CN111401232B - Customer type judgment method, system, equipment and medium - Google Patents

Customer type judgment method, system, equipment and medium Download PDF

Info

Publication number
CN111401232B
CN111401232B CN202010177123.8A CN202010177123A CN111401232B CN 111401232 B CN111401232 B CN 111401232B CN 202010177123 A CN202010177123 A CN 202010177123A CN 111401232 B CN111401232 B CN 111401232B
Authority
CN
China
Prior art keywords
picture
snapshot
time
customer
threshold
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010177123.8A
Other languages
Chinese (zh)
Other versions
CN111401232A (en
Inventor
唐士锵
王欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen Ruiwei Information Technology Co ltd
Original Assignee
Xiamen Ruiwei Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiamen Ruiwei Information Technology Co ltd filed Critical Xiamen Ruiwei Information Technology Co ltd
Priority to CN202010177123.8A priority Critical patent/CN111401232B/en
Publication of CN111401232A publication Critical patent/CN111401232A/en
Application granted granted Critical
Publication of CN111401232B publication Critical patent/CN111401232B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method, a system, equipment and a medium for judging customer types, wherein the method comprises the following steps: receiving the uploaded face snapshot picture; replacing the face snapshot picture with other face snapshot pictures; comparing the snapshot picture with pictures in a face library, and pushing a comparison result; through the face recognition equipment who lays in store or the shop, through snapshot face and upload to the high in the clouds, thereby judge the customer type in corresponding people's face storehouse. After the customer enters the store, the type and the historical purchasing preference of the customer are pushed, so that the store clerk can carry out sales promotion by adopting different dialogues in a targeted manner.

Description

Customer type judgment method, system, equipment and medium
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, a system, a device, and a medium for determining a customer type.
Background
In the retail industry, most merchants have their own CRM systems, which include new customers, back customers, members of different grades, black lists, and the like. However, in order to know what status a customer is, it is necessary for the customer to present a membership card or other card registered in the store, and the store clerk can determine whether the customer is a member by reading information on the card.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method, a system, equipment and a medium for judging the type of a customer, and the retail industry can energize off-line retail stores by means of the latest face recognition technology, thereby improving the operation efficiency and the management level of the stores.
In a first aspect, the present invention provides a method comprising:
step 1, receiving an uploaded face snapshot picture;
step 2, replacing the face snapshot picture with other face snapshot pictures;
and 3, comparing the snapshot picture with pictures in the face library, and pushing a comparison result.
Further, the step 1 is further specifically: when a customer enters a store, a picture is taken at set time intervals from T0 time to T1 time of leaving, the picture quality score is calculated, and when the customer leaves at T1 time, a Qmax-shot picture P1 with the highest quality score Q in the whole capturing process is reported.
Further, the step 1 is further specifically: when the customer enters the store, the time T0 begins until the time T1 of departure,
if the time T1-T0 is smaller than the first threshold value time, capturing a picture at set time intervals and calculating the picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process when a customer leaves at the time T1;
if the time T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
and if the picture quality score of the snapshot picture P1 is larger than or equal to the quality threshold value and the snapshot picture P2 with the quality score larger than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2.
Further, the step 3 is further specifically: comparing the snap shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, comparing the snap shot pictures with the pictures in the VIP picture library respectively,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining that the customer is a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare with pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, the client is the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, the client is a new client; and pushing the comparison result.
In a second aspect, the present invention provides a system comprising:
the uploading module receives the uploaded face snapshot pictures;
the replacing module is used for replacing the face snapshot picture with other face snapshot pictures;
and the comparison module is used for comparing the snapshot picture with pictures in the face library and pushing a comparison result.
Further, the uploading module further specifically includes: when a customer enters a store, a picture is captured at set time intervals from T0 time to T1 time of leaving, picture quality scores are calculated, and when the customer leaves at T1 time, a Qmax captured picture P1 with the highest quality score Q in the whole capturing process is reported.
Further, the uploading module further specifically comprises: the customer enters the store, starting at time T0 until leaving time T1,
if the time T1-T0 is less than the first threshold time, capturing a picture at set intervals and calculating the picture quality score, and uploading the captured picture P1 with the highest quality score in the capturing process when the customer leaves at the time T1;
if the time T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
and if the picture quality score of the snapshot picture P1 is greater than or equal to the quality threshold value and the snapshot picture P2 with the quality score greater than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2.
Further, the alignment module further comprises: comparing the snap shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, comparing the snap shot pictures with the pictures in the VIP picture library respectively,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining the customer as a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare with pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, the client is the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, the client is a new client; and pushing the comparison result.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of the first aspect when executing the program.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of the first aspect.
One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:
the method, the system, the equipment and the medium provided by the embodiment of the application can judge the type of the customer by legally using the face recognition equipment arranged in the store or the shop and snapping the face and uploading the face to the cloud end and comparing the face with the corresponding face library. The customer can push the type and the historical purchasing preference of the customer after entering the store, so that the store clerk can carry out commodity sales by pertinently adopting different dialogues, and the customer can enjoy the member price and the member points without showing a member card during settlement.
The above description is only an overview of the technical solutions of the present invention, and the present invention can be implemented in accordance with the content of the description so as to make the technical means of the present invention more clearly understood, and the above and other objects, features, and advantages of the present invention will be more clearly understood.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a schematic structural diagram of a system according to a second embodiment of the present invention;
FIG. 2 is a schematic view of a snapshot in accordance with the present invention;
FIG. 3 is a schematic diagram of a secondary snapshot in accordance with the present invention;
FIG. 4 is a schematic diagram of a triple snapshot of the present invention;
FIG. 5 is a flow chart of a snapshot in accordance with the present invention;
FIG. 6 is a flow chart of the secondary snapshot of the present invention;
fig. 7 is a logic diagram of reporting cashier desk device data in three snapshots of the present invention.
Fig. 8 is a logic diagram of multiple matching reported by a cashier in a triple snapshot according to the present invention.
Detailed Description
The embodiment of the application provides a method, a system, equipment and a medium, aims to solve the technical problem of rapidly identifying the state of a store-entering customer, enables an off-line retail store by means of a face recognition technology, and improves the operation efficiency and the management level of the store.
The technical scheme in the embodiment of the application has the following general idea:
1.1 one snapshot
And after the snapshot strategy of the cloud configuration equipment is a snapshot and is successfully issued to the equipment, the equipment executes the snapshot strategy.
And one snapshot is that when the customer leaves at the time T1, the picture P1 with the highest snapshot quality Qmax is uploaded.
Snapshot data: entering time T0, leaving time T1, picture P1, photographing time T.P1 and reporting time T1
As shown in fig. 2, the snapshot logic: from the time T0 when a customer enters a store to the time T1 when the customer leaves, a photo is captured every 0.1s, the quality score of the photo is calculated and stored locally (the quality of the photo is calculated by weighting the angle of the face front/side, the face pixel and the ambiguity) and when the customer leaves at the time T1, the Qmax captured photo P1 with the highest quality score Q in the whole capturing process is reported.
1.2 double-shot
As shown in fig. 3, the apparatus: and when the equipment successfully logs in the cloud, the cloud returns a starting parameter.
If the quality threshold value Q is reached, the entering time exceeds 3 seconds and the best picture quality is more than or equal to Q, the snapshot is carried out, and the snapshot picture P1 is uploaded in the T.P1 time
If T.P1 is less than 3 seconds, namely, the pictures with quality more than or equal to Q exist in 3 seconds, uploading the snap shot pictures P1 in 3 seconds
Snapshot data: entering time T0, photo P1, photo time T.P1 and reporting time T.P1
When the T1 leaves the picture P2 with better quality Qmax, the picture P2 is submitted to be snapshot and updated
Snapshot data: entry time T0, exit time T1, photo P2, photo time T.P2, and reporting time T1
If the T1 leaves without the picture P2 with better quality, only the leaving data is reported
Snapshot data: entering time T0, leaving time T1 and reporting time T1
When T1 leaves, if the picture of the reported quality is not reached before, the picture with the highest quality in the period from T0 to T1 is uploaded
Snapshot data: entering time T0, leaving time T1, picture P2, picture time T.P2, reporting time T1
1.3 triple snapshot
As shown in fig. 4, the apparatus: at present, aiming at some equipment for snapshotting a cash register, in order to obtain more snapshotting, a face of a snapshotted person is matched with an order according to a certain strategy, and therefore the face of a customer of a purchase order is obtained. And after the equipment successfully logs in, returning the configuration by the cloud.
A quality threshold Q, and uploading an optimal picture P1 when entering 3 seconds
Snapshot data: entering time T0, photo P1, photo time T.P1 and reporting time 3S
If the first snapshot quality Q1 is smaller than Q, if a picture P2 with quality larger than or equal to Q exists after 3 seconds, snapshot updating is carried out at T.P 2. (if Q1 is equal to or greater than Q, there is no such step)
Snapshot data: entering time T0, photo P2, photo time T.P2 and reporting time T.P2
When T1 leaves, if a picture P3 with better quality Qmax exists, submitting P3 to snapshot update
Snapshot data: entry time T0, exit time T1, photo P3, photo time T.P3, and reporting time T1
If no better quality picture P3 exists, only the leaving data is reported
Snapshot data: entering time T0, leaving time T1 and reporting time T1
2 cloud policy
2.1 one snapshot
One-time snapshot is suitable for most scenes, and the requirement on bandwidth is not high under the common condition. The device performs a reporting.
As shown in fig. 5, the detailed steps of one snapshot are as follows:
after the cloud receives the face snapshot picture uploaded by the equipment end, whether the face snapshot picture is a positive face or not and whether the features can be extracted or not are judged.
The face is taken and the characteristic can be extracted to continuously judge whether the quality score of the picture is larger than 1.1 (the picture quality score is obtained by weighted calculation of the face front/side angle, the face pixel and the ambiguity) which are captured. The candid shots with the scores larger than 1.1 are directly subjected to duplicate removal, and the candid shots with the scores smaller than 1.1 need to be judged whether to be subjected to duplicate removal or not according to cloud configuration.
The snapshot of the side face and the extractable features is set by the cloud to judge whether to perform de-duplication.
Other snapshot types are directly judged as head and shoulder without counting as passenger flow.
The duplication removing is divided into two parts, wherein the first part is to duplicate the equipment for capturing the current face within a certain time so as to prevent the tracking number of the equipment from being changed into two or even more numbers in the process of tracking the current customer and capturing, and the customer is captured as two or even more people to upload two or more pictures. The second part is to carry out the duplicate removal for the face snapshot of this shop certain time to avoid present customer to make a round trip to get in and out the shop in the short time and cause the influence to the passenger flow statistics.
After the duplication is removed, the current snapshot is compared with the pictures of the VIP of the store and the face library of the store clerk (the VIP and the store clerk are one face library and have different labels), and if the picture with the highest comparison similarity in the VIP and the store clerk library exceeds a threshold value, the current snapshot is directly judged to be the VIP/store clerk in comparison. If the picture with the highest similarity does not exceed the threshold, the picture is continuously compared with the pictures in the return client library (the return client library is dynamically refreshed once a day according to the set time), and similarly, if the picture with the highest similarity exceeds the threshold, the picture is directly judged as the return client on comparison, otherwise, the picture is judged as a new client.
And after judging the type of the customer, marking a label on the current snapshot customer, pushing the label to the customer, and simultaneously carrying out corresponding customer flow statistics.
2.2 double-shot
As shown in fig. 6, the secondary snapshot is more bandwidth demanding, but pushing the VIP customer to the store is more timely.
The detailed steps of the secondary snapshot are as follows:
the equipment side reports the snapshot and judges whether the snapshot is the first snapshot (considering that the problems such as network delay and the like can cause that the second snapshot is reported to the cloud earlier than the first snapshot), and if the first snapshot is carried out and the second snapshot is reported, the first snapshot does not need to be processed. If the customer is the VIP, the process of capturing the VIP is carried out for the first time and the second time, whether the customer is the VIP is judged, if yes, the VIP customer is directly pushed to visit, a salesperson can conveniently receive the VIP (the whole process is within 2 s), and if not, the process is directly finished. The first snapshot is required to be timely, and the reported picture quality at the equipment end is usually not high enough, so that comparison errors occasionally occur. Under the scene that a salesclerk receives customers, the selection is more biased to the timeliness, and the comparison error with a certain probability can be accepted.
If the snapshot is taken for the second time, whether a snapshot picture exists needs to be judged. If the snapshot picture exists, the process of snapshot is directly carried out once, and the result of the first snapshot is updated. If no higher-quality snapshot is available after the first snapshot, the information of the second snapshot is only reported when the customer leaves the picture, and the picture is not reported. In this case, it is necessary to continuously determine whether the first snapshot has been reported.
If the first snapshot is not reported, the information of the second snapshot is cached, and the data of the first snapshot is processed after the first snapshot is reported. If the first snapshot is reported, the first snapshot picture is taken. And then directly executing the snapshot process once and ending.
2.3 triple snapshot
As shown in fig. 7 and 8, the triple snapshot is suitable for scenes such as cash registers and the like requiring a plurality of photos for comparison.
The detailed steps of the three-time snapshot are as follows:
the third snapshot is similar to the second snapshot in processing logic, and comparison is performed according to the pictures reported each time, so that the types of the customers are updated. The method comprises the steps of three-time snapshot except the exterior, the key point is that the cloud end can store 3 pictures of the same customer at different time points, in an order matching strategy of a cashier desk, faces can be matched and snapshot according to a certain time before and after the order purchasing time, suspected order purchasing personnel of cashier desk node equipment in the time are obtained, after the selection, a selection frame is popped up through a desktop application program, and the order purchasing personnel of corresponding orders are selected by a salesman, so that important data basis is provided for further analysis of order purchasing customer groups of subsequent merchants.
Example one
The present embodiment provides a method, including:
step 1, receiving an uploaded face snapshot picture;
the customer enters the store, starting at time T0 until leaving time T1,
if the time T1-T0 is less than the first threshold time, capturing a picture at set intervals and calculating the picture quality score, and uploading the captured picture P1 with the highest quality score in the capturing process when the customer leaves at the time T1;
if the time T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
and if the picture quality score of the snapshot picture P1 is greater than or equal to the quality threshold value and the snapshot picture P2 with the quality score greater than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2.
Step 2, replacing the face snapshot picture with other face snapshot pictures;
step 3, comparing the snap shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, comparing the snap shot pictures with the pictures in the VIP picture library respectively,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining the customer as a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare with pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, the client is the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, the client is a new client; and pushing the comparison result.
Based on the same inventive concept, the application also provides a system corresponding to the method in the first embodiment, which is detailed in the second embodiment.
Example two
In the present embodiment, there is provided a system, as shown in fig. 1, including:
an uploading module, wherein the customer enters the store, the time T0 is started until the leaving time T1,
if the time T1-T0 is less than the first threshold time, capturing a picture at set intervals and calculating the picture quality score, and uploading the captured picture P1 with the highest quality score in the capturing process when the customer leaves at the time T1;
if the time T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
if the picture quality score of the snapshot picture P1 is larger than or equal to the quality threshold value and the snapshot picture P2 with the quality score larger than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2;
the replacing module is used for replacing the face snapshot picture with other face snapshot pictures;
a comparison module for comparing the snap shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, the snap shot pictures are respectively compared with the pictures in the VIP picture library,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining the customer as a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare with pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, the client is the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, the client is a new client; and pushing the comparison result.
Since the system described in the second embodiment of the present invention is a system used for implementing the method in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the system based on the method described in the first embodiment of the present invention, and thus the details are not described herein again. All systems adopted by the method of the first embodiment of the present invention belong to the protection scope of the present invention.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, which is detailed in the third embodiment.
EXAMPLE III
The embodiment provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, any one of the embodiments may be implemented.
Since the electronic device described in this embodiment is a device used for implementing the method in the first embodiment of the present application, based on the method described in the first embodiment of the present application, a person skilled in the art can understand a specific implementation manner of the electronic device in this embodiment and various variations thereof, and therefore, a detailed description of how the electronic device implements the method in the first embodiment of the present application is not given here. The equipment used by those skilled in the art to implement the methods in the embodiments of the present application is within the scope of the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the fourth embodiment, which is described in detail in the fourth embodiment.
Example four
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any one of the first embodiment can be implemented.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages: the methods, systems, devices, and media provided by embodiments of the present application,
as will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.

Claims (6)

1. A customer type determination method, characterized by: the method comprises the following steps:
step 1, receiving an uploaded face snapshot picture;
step 2, replacing the face snapshot picture with other face snapshot pictures;
step 3, comparing the snapshot picture with pictures in a face library, and pushing a comparison result;
wherein, the step 1 further comprises: the customer enters the store, starting at time T0 until leaving time T1,
if the time T1-T0 is less than the first threshold time, capturing a picture at set intervals and calculating the picture quality score, and uploading the captured picture P1 with the highest quality score in the capturing process when the customer leaves at the time T1;
if the T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
if the picture quality score of the snapshot picture P1 is larger than or equal to the quality threshold value and the snapshot picture P2 with the quality score larger than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2;
wherein, the step 3 further comprises: comparing the snap shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, comparing the snap shot pictures with the pictures in the VIP picture library respectively,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining the customer as a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare with pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, the client is the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, the client is a new client; and pushing the comparison result.
2. The customer type determination method according to claim 1, wherein: the step 1 is further specifically as follows: when a customer enters a store, a picture is captured at set time intervals from T0 time to T1 time of leaving, picture quality scores are calculated, and when the customer leaves at T1 time, a Qmax captured picture P1 with the highest quality score Q in the whole capturing process is reported.
3. A customer type determination system characterized by: the method comprises the following steps:
the uploading module receives the uploaded face snapshot picture;
the replacing module is used for replacing the face snapshot picture with other face snapshot pictures;
the comparison module is used for comparing the snapshot picture with pictures in the face library and pushing a comparison result;
wherein, the uploading module further comprises: the customer enters the store, starting at time T0 until leaving time T1,
if the time T1-T0 is less than the first threshold time, capturing a picture at set intervals and calculating the picture quality score, and uploading the captured picture P1 with the highest quality score in the capturing process when the customer leaves at the time T1;
if the time T1-T0 is larger than or equal to a first threshold time, capturing a picture at intervals of a set time within the first threshold time, calculating a picture quality score, and uploading a captured picture P1 with the highest quality score in the capturing process at the first threshold time;
if the picture quality score of the snapshot picture P1 is smaller than the quality threshold, after the first threshold time, the picture quality score of the obtained snapshot picture P2 is larger than or equal to the quality threshold, and the snapshot picture P2 is uploaded; when the customer leaves at the time T1, if a snapshot picture P3 with the quality score larger than the picture quality score of the snapshot picture P2 exists, uploading the snapshot picture P3;
if the picture quality score of the snapshot picture P1 is larger than or equal to the quality threshold value and the snapshot picture P2 with the quality score larger than the picture quality score of the snapshot picture P1 exists when the customer leaves at the time T1, uploading the snapshot picture P2;
wherein, the comparison module further comprises: comparing the snap-shot pictures with pictures in a face library, wherein the face library comprises a VIP picture library, a store clerk picture library and a return guest picture library, comparing the snap-shot pictures with the pictures in the VIP picture library respectively,
if the obtained picture with the highest similarity exceeds a first comparison threshold, the customer is a VIP customer;
if the obtained picture with the highest similarity does not exceed the first comparison threshold, comparing the snapshot picture with a store clerk picture library, and if the obtained picture with the highest similarity exceeds the second comparison threshold, determining the customer as a store clerk;
if the obtained picture with the highest similarity does not exceed the second comparison threshold, continuing to compare the picture with the pictures in the return client picture library, if the obtained picture with the highest similarity exceeds a third comparison threshold, determining the client as the return client, and if the obtained picture with the highest similarity does not exceed the third comparison threshold, determining the client as a new client; and pushing the comparison result.
4. A customer type judging system according to claim 3, wherein: the uploading module further comprises: when a customer enters a store, a picture is captured at set time intervals from T0 time to T1 time of leaving, picture quality scores are calculated, and when the customer leaves at T1 time, a Qmax captured picture P1 with the highest quality score Q in the whole capturing process is reported.
5. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 2 when executing the program.
6. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 2.
CN202010177123.8A 2020-03-13 2020-03-13 Customer type judgment method, system, equipment and medium Active CN111401232B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010177123.8A CN111401232B (en) 2020-03-13 2020-03-13 Customer type judgment method, system, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010177123.8A CN111401232B (en) 2020-03-13 2020-03-13 Customer type judgment method, system, equipment and medium

Publications (2)

Publication Number Publication Date
CN111401232A CN111401232A (en) 2020-07-10
CN111401232B true CN111401232B (en) 2023-04-07

Family

ID=71434774

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010177123.8A Active CN111401232B (en) 2020-03-13 2020-03-13 Customer type judgment method, system, equipment and medium

Country Status (1)

Country Link
CN (1) CN111401232B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004213121A (en) * 2002-12-27 2004-07-29 Casio Comput Co Ltd Picture processing system and program
CN107463608A (en) * 2017-06-20 2017-12-12 上海汇尔通信息技术有限公司 A kind of information-pushing method and system based on recognition of face
CN108960038A (en) * 2018-05-04 2018-12-07 广州图匠数据科技有限公司 A kind of shopping cart and its recognition methods based on image recognition technology
CN110175589A (en) * 2019-05-31 2019-08-27 陕西蜂狐智能家居科技有限公司 A kind of household retail business information sharing platform based on face alignment video camera

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004213121A (en) * 2002-12-27 2004-07-29 Casio Comput Co Ltd Picture processing system and program
CN107463608A (en) * 2017-06-20 2017-12-12 上海汇尔通信息技术有限公司 A kind of information-pushing method and system based on recognition of face
CN108960038A (en) * 2018-05-04 2018-12-07 广州图匠数据科技有限公司 A kind of shopping cart and its recognition methods based on image recognition technology
CN110175589A (en) * 2019-05-31 2019-08-27 陕西蜂狐智能家居科技有限公司 A kind of household retail business information sharing platform based on face alignment video camera

Also Published As

Publication number Publication date
CN111401232A (en) 2020-07-10

Similar Documents

Publication Publication Date Title
US8774462B2 (en) System and method for associating an order with an object in a multiple lane environment
US20100042657A1 (en) Method and system for saving database storage space
US9892437B2 (en) Digitization of a catalog of retail products
WO2019096222A1 (en) Unmanned vending method and device based on identity identification and product identification
CN112464697A (en) Vision and gravity sensing based commodity and customer matching method and device
CN106875595B (en) Method and device for determining using place of POS terminal
CN110998592A (en) Non-canonical scanning for retail systems
CN111784462A (en) Transaction processing method, client, processing terminal and system based on block chain
CN111612657A (en) Client type identification method and device, electronic equipment and storage medium
KR101771524B1 (en) Method for extracting price information from a receipt and method for providing price information
US20170330206A1 (en) Motion line processing system and motion line processing method
CN111401232B (en) Customer type judgment method, system, equipment and medium
CN112966504B (en) Name identification and association recommendation method and device, computer equipment and storage medium
JP2018142293A (en) Commodity discrimination device, commodity discrimination program, and commodity discrimination method
CN113688650A (en) Method and device for identifying picture
US20230385456A1 (en) Automatic segmentation using hierarchical timeseries analysis
CN115795408B (en) Intelligent community commodity big data intelligent bill spelling and settlement method based on blockchain
CN110796464A (en) Monitoring data anti-cheating method and verification method, device, storage medium and terminal
CN110390332B (en) Class determination method, device and equipment
CN117455579B (en) Commodity recommendation intervention method, commodity recommendation intervention device, medium and equipment
CN111652636B (en) Customer purchase intention analysis method, device, terminal equipment and medium
CN115796862A (en) Resource transfer method, device and equipment based on human face features and storage medium
JP7342943B2 (en) Sales management systems, store equipment, sales management methods, and programs
CN116629756A (en) Commodity warehouse-in method, device, equipment and storage medium
CN114819835A (en) Automatic management method, device, equipment and medium for commodity information base

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant