Promotion content evaluation method and device, electronic device and storage medium

An evaluation method and content technology, applied in the field of content promotion, can solve the problems of deep learning models affecting evaluation results, low sample utilization, and few supported scenarios, so as to improve sample diversity and feature richness, and alleviate sample bias. , the effect of improving the accuracy rate

Pending Publication Date: 2019-08-30
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this also brings new problems. The type of deep learning model and the selection of samples are all factors that affect the evaluation effect.
Th

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
  • Promotion content evaluation method and device, electronic device and storage medium
  • Promotion content evaluation method and device, electronic device and storage medium
  • Promotion content evaluation method and device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present application can be more thoroughly understood, and the scope of the present application can be fully conveyed to those skilled in the art.

[0049] Taking Internet advertising as an example, in the on-site scenario (for example, advertisements related to products in the APP are placed inside the APP), the display data, click data and conversion data of the advertisement are the factors that affect the advertiser's payment. The conversion behavior refers to the behavior that the user finally purchases the product or service corresponding to the advertis...

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 promotion content evaluation method and device, an electronic device and a storage medium. The method comprises the following steps: generating sample data according to promotion data; wherein the sample data comprises a plurality of tags, and at least comprises calling tags corresponding to calling behaviors; inputting the sample data into a multi-target model based on adeep learning network for training to obtain an evaluation model of promotion content; wherein the multi-target model comprises sub-networks corresponding to the tags respectively; and evaluating thepromotion content to be evaluated according to the evaluation model of the promotion content. The technical scheme has the beneficial effects that the calling behavior of the promotion content related to the APP is considered, the method is suitable for a complex scene combining the interior of the station and the exterior of the station, and the possibility that the equipment jumps from the exterior of the station to the interior of the station APP can be effectively evaluated. Due to the fact that the calling tag is added to the sample utilization rate, and the multi-target model is adopted, the sample diversity and the feature richness are improved, the sample deviation problem is relieved, and the evaluation accuracy is improved.

Description

technical field [0001] The present application relates to the technical field of content promotion, and specifically relates to a promotion content evaluation method, device, electronic equipment and storage medium. Background technique [0002] How to evaluate the fit between promotional content and user needs has always been a difficult problem. The continuous development of deep learning has brought new solutions to the evaluation of promotional content. By learning various behaviors related to users and promotional content as samples, we can Estimate whether a promotional content can be clicked by users, etc. But this also brings new problems. The type of deep learning model and the selection of samples are all factors that affect the evaluation effect. The evaluation methods in the existing technology have defects such as few supported scenarios and low sample utilization, which need to be improved. Contents of the invention [0003] In view of the above problems, t...

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): G06Q30/02G06N3/08
CPCG06N3/08G06Q30/0242
Inventor 程建明
Owner BEIJING SANKUAI ONLINE 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