CN115100640B - Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence - Google Patents
Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115100640B CN115100640B CN202211036744.XA CN202211036744A CN115100640B CN 115100640 B CN115100640 B CN 115100640B CN 202211036744 A CN202211036744 A CN 202211036744A CN 115100640 B CN115100640 B CN 115100640B
- Authority
- CN
- China
- Prior art keywords
- target commodity
- image
- commodity
- target
- area
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000005516 engineering process Methods 0.000 claims abstract description 59
- 238000007689 inspection Methods 0.000 claims abstract description 44
- 230000011218 segmentation Effects 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims description 73
- 238000012545 processing Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000001684 chronic effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
- G06V30/164—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an intelligent supermarket commodity sales big data detection method and system based on artificial intelligence, and relates to the technical field of commodity sales data detection. Respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2; respectively detecting peak signal-to-noise ratio; then denoising the target commodity area image at the moment T1 and the target commodity area image at the moment T2 respectively; then respectively reconstructing super resolution; detecting the number of the commodities by adopting a multi-instance segmentation and mutual inspection technology, and generating a first target commodity number and a second target commodity number; then calculating to obtain the sales quantity of the target commodity; acquiring and identifying the target commodity region image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity region; and finally, generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information, so that the commodity sales data can be accurately detected.
Description
Technical Field
The invention relates to the technical field of commodity sales data detection, in particular to an intelligent supermarket commodity sales big data detection method and system based on artificial intelligence.
Background
With the development of the times, more and more shopping supermarkets are built, and great convenience is provided for the shopping of the masses. In the supermarket operation process, accurate commodity sales data is obtained, so that direct data support can be provided for timely commodity replenishment, outdated commodity, unloading and the like, and direct data support can be provided for optimizing the type of commodity sold.
However, the traditional commodity sales data acquisition is often completed by means of staff checking and the like, huge manpower resources are consumed, and even though some supermarkets already use methods such as target detection, target identification and the like to detect the commodity sales data, larger errors still exist. With the continuous updating of the technology in the artificial intelligence field, the method can provide direct technical support for commodity sales big data detection. Therefore, the intelligent supermarket commodity sales big data detection method based on the artificial intelligence has important value and significance.
Disclosure of Invention
The invention aims to provide an intelligent supermarket commodity sales big data detection method and system based on artificial intelligence, which are used for solving the problem that in the prior art, large errors exist in detection of commodity sales data by adopting methods such as target detection and target identification.
In a first aspect, an embodiment of the present application provides an artificial intelligence-based smart supermarket commodity sales big data detection method, including the following steps:
respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2;
respectively detecting peak signal-to-noise ratios of the target commodity area image at the moment T1 and the target commodity area image at the moment T2, and generating a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio;
denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image;
denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image;
respectively carrying out super-resolution reconstruction on the first target commodity area preprocessed image and the second target commodity area preprocessed image to generate a first target commodity area reconstructed image and a second target commodity area reconstructed image;
the method comprises the steps of respectively detecting the quantity of commodities in a first target commodity area reconstruction image and a second target commodity area reconstruction image by adopting a multi-instance segmentation and mutual inspection technology, and generating the quantity of the first target commodities and the quantity of the second target commodities;
Calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity;
acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area;
and generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information.
In the implementation process, firstly, respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2; then, respectively carrying out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2 to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio; denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image; denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image; then, super-resolution reconstruction is carried out on the first target commodity area preprocessed image and the second target commodity area preprocessed image respectively, and a first target commodity area reconstructed image and a second target commodity area reconstructed image are generated; then, carrying out commodity quantity detection on the first target commodity area reconstruction image and the second target commodity area reconstruction image respectively by adopting a multi-instance segmentation and mutual inspection technology, and generating a first target commodity quantity and a second target commodity quantity; calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity; then acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area; and finally, generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information. The image denoising method based on peak signal-to-noise ratio detection is utilized to denoise the target commodity area image with higher noise, the target commodity area image is optimized in a targeted manner, the multi-instance segmentation and mutual inspection technology based on image super-resolution reconstruction is utilized to detect the target commodity area image, the number of target commodities is detected more accurately, and for commodities with slower sales, the OCR technology of multi-image enhancement and mutual inspection is utilized to identify the information such as the production date and the quality guarantee period of the target commodities more accurately, so that commodity sales data can be detected accurately.
Based on the first aspect, in some embodiments of the present invention, denoising the target commodity region image at time T1 according to a first image peak signal-to-noise ratio, the step of generating a first target commodity region pre-processed image includes the steps of:
judging whether the peak signal-to-noise ratio of the first image is larger than a preset signal-to-noise ratio threshold, if so, taking the target commodity area image at the moment T1 as a first target commodity area preprocessing image; if not, denoising the target commodity area image at the moment T1 to generate a first target commodity area pretreatment image.
Based on the first aspect, in some embodiments of the invention, the method further comprises the steps of:
carrying out commodity quantity detection on the reconstructed image of the first target commodity area by adopting a plurality of example segmentation technologies respectively to generate a plurality of commodity detection quantities;
and determining and obtaining the first target commodity quantity according to the commodity detection quantities.
Based on the first aspect, in some embodiments of the present invention, the step of acquiring and identifying the target commodity area image at the time T2 according to the commodity information of the target commodity area by using the OCR technology of multiple image enhancement mutual inspection, and generating the commodity identification information of the target commodity area includes the steps of:
Acquiring commodity information of a target commodity area;
judging whether commodity information of the target commodity area is a chronic sales commodity, if so, identifying the target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection, and generating commodity identification information of the target commodity area; if not, ending.
Based on the first aspect, in some embodiments of the application, the method further comprises the steps of:
performing image enhancement on the target commodity area image at the moment T2 by adopting a plurality of image enhancement methods to generate a plurality of target commodity area enhancement images at the moment T2;
respectively identifying a plurality of target commodity area enhanced images at the moment T2 by adopting an OCR technology to generate a plurality of identification results;
and determining and obtaining commodity identification information of the target commodity area according to the plurality of identification results.
Based on the first aspect, in some embodiments of the application, the method further comprises the steps of:
and generating and sending the replenishment reminding information to the merchant according to the sales quantity of the target commodity.
Based on the first aspect, in some embodiments of the application, the method further comprises the steps of:
and generating and sending commodity expiration reminding information to the merchant according to the commodity identification information of the target commodity area.
In a second aspect, an embodiment of the present application provides an artificial intelligence-based smart supermarket commodity sales big data detection system, including:
The target commodity area image acquisition module is used for respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2;
the peak signal-to-noise ratio detection module is used for respectively carrying out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2 to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio;
the first denoising processing module is used for denoising the target commodity area image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity area preprocessing image;
the second denoising processing module is used for denoising the target commodity area image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity area preprocessing image;
the super-resolution reconstruction module is used for performing super-resolution reconstruction on the first target commodity area pretreatment image and the second target commodity area pretreatment image respectively to generate a first target commodity area reconstruction image and a second target commodity area reconstruction image;
the commodity quantity detection module is used for detecting commodity quantity by adopting a multi-instance segmentation and mutual inspection technology to respectively reconstruct a first target commodity area reconstruction image and a second target commodity area reconstruction image to generate a first target commodity quantity and a second target commodity quantity;
The commodity sales number calculation module is used for calculating the target commodity sales number according to the first target commodity number and the second target commodity number;
the commodity information identification module is used for acquiring and identifying the target commodity area image at the moment T2 by utilizing the OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area to generate commodity identification information of the target commodity area;
and the target commodity sales information generation module is used for generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information.
In the implementation process, the target commodity area image acquisition module acquires a target commodity area image at the moment T1 and a target commodity area image at the moment T2 respectively; the peak signal-to-noise ratio detection module respectively carries out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2, and the first denoising processing module denoises the target commodity area image at the moment T1 according to the peak signal-to-noise ratio of the first image; the second denoising processing module denoises the target commodity area image at the moment T2 according to the peak signal-to-noise ratio of the second image; the super-resolution reconstruction module is used for performing super-resolution reconstruction on the first target commodity area preprocessed image and the second target commodity area preprocessed image respectively; the commodity quantity detection module adopts a multi-instance segmentation and mutual inspection technology to detect commodity quantity of the first target commodity area reconstruction image and the second target commodity area reconstruction image respectively; the commodity sales number calculation module calculates the target commodity sales number; the commodity information recognition module obtains commodity information of a target commodity area and recognizes a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to the commodity information of the target commodity area; the target commodity sales information generation module generates target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information. The image denoising method based on peak signal-to-noise ratio detection is utilized to denoise the target commodity area image with higher noise, the target commodity area image is optimized in a targeted manner, the multi-instance segmentation and mutual inspection technology based on image super-resolution reconstruction is utilized to detect the target commodity area image, the number of target commodities is detected more accurately, and for commodities with slower sales, the OCR technology of multi-image enhancement and mutual inspection is utilized to identify the information such as the production date and the quality guarantee period of the target commodities more accurately, so that commodity sales data can be detected accurately.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory for storing one or more programs; a processor. The method of any of the first aspects described above is implemented when one or more programs are executed by a processor.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as in any of the first aspects described above.
The embodiment of the application has at least the following advantages or beneficial effects:
the embodiment of the application provides an intelligent supermarket commodity sales big data detection method and system based on artificial intelligence, which are implemented by respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2; then, respectively carrying out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2 to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio; denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image; denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image; then, super-resolution reconstruction is carried out on the first target commodity area preprocessed image and the second target commodity area preprocessed image respectively, and a first target commodity area reconstructed image and a second target commodity area reconstructed image are generated; then, carrying out commodity quantity detection on the first target commodity area reconstruction image and the second target commodity area reconstruction image respectively by adopting a multi-instance segmentation and mutual inspection technology, and generating a first target commodity quantity and a second target commodity quantity; calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity; then acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area; and finally, generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information. The image denoising method based on peak signal-to-noise ratio detection is utilized to denoise the target commodity area image with higher noise, the target commodity area image is optimized in a targeted manner, the multi-instance segmentation and mutual inspection technology based on image super-resolution reconstruction is utilized to detect the target commodity area image, the number of target commodities is detected more accurately, and for commodities with slower sales, the OCR technology of multi-image enhancement and mutual inspection is utilized to identify the information such as the production date and the quality guarantee period of the target commodities more accurately, so that commodity sales data can be detected accurately.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting big data of commodity sales in an intelligent supermarket based on artificial intelligence provided by the embodiment of the invention;
FIG. 2 is a detailed process diagram of step S130 according to an embodiment of the present invention;
FIG. 3 is a detailed process diagram of the commodity quantity detection according to the present invention;
FIG. 4 is a block diagram of an artificial intelligence based intelligent supermarket commodity sales big data detection system according to an embodiment of the invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Icon: 110-a target commodity area image acquisition module; a 120-peak signal-to-noise ratio detection module; 130-a first denoising processing module; 140-a second denoising processing module; 150-a super-resolution reconstruction module; 160-commodity quantity detection module; 170-a commodity sales number calculation module; 180-a commodity information identification module; 190-a target commodity sales information generation module; 101-memory; 102-a processor; 103-communication interface.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
Examples
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The various embodiments and features of the embodiments described below may be combined with one another without conflict.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting big data of commodity sales in an intelligent supermarket based on artificial intelligence according to an embodiment of the application. The intelligent supermarket commodity sales big data detection method based on artificial intelligence comprises the following steps:
Step S110: respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2; the time T2 is greater than the time T1, and the time T1 and the time T2 may be spaced by a certain time, such as half a day or one day. The target commodity area image can be obtained by extracting a picture of an area where the target commodity is placed by using shooting equipment in a supermarket. The method comprises the steps of firstly obtaining a target commodity area image at the moment T1, and obtaining the target commodity area image at the moment T2 after a certain time interval.
Step S120: respectively detecting peak signal-to-noise ratios of the target commodity area image at the moment T1 and the target commodity area image at the moment T2, and generating a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio; the peak signal-to-noise ratio detection is an objective standard for evaluating an image, the peak signal-to-noise ratio detection is performed by detecting noise of the image, and the peak signal-to-noise ratio detection can be realized by adopting the existing technology and is not described herein.
Step S130: denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image; specifically, if the peak signal-to-noise ratio of the first image is high, the noise is not obvious, and denoising processing can be omitted; if the peak signal-to-noise ratio of the first image is low, the noise is obvious, and the denoising processing is directly carried out on the first image.
Referring to fig. 2, fig. 2 is a detailed process diagram of step S130 provided in an embodiment of the present invention, and a specific denoising process includes the following steps:
judging whether the peak signal-to-noise ratio of the first image is larger than a preset signal-to-noise ratio threshold, if so, taking the target commodity area image at the moment T1 as a first target commodity area preprocessing image; if not, denoising the target commodity area image at the moment T1 to generate a first target commodity area pretreatment image. The preset snr threshold may be an empirically preset value.
Step S140: denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image; specifically, if the peak signal-to-noise ratio of the second image is high, the noise is not obvious, and denoising treatment can be omitted; if the peak signal-to-noise ratio of the second image is low, the noise is obvious, and the denoising processing is directly carried out on the second image. The denoising process is the same as that in step S130, and will not be described here.
It should be noted that, the image denoising method may be a filter-based method, such as a median filter, a model-based method, such as a sparse model, a gradient model, a markov random field model, or a learning-based method, and the image denoising method belongs to the prior art, and will not be described herein.
Step S150: respectively carrying out super-resolution reconstruction on the first target commodity area preprocessed image and the second target commodity area preprocessed image to generate a first target commodity area reconstructed image and a second target commodity area reconstructed image; a clearer image can be obtained by super-resolution reconstruction. The above-mentioned super-resolution reconstruction belongs to the prior art, and will not be described in detail here.
Step S160: the method comprises the steps of respectively detecting the quantity of commodities in a first target commodity area reconstruction image and a second target commodity area reconstruction image by adopting a multi-instance segmentation and mutual inspection technology, and generating the quantity of the first target commodities and the quantity of the second target commodities; the multi-instance segmentation and mutual inspection technology is to detect the number of commodities by using a plurality of instance segmentation technologies, and the instance segmentation method with the largest number of commodities is detected.
The process of generating the first target commodity number is taken as an example, and specifically explaining how to perform commodity number detection, the commodity number detection of the second target commodity area reconstructed image is the same as the commodity number detection process of the first target commodity area reconstructed image, and here, the process of generating the first target commodity number is taken as an example, and specifically explaining how to perform commodity number detection, please refer to fig. 3, and fig. 3 is a detailed process diagram of commodity number detection provided in the embodiment of the present invention.
Firstly, carrying out commodity quantity detection on a first target commodity area reconstruction image by adopting a plurality of example segmentation technologies respectively to generate a plurality of commodity detection quantities; the above-described instance segmentation techniques include semantic instance segmentation based on discriminant loss functions, video instance segmentation VisTR, real-time instance segmentation, and the like. The above example segmentation technique belongs to the prior art, and will not be described herein.
Then, the first target commodity number is determined according to the commodity detection numbers. The determination may be to set the largest of the plurality of article detection amounts as the first target article data. For example: the first target commodity number is 22 by detecting the commodity detection numbers of 21, 22 and 19 respectively by using three classical example segmentation methods.
Step S170: calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity; the sales number of the target commodity can be obtained by subtracting the second target commodity number from the first target commodity number, and the sales number of the commodity in the time period from T1 to T2 can be obtained.
Step S180: acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area;
Firstly, acquiring commodity information of a target commodity area; the commodity information includes commodity names, commodity categories, commodity attributes, and the like. The acquisition may be obtained by human input or by identifying a shelf type tag.
Then judging whether commodity information of the target commodity area is a chronic sales commodity, if so, identifying the target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection, and generating commodity identification information of the target commodity area; if not, ending. The judgment can be performed according to the comparison between the commodity category in the commodity information and the preset classification information, for example, cola and farmer mountain spring belong to the commodity sold faster, and milk powder belongs to the commodity sold slower.
Specifically, the process of identifying the target commodity area image at the time T2 by utilizing the OCR technology of multi-image enhancement mutual inspection includes the following steps:
firstly, performing image enhancement on a target commodity area image at the moment T2 by adopting a plurality of image enhancement methods to generate a plurality of target commodity area enhancement images at the moment T2; the image enhancement can be performed by adopting different image enhancement methods, wherein the image enhancement methods comprise a point operation algorithm, a neighborhood denoising algorithm, a space domain-based algorithm and the like, the image enhancement can be realized by adopting the prior art, and the description is omitted here.
Then, an OCR technology is adopted to respectively identify a plurality of target commodity area enhanced images at the moment T2, and a plurality of identification results are generated; based on different image enhancement methods, characters are respectively identified by utilizing OCR technology. And identifying the production date and the quality guarantee period of the commodity in the target commodity area image by utilizing the OCR technology of multi-image enhancement mutual inspection. For the same commodity delivered from the same batch, only the production date and the quality guarantee period of one commodity can be identified. The OCR technology described above belongs to the prior art and will not be described in detail here.
And finally, determining and obtaining commodity identification information of the target commodity area according to the plurality of identification results. The target commodity area commodity identification information can be determined by adopting a few principles subject to majority. Such as: after the image is enhanced by most image enhancement methods, a certain character is identified as "8"; after the image is enhanced by a few image enhancement methods, a certain character is recognized as "0", and finally the character is recognized as "8". The recognition accuracy can be improved by adopting the OCR technology of multi-image enhancement mutual inspection for recognition.
Step S190: and generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information. The target commodity sales information includes a target commodity sales number and target commodity area commodity identification information. The information such as the sales quantity, the production date and the quality guarantee period of the goods on the goods shelf at present can be known through the sales information of the target goods. The information of the quality guarantee period can be utilized, and the problem that the commodity is not actually sold but automatically put off in the commodity selling process is considered, so that the information of the production date, the quality guarantee period and the like of the target commodity is identified, and commodity sales data can be detected more comprehensively and accurately.
And the method can also generate and send the replenishment reminding information to the merchant according to the sales quantity of the target commodity. And if the commodity is lower than a certain quantity, reminding a merchant to timely replenish the commodity.
And generating and sending commodity expiration reminding information to the merchant according to the commodity identification information of the target commodity area. For commodities which have exceeded or are about to exceed the shelf life, merchants are reminded to take off the shelves in time.
In the implementation process, firstly, respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2; then, respectively carrying out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2 to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio; denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image; denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image; then, super-resolution reconstruction is carried out on the first target commodity area preprocessed image and the second target commodity area preprocessed image respectively, and a first target commodity area reconstructed image and a second target commodity area reconstructed image are generated; then, carrying out commodity quantity detection on the first target commodity area reconstruction image and the second target commodity area reconstruction image respectively by adopting a multi-instance segmentation and mutual inspection technology, and generating a first target commodity quantity and a second target commodity quantity; calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity; then acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area; and finally, generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information. The image denoising method based on peak signal-to-noise ratio detection is utilized to denoise the target commodity area image with higher noise, the target commodity area image is optimized in a targeted manner, the multi-instance segmentation and mutual inspection technology based on image super-resolution reconstruction is utilized to detect the target commodity area image, the number of target commodities is detected more accurately, and for commodities with slower sales, the OCR technology of multi-image enhancement and mutual inspection is utilized to identify the information such as the production date and the quality guarantee period of the target commodities more accurately, so that commodity sales data can be detected accurately.
Based on the same inventive concept, the invention also provides an intelligent supermarket commodity sales big data detection system based on artificial intelligence, please refer to fig. 4, and fig. 4 is a block diagram of the intelligent supermarket commodity sales big data detection system based on artificial intelligence provided by the embodiment of the invention. This wisdom supermarket commodity sales big data detecting system based on artificial intelligence includes:
a target commodity area image obtaining module 110, configured to obtain a target commodity area image at a time T1 and a target commodity area image at a time T2, respectively;
the peak signal-to-noise ratio detection module 120 is configured to perform peak signal-to-noise ratio detection on the target commodity area image at the time T1 and the target commodity area image at the time T2, respectively, to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio;
the first denoising processing module 130 is configured to denoise the target commodity region image at the time T1 according to a first image peak signal-to-noise ratio, and generate a first target commodity region preprocessed image;
the second denoising processing module 140 is configured to denoise the target commodity area image at the time T2 according to a second image peak signal-to-noise ratio, and generate a second target commodity area preprocessed image;
the super-resolution reconstruction module 150 is configured to perform super-resolution reconstruction on the first target commodity area preprocessed image and the second target commodity area preprocessed image, respectively, to generate a first target commodity area reconstructed image and a second target commodity area reconstructed image;
The commodity number detection module 160 is configured to detect the commodity number by using a multi-instance segmentation and mutual verification technology on the first target commodity area reconstructed image and the second target commodity area reconstructed image, so as to generate a first target commodity number and a second target commodity number;
the commodity sales number calculation module 170 is configured to calculate a target commodity sales number according to the first target commodity number and the second target commodity number;
the commodity information identification module 180 is configured to acquire and identify a target commodity area image at a time T2 by using an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generate commodity identification information of the target commodity area;
the target commodity sales information generation module 190 is configured to generate target commodity sales information according to the target commodity sales number and the target commodity area commodity identification information.
In the above implementation process, the target commodity area image acquiring module 110 acquires a target commodity area image at the time T1 and a target commodity area image at the time T2 respectively; the peak signal-to-noise ratio detection module 120 respectively carries out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2, and the first denoising processing module 130 denoises the target commodity area image at the moment T1 according to the peak signal-to-noise ratio of the first image; the second denoising processing module 140 denoises the target commodity area image at the moment T2 according to the peak signal-to-noise ratio of the second image; the super-resolution reconstruction module 150 performs super-resolution reconstruction on the first target commodity region preprocessed image and the second target commodity region preprocessed image respectively; the commodity quantity detection module 160 performs commodity quantity detection on the first target commodity region reconstructed image and the second target commodity region reconstructed image respectively by adopting a multi-instance segmentation and mutual inspection technology; the commodity sales quantity calculating module 170 calculates the target commodity sales quantity; the commodity information identification module 180 acquires and identifies the target commodity area image at the moment T2 by utilizing the OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area; the target commodity sales information generation module 190 generates target commodity sales information from the target commodity sales quantity and the target commodity region commodity identification information. The image denoising method based on peak signal-to-noise ratio detection is utilized to denoise the target commodity area image with higher noise, the target commodity area image is optimized in a targeted manner, the multi-instance segmentation and mutual inspection technology based on image super-resolution reconstruction is utilized to detect the target commodity area image, the number of target commodities is detected more accurately, and for commodities with slower sales, the OCR technology of multi-image enhancement and mutual inspection is utilized to identify the information such as the production date and the quality guarantee period of the target commodities more accurately, so that commodity sales data can be detected accurately.
Referring to fig. 5, fig. 5 is a schematic block diagram of an electronic device according to an embodiment of the present application. The electronic device comprises a memory 101, a processor 102 and a communication interface 103, wherein the memory 101, the processor 102 and the communication interface 103 are electrically connected with each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, such as program instructions/modules corresponding to the intelligent supermarket commodity sales big data detection system based on artificial intelligence according to the embodiment of the present application, and the processor 102 executes the software programs and modules stored in the memory 101, thereby executing various functional applications and data processing. The communication interface 103 may be used for communication of signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
It will be appreciated that the configuration shown in fig. 5 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 5, or have a different configuration than shown in fig. 5. The components shown in fig. 5 may be implemented in hardware, software, or a combination thereof.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (8)
1. The intelligent supermarket commodity sales big data detection method based on artificial intelligence is characterized by comprising the following steps of:
respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2;
respectively detecting peak signal-to-noise ratios of the target commodity area image at the moment T1 and the target commodity area image at the moment T2, and generating a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio;
denoising the target commodity region image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity region preprocessing image;
Denoising the target commodity region image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity region preprocessing image;
respectively carrying out super-resolution reconstruction on the first target commodity area preprocessed image and the second target commodity area preprocessed image to generate a first target commodity area reconstructed image and a second target commodity area reconstructed image;
the method comprises the steps of respectively detecting the quantity of commodities in a first target commodity area reconstruction image and a second target commodity area reconstruction image by adopting a multi-instance segmentation and mutual inspection technology, and generating the quantity of the first target commodities and the quantity of the second target commodities; the multi-instance segmentation and mutual inspection technology is to detect the number of commodities by utilizing a plurality of instance segmentation technologies, and the instance segmentation method with the largest number of commodities is detected;
calculating to obtain the sales quantity of the target commodity according to the first target commodity quantity and the second target commodity quantity;
acquiring and identifying a target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity identification information of the target commodity area, wherein the method comprises the following steps: acquiring commodity information of a target commodity area; judging whether commodity information of the target commodity area is a chronic sales commodity, if so, identifying the target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection to generate target commodity area commodity identification information, wherein the method comprises the following steps: performing image enhancement on the target commodity area image at the moment T2 by adopting a plurality of image enhancement methods to generate a plurality of target commodity area enhancement images at the moment T2; respectively identifying a plurality of target commodity area enhanced images at the moment T2 by adopting an OCR technology to generate a plurality of identification results; determining and obtaining commodity identification information of the target commodity area according to a plurality of identification results, and determining the commodity identification information of the target commodity area by adopting a rule of minority compliance and majority compliance; if not, ending; the image enhancement method comprises a point operation algorithm, a neighborhood denoising algorithm and a airspace-based algorithm;
And generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information.
2. The intelligent supermarket commodity sales big data detection method based on artificial intelligence according to claim 1, wherein the step of denoising the target commodity area image at the time of T1 according to the peak signal-to-noise ratio of the first image to generate the first target commodity area preprocessed image comprises the following steps:
judging whether the peak signal-to-noise ratio of the first image is larger than a preset signal-to-noise ratio threshold, if so, taking the target commodity area image at the moment T1 as a first target commodity area preprocessing image; if not, denoising the target commodity area image at the moment T1 to generate a first target commodity area pretreatment image.
3. The intelligent supermarket commodity sales big data detection method based on artificial intelligence of claim 1, further comprising the steps of:
carrying out commodity quantity detection on the reconstructed image of the first target commodity area by adopting a plurality of example segmentation technologies respectively to generate a plurality of commodity detection quantities;
and determining and obtaining the first target commodity quantity according to the commodity detection quantities.
4. The intelligent supermarket commodity sales big data detection method based on artificial intelligence of claim 1, further comprising the steps of:
And generating and sending the replenishment reminding information to the merchant according to the sales quantity of the target commodity.
5. The intelligent supermarket commodity sales big data detection method based on artificial intelligence of claim 1, further comprising the steps of:
and generating and sending commodity expiration reminding information to the merchant according to the commodity identification information of the target commodity area.
6. Intelligent supermarket commodity sales big data detecting system based on artificial intelligence, its characterized in that includes:
the target commodity area image acquisition module is used for respectively acquiring a target commodity area image at the moment T1 and a target commodity area image at the moment T2;
the peak signal-to-noise ratio detection module is used for respectively carrying out peak signal-to-noise ratio detection on the target commodity area image at the moment T1 and the target commodity area image at the moment T2 to generate a first image peak signal-to-noise ratio and a second image peak signal-to-noise ratio;
the first denoising processing module is used for denoising the target commodity area image at the moment T1 according to the peak signal-to-noise ratio of the first image to generate a first target commodity area preprocessing image;
the second denoising processing module is used for denoising the target commodity area image at the moment T2 according to the peak signal-to-noise ratio of the second image to generate a second target commodity area preprocessing image;
The super-resolution reconstruction module is used for performing super-resolution reconstruction on the first target commodity area pretreatment image and the second target commodity area pretreatment image respectively to generate a first target commodity area reconstruction image and a second target commodity area reconstruction image;
the commodity quantity detection module is used for detecting commodity quantity by adopting a multi-instance segmentation and mutual inspection technology to respectively reconstruct a first target commodity area reconstruction image and a second target commodity area reconstruction image to generate a first target commodity quantity and a second target commodity quantity; the multi-instance segmentation and mutual inspection technology is to detect the number of commodities by utilizing a plurality of instance segmentation technologies, and the instance segmentation method with the largest number of commodities is detected;
the commodity sales number calculation module is used for calculating the target commodity sales number according to the first target commodity number and the second target commodity number;
the commodity information recognition module is used for acquiring and recognizing the target commodity area image at the moment T2 by utilizing the OCR technology of multi-image enhancement mutual inspection according to commodity information of the target commodity area, and generating commodity recognition information of the target commodity area, and comprises the following steps: acquiring commodity information of a target commodity area; judging whether commodity information of the target commodity area is a chronic sales commodity, if so, identifying the target commodity area image at the moment T2 by utilizing an OCR technology of multi-image enhancement mutual inspection to generate target commodity area commodity identification information, wherein the method comprises the following steps: performing image enhancement on the target commodity area image at the moment T2 by adopting a plurality of image enhancement methods to generate a plurality of target commodity area enhancement images at the moment T2; respectively identifying a plurality of target commodity area enhanced images at the moment T2 by adopting an OCR technology to generate a plurality of identification results; determining and obtaining commodity identification information of the target commodity area according to a plurality of identification results, and determining the commodity identification information of the target commodity area by adopting a rule of minority compliance and majority compliance; if not, ending; the image enhancement method comprises a point operation algorithm, a neighborhood denoising algorithm and a airspace-based algorithm;
And the target commodity sales information generation module is used for generating target commodity sales information according to the target commodity sales quantity and the target commodity area commodity identification information.
7. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the method of any of claims 1-5 is implemented when the one or more programs are executed by the processor.
8. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211036744.XA CN115100640B (en) | 2022-08-29 | 2022-08-29 | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211036744.XA CN115100640B (en) | 2022-08-29 | 2022-08-29 | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115100640A CN115100640A (en) | 2022-09-23 |
CN115100640B true CN115100640B (en) | 2023-12-12 |
Family
ID=83300872
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211036744.XA Active CN115100640B (en) | 2022-08-29 | 2022-08-29 | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115100640B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116543373B (en) * | 2023-04-14 | 2024-05-28 | 北京嘉沐安科技有限公司 | Block chain-based live video big data intelligent analysis and optimization method and system |
CN116227897A (en) * | 2023-05-09 | 2023-06-06 | 天津温阳生物技术有限公司 | Food sample detection data processing method and system |
CN117078358A (en) * | 2023-10-13 | 2023-11-17 | 北京未来链技术有限公司 | Intelligent construction method and system for meta-space electronic commerce platform system based on voice recognition |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109377289A (en) * | 2018-12-14 | 2019-02-22 | 深圳码隆科技有限公司 | Sales data acquisition method, device and server |
CN109523320A (en) * | 2018-11-27 | 2019-03-26 | 西安数拓网络科技有限公司 | A kind of commodity monitoring method based on comprehensive sensor, apparatus and system |
CN111476609A (en) * | 2020-04-10 | 2020-07-31 | 广西中烟工业有限责任公司 | Retail data acquisition method, system, device and storage medium |
CN113627411A (en) * | 2021-10-14 | 2021-11-09 | 广州市玄武无线科技股份有限公司 | Super-resolution-based commodity identification and price matching method and system |
CN114648568A (en) * | 2020-12-17 | 2022-06-21 | 顺丰科技有限公司 | Object size recognition method and device, computer equipment and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111369317B (en) * | 2020-02-27 | 2023-08-18 | 创新奇智(上海)科技有限公司 | Order generation method, order generation device, electronic equipment and storage medium |
-
2022
- 2022-08-29 CN CN202211036744.XA patent/CN115100640B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109523320A (en) * | 2018-11-27 | 2019-03-26 | 西安数拓网络科技有限公司 | A kind of commodity monitoring method based on comprehensive sensor, apparatus and system |
CN109377289A (en) * | 2018-12-14 | 2019-02-22 | 深圳码隆科技有限公司 | Sales data acquisition method, device and server |
CN111476609A (en) * | 2020-04-10 | 2020-07-31 | 广西中烟工业有限责任公司 | Retail data acquisition method, system, device and storage medium |
CN114648568A (en) * | 2020-12-17 | 2022-06-21 | 顺丰科技有限公司 | Object size recognition method and device, computer equipment and storage medium |
CN113627411A (en) * | 2021-10-14 | 2021-11-09 | 广州市玄武无线科技股份有限公司 | Super-resolution-based commodity identification and price matching method and system |
Also Published As
Publication number | Publication date |
---|---|
CN115100640A (en) | 2022-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115100640B (en) | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence | |
CN111681273B (en) | Image segmentation method and device, electronic equipment and readable storage medium | |
Zhang et al. | Toward new retail: A benchmark dataset for smart unmanned vending machines | |
CN112700408B (en) | Model training method, image quality evaluation method and device | |
CN116562991B (en) | Commodity big data information identification method and system for meta-space electronic commerce platform | |
CN111666275B (en) | Data processing method and device, electronic equipment and storage medium | |
CN103383732B (en) | Image processing method and device | |
CN114581207B (en) | Commodity image big data accurate pushing method and system for E-commerce platform | |
CN114241484B (en) | Social network-oriented image big data accurate retrieval method and system | |
CN112906697B (en) | Commodity identification and settlement method, commodity identification and settlement device, electronic equipment and storage medium | |
CN114596441A (en) | Massive image denoising method and system for live webcast social big data | |
CN111782927A (en) | Article recommendation method and device, computer storage medium | |
CN115860882A (en) | Intelligent city commodity big data intelligent purchasing method and system based on block chain | |
CN116739704A (en) | E-commerce platform interest analysis type commodity recommendation method and system based on artificial intelligence | |
Khosravian et al. | Enhancing the robustness of the convolutional neural networks for traffic sign detection | |
CN115063084A (en) | Inventory checking method and system for cigarette retail merchants | |
Zhang et al. | QA-USTNet: yarn-dyed fabric defect detection via U-shaped swin transformer network based on quadtree attention | |
CN110826481A (en) | Data processing method, commodity identification method, server and storage medium | |
CN111967970B (en) | Bank product recommendation method and device based on spark platform | |
CN114723536B (en) | E-commerce platform cheap commodity selection method and system based on image big data comparison | |
CN112364702A (en) | Article verification method and device | |
US10475057B2 (en) | System and method for transaction volume determination | |
CN106779843B (en) | Method and device for analyzing merchant competitive relationship based on customer group characteristics | |
CN110598125A (en) | Method and device for evaluating key opinion leader investment and storage medium | |
CN114219084B (en) | Sales visit display counterfeiting identification method and device in fast moving industry |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20231115 Address after: 515000, No. 101, Building 53, Jintaozhuang West District, Longhu District, Shantou City, Guangdong Province Applicant after: Guangdong Fanke Chain Brand Management Co.,Ltd. Address before: China (Beijing) Pilot Free Trade Zone High-end Industry Area, No. 1051, Block D, No. 12, Yushun Road, Daxing District, Beijing 102602 Applicant before: Beijing Haisheng Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |