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

Key opinion consumer mining method, device and equipment and medium

A technology of consumers and opinions, applied in business, instruments, data processing applications, etc., can solve the problem of difficulty in ensuring the efficiency and accuracy of identification

Pending Publication Date: 2020-07-10
上海络昕信息科技有限公司
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when evaluating KOC in traditional operations, the identification of KOC mainly depends on the experience of operators, and the efficiency and accuracy of identification are difficult to guarantee.

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
  • Key opinion consumer mining method, device and equipment and medium
  • Key opinion consumer mining method, device and equipment and medium
  • Key opinion consumer mining method, device and equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 of the present invention provides a key opinion consumer mining method, figure 1 A flow chart showing Embodiment 1 of the method for mining key opinion consumers of the present invention, including: a method for mining key opinion consumers, characterized in that it includes:

[0048] Step S101: Determine a first preset number of target features in the activity field, community field, and consumption field according to the determined key opinion consumer KOC and the determined non-KOC, as well as the feature values ​​corresponding to each of the target features and target sample space;

[0049]Determine the target characteristics in the activity field, community field and consumption field according to the currently identified key consumer KOC and identified non-KOC, and the identified KOC and identified non-KOC can be extracted from the database of identified data Obtained, for example, extracting 3000 determined KOCs and 3000 determined non-KOCs, as a sp...

specific Embodiment approach

[0050] As a specific implementation, the method of defining the characteristic value of the target characteristic can be as follows:

[0051] In the field of activity dimension:

[0052] Participation frequency of publicity activities: In daily operation, the monthly granularity is the number of times each user participates in publicity activities. More than or equal to 4 times is 1 point, less than 4 times and greater than or equal to 2 times is 0.5 points, less than 2 times is 0 Minute;

[0053] Coupon activity participation frequency: with monthly granularity, the number of coupons received by each user per month accounts for the percentage of monthly card coupon activities, 1 point for more than or equal to 60% of times, 0.5 points for less than 60% and greater than or equal to 40%, 0.5 points for less than 60% 40% is 0 points;

[0054] Activity sharing frequency: 1 point for each user sharing 80% to 50% of activities per month, 0.5 points for sharing 50% to 20% of activ...

Embodiment approach

[0082] A specific implementation, the accuracy of the labeling results can be evaluated and calculated according to the ROC receiver operating characteristic curve, the area under the ROC curve is called the AUC (Area Under Curve) value, which means randomly selecting a positive sample and a negative sample, The probability that the current classification algorithm ranks the positive sample score before the negative sample. The larger the AUC, the more accurate the classification result.

[0083] AUC is calculated based on the two values ​​of true positive rate TPR and false positive rate FPR, true positive rate TPR=TP / (TP+FN), false positive rate FPR=FP / (TN+FP);

[0084] Among them, TP: true example, FP: false positive example, TN: true negative example, FN: false negative example, as shown in the following table:

[0085]

[0086] TP true cases are the number of samples where the real situation is positive and the classification result is positive; FP false positives are ...

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 key opinion consumer mining method, device and equipment and a medium. The method comprises the steps: according to determined key opinion consumers KOC and non-KOC, a firstpreset number of target features in an activity field, a community field and a consumption field, determining feature values corresponding to the target features and a target sample space; taking thedetermined KOC and the determined non-KOC target features and feature values as a training set, and performing training to obtain a KOC classifier; obtaining unlabeled users, obtaining feature vectorsof the unlabeled users in the target sample space, and grouping the unlabeled users; using a current KOC classifier to classify and label a group which is not labeled in the group; judging whether the accuracy of the labeling result reaches a preset accuracy threshold value or not; if yes, determining the current KOC classifier as a final classifier, otherwise, supplementing the training set by using the annotation result, performing training to obtain an updated KOC classifier, and circularly performing training until the annotation result reaches an accuracy standard, so key opinion consumers can be efficiently and accurately mined.

Description

technical field [0001] The invention relates to the field of marketing, in particular to a key opinion consumer mining method, device, equipment and medium. Background technique [0002] Key Opinion Consumers (Key Opinion Consumers, KOCs) generally refer to consumers who can influence their friends, family members or fans to generate consumption behavior. [0003] High-value KOC can achieve high conversion of exposure and bring great benefits to the brand, so mining high-value KOC is very important for brand operation. However, when evaluating KOC in traditional operations, the identification of KOC mainly depends on the experience of operators, and the efficiency and accuracy of identification are difficult to guarantee. Contents of the invention [0004] In view of this, the main purpose of the present invention is to provide a method, device, equipment and medium for mining key opinion consumers, which can efficiently and accurately mine key opinion consumers. [0005...

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): G06Q30/02
CPCG06Q30/0201G06Q30/0202
Inventor 陈纪培
Owner 上海络昕信息科技有限公司
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