Passenger flow statistics goods shelf regularization method based on face identity recognition

An identity recognition and shelf technology, applied in the field of passenger flow statistics, can solve problems such as association, and achieve the effect of reducing walking, improving purchasing desire, and improving practicability.

Inactive Publication Date: 2019-06-07
CHENGDU REMARK TECH CO LTD +1
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, most of the passenger flow statistics systems in shopping malls and supermarkets are based on camera face statistics or Wi-Fi probes. These two statistical methods have some shortcomings: the former only detects faces, or counts the individuality of faces in videos. count, rather than actually identify the face
This leads to counting every time a customer appears in front of the camera, which will cause a lot of double counting; the latter cannot intuitively associate the customer's specific browsing behavior with the customer itself, providing support for further in-store personalized marketing

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
  • Passenger flow statistics goods shelf regularization method based on face identity recognition
  • Passenger flow statistics goods shelf regularization method based on face identity recognition
  • Passenger flow statistics goods shelf regularization method based on face identity recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] A method for organizing shelves based on passenger flow statistics based on face recognition, collecting Facial ID, Location ID and Timestamp of customers based on face recognition, mainly includes the following steps:

[0028] Step S100: Create a hash value for moving line counting, the key of the hash table includes the Location ID of the start position and the end position; the value of the hash table is an integer, used to represent the start position and the end position The number of customers who have passed between locations, the initial value of the integer is 0;

[0029] Step S200: Put all the different Facial IDs into the set f={f1,f2,...fn}, for each Facial ID, summarize the Location IDs that have appeared in it, and perform forward sorting according to Timestamp, so as to obtain customers The moving line [L1, L2, ... Ln].

[0030] The invention accurately obtains the moving lines of customers in the shopping mall through the establishment of the hash value...

Embodiment 2

[0032] This embodiment is optimized on the basis of Embodiment 1, and also includes step S300: calculate the customer movement lines between locations within a time period, and aggregate according to the location pairs to obtain a directed graph, in which each edge in the graph is The weight is the number of times customers go from one location to another, and the order of the shelves is adjusted according to the weight of the moving lines between different shelves.

[0033] The invention accurately obtains the moving lines of customers in the shopping mall through the establishment of the hash value, thereby providing data support for shelf display optimization, improving operation efficiency, and having better practicability. The invention adjusts the sorting of the shelves through the sorting of the weight of each customer moving line, effectively reduces the walking of customers, enables customers to find the items they are interested in in time, thereby improving the shopp...

Embodiment 3

[0036] This embodiment is optimized on the basis of Embodiment 1 or 2, and the passenger flow aggregation degree between locations within a statistical time period is counted, aggregated according to Location ID, and the total number of Facial IDs at the location is calculated; thus, the shopping mall can be obtained according to the shelf location The heat map in the store can get the most popular shelf sorting, so as to recommend personalized products to customers.

[0037] The present invention can improve the purchase desire of customers by recommending personalized product information that they are interested in for a certain customer or a certain type of customers, and has better practicability.

[0038] Other parts of this embodiment are the same as those of Embodiment 1 or 2 above, so details are not repeated here.

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 passenger flow statistics goods shelf regularization method based on face identity recognition. The method comprises the following steps: acquiring a Face ID, a Logistic ID and a Timegamp of a customer based on face recognition; S200, preparing a blank; all different Facinal IDs are put into a set f = {f1, f2,and the like, fn}; The method comprises the following steps of:for each Face ID, summarizing the appeared Location IDs of each Face ID, and carrying out forward sorting according to Timegamp so as to obtain the moving lines (L1, L2, and the like Ln) of a customer in each Face ID; According to the method, the dynamic line of the customer in the shopping mall is accurately obtained through creation of the hash value, so that data support is provided for shelfdisplay optimization, the operation efficiency is improved, and the method has relatively good practicability.

Description

technical field [0001] The invention belongs to the technical field of passenger flow statistics, and in particular relates to a racking method for passenger flow statistics based on face recognition. Background technique [0002] At present, most of the passenger flow statistics systems in shopping malls and supermarkets are based on camera face statistics or Wi-Fi probes. These two statistical methods have some shortcomings: the former only detects faces, or counts the individuality of faces in videos. count, rather than actually identify the face. This leads to counting every time a customer appears in front of the camera, which will cause a lot of double counting; the latter cannot intuitively associate the customer's specific browsing behavior with the customer himself, providing support for further in-store personalized marketing. The supermarket passenger flow analysis system based on face recognition that we designed can just overcome the above deficiencies, thus. ...

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): G06Q30/06
Inventor 毛帆曾敏
Owner CHENGDU REMARK TECH CO LTD
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