苏州创旅天下信息技术有限公司
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