Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for mining customer style preferences through IM chat content analysis

A technology of chat content and style, applied in instruments, probabilistic networks, computing models, etc., can solve problems such as affecting delivery quality and user experience, inability to deeply understand user preferences, and inability to accurately convey requirements, reducing follow-up communication time. , convenient introduction and recommendation, the effect of reducing the time to choose a style

Inactive Publication Date: 2020-06-02
江苏艾佳家居用品有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Obtaining user style preferences is the cornerstone of designers' design and creation, and a necessary process to provide satisfactory design solutions and improve user satisfaction; the existing process of obtaining user decoration style preferences is mainly through manual docking with users, through one by one Asking questions and providing a large number of style solutions for users to choose by themselves. As the number of users continues to increase, the efficiency of staff docking is limited. During this period, users will need a lot of waiting time, user needs cannot be accurately conveyed, and user preferences Unable to understand deeply, which will ultimately affect the delivery quality and user experience, and affect the interests of the company

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
  • Method for mining customer style preferences through IM chat content analysis
  • Method for mining customer style preferences through IM chat content analysis
  • Method for mining customer style preferences through IM chat content analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] 1) Query the customer's historical orders and classify the orders into each style;

[0031] 2) Sorting customer IM chat information, separating vocabulary through word segmentation tools, sorting, merging, listing the frequency of keywords in it, sorting according to frequency, and taking out keywords with higher frequency of occurrence as statistical dimensions;

[0032] 3) Count the number of occurrences of keywords obtained in the previous step in each order.

[0033] Table 1 is sorted out as follows:

[0034]

[0035]

[0036] Table 1 takes 4 keywords as an example. In practical applications, the more keywords, the greater the reference value of the final results.

[0037] The process of calculating the probability in this embodiment is as follows:

[0038] Suppose, at this time, in the user's chat history, two keywords "wooden" and "smart" appear; by the above formula:

[0039] max(P)=max(P(A1|S)P(A2|S)...P(An|S)P(S))

[0040] The relative possibility can...

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 method for mining customer style preferences through IM chat content analysis. The method comprises the following steps: establishing a style library, setting a style libraryset as S, dividing design styles, and continuing to refine the styles based on the existing styles, for example, the European style can be refined into bright European style, European style naive andthe like; analyzing IM chat records, decomposing vocabularies in the client chat records through an existing natural language processing technology, listing the vocabularies related to style preferences as keywords, sorting the keywords to form a set, setting the keyword set as X, and manually removing segmented words without reference. According to the method, the IM chat data is analyzed and processed to assist workers, the efficiency of the workers is improved, and more complete style preferences more conforming to user ideas are obtained in a short time, so that the satisfaction degree ofa final output scheme of a designer is improved.

Description

technical field [0001] The invention relates to the technical field of home decoration design, in particular to a method for mining customer style preferences through IM chat content analysis. Background technique [0002] Obtaining user style preferences is the cornerstone of designers' design and creation, and a necessary process to provide satisfactory design solutions and improve user satisfaction; the existing process of obtaining user decoration style preferences is mainly through manual docking with users, through one by one Asking questions and providing a large number of style solutions for users to choose by themselves. As the number of users continues to increase, the efficiency of staff docking is limited. During this period, users will need a lot of waiting time, user needs cannot be accurately conveyed, and user preferences Without a deep understanding, it will ultimately affect the delivery quality and user experience, and affect the company's interests. Con...

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): G06F30/13G06F30/27G06N7/00
CPCG06N7/01
Inventor 陈旋王冲张平居凌宇
Owner 江苏艾佳家居用品有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com