CN112561662A - E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform - Google Patents
E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform Download PDFInfo
- Publication number
- CN112561662A CN112561662A CN202011570729.4A CN202011570729A CN112561662A CN 112561662 A CN112561662 A CN 112561662A CN 202011570729 A CN202011570729 A CN 202011570729A CN 112561662 A CN112561662 A CN 112561662A
- Authority
- CN
- China
- Prior art keywords
- returned
- goods
- appearance
- module
- commodity
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000012795 verification Methods 0.000 title claims description 34
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000004891 communication Methods 0.000 claims abstract description 29
- 238000004806 packaging method and process Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 49
- 238000010191 image analysis Methods 0.000 claims description 20
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 description 5
- 230000000717 retained effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000032258 transport Effects 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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a remote checking method of goods returned orders based on an artificial intelligence electronic commerce platform and a cloud computing checking platform, which are characterized in that relevant videos of goods returned in goods returned orders are collected, orientation appearance images of the goods returned in each video frame are identified, each standard orientation appearance image is compared, whether the appearance of the goods returned is qualified or not is judged, the goods returned with unqualified appearance is manually communicated, the main function of the goods returned is checked through a merchant remote distance, each parameter data of the goods returned is detected through logistics personnel after the checking is passed, each parameter data comparison difference value of the goods returned in the goods returned orders is contrasted and analyzed, the conformity degree influence coefficient of the goods returned in the goods returned orders is calculated, whether the goods returned meets the goods returning requirement or not is judged, if the goods returned requirement is met, packaging transportation is carried out, if the goods returned requirement is not met, corresponding communication and processing are carried out, thereby reducing the waiting time of the goods returning party and meeting the satisfaction and experience of the goods returning party.
Description
Technical Field
The invention relates to the technical field of returned commodity verification, in particular to a remote verification method for returned orders of commodities on an E-commerce platform based on artificial intelligence and a cloud computing verification platform.
Background
After the 21 st century, electronic commerce has entered a rapidly growing era and has been faced with great challenges while continuing to grow. The problem of returning goods is inevitable no matter the size of the e-commerce platform.
At present, the existing E-commerce platform commodity returned order checking method mainly depends on manual checking, specifically, after a goods returning party reversely delivers returned commodities to a merchant, the staff of the merchant checks, and then waits for the next processing, the goods returning and checking method not only increases the human resource cost, reduces the goods returning efficiency of the E-commerce platform, but also increases the waiting time of the goods returning party, reduces the satisfaction degree and the experience feeling of the goods returning party, thereby causing the loss of users of the E-commerce platform, simultaneously, the existing E-commerce platform commodity return order checking method can not be checked by three parties, namely a return party, a merchant and logistics personnel, and has the problems that the responsibility can not be traced due to the damage of commodities when the returned commodities are delivered, therefore, the credit of each party can be greatly influenced, and in order to solve the problems, the E-commerce platform commodity return order remote checking method and the cloud computing checking platform based on artificial intelligence are designed.
Disclosure of Invention
The invention aims to provide a remote checking method of goods returned orders of an E-commerce platform and a cloud computing checking platform based on artificial intelligence, wherein the method comprises the steps of collecting relevant videos of goods returned in the goods returned orders, identifying orientation appearance images of the goods returned in each video frame, removing similar orientation appearance enhanced images, simultaneously comparing each standard orientation appearance image, judging whether the appearance of the goods returned is qualified, carrying out manual communication on the goods returned with unqualified appearance, remotely checking the main functions of the goods returned by a merchant, detecting each parameter data of the goods returned by logistics personnel after passing the checking, comparing and analyzing each parameter data comparison difference of the goods returned in the goods returned orders, calculating the conformity influence coefficient of the goods returned in the goods returned orders, and judging whether the goods returned meets the goods returned requirement, if the goods returning requirement is met, packaging transportation is carried out, and if the goods returning requirement is not met, corresponding communication and processing are carried out, so that the problems in the background technology are solved.
The purpose of the invention can be realized by the following technical scheme:
the E-commerce platform commodity return order remote checking method based on artificial intelligence comprises the following steps:
s1, collecting related videos of returned commodities in the returned orders, identifying orientation appearance images of the returned commodities in all video frames, and removing similar orientation appearance enhancement images;
s2, comparing the standard orientation appearance images, judging whether the appearance of the returned goods is qualified, and manually communicating the returned goods with unqualified appearance;
s3, remotely checking the main functions of the returned commodities through a merchant, and detecting each parameter data of the returned commodities through logistics personnel after the checking is passed;
s4, comparing and analyzing the parameter data of returned goods in the returned order, and calculating the conformity influence coefficient of the returned goods in the returned order;
s5, judging whether the returned goods meet the return requirements, if so, packing and transporting, and if not, performing corresponding communication and processing;
the E-commerce platform commodity return order remote checking method based on artificial intelligence uses an E-commerce platform commodity return order remote checking system based on artificial intelligence, and comprises a video acquisition module, a video processing module, an image analysis module, a commodity function checking module, a commodity logistics receiving module, a commodity parameter analysis module, a cloud analysis server, an artificial communication module and a cloud database;
the cloud analysis server is respectively connected with the video acquisition module, the image analysis module, the commodity function verification module, the commodity parameter analysis module and the cloud database, the video processing module is respectively connected with the video acquisition module and the image analysis module, the commodity logistics receiving module is respectively connected with the commodity function verification module and the commodity parameter analysis module, the manual communication module is connected with the commodity function verification module, and the cloud database is connected with the commodity parameter analysis module;
the video acquisition module is used for carrying out video acquisition on returned goods in a returned order in the E-commerce platform, acquiring related videos of the returned goods in the returned order, and respectively sending the related videos of the returned goods in the acquired returned order to the video processing module and the cloud analysis server;
the video processing module is used for receiving the related video of the returned goods in the returned order sent by the video acquisition module, acquiring each video frame in the related video of the returned goods in the received returned order, identifying the orientation appearance image of the returned goods in each video frame, counting each orientation appearance image of the returned goods, carrying out image segmentation on each orientation appearance image of the returned goods, selecting the minimum area wrapping the returned goods, removing the images outside the minimum area wrapping the returned goods, simultaneously changing the minimum area image wrapping the returned goods into the image with consistent size through geometric normalization processing, carrying out image noise reduction processing and image enhancement processing, and sending each orientation appearance enhancement image of the processed returned goods to the image analysis module;
the image analysis module is used for receiving each orientation appearance enhanced image of the returned goods sent by the video processing module, comparing each orientation appearance enhanced image of the received returned goods with each other, counting the similarity between each orientation appearance enhanced image of the returned goods and other each orientation appearance enhanced images, if the similarity between a certain orientation appearance enhanced image of the returned goods and other certain orientation appearance enhanced images is larger than or equal to a set similarity threshold value, indicating that the orientation appearance enhanced image of the returned goods is similar to other orientation appearance enhanced images, keeping a similar orientation appearance enhanced image, counting each orientation appearance enhanced image of the reserved returned goods, and forming each orientation appearance enhanced image set P (P) of the reserved returned goods1,p2,...,pi,...,pn)，piThe ith orientation appearance enhancement image expressed as the reserved returned commodity is sent to the cloud analysis server;
the cloud analysis server is used for receiving related videos of returned goods in the returned orders sent by the video acquisition module, receiving a set of appearance enhancement images of each position of the returned goods sent by the image analysis module, extracting appearance images of each standard position of the returned goods in the returned orders stored in the cloud database, comparing the appearance enhancement images of each position of the returned goods with the corresponding appearance images of the standard position, counting the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position, and if the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position of the returned goods is larger than or equal to a set matching degree threshold value, indicating that the returned goods are qualified in appearance, and sending the related videos of the returned goods qualified in appearance to the goods function verification module; if the matching degree of the certain-direction appearance enhanced image of the returned commodity and the corresponding standard-direction appearance image is smaller than the set matching degree threshold value, the returned commodity is indicated to be unqualified in appearance, unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are counted, and the unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are sent to the manual communication module;
the commodity function checking module is used for receiving returned commodity relevant videos which are sent by the cloud analysis server and are qualified in appearance, remotely watching the received returned commodity relevant videos through a merchant, checking the main functions of the returned commodities, and sending a logistics receiving instruction to the commodity logistics receiving module if the returned commodities are checked to pass through the main functions; if the main function of the returned goods fails, sending an instruction that the main function of the returned goods fails to pass the verification to the manual communication module;
the commodity logistics receiving module is used for receiving a logistics receiving instruction sent by the commodity function verification module, informing logistics personnel to go to a goods returning party sending address to receive goods returning commodities, and meanwhile, receiving the received goods through the logistics personnelDetecting the volume data, the quantity data and the weight data of returned goods in the returned order, and respectively recording as av,am,agCounting the parameter data of the returned goods in the returned order, and sending the parameter data of the returned goods in the returned order to a goods parameter analysis module;
the goods parameter analysis module is used for receiving each parameter data of returned goods in the returned orders sent by the goods logistics receiving module, extracting each standard parameter data of the returned goods in the returned orders stored in the cloud database, comparing each parameter data of the returned goods in the received returned orders with the corresponding standard parameter data, and obtaining comparison difference values of volume data, quantity data and weight data of the returned goods in the returned orders, wherein the comparison difference values are respectively marked as delta alphav,Δam,ΔagComparing the difference values of the parameter data of the returned commodities in the returned order and sending the parameter data to a cloud analysis server;
the cloud analysis server is used for receiving a comparison difference set of each parameter data of returned commodities in the returned orders sent by the commodity parameter analysis module, extracting standard weight coefficients corresponding to the volume, the quantity and the weight of the returned commodities stored in the cloud database, calculating a conformity degree influence coefficient of the returned commodities in the returned orders, simultaneously extracting a standard conformity degree influence coefficient of the commodities stored in the cloud database and meeting the returned requirements, comparing the calculated conformity degree influence coefficient of the returned commodities in the returned orders with the standard conformity degree influence coefficient of the commodities and meeting the returned requirements, and informing logistics personnel to carry out packaging transportation if the conformity degree influence coefficient of the returned commodities in the returned orders is smaller than or equal to the standard conformity degree influence coefficient, which indicates that the returned commodities meet the returned requirements; if the conformity influence coefficient of the returned goods in the returned order is greater than the standard conformity influence coefficient, which indicates that the returned goods do not meet the returned requirement, sending an instruction that the returned goods do not meet the returned requirement to the manual communication module;
the manual communication module is used for receiving unmatched orientation appearance enhancement images and unmatched orders of returned commodities, which are sent by the cloud analysis server and do not meet the return requirement, receiving orders of main function check failure of the returned commodities, which are sent by the commodity function check module, and carrying out corresponding communication and processing with a return party through a merchant;
the cloud database is used for storing each standard orientation appearance image of returned goods in the returned order, simultaneously storing each standard parameter data of the returned goods in the returned order, storing standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods, and respectively recording the standard weight coefficients as lambdav,λm,λgAnd storing the standard conformity influence coefficient of the goods meeting the return requirement.
In a possible design of the first aspect, the video capture module includes a video camera, and the goods returning party captures a video related to the returned goods in the returned order through the video camera.
In one possible design of the first aspect, the video photographing apparatus includes a mobile phone, a computer camera, or a digital video camera.
In one possible design of the first aspect, the return order includes a return name, a return contact address, a return mailing address, a merchant name, a merchant recipient address, a merchant contact address, and a return item name.
In a possible design of the first aspect, the equation for calculating the impact coefficient of the compliance of the returned goods in the returned order is
Xi is expressed as the influence coefficient of conformity of returned goods in returned order, lambdav,λm,λgRespectively expressed as standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods, and the comparison difference value of each parameter data of the returned goods in the returned order is respectively marked as delta av,Δam,ΔagRespectively expressed as the comparison difference value of returned goods volume data, quantity data and weight data in returned order, a'v,a′m,a′gRespectively expressed as standard volume data, standard quantity data and standard weight data of returned goods in returned order, and e is expressed as natural number and is equal to 2.718。
In a possible design of the first aspect, a greater influence coefficient of the degree of conformance of the returned goods in the returned order indicates that the returned goods are less satisfied with the return requirement.
In a second aspect, the invention further provides a cloud computing verification platform, where the cloud computing verification platform includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected with at least one e-commerce platform goods return order remote verification terminal, the machine-readable storage medium is used for storing programs, instructions, or codes, and the processor is used for executing the programs, instructions, or codes in the machine-readable storage medium to execute the e-commerce platform goods return order remote verification method of the invention.
Has the advantages that:
(1) the E-commerce platform commodity return order remote checking method and the cloud computing checking platform based on artificial intelligence provided by the invention have the advantages that by collecting relevant videos of return commodities in return orders, orientation appearance images of the return commodities in all video frames are identified, similar orientation appearance enhancement images are removed, so that the time and the task amount required by image analysis are reduced, meanwhile, the standard orientation appearance images are compared, whether the appearances of the return commodities are qualified or not is judged, manual communication is carried out on the return commodities with unqualified appearances, the main functions of the return commodities are checked through a remote merchant, after the check is passed, logistics personnel are used for detecting all parameter data of the return commodities, so that the problem that the credit of the return commodities cannot be traced due to commodity damage is avoided, all parties are guaranteed not to be influenced, and meanwhile, the comparison difference values of all parameter data of the return commodities in the return orders are contrasted and analyzed, and reliable reference data are provided for calculating the conformity influence coefficient of the returned goods in the returned order at the later stage.
(2) The method calculates the conformity influence coefficient of the returned commodities in the returned order, judges whether the returned commodities meet the returned requirement, packs and transports if the returned requirement is met, and correspondingly communicates and processes if the returned requirement is not met, thereby saving the human resource cost, improving the commodity returning efficiency of the E-commerce platform, reducing the waiting time of the returned party, meeting the satisfaction and experience of the returned party and further avoiding the problem of loss of users of the E-commerce platform.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the method steps of the present invention;
fig. 2 is a schematic view of a module connection structure according to the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, the remote checking method for the goods return order of the e-commerce platform based on artificial intelligence comprises the following steps:
s1, collecting related videos of returned commodities in the returned orders, identifying orientation appearance images of the returned commodities in all video frames, and removing similar orientation appearance enhancement images;
s2, comparing the standard orientation appearance images, judging whether the appearance of the returned goods is qualified, and manually communicating the returned goods with unqualified appearance;
s3, remotely checking the main functions of the returned commodities through a merchant, and detecting each parameter data of the returned commodities through logistics personnel after the checking is passed;
s4, comparing and analyzing the parameter data of returned goods in the returned order, and calculating the conformity influence coefficient of the returned goods in the returned order;
s5, judging whether the returned goods meet the return requirements, if so, packing and transporting, and if not, performing corresponding communication and processing;
the E-commerce platform commodity return order remote checking method based on artificial intelligence uses an E-commerce platform commodity return order remote checking system based on artificial intelligence, and comprises a video acquisition module, a video processing module, an image analysis module, a commodity function checking module, a commodity logistics receiving module, a commodity parameter analysis module, a cloud analysis server, an artificial communication module and a cloud database.
The cloud analysis server is respectively connected with the video acquisition module, the image analysis module, the commodity function verification module, the commodity parameter analysis module and the cloud database, the video processing module is respectively connected with the video acquisition module and the image analysis module, the commodity logistics receiving module is respectively connected with the commodity function verification module and the commodity parameter analysis module, the manual communication module is connected with the commodity function verification module, and the cloud database is connected with the commodity parameter analysis module.
The system comprises a video acquisition module, a cloud analysis server and a video processing module, wherein the video acquisition module comprises video photographing equipment, the video photographing equipment comprises a mobile phone, a computer camera or a digital camera and is used for carrying out video acquisition on returned goods in a returned order in an e-commerce platform, a goods returning party acquires related videos of the returned goods in the returned order through the video photographing equipment and sends the related videos of the returned goods in the acquired returned order to the video processing module and the cloud analysis server respectively;
the video processing module is used for receiving videos related to returned goods in the returned orders sent by the video acquisition module, acquiring video frames in the videos related to the returned goods in the received returned orders, identifying orientation appearance images of the returned goods in the video frames, counting the orientation appearance images of the returned goods, performing image segmentation on the orientation appearance images of the returned goods, selecting a minimum area wrapping the returned goods, removing images outside the minimum area wrapping the returned goods, changing the minimum area image wrapping the returned goods into images with consistent size through geometric normalization processing, performing image noise reduction processing and image enhancement processing, and sending the orientation appearance enhancement images of the processed returned goods to the image analysis module.
The image analysis module is used for receiving each azimuth appearance enhanced image of the returned goods sent by the video processing module, comparing the received each azimuth appearance enhanced images of the returned goods with each other, counting the similarity between each azimuth appearance enhanced image of the returned goods and each other azimuth appearance enhanced image, if the similarity between a certain azimuth appearance enhanced image of the returned goods and each other azimuth appearance enhanced image is larger than or equal to a set similarity threshold value, indicating that the azimuth appearance enhanced image of the returned goods is similar to each other azimuth appearance enhanced image, keeping a similar azimuth appearance enhanced image, thus, the time and the amount of tasks required for image analysis are reduced, and the orientation enhancement images of the retained returned products are counted to form an orientation enhancement image set P (P) of the retained returned products.1,p2,...,pi,...,pn)，piAnd sending the ith orientation appearance enhanced image represented as the reserved returned commodity to the cloud analysis server.
The cloud analysis server is used for receiving related videos of returned goods in the returned orders sent by the video acquisition module, receiving a set of appearance enhancement images of each position of the returned goods sent by the image analysis module, extracting appearance images of each standard position of the returned goods in the returned orders stored in the cloud database, comparing the appearance enhancement images of each position of the returned goods with the corresponding appearance images of the standard position, counting the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position, and if the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position of the returned goods is larger than or equal to a set matching degree threshold value, indicating that the returned goods are qualified in appearance, and sending the related videos of the returned goods qualified in appearance to the goods function verification module; and if the matching degree of the certain-direction appearance enhanced image of the returned commodity and the corresponding standard-direction appearance image is smaller than the set matching degree threshold value, the appearance of the returned commodity is unqualified, the unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are counted, and the unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are sent to the manual communication module.
The commodity function checking module is used for receiving returned commodity relevant videos which are sent by the cloud analysis server and are qualified in appearance, remotely watching the received returned commodity relevant videos through a merchant, checking the main functions of the returned commodities, and sending a logistics receiving instruction to the commodity logistics receiving module if the returned commodities are checked to pass through the main functions; and if the main function of the returned commodity fails to be checked, sending an instruction that the main function of the returned commodity fails to be checked to the manual communication module.
The commodity logistics receiving module is used for receiving a logistics receiving instruction sent by the commodity function verification module, informing logistics personnel of sending a goods returning address to receive goods returning commodities, and detecting volume data, quantity data and weight data of the goods returning in a received goods returning order through the logistics personnel, wherein the volume data, the quantity data and the weight data are respectively marked as av,am,agTherefore, the problem that responsibility cannot be traced due to the fact that goods are damaged when returned goods are delivered is avoided, credit of each party is not affected, parameter data of the returned goods in the returned order are counted, and the parameter data of the returned goods in the returned order are sent to the goods parameter analysis module.
The goods parameter analysis module is used for receiving each parameter data of returned goods in the returned orders sent by the goods logistics receiving module, extracting each standard parameter data of the returned goods in the returned orders stored in the cloud database, comparing each parameter data of the returned goods in the received returned orders with the corresponding standard parameter data, and obtaining comparison difference values of volume data, quantity data and weight data of the returned goods in the returned orders, wherein the comparison difference values are respectively marked as delta alphav,Δam,ΔagAnd reliable reference data are provided for calculating the conformity influence coefficient of the returned goods in the returned order at the later stage, and the parameter data of the returned goods in the returned order are compared with the difference value and sent to the cloud analysis server.
The cloud analysis server is used for receiving parameter data comparison difference value sets of returned commodities in the returned orders sent by the commodity parameter analysis module, extracting standard weight coefficients corresponding to the volume, the quantity and the weight of the returned commodities stored in the cloud database, and calculating the conformity influence coefficient of the returned commodities in the returned orders, wherein the conformity influence coefficient calculation formula of the returned commodities in the returned orders is
Xi is expressed as the influence coefficient of conformity of returned goods in returned order, lambdav,λm,λgRespectively expressed as standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods, and the comparison difference value of each parameter data of the returned goods in the returned order is respectively marked as delta av,Δam,ΔagRespectively expressed as the comparison difference value of returned goods volume data, quantity data and weight data in returned order, a'v,a′m,a′gRespectively representing standard volume data, standard quantity data and standard weight data of returned goods in the returned order, wherein e represents a natural number which is equal to 2.718, simultaneously extracting a standard conformity degree influence coefficient of goods which are stored in a cloud database and meet the returned requirement, comparing the calculated conformity degree influence coefficient of the returned goods in the returned order with the standard conformity degree influence coefficient of the goods which meet the returned requirement, and informing logistics personnel to carry out packaging transportation if the conformity degree influence coefficient of the returned goods in the returned order is less than or equal to the standard conformity degree influence coefficient, which indicates that the returned goods meet the returned requirement; if the influence coefficient of the conformity of the returned goods in the returned order is greater than the influence coefficient of the standard conformity, which indicates that the returned goods do not meet the returned requirement, an instruction that the returned goods do not meet the returned requirement is sent to the manual communication module.
The larger the conformity influence coefficient of the returned goods in the returned order is, the more the returned goods do not meet the returned requirement.
The manual communication module is used for receiving unmatched orientation appearance enhancement images and the orders that returned commodities can not meet the return requirement in the returned commodities with unqualified appearances sent by the cloud analysis server, receiving the orders that main function check of the returned commodities sent by the commodity function check module can not pass, and performing corresponding communication and processing with the returned commodities through merchants, so that the human resource cost is saved, the commodity return efficiency of the e-commerce platform is improved, the waiting time of the returned commodities is reduced, the satisfaction and experience of the returned commodities are met, and the problem that users of the e-commerce platform run off is avoided.
The cloud database is used for storing each standard orientation appearance image of returned goods in the returned goods order, and simultaneously storing each standard parameter data of the returned goods in the returned goods order, wherein the returned goods order comprises a name of a returned goods party, a contact way of the returned goods party, a sending address of the returned goods party, a name of a merchant, an receiving address of the merchant, a contact way of the merchant and a name of the returned goods, and standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods are stored and are respectively marked as lambdav,λm,λgAnd storing the standard conformity influence coefficient of the goods meeting the return requirement.
In a second aspect, the invention further provides a cloud computing verification platform, where the cloud computing verification platform includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected with at least one e-commerce platform goods return order remote verification terminal, the machine-readable storage medium is used for storing programs, instructions, or codes, and the processor is used for executing the programs, instructions, or codes in the machine-readable storage medium to execute the e-commerce platform goods return order remote verification method of the invention.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
Claims (7)
1. E-commerce platform commodity return order remote verification method based on artificial intelligence is characterized by comprising the following steps: the method comprises the following steps:
s1, collecting related videos of returned commodities in the returned orders, identifying orientation appearance images of the returned commodities in all video frames, and removing similar orientation appearance enhancement images;
s2, comparing the standard orientation appearance images, judging whether the appearance of the returned goods is qualified, and manually communicating the returned goods with unqualified appearance;
s3, remotely checking the main functions of the returned commodities through a merchant, and detecting each parameter data of the returned commodities through logistics personnel after the checking is passed;
s4, comparing and analyzing the parameter data of returned goods in the returned order, and calculating the conformity influence coefficient of the returned goods in the returned order;
s5, judging whether the returned goods meet the return requirements, if so, packing and transporting, and if not, performing corresponding communication and processing;
the E-commerce platform commodity return order remote checking method based on artificial intelligence uses an E-commerce platform commodity return order remote checking system based on artificial intelligence, and comprises a video acquisition module, a video processing module, an image analysis module, a commodity function checking module, a commodity logistics receiving module, a commodity parameter analysis module, a cloud analysis server, an artificial communication module and a cloud database;
the cloud analysis server is respectively connected with the video acquisition module, the image analysis module, the commodity function verification module, the commodity parameter analysis module and the cloud database, the video processing module is respectively connected with the video acquisition module and the image analysis module, the commodity logistics receiving module is respectively connected with the commodity function verification module and the commodity parameter analysis module, the manual communication module is connected with the commodity function verification module, and the cloud database is connected with the commodity parameter analysis module;
the video acquisition module is used for carrying out video acquisition on returned goods in a returned order in the E-commerce platform, acquiring related videos of the returned goods in the returned order, and respectively sending the related videos of the returned goods in the acquired returned order to the video processing module and the cloud analysis server;
the video processing module is used for receiving the related video of the returned goods in the returned order sent by the video acquisition module, acquiring each video frame in the related video of the returned goods in the received returned order, identifying the orientation appearance image of the returned goods in each video frame, counting each orientation appearance image of the returned goods, carrying out image segmentation on each orientation appearance image of the returned goods, selecting the minimum area wrapping the returned goods, removing the images outside the minimum area wrapping the returned goods, simultaneously changing the minimum area image wrapping the returned goods into the image with consistent size through geometric normalization processing, carrying out image noise reduction processing and image enhancement processing, and sending each orientation appearance enhancement image of the processed returned goods to the image analysis module;
the image analysis module is used for receiving each orientation appearance enhanced image of the returned goods sent by the video processing module, comparing each orientation appearance enhanced image of the received returned goods with each other, counting the similarity between each orientation appearance enhanced image of the returned goods and other each orientation appearance enhanced images, if the similarity between a certain orientation appearance enhanced image of the returned goods and other certain orientation appearance enhanced images is larger than or equal to a set similarity threshold value, indicating that the orientation appearance enhanced image of the returned goods is similar to other orientation appearance enhanced images, keeping a similar orientation appearance enhanced image, counting each orientation appearance enhanced image of the reserved returned goods, and forming each orientation appearance enhanced image set P (P) of the reserved returned goods1,p2,...,pi,...,pn)，piThe ith orientation enhanced image of the reserved returned goods is displayed as the enhanced image of the orientation of the reserved returned goodsThe collection is sent to a cloud analysis server;
the cloud analysis server is used for receiving related videos of returned goods in the returned orders sent by the video acquisition module, receiving a set of appearance enhancement images of each position of the returned goods sent by the image analysis module, extracting appearance images of each standard position of the returned goods in the returned orders stored in the cloud database, comparing the appearance enhancement images of each position of the returned goods with the corresponding appearance images of the standard position, counting the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position, and if the matching degree of the appearance enhancement images of each position of the returned goods and the corresponding appearance images of the standard position of the returned goods is larger than or equal to a set matching degree threshold value, indicating that the returned goods are qualified in appearance, and sending the related videos of the returned goods qualified in appearance to the goods function verification module; if the matching degree of the certain-direction appearance enhanced image of the returned commodity and the corresponding standard-direction appearance image is smaller than the set matching degree threshold value, the returned commodity is indicated to be unqualified in appearance, unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are counted, and the unmatched various-direction appearance enhanced images in the returned commodity with unqualified appearance are sent to the manual communication module;
the commodity function checking module is used for receiving returned commodity relevant videos which are sent by the cloud analysis server and are qualified in appearance, remotely watching the received returned commodity relevant videos through a merchant, checking the main functions of the returned commodities, and sending a logistics receiving instruction to the commodity logistics receiving module if the returned commodities are checked to pass through the main functions; if the main function of the returned goods fails, sending an instruction that the main function of the returned goods fails to pass the verification to the manual communication module;
the commodity logistics receiving module is used for receiving a logistics receiving instruction sent by the commodity function verification module, informing logistics personnel of sending a goods returning address to receive goods returning commodities, and detecting volume data, quantity data and weight data of the goods returning in a received goods returning order through the logistics personnel, wherein the volume data, the quantity data and the weight data are respectively marked as av,am,agCounting return ordersSending each parameter data of the returned goods in the returned order to a goods parameter analysis module;
the goods parameter analysis module is used for receiving each parameter data of returned goods in the returned orders sent by the goods logistics receiving module, extracting each standard parameter data of the returned goods in the returned orders stored in the cloud database, comparing each parameter data of the returned goods in the received returned orders with the corresponding standard parameter data, and obtaining comparison difference values of volume data, quantity data and weight data of the returned goods in the returned orders, wherein the comparison difference values are respectively marked as delta alphav,Δam,ΔagComparing the difference values of the parameter data of the returned commodities in the returned order and sending the parameter data to a cloud analysis server;
the cloud analysis server is used for receiving a comparison difference set of each parameter data of returned commodities in the returned orders sent by the commodity parameter analysis module, extracting standard weight coefficients corresponding to the volume, the quantity and the weight of the returned commodities stored in the cloud database, calculating a conformity degree influence coefficient of the returned commodities in the returned orders, simultaneously extracting a standard conformity degree influence coefficient of the commodities stored in the cloud database and meeting the returned requirements, comparing the calculated conformity degree influence coefficient of the returned commodities in the returned orders with the standard conformity degree influence coefficient of the commodities and meeting the returned requirements, and informing logistics personnel to carry out packaging transportation if the conformity degree influence coefficient of the returned commodities in the returned orders is smaller than or equal to the standard conformity degree influence coefficient, which indicates that the returned commodities meet the returned requirements; if the conformity influence coefficient of the returned goods in the returned order is greater than the standard conformity influence coefficient, which indicates that the returned goods do not meet the returned requirement, sending an instruction that the returned goods do not meet the returned requirement to the manual communication module;
the manual communication module is used for receiving unmatched orientation appearance enhancement images and unmatched orders of returned commodities, which are sent by the cloud analysis server and do not meet the return requirement, receiving orders of main function check failure of the returned commodities, which are sent by the commodity function check module, and carrying out corresponding communication and processing with a return party through a merchant;
the cloud database is used for storing each standard orientation appearance image of returned goods in the returned order, simultaneously storing each standard parameter data of the returned goods in the returned order, storing standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods, and respectively recording the standard weight coefficients as lambdav,λm,λgAnd storing the standard conformity influence coefficient of the goods meeting the return requirement.
2. The remote checking method for goods return orders based on artificial intelligence electronic commerce platform as claimed in claim 1, wherein: the video acquisition module comprises video photographing equipment, and the goods returning party acquires related videos of goods returned in the goods returning order through the video photographing equipment.
3. The remote checking method for goods return orders based on artificial intelligence electronic commerce platform as claimed in claim 2, wherein: the video photographing equipment comprises a mobile phone, a computer camera or a digital video camera.
4. The remote checking method for goods return orders based on artificial intelligence electronic commerce platform as claimed in claim 1, wherein: the goods return order comprises a goods return name, a goods return contact mode, a goods return sending address, a merchant name, a merchant receiving address, a merchant contact mode and a goods return name.
5. The remote checking method for goods return orders based on artificial intelligence electronic commerce platform as claimed in claim 1, wherein: the calculation formula of the conformity influence coefficient of the returned goods in the returned order is
Xi is expressed as the influence coefficient of conformity of returned goods in returned order, lambdav,λm,λgRespectively expressed as standard weight coefficients corresponding to the volume, the quantity and the weight of the returned goods, and the comparison difference value of each parameter data of the returned goods in the returned orderIs denoted by Δ av,Δam,ΔagRespectively expressed as the comparison difference value of returned goods volume data, quantity data and weight data in returned order, a'v,a′m,a′gRespectively, as standard volume data, standard quantity data and standard weight data of returned goods in the returned order, and e is expressed as a natural number, equal to 2.718.
6. The remote checking method for goods return orders based on artificial intelligence electronic commerce platform as claimed in claim 1, wherein: the larger the conformity influence coefficient of the returned goods in the returned order is, the more the returned goods do not meet the returned requirement.
7. A cloud computing verification platform is characterized in that: the cloud computing checking platform comprises a processor, a machine readable storage medium and a network interface, wherein the machine readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one E-commerce platform goods return order remote checking terminal, the machine readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine readable storage medium so as to execute the E-commerce platform goods return order remote checking method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011570729.4A CN112561662A (en) | 2020-12-26 | 2020-12-26 | E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011570729.4A CN112561662A (en) | 2020-12-26 | 2020-12-26 | E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561662A true CN112561662A (en) | 2021-03-26 |
Family
ID=75033320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011570729.4A Withdrawn CN112561662A (en) | 2020-12-26 | 2020-12-26 | E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561662A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674005A (en) * | 2021-08-26 | 2021-11-19 | 连尚(北京)网络科技有限公司 | Method, apparatus, medium, and program product for processing returned items |
| CN114358479A (en) * | 2021-11-27 | 2022-04-15 | 杭州拼便宜网络科技有限公司 | E-commerce platform return goods remote verification method and device, electronic equipment and storage medium |
| CN114612048A (en) * | 2022-05-09 | 2022-06-10 | 天津外轮理货有限公司 | Container cargo tallying monitoring and analyzing method and storage medium |
| CN115730951A (en) * | 2022-12-10 | 2023-03-03 | 武汉小帆船电子商务有限公司 | Management method, system and storage medium based on community e-commerce operation platform |
| CN115879855A (en) * | 2022-12-12 | 2023-03-31 | 泉州市融兴信息科技有限公司 | Order data analysis system and method based on ERP management system |
-
2020
- 2020-12-26 CN CN202011570729.4A patent/CN112561662A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674005A (en) * | 2021-08-26 | 2021-11-19 | 连尚(北京)网络科技有限公司 | Method, apparatus, medium, and program product for processing returned items |
| CN113674005B (en) * | 2021-08-26 | 2024-02-13 | 连尚(北京)网络科技有限公司 | Method, apparatus, medium and program product for handling return items |
| CN114358479A (en) * | 2021-11-27 | 2022-04-15 | 杭州拼便宜网络科技有限公司 | E-commerce platform return goods remote verification method and device, electronic equipment and storage medium |
| CN114612048A (en) * | 2022-05-09 | 2022-06-10 | 天津外轮理货有限公司 | Container cargo tallying monitoring and analyzing method and storage medium |
| CN114612048B (en) * | 2022-05-09 | 2022-08-05 | 天津外轮理货有限公司 | Container cargo tallying monitoring and analyzing method and storage medium |
| CN115730951A (en) * | 2022-12-10 | 2023-03-03 | 武汉小帆船电子商务有限公司 | Management method, system and storage medium based on community e-commerce operation platform |
| CN115730951B (en) * | 2022-12-10 | 2024-01-05 | 长沙海商网络技术有限公司 | Management method, system and storage medium based on community e-commerce operation platform |
| CN115879855A (en) * | 2022-12-12 | 2023-03-31 | 泉州市融兴信息科技有限公司 | Order data analysis system and method based on ERP management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112561662A (en) | E-commerce platform commodity return order remote verification method based on artificial intelligence and cloud computing verification platform | |
| CN108229322B (en) | Video-based face recognition method and device, electronic equipment and storage medium | |
| WO2019015682A1 (en) | Dynamic facial image warehousing method and apparatus, electronic device, medium, and program | |
| CN110738236A (en) | Image matching method and device, computer equipment and storage medium | |
| CN112561543A (en) | E-commerce platform false transaction order monitoring method and system based on full-period logistics data analysis and cloud server | |
| CN112257644B (en) | Intelligent management system for commodity inventory of electronic commerce platform stores based on cloud computing | |
| CN110827432B (en) | Class attendance checking method and system based on face recognition | |
| CN111639970A (en) | Method for determining price of article based on image recognition and related equipment | |
| CN111597933A (en) | Face recognition method and device | |
| CN111461101A (en) | Method, device and equipment for identifying work clothes mark and storage medium | |
| CN115311632A (en) | Vehicle weight recognition method and device based on multiple cameras | |
| CN111369317B (en) | Order generation method, order generation device, electronic equipment and storage medium | |
| CN114418922A (en) | Tea cake anti-counterfeiting method, tea cake anti-counterfeiting system and cloud server | |
| CN115861210A (en) | Transformer substation equipment abnormity detection method and system based on twin network | |
| CN117151595A (en) | Commodity inventory management method, equipment and storage medium | |
| CN114610768A (en) | Cross-border commodity information processing method and device | |
| CN114455255A (en) | Abnormal cigarette sorting error detection method based on multi-feature recognition | |
| CN111860358B (en) | Material acceptance method based on industrial internet | |
| CN112906592A (en) | Passenger flow volume analysis method and system and electronic equipment | |
| CN115620235A (en) | Parcel reinspection method, device, equipment and storage medium | |
| CN112598068B (en) | Loan application verification method, device and equipment | |
| CN111797922B (en) | Text image classification method and device | |
| CN113421041A (en) | Self-operated warehouse commodity intelligent management method based on electronic commerce platform transaction and cloud management platform | |
| CN113674050A (en) | Chinese-medicinal material electronic commerce transaction system based on big data and thing networking | |
| CN113160414A (en) | Automatic identification method and device for remaining amount of goods, electronic equipment and computer readable medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210326 |
|
| WW01 | Invention patent application withdrawn after publication |