E-commerce advertisement ROAS anomaly detection method and device and electronic equipment

An anomaly detection and advertising technology, applied in the computer field, can solve problems such as low accuracy rate, too subjective detection results, timeliness, and unacceptable labor costs, and achieve the effect of improving detection rate and objective and accurate detection

Active Publication Date: 2022-06-03
上海飞书深诺数字科技集团股份有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, merchants will place advertisements on e-commerce platforms. In order to determine the return on advertising expenditure (ROAS) of the advertisements placed, they usually use manual labeling to detect ROAS, which is impossible in terms of timeliness and labor costs. Accepted, and artificial detection of ROAS makes the detection results too subjective, resulting in low accuracy of ROAS detection results

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
  • E-commerce advertisement ROAS anomaly detection method and device and electronic equipment
  • E-commerce advertisement ROAS anomaly detection method and device and electronic equipment
  • E-commerce advertisement ROAS anomaly detection method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment proposes a method for detecting ROAS anomaly in e-commerce advertisements, and the execution subject is a server.

[0033] The server may use any computing device in the prior art capable of detecting anomalies in the ROAS of e-commerce advertisements, which will not be repeated here.

[0034] see figure 1 Shown is a flow chart of a method for detecting ROAS anomaly in e-commerce advertisements. This embodiment proposes a method for detecting ROAS anomalies in e-commerce advertisements, including:

[0035] Step 100: Acquire advertisement information of an e-commerce advertisement to be subjected to ROAS detection.

[0036] In the above step 100, the advertisement information includes but is not limited to: the text of the advertisement, the image of the advertisement, and the video frequency band of the advertisement.

[0037] Step 102: Input the advertisement information of the e-commerce advertisement into a category classifier, and determine the cat...

Embodiment 2

[0084] This embodiment provides a device for detecting ROAS anomaly in e-commerce advertisements, which is used for executing the above-mentioned method for detecting ROAS anomalies in e-commerce advertisements.

[0085] see image 3 Shown is a schematic structural diagram of a ROAS abnormality detection device for e-commerce advertisements. This embodiment proposes a ROAS abnormality detection device for e-commerce advertisements, including:

[0086] an acquisition module 200, configured to acquire advertisement information of e-commerce advertisements to be subjected to ROAS detection;

[0087] A determination module 202, configured to input the advertisement information of the e-commerce advertisement into a category classifier, and determine the category to which the e-commerce advertisement belongs;

[0088] The first processing module 204 is configured to obtain the ROAS and commodity unit resources of the commodity of the category to which the e-commerce advertisement ...

Embodiment 3

[0112] This embodiment proposes a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the method for detecting ROAS anomaly in e-commerce advertisements described in the foregoing embodiment 1 are executed. . For specific implementation, refer to Method Embodiment 1, which will not be repeated here.

[0113] In addition, see Figure 4 A schematic structural diagram of an electronic device is shown. This embodiment also provides an electronic device. The electronic device includes a bus 51 , a processor 52 , a transceiver 53 , a bus interface 54 , a memory 55 and a user interface 56 . The above-mentioned electronic device includes the memory 55 .

[0114] In this embodiment, the above-mentioned electronic device further includes: one or more programs stored on the memory 55 and executable on the processor 52, configured to be executed by the above-mentio...

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 provides an E-commerce advertisement ROAS anomaly detection method and device and electronic equipment, and the method comprises the steps: obtaining a splitting condition of commodity unit resource information through employing the commodity unit resource information of a commodity of a category to which an E-commerce advertisement belongs; whether the ROAS of the e-commerce advertisement is abnormal or not is detected through the obtained splitting condition of the ROAS and the splitting condition of the commodity unit resource information, manual participation is not needed in the whole detection process, and the ROAS abnormity of the e-commerce advertisement can be detected more objectively and accurately; moreover, on the basis of the single judgment condition of the splitting condition of the ROAS, the judgment condition of the splitting condition of the commodity unit resource information is added to detect whether the ROAS of the e-commerce advertisement is abnormal or not, so that the detection rate of the abnormal ROAS is greatly improved.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular, to a method, device and electronic device for detecting ROAS anomaly in e-commerce advertisements. Background technique [0002] At present, merchants will place advertisements on the e-commerce platform. In order to determine the return on advertising spend (ROAS) of the advertisements, the ROAS is usually detected by manual labeling, which is impossible in terms of timeliness and labor costs. Accepted, and the artificial detection of ROAS makes the detection results too subjective, resulting in a low accuracy of the ROAS detection results. SUMMARY OF THE INVENTION [0003] In order to solve the above problems, the purpose of the embodiments of the present invention is to provide a method, device and electronic device for detecting ROAS anomaly in e-commerce advertisements. [0004] In a first aspect, an embodiment of the present invention provides a method for de...

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
CPCG06Q30/0242
Inventor 陈文海沈菁康单张天生张聪
Owner 上海飞书深诺数字科技集团股份有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap