A brand intimacy calculation method based on the speech of a forum user

A computational method and a technology of intimacy, which can be used in sentiment analysis tasks and crowd classification tasks in natural language processing, and in the field of marketing theory, which can solve problems such as the inability to accurately obtain users' intimacy with brands.

Inactive Publication Date: 2019-02-19
上海宏原信息科技有限公司
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the traditional group division is usually based on the inherent attributes of some users, such as using static information such as users' personal data for group division. This kind of group division is usually one-sided. When companies do brand market research, except In addition to the inherent information above, the user's attitude and behavior can also directly reflect the user's behavior preference for the brand. If the above rough ore crowd classification method is used, the company's research results can only be a general result, and cannot be obtained accurately. Therefore, in the prior art, there is still a lack of a method for judging the user’s intimacy with a brand by combining the user’s inherent attributes, user’s attitude, behavior, and user’s attitude towards other brands.

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 brand intimacy calculation method based on the speech of a forum user
  • A brand intimacy calculation method based on the speech of a forum user
  • A brand intimacy calculation method based on the speech of a forum user

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the embodiments and accompanying drawings, and the contents mentioned in the embodiments are not intended to limit the present invention.

[0030] Such as figure 1 As shown, in one embodiment of the present invention, the brand intimacy calculation method based on the comments of forum users of the present application is used to predict the intimacy of users of a certain maternal and child forum to each diaper brand. The steps include:

[0031] S1: Obtain all the user's speech and mark it with a set label, and output the user's attitude towards different brands through the pre-trained word vector and deep attitude prediction model;

[0032] Obtain all the text data (content) of the user according to the ID (user_id) of the Maternal and Child Forum user. Each text has a corresponding ID mark (id) and speech time (created_at), and...

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 brand intimacy calculation method based on the speech of a forum user, which comprises the following steps: obtaining all the speech of the user and labeling the set labels;outputting the attitude of the user to different brands through a pre-trained word vector and a depth attitude prediction model; outputting the attitude of the user to different brands; obtaining allthe user's comments and labelling them, and outputting the user's behavior labels to different brands; combined with the user's attitude to the brand, behavior and the user's attitude to other brands, calculating the user's intimacy to each brand. The invention realizes accurate crowd division through modeling, and can effectively help enterprises to carry out market and user group analysis.

Description

technical field [0001] The invention relates to the field of computers and marketing theory, specifically to the field of machine learning, in particular to emotion analysis tasks and crowd classification tasks in natural language processing. Background technique [0002] In recent years, social networks have developed rapidly, and more and more content is generated by network users themselves. Some specific groups of users usually discuss some common topics in some specific forums, and these specific personalized information contains a large number of users' personal information. Likes and followers, these speech data can help brands better understand user needs and experience, help brands enhance and improve brand image, and help discover new market growth points. For platforms, it can also help platforms It is easier to understand user behavior, which is helpful for cooperation and precise delivery. [0003] At present, the traditional group division is usually based on ...

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): G06F16/9535G06Q30/02
CPCG06Q30/0201G06Q30/0203
Inventor 杨骏
Owner 上海宏原信息科技有限公司
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