Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

4S store potential customer behavior analysis system based on Reid and face recognition technology

A face recognition and behavior analysis technology, applied in character and pattern recognition, image analysis, biometric identification, etc., can solve the problems of unable to remove repeated passenger flow counts, unable to obtain customer trajectories, unable to obtain customer characteristics, etc., to achieve high-quality personality Streamlined content push, removal of duplicate passenger flow, and better user experience

Inactive Publication Date: 2021-02-09
上海蜂雀网络科技有限公司
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is more efficient, and a single camera covers a wider area, but there are problems such as the inability to remove repeated passenger flow counts, the inability to obtain more customer characteristics except passenger flow, and the inability to obtain customer trajectories

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
  • 4S store potential customer behavior analysis system based on Reid and face recognition technology
  • 4S store potential customer behavior analysis system based on Reid and face recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Such as figure 1 , figure 2 As shown, a 4S store potential customer behavior analysis system based on Reid and face recognition technology includes the following steps:

[0025] Step (1). Decode from the surveillance video stream, extract picture frames at intervals, use the pedestrian detection deep neural network model, detect pedestrians in the picture frames, and intercept all human body pictures therein.

[0026] Step (2). Analyze each human body picture described in the previous step. Use the pedestrian recognition neural network model to extract the human body feature vector, compare the human body feature vector to be recognized with the current store in the redis database, and compare all the human body feature records of the day to calculate the cosine distance. If the minimum value of all distance values ​​is less than the distance threshold, it is considered that the pictures corresponding to the two human feature vectors are the same person, otherwise it...

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 a 4S store potential customer behavior analysis system based on a Reid and face recognition technology, and the system comprises the following steps: (1), decoding a video stream from video monitoring, and extracting a picture frame at regular time; (2), performing pedestrian detection on the picture frame to obtain a pedestrian human body picture; (3) calculating pedestrianpictures by using a Reid model, and extracting pedestrian feature vectors; (4) storing the data in the step (3) into a database, including picture shooting time and camera numbers; (5), screening human body trajectory data associated with a human face so as to know trajectory behavior data of a corresponding customer; for each subsequent picture frame, calculating a pedestrian feature vector, andjudging whether the pedestrian appears before or not; the passenger flow calculation reliability is higher, the data is more complete, and the repeated passenger flow can be effectively removed. Datais collected in a non-inductive mode, customer behaviors are not intervened, and the experience feeling is good.

Description

technical field [0001] The invention relates to the field of data structured processing, in particular to a 4S store potential customer behavior analysis system based on Reid and face recognition technology. Background technique [0002] For e-commerce, data is very important. They can obtain the user's source, time, hobbies, and even find the offline location of the user through the user's click, browse, purchase, etc., and find out by analyzing these data. The promotion channels and promotion content have been improved, so as to truly meet the needs of users and make accurate product recommendations to promote transactions. [0003] There are very few data sources for physical 4S stores. Except for transaction data such as CRM\ERP\POS, physical merchants often ignore the importance of customer flow, or realize that customer flow is the leader of all transactions, but they are not very good. way to solve this problem. The birth of customer flow statistics and customer flo...

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): G06K9/00G06T7/246G06F16/532G06F16/28
CPCG06F16/284G06T7/246G06F16/532G06T2207/30241G06V40/161G06V40/10G06V40/172G06V20/52
Inventor 焦源罗必流常谦杨小敏刘云辉王宾
Owner 上海蜂雀网络科技有限公司
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
Eureka Blog
Learn More
PatSnap group products