CN111476609A - Retail data acquisition method, system, device and storage medium - Google Patents
Retail data acquisition method, system, device and storage medium Download PDFInfo
- Publication number
- CN111476609A CN111476609A CN202010277158.9A CN202010277158A CN111476609A CN 111476609 A CN111476609 A CN 111476609A CN 202010277158 A CN202010277158 A CN 202010277158A CN 111476609 A CN111476609 A CN 111476609A
- Authority
- CN
- China
- Prior art keywords
- information
- commodity
- image
- user
- human body
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000006399 behavior Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 claims 1
- 239000013598 vector Substances 0.000 description 20
- 238000001514 detection method Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000012447 hatching Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/0203—Market surveys; Market polls
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data acquisition, in particular to a retail data acquisition method, a retail data acquisition system, retail data acquisition equipment and a storage medium. The retail data acquisition method of the invention comprises the following steps: acquiring a commodity image and a user image; extracting user characteristic information according to the user image, wherein the user characteristic information comprises: face image information and human body posture information; judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image; when a commodity purchasing behavior exists, commodity information is obtained according to the commodity image, and the user characteristic information and the commodity information are generated into retail data.
Description
Technical Field
The invention relates to the technical field of data acquisition, in particular to a retail data acquisition method, a retail data acquisition system, retail data acquisition equipment and a storage medium.
Background
By collecting and analyzing retail data of zero commodities, the commodity sales trend can be known, and further, the sales strategy and the production plan can be made in a targeted manner, so that the acquisition of the retail data is very important for commodity retail enterprises and commodity manufacturing enterprises.
The traditional way of acquiring retail data is: retail data acquisition is carried out from market personnel to commodity retail sites, the commodity retail sites are generally very dispersed and numerous, if comprehensive commodity retail data are required to be acquired, the market personnel need to be held and dispatched in all the retail sites, however, the manpower, material resources and financial resources brought by the retail data acquisition are high in consumption, only a small part of data information is generally acquired and analyzed, and therefore accuracy and reliability are poor.
Another way to obtain retail data is: the retail point of sale is provided with a point of sale (POS) machine, the retail point of sale is required to complete the retail of the goods through the POS machine, and finally, the retail data of the goods is obtained through the retail records of the goods in each POS machine. Compared with traditional manual acquisition, the POS machine can acquire comprehensive data, solves the problem of retail information management blind spots, and is widely applied at present.
Because the POS machine can acquire the purchased commodity information only by actively swiping a card or scanning a payment code by a buyer, the problems of missing report and concealing report are likely to exist, the accuracy and the reliability of the information are still not good enough, and with the development of intellectualization, an unmanned supermarket becomes a trend, and the method for acquiring the information by the POS machine obviously cannot meet the requirements of the unmanned supermarket.
Disclosure of Invention
Therefore, the invention provides a retail data acquisition method, a retail data acquisition system, a retail data acquisition device and a storage medium, which aim to solve the problems of poor accuracy and reliability of a retail data acquisition mode in the prior art.
According to a first aspect, an embodiment of the present invention provides a retail data acquisition method, including: acquiring a commodity image and a user image; extracting user characteristic information according to the user image, wherein the user characteristic information comprises: face image information and human body posture information; judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image; and when a commodity purchasing behavior exists, acquiring commodity information according to the commodity image, and generating retail data by using the user characteristic information and the commodity information.
With reference to the first aspect, in a first implementation manner of the first aspect, the user feature information further includes: and obtaining identity information according to the face image information.
With reference to the first aspect, in a first implementation manner of the first aspect, extracting human body posture information from the user image includes: and recognizing the human body posture information in the user image through a preset human body posture recognition model.
With reference to the first aspect, in a third implementation manner of the first aspect, the human body posture recognition model is constructed by the following processes: acquiring a user image sample in a set area, wherein the user image sample is marked with human body key point information; and training a preset neural network model according to the user image sample and the human body key points to generate the human body posture recognition model.
With reference to the first aspect, in a fourth embodiment of the first aspect, the method further includes: and associating the face image information with the corresponding human body posture information.
With reference to the first aspect, in a fifth implementation manner of the first aspect, associating the face image information with the corresponding body posture information includes: calculating the distance from each face image information to the space position of the human body key point; and associating the human face image information with the spatial position distance smaller than the threshold distance and the human body posture information corresponding to the human body key points as the same user.
With reference to the first aspect, in a fourth implementation manner of the first aspect, the determining whether a commodity purchasing behavior exists according to the human body posture information and the commodity image includes: judging whether the left-hand key points and/or the right-hand key points in the human body key points are overlapped with the commodity image; when the commodity images are overlapped, judging whether the commodity images leave the set area; and when the commodity image leaves the set area, judging that purchasing behavior exists.
According to a second aspect, embodiments of the present invention provide a retail data acquisition system, comprising: the image acquisition module is used for acquiring a commodity image and a user image; a user feature extraction module, configured to extract user feature information according to the user image, where the user feature information includes: face image information and human body posture information; the information processing module is used for judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image; and the information generation module is used for acquiring commodity information according to the commodity image and generating retail data by the user characteristic information and the commodity information when a commodity purchasing behavior exists.
According to a third aspect, an embodiment of the present invention provides a retail data acquisition device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing therein computer instructions, and the processor executing the computer instructions to perform the retail sales data acquisition method according to the first aspect or any one of the embodiments of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the retail sales data acquisition method described in the first aspect or any one of the implementation manners of the first aspect.
The technical scheme of the invention has the following advantages:
the retail data acquisition method, the system, the device and the storage medium acquire the commodity image and the user image; extracting user characteristic information according to the user image, wherein the user characteristic information comprises: face image information and human body posture information; judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image; and when a commodity purchasing behavior exists, acquiring commodity information according to the commodity image, and generating retail data by using the user characteristic information and the commodity information. Compared with the existing retail data acquisition method, the retail data acquisition method provided by the embodiment of the invention has the advantages that the retail data acquisition is automatically performed, no interaction or cooperation with users exists, the acquired data is more comprehensive, accurate and reliable, the retail data acquisition method can be applied to an unmanned supermarket, the traditional method for acquiring retail data by adopting POS can be replaced, and the applicability is good.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is one of the flow charts of a retail data acquisition method of an embodiment of the present invention;
FIG. 2 is a second flowchart of a retail data acquisition method according to an embodiment of the invention;
FIG. 3 is a schematic diagram of human key points according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a scenario of a retail data acquisition method according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a retail data acquisition system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, a retail data acquisition method according to an embodiment of the present invention includes:
s11, acquiring a commodity image and a user image; the merchandise image may be in a front view or in another orientation.
S12, extracting user characteristic information according to the user image, wherein the user characteristic information comprises: face image information and human body posture information;
in step S12, extracting body posture information from the user image includes:
and constructing a human body posture recognition model, and recognizing the human body posture information in the user image through a preset human body posture recognition model. As shown in fig. 2, constructing the human body posture recognition model includes the following processes:
s31, collecting a user image sample in a set area, and acquiring a depth image according to the user image sample, wherein the depth image can be a depth image in an RGBD format.
S32, acquiring a corresponding feature map group according to the depth image, wherein in the embodiment, feature extraction is performed on the depth image through a Residual Network (ResNet) to acquire the feature map group;
s33, acquiring the positions of the key points of the human bodies and limb vectors for connecting the key points of the human bodies according to the feature map group;
specifically, the obtaining of the positions of the key points of the human body according to the feature map group includes: and detecting the feature map group according to a bottom-up sequence through a partial Detection Confidence Map (CMP) network and a Partial Affinity Field (PAF) network, and extracting the positions of all human key points and limb vectors for connecting the human key points.
And S34, training a preset neural network model according to the key points of the human body and the limb vectors to generate the human body posture recognition model. Specifically, all human body key points in the depth image and limb vectors used for connecting the human body key points are detected, then the correlation between the human body key points and the limb vectors is calculated, and the related human body key points and the limb vectors are matched to obtain a human body key point connection map of each user.
As shown in fig. 3, when all the human body key points in the depth image are detected, the top-down view angle is used to acquire the depth image, and a head key point 41, a left shoulder key point 42, a right shoulder key point 43, a left elbow key point 44, a right elbow key point 45, a left hand key point 46 and a right hand key point 47 are detected; at present, commonly used human body key point detection algorithms in the prior art include OpenPose, DensePose, and AlphaPose, but these detection algorithms are performed by performing 21 human body key point detections based on a planar image, the required calculation amount is large, real-time calculation cannot be guaranteed in a mobile terminal or an embedded device with limited calculation capability, and further detection delay may be large, or even detection failure may be caused.
The human body posture recognition model only needs to detect 7 human body key points, so that the required calculated amount can be reduced on the basis of keeping the detection accuracy, and the real-time performance of the human body key points and the limb vectors connected with the human body key points is improved.
It should be noted that, in the process of training the neural network model, because the traditional planar image data enhancement method cannot be applied to the depth image, the angle and the distance of the acquisition point in the image relative to the camera can be changed according to the imaging principle of the depth camera, and the image data of the original depth image after being transformed through different angles and distances is obtained.
As another embodiment, associating the face image information with the corresponding body posture information includes:
calculating the distance from each face image information to the space position of the human body key point;
and associating the human face image information with the spatial position distance smaller than the threshold distance and the human body posture information corresponding to the human body key points as the same user. It should be noted that, when a plurality of image capturing devices are used, images captured by the plurality of image capturing devices may be converted into the same spatial coordinate system. The size of the threshold distance in the embodiment of the invention can be determined according to the calculation error in the coordinate conversion process, the face image information of the same user and the real distance of the head key point, and the size of the threshold distance is not limited in the embodiment of the invention.
As another embodiment, the user feature information further includes: the identity information is obtained according to the face image information, and the identity information of the first user can be obtained according to a face recognition technology, wherein the face recognition technology is a biological recognition technology for carrying out identity recognition based on face feature information of people. The process of face recognition generally includes: .
a. Acquiring a source image for face recognition; the source image of the face recognition in the embodiment of the invention is the face image information of each user in the set area.
Optionally, after the source image of the face recognition is obtained, it may be determined whether the source image meets the definition requirement of the face recognition, if yes, the subsequent steps are executed, and if not, the source image collected this time is discarded.
b. And detecting position boxes of all human faces in the source image (the position boxes are the boxes for identifying specific targets).
c. And extracting the features of the face in each position frame to obtain a face feature vector.
d. Matching the face feature vector with a face feature vector in a face feature database; if the extracted face feature vector is matched with the face feature vector in the face feature database, determining that the identity information of the corresponding user is the user identity information corresponding to the face feature vector in the face feature database, if the extracted face feature vector is not matched with the face feature vector in the face feature database, adding the unique identity information as the identity information of the user extracting the face of the face feature vector, and adding the identity information and the face feature vector of the user in the face feature database.
As a convertible implementation, acquiring identity information according to the face image information comprises: the method comprises the steps of firstly acquiring face image information of all users in a set area, acquiring identity information of each user according to the face image information, determining the identity information of the first user from the identity information of all users in a user information acquisition area when the first user is determined to purchase a first commodity, or acquiring the face image information of all users in the set area for the first user, and acquiring the identity information of the first user according to the face image information of the first user after the first user is determined to purchase the first commodity. By acquiring the identity information, the acquired information is more comprehensive, the commodity sales quantity can be acquired, and meanwhile, information such as the age and the sex of the user purchasing the commodities can be acquired for analysis.
After the user feature information is extracted from the user image through the above step S12 to obtain face image information and body posture information, step S13 is performed.
Step S13 includes determining whether there is a commodity purchasing behavior according to the face image information, the body posture information, and the commodity image, and specifically includes:
judging whether the left-hand key points and/or the right-hand key points in the human body key points are overlapped with the commodity image;
when the commodity images are overlapped, judging whether the commodity images leave the set area;
s14, when a commodity purchasing behavior exists, acquiring commodity information according to the commodity image, and generating retail data by the user characteristic information and the commodity information; when there is no purchase, step S11 is executed to implement a loop.
The commodity identification technology can be used when the commodity information is obtained according to the commodity image, and comprises the following steps:
1. acquiring a source image of commodity identification;
the source image of the commodity identification in the embodiment of the invention is a commodity image of each commodity.
Optionally, after the source image of the commodity recognition is obtained, whether the source image meets the definition requirement of the commodity recognition can be judged, if yes, the subsequent steps are executed, and if not, the source image collected this time is discarded.
2. Detecting position frames of all commodities in a source image;
3. extracting the characteristics of the commodities in each position frame to obtain commodity characteristic vectors;
4. matching the commodity characteristic vector with the commodity characteristic vector in the commodity characteristic database to obtain corresponding commodity information;
illustratively, the commodity information may include information on the brand, model, retail price, etc. of the commodity. For example: the commodity information of a certain commodity may be: the name of the product is: xx cigarettes, model: xy111020, retail price: 99 yuan.
As a switchable embodiment, the acquiring of the commodity information from the commodity image includes: the method comprises the steps of firstly collecting commodity images of all commodities in the set area, obtaining commodity information of each commodity according to the commodity images, and determining the commodity information of a first commodity from the commodity information of all commodities in the commodity identification when a first user is determined to purchase the first commodity, wherein the method can also comprise the following steps: the method comprises the steps of firstly, obtaining commodity images of all commodities in a commodity identification area, and then obtaining commodity information of a first commodity according to the commodity images of the first commodity after a first user is confirmed to purchase the first commodity.
In summary, in the embodiment of the present invention, the time sequence for acquiring the identity information according to the face image information and the commodity information according to the commodity image is not limited, as long as the identity information of the first user and the commodity information of the first commodity are acquired before the retail data is generated.
The retail data acquisition method provided by the embodiment of the invention automatically performs real-time acquisition and real-time processing, namely the acquired data is structured data, secondary identification processing work is not needed to be performed at the cloud, no interaction and cooperation exists between the retail data acquisition method and a user, the acquired data is more efficient, comprehensive, accurate and reliable, and the retail data acquisition method can be applied to an unmanned supermarket, can also replace the traditional method for acquiring retail data by adopting POS, and has good applicability.
Example two
An embodiment of the present invention provides a retail data acquiring system, as shown in fig. 5, including:
an image acquisition module 51, configured to acquire a commodity image and a user image;
a user feature extraction module 52, configured to extract user feature information according to the user image, where the user feature information includes: face image information and human body posture information;
the information processing module 53 is configured to determine whether a commodity purchasing behavior exists according to the face image information, the human body posture information, and the commodity image;
and the information generating module 54 is configured to, when a commodity purchasing behavior exists, obtain commodity information according to the commodity image, and generate retail data from the user characteristic information and the commodity information.
EXAMPLE III
The embodiment of the invention provides retail data acquisition equipment, which comprises: the retail sales data acquisition system comprises a memory and a processor, wherein the memory and the processor are mutually connected in a communication mode, computer instructions are stored in the memory, and the processor executes the computer instructions to execute the retail sales data acquisition method in one embodiment or any one embodiment of the embodiment.
As shown in fig. 4, the system further includes a first image acquisition device 21 and a second image acquisition device 22, the first image acquisition device 21 is obliquely arranged so as to acquire face image information, the second image acquisition device 22 is vertically arranged downwards and is used for acquiring human body posture information and commodity images, and optionally, the second image acquisition device 22 may be an RGBD (red green blue depth) camera.
In an embodiment of the present invention, the setting region includes: a user information acquisition area 201 for acquiring user face image information and user body posture, and a commodity information acquisition area 202 for acquiring commodity information, two different areas are schematically illustrated by the hatching in fig. 4.
Example four
The embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to enable a computer to execute a retail sales data acquisition method as described in one or any one of the first embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a flash Memory (FlashMemory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A retail data acquisition method, comprising:
acquiring a commodity image and a user image;
extracting user characteristic information according to the user image, wherein the user characteristic information comprises: face image information and human body posture information;
judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image;
and when a commodity purchasing behavior exists, acquiring commodity information according to the commodity image, and generating retail data by using the user characteristic information and the commodity information.
2. The retail data acquisition method of claim 1, wherein the user characteristic information further comprises: and obtaining identity information according to the face image information.
3. The retail data acquisition method of claim 1, wherein extracting human pose information from the user image comprises:
and recognizing the human body posture information in the user image through a preset human body posture recognition model.
4. The retail data acquisition method according to claim 3, wherein the human pose recognition model is constructed by:
acquiring a user image sample in a set area, wherein the user image sample is marked with human body key point information;
and training a preset neural network model according to the user image sample and the human body key points to generate the human body posture recognition model.
5. The retail data acquisition method of claim 4, further comprising:
and associating the face image information with the corresponding human body posture information.
6. The retail data acquisition method of claim 5, wherein associating the facial image information with the corresponding body pose information comprises:
calculating the distance from each face image information to the space position of the human body key point;
and associating the human face image information with the spatial position distance smaller than the threshold distance and the human body posture information corresponding to the human body key points as the same user.
7. The retail data acquisition method according to claim 4, wherein determining whether a commodity purchasing behavior exists according to the human body posture information and the commodity image comprises:
judging whether the left-hand key points and/or the right-hand key points in the human body key points are overlapped with the commodity image;
when the commodity images are overlapped, judging whether the commodity images leave the set area;
and when the commodity image leaves the set area, judging that purchasing behavior exists.
8. A retail data acquisition system, comprising:
the image acquisition module is used for acquiring a commodity image and a user image;
a user feature extraction module, configured to extract user feature information according to the user image, where the user feature information includes: face image information and human body posture information;
the information processing module is used for judging whether a commodity purchasing behavior exists or not according to the face image information, the human body posture information and the commodity image;
and the information generation module is used for acquiring commodity information according to the commodity image and generating retail data by the user characteristic information and the commodity information when a commodity purchasing behavior exists.
9. A retail data acquisition device, comprising:
a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the retail sales data acquisition method of any one of claims 1-8.
10. A computer-readable storage medium storing computer instructions for causing a computer to perform the retail sales data acquisition method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010277158.9A CN111476609A (en) | 2020-04-10 | 2020-04-10 | Retail data acquisition method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010277158.9A CN111476609A (en) | 2020-04-10 | 2020-04-10 | Retail data acquisition method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111476609A true CN111476609A (en) | 2020-07-31 |
Family
ID=71751773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010277158.9A Pending CN111476609A (en) | 2020-04-10 | 2020-04-10 | Retail data acquisition method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476609A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149577A (en) * | 2020-09-24 | 2020-12-29 | 信雅达系统工程股份有限公司 | Intelligent settlement system based on neural network image recognition |
| CN112784786A (en) * | 2021-01-29 | 2021-05-11 | 联想(北京)有限公司 | Human body posture recognition method and device |
| CN115100640A (en) * | 2022-08-29 | 2022-09-23 | 北京海上升科技有限公司 | Artificial intelligence-based intelligent supermarket commodity sales big data detection method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399367A (en) * | 2018-01-31 | 2018-08-14 | 深圳市阿西莫夫科技有限公司 | Hand motion recognition method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
| CN108830251A (en) * | 2018-06-25 | 2018-11-16 | 北京旷视科技有限公司 | Information correlation method, device and system |
| CN109117803A (en) * | 2018-08-21 | 2019-01-01 | 腾讯科技（深圳）有限公司 | Clustering method, device, server and the storage medium of facial image |
| CN110647819A (en) * | 2019-08-28 | 2020-01-03 | 中国矿业大学 | Method and device for detecting abnormal behavior of underground personnel crossing belt |
-
2020
- 2020-04-10 CN CN202010277158.9A patent/CN111476609A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520194A (en) * | 2017-12-18 | 2018-09-11 | 上海云拿智能科技有限公司 | Kinds of goods sensory perceptual system based on imaging monitor and kinds of goods cognitive method |
| CN108399367A (en) * | 2018-01-31 | 2018-08-14 | 深圳市阿西莫夫科技有限公司 | Hand motion recognition method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN108830251A (en) * | 2018-06-25 | 2018-11-16 | 北京旷视科技有限公司 | Information correlation method, device and system |
| CN109117803A (en) * | 2018-08-21 | 2019-01-01 | 腾讯科技（深圳）有限公司 | Clustering method, device, server and the storage medium of facial image |
| CN110647819A (en) * | 2019-08-28 | 2020-01-03 | 中国矿业大学 | Method and device for detecting abnormal behavior of underground personnel crossing belt |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149577A (en) * | 2020-09-24 | 2020-12-29 | 信雅达系统工程股份有限公司 | Intelligent settlement system based on neural network image recognition |
| CN112784786A (en) * | 2021-01-29 | 2021-05-11 | 联想(北京)有限公司 | Human body posture recognition method and device |
| CN115100640A (en) * | 2022-08-29 | 2022-09-23 | 北京海上升科技有限公司 | Artificial intelligence-based intelligent supermarket commodity sales big data detection method and system |
| CN115100640B (en) * | 2022-08-29 | 2023-12-12 | 广东番客连锁品牌管理有限公司 | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3910608B1 (en) | Article identification method and system, and electronic device | |
| US11638490B2 (en) | Method and device for identifying product purchased by user and intelligent shelf system | |
| CN108416902B (en) | Real-time object identification method and device based on difference identification | |
| CN106203242B (en) | Similar image identification method and equipment | |
| KR102358607B1 (en) | Artificial intelligence appraisal system, artificial intelligence appraisal method and storage medium | |
| CN111476609A (en) | Retail data acquisition method, system, device and storage medium | |
| CA3014365C (en) | System and method for gathering data related to quality of service in a customer service environment | |
| US12008614B2 (en) | Occluded item detection for vision-based self-checkouts | |
| US20220414899A1 (en) | Item location detection using homographies | |
| US12131516B2 (en) | Reducing a search space for item identification using machine learning | |
| WO2016038901A1 (en) | Image processing device, image processing program, image processing method, and recording medium | |
| US20220414900A1 (en) | Item identification using multiple cameras | |
| US20220414379A1 (en) | Hand detection trigger for item identification | |
| CN113222582B (en) | Face payment retail terminal | |
| US8651389B2 (en) | System and method for identifying and tracking shopping carts | |
| US10891561B2 (en) | Image processing for item recognition | |
| AU2017231602A1 (en) | Method and system for visitor tracking at a POS area | |
| CN111445252A (en) | Method, device and equipment for establishing biological feature library | |
| CN110866746A (en) | Order matching method based on face recognition and computer equipment | |
| CN114332602A (en) | Commodity identification method of intelligent container | |
| US20220414587A1 (en) | Determining dimensions of an item using point cloud information | |
| CN115565097A (en) | Method and device for detecting compliance of personnel behaviors in transaction scene | |
| CN114360057A (en) | Data processing method and related device | |
| CN114066564A (en) | Service recommendation time determination method and device, computer equipment and storage medium | |
| US20230237558A1 (en) | Object recognition systems and methods |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200731 |
|
| RJ01 | Rejection of invention patent application after publication |