Check patentability & draft patents in minutes with Patsnap Eureka AI!

A method and system for labeling an advertisement label

An advertising and labeling technology, applied in advertising, marketing, instruments, etc., to achieve the effect of batch labeling engineering, cost reduction, and efficiency improvement

Active Publication Date: 2020-02-18
ALIBABA (CHINA) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of this, the present invention provides a labeling method and system for advertising labels, which solves the problem that the automatic labeling of labels cannot be realized in engineering

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
  • A method and system for labeling an advertisement label
  • A method and system for labeling an advertisement label
  • A method and system for labeling an advertisement label

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, it is a schematic flow chart of an embodiment of the marking method of the advertisement label of the present invention. In this embodiment, by calculating the similarity of each advertisement and constructing a probability transition matrix, the labels that need to be marked on the untagged advertisements are selected from the labeled advertisements through the probability transition matrix, and automatic labeling is realized. The labeling method of advertisement label in the present embodiment comprises the following steps:

[0055] Step 101. Obtain tag information of each advertisement, and obtain the similarity between the tags of each advertisement in combination with the tag information of the advertisement.

[0056] In this embodiment, the labeled advertisements are used to label the advertisements that have a certain correlation with them and the labels are not labeled, so that the labeled advertisements can be fully utilized to impro...

Embodiment 2

[0067] Such as figure 2 As shown, it is an optional embodiment of the labeling method of the advertisement label described in the embodiment of the present invention. Compared with the flow in the embodiment shown in Embodiment 1, this embodiment optionally describes the process of constructing a label matrix and obtaining a score matrix. The method described in this embodiment includes the following steps:

[0068] Step 201. Obtain the behavioral similarity between the advertisements by clicking on the user information of the advertisements.

[0069] Obtain the user set of each advertisement separately, and calculate the behavioral similarity between the advertisements through the user set of each advertisement, as follows:

[0070] A and B are the user sets of advertisement a and b respectively, which respectively represent the clicks of their users. Then, the cosine distance is used to calculate the user similarity of the behavior of advertisement a and advertisement b a...

Embodiment 3

[0096] In this implementation, a specific example is used to illustrate the labeling method of the advertisement label of the present invention. In this embodiment, there are a total of three advertisements in the advertisement library, which are respectively marked as ad1, ad2, and ad3, where ad1 is marked with the t1 label, ad2 is marked with the t2 and t3 labels, and ad3 is not marked with the label. Now we need To label ad3, the labeling steps are as follows:

[0097] First calculate the behavior similarity between the three advertisements, among them, the users who click ad1 are {u1, u2, u3}, the users who click ad2 are {u2, u3, u4, u5}, and the users who click ad3 are {u2, u5, u6}, then

[0098]

[0099]

[0100] Then calculate the similarity of the description information between the three advertisements. Among them, the word segmentation after word segmentation and stop word filtering for ad1 are: word1, word2, word3; the word segmentation after word segmentat...

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 label marking method and system. The method includes obtaining label information of different advertisements and obtaining the similarity of the advertisement labels according to the label information of the advertisements; constructing a weighing structural graph of the similarity of the advertisements according to the similarity of the advertisement labels and the label information of the advertisements; obtaining the transfer possibilities of the advertisement labels according to the weighing structural graph and constructing a possibility transfer matrix among the advertisement labels; constructing label matrixes for the advertisements that marked with labels and are not marked with labels, and generating a combined label matrix through combination; generating a scoring matrix through combining the combined label matrix and the possibility transfer matrix, comparing the score in the scoring matrix with a predetermined threshold value and marking the advertisements having no marking labels with advertisement labels whose scores meeting the threshold value. By adopting the method and system provided by the invention, the cost of marking advertisements with labels is reduced.

Description

technical field [0001] The invention relates to the technical field of advertisement data processing, and relates to a method and system for adding labels to advertisements. Background technique [0002] With the continuous development of technologies such as the Internet, commodity advertisements have gradually developed from the original physical advertisement forms such as commodity packaging and billboards to virtual advertisement forms such as media. Nowadays, publishing advertisements on online media to display products has become a common method for merchants, and the way of displaying products through online media can achieve better product marketing effects. Furthermore, various technologies are now pursuing intelligent and automatic functions, which can better meet the needs of users in real life and improve the actual experience of users in practice. [0003] The current advertisement delivery also proposes the form of push delivery based on user interests. Accor...

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 Patents(China)
IPC IPC(8): G06F40/289G06Q30/02
CPCG06F40/289G06Q30/0271
Inventor 袁树仑章岑杨田周盛潘柏宇王冀
Owner ALIBABA (CHINA) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com