WO2020233076A1 - 基于身份验证的物品入库方法、装置、设备及存储介质 - Google Patents

基于身份验证的物品入库方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2020233076A1
WO2020233076A1 PCT/CN2019/122321 CN2019122321W WO2020233076A1 WO 2020233076 A1 WO2020233076 A1 WO 2020233076A1 CN 2019122321 W CN2019122321 W CN 2019122321W WO 2020233076 A1 WO2020233076 A1 WO 2020233076A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
purchaser
identity
inbound
audio
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.)
Ceased
Application number
PCT/CN2019/122321
Other languages
English (en)
French (fr)
Inventor
韩亚洲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Publication of WO2020233076A1 publication Critical patent/WO2020233076A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31User authentication
    • G06F21/32User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/08Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083Shipping
    • G06Q10/0831Overseas transactions
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/08Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/28Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/30Noise filtering
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/62Text, e.g. of license plates, overlay texts or captions on TV images
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition

Definitions

  • This application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for warehousing items based on identity verification.
  • the existing spot check method requires the customs staff to manually verify the buyer's identity information, and only after the verification is successful, will the incoming mail items be stored in the warehouse, so the storage efficiency is relatively low.
  • the main purpose of this application is to provide a method, device, equipment, and storage medium for warehousing items based on identity verification, which aims to improve the inspection efficiency of inbound postal items, so as to achieve rapid inspection of all inbound postal items, and Ensure the accuracy of the inspection results.
  • this application provides a method for warehousing items based on identity verification.
  • the method includes the following steps:
  • the reserved identity information is compared with the real identity information, and if the reserved identity information matches the real identity information, the inbound postal item is put into the warehouse.
  • an identity verification-based article storage device which includes:
  • the extraction module is used to obtain the item information of the inbound postal items, and extract the buyer's contact information and reserved identity information from the item information;
  • a sending module configured to use the contact information to issue an identity authentication notification to the purchaser, so as to obtain audio and video information containing the biometric information of the purchaser;
  • a determining module configured to receive the audio and video information, extract the biometric information of the buyer from the audio and video information, and determine the real identity information of the buyer according to the biometric information;
  • the comparison module is used to compare the reserved identity information with the real identity information, and if the reserved identity information matches the real identity information, the inbound postal item is put into the warehouse.
  • this application also proposes an identity verification-based article storage device, the device includes: a memory, a processor, and a computer readable that is stored on the memory and can be executed by the processor Instructions, wherein when the computer-readable instructions are executed by the processor, the steps of the method for warehousing items based on identity verification as described above are realized.
  • this application also proposes a computer-readable storage medium with computer-readable instructions stored on the computer-readable storage medium.
  • the computer-readable instructions are executed by a processor, the implementation is as described above.
  • FIG. 1 is a schematic structural diagram of an identity verification-based item storage device in a hardware operating environment involved in a solution of an embodiment of the present application;
  • FIG. 2 is a schematic flowchart of the first embodiment of the method for warehousing items based on identity verification according to this application;
  • step S40 is a schematic diagram of a specific implementation process of step S40 in the first embodiment of the method for warehousing items based on identity verification according to this application;
  • FIG. 4 is a schematic flowchart of a second embodiment of a method for warehousing items based on identity verification according to this application;
  • Fig. 5 is a structural block diagram of a first embodiment of an article storage device based on identity verification in this application.
  • FIG. 1 is a schematic structural diagram of an identity verification-based article storage device in a hardware operating environment involved in a solution of an embodiment of the application.
  • the identity verification-based item storage device may include a processor 1001, such as a central processing unit (Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface).
  • WIreless-FIdelity WI-FI
  • the memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, can also be a stable non-volatile memory (Non-Volatile Memory, NVM), such as disk storage.
  • RAM Random Access Memory
  • NVM Non-Volatile Memory
  • the memory 1005 may also be a storage device independent of the foregoing processor 1001.
  • FIG. 1 does not constitute a limitation on the storage device for items based on identity verification, and may include more or less components than shown, or combine certain components, or different The layout of the components.
  • a memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and computer-readable instructions.
  • the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with users; the warehousing of items based on identity verification in this application
  • the processor 1001 and the memory 1005 in the device may be set in an item warehousing device based on identity verification.
  • the item warehousing device based on identity verification calls the computer-readable instructions stored in the memory 1005 through the processor 1001, and executes this The method for warehousing items based on identity verification provided in the application embodiment.
  • FIG. 2 is a schematic flowchart of a first embodiment of a method for warehousing an item based on identity verification according to this application.
  • the method for warehousing items based on identity verification includes the following steps:
  • Step S10 Obtain the item information of the inbound postal item, and extract the buyer's contact information and reserved identity information from the item information.
  • the execution subject in this embodiment is a pre-built system for checking inbound postal items.
  • the system can be deployed on the customs server provided for the customs office, and cooperate with the corresponding collection equipment (such as a camera) to realize the collection of item information of inbound postal items, so that the inspection system can perform follow-up Authentication operation.
  • the contact information mentioned in this embodiment is usually the mobile phone number of the purchaser; the reserved identity information is usually the ID number of the purchaser sent and the user name.
  • the ID number is relatively private, in order to avoid revealing the ID number reserved by the purchaser, the ID number is usually converted into other forms of identification codes, such as QR codes or barcodes. Wait for the image identification code. Then, the image identification code is scanned by a code scanner or other scanning equipment, and the ID number carried in the image identification code is identified.
  • the item information of the inbound postal items is usually recorded in the paper order pasted on the outer packaging of the inbound postal items, so in order to be able to quickly and accurately
  • optical character recognition Optical Character Recognition
  • Character Recognition OCR
  • OCR Character Recognition
  • the logistics company will paste the logistics list on the packaging bag or box of the item, and the logistics list usually fills in the name of the recipient (that is, the buyer's name in this embodiment). Name), recipient address, recipient phone number, name of purchased items, quantity and other information.
  • optical character recognition Optical Character Recognition
  • OCR optical Character Recognition
  • electronic devices such as scanners or digital cameras
  • OCR optical Character Recognition
  • determine their shapes by detecting dark and light patterns and then use character recognition methods to translate the shapes into computer text. That is, for printed characters, the text in a paper document is optically converted into a black and white dot matrix image file, and the text in the image is converted into a text format through recognition software for further editing and processing by word processing software .
  • the following operations may also be performed first: Perform image preprocessing operations on the electronic picture, such as grayscale processing, binarization processing, noise reduction, etc., to obtain the electronic picture to be recognized; then, use OCR technology to perform optical character recognition on the electronic picture to be recognized To determine the computer text corresponding to each character in the electronic picture.
  • image preprocessing operations such as grayscale processing, binarization processing, noise reduction, etc.
  • this embodiment provides a specific image preprocessing method, and the specific implementation process is roughly as follows:
  • RGBColor images have formats such as BMP and JPG, and their color representations mostly use three-dimensional vectors in the RGB color space.
  • Each pixel is described by a ternary component with a value ranging from 0 to 255.
  • the size of the data represents the value of the primary color, and is finally represented by a mixture of three primary colors.
  • the grayscale image is through the grayscale Gray Level represents, so the conversion process can be understood as a projection operation from a three-dimensional vector to a one-dimensional vector.
  • the commonly used gray-scale processing methods include the maximum value method, that is, the largest value among the three primary colors of R, G, and B is selected as the gray value.
  • the gray processing method Specifically, the three primary colors are summed according to different proportions (weights), and then projected into a one-dimensional space.
  • the gray-scale processed image will have a blurred background, which will cause greater interference to the text device. Therefore, it is necessary to perform binarization processing on the grayscale image to remove these interferences, so that the processed result forms a binary image with only the form of 0 and 1 for computer recognition and processing.
  • the binary image (Binary Image), specifically refers to the fact that each pixel on the image has only two possible values or gray levels. People often use black and white, B&W, and monochrome images to represent binary images. In other words, any pixel in the binary image is either 0 or 1, and there is no other transitional gray value.
  • the binary image obtained after the binarization process is a picture with black characters on a white background (the corresponding digital matrix is only composed of 0 and 1)
  • black characters on a white background There are often some interfering pixels in the picture, for example, a few white pixels in a pile of dense black pixels, or a few black pixels in a pile of white pixels.
  • these few white pixels and black pixels will not affect the overall content of the image, they will affect the extraction of the main features. Therefore, in order to ensure the accuracy of the contour features of the subsequently extracted characters, the two values obtained by the binarization process need to be processed.
  • the value image undergoes noise reduction processing to realize the conversion of a few white pixels in a bunch of dense black pixels into black pixels, or a few black pixels in a bunch of dense white pixels into white pixels.
  • this embodiment provides a specific implementation manner, which is roughly as follows:
  • the RGB color value corresponding to any pixel in the binary image is either black or white.
  • the RGB color value of the current pixel traversed is (255, 255, 255), it indicates that the current pixel is a white pixel; if the RGB color value of the current pixel traversed is (0, 0, 0), it means that the current pixel is a black pixel.
  • the preset area is an area determined by using the position corresponding to the current pixel as the center of the circle and the preset length as the radius.
  • the first threshold number mentioned here may be 8.
  • C3 Obtain the RGB color value of each reference pixel respectively, and determine the color of the corresponding reference pixel according to the RGB color value of each reference pixel, and the color is black or white.
  • (C4) Classify each reference pixel according to the color of each reference pixel to obtain a set of black pixels and a set of white pixels.
  • the second threshold number is preferably set to be greater than half of the first threshold number.
  • the second threshold number is preferably greater than or equal to 5, and an integer less than 8, such as 5, 6, or 7.
  • the RGB color value corresponding to the current pixel is converted to the RGB color value corresponding to the black pixel, and the binary value Image noise reduction processing to obtain the electronic picture to be recognized; if the number of white pixels is greater than the second threshold number, the RGB color value corresponding to the current pixel is converted to the corresponding white pixel.
  • the RGB color values of, the noise reduction processing of the binary picture is completed, and the electronic picture to be recognized is obtained.
  • optical character recognition technology to perform optical character recognition on the electronic picture to determine the computer text corresponding to each character in the electronic picture is specifically as follows:
  • templates stored in the aforementioned pre-built feature template library mainly record contour features of different characters.
  • contour feature of each known character in the template corresponds to a certain computer text.
  • the computer text corresponding to the current character can be determined.
  • the inbound postal items are sequentially placed on a conveyor (such as a conveyor belt) equipped with image capture equipment (such as a camera), so that the inbound postal items are in the process of being transferred. It will be photographed on the paper order information pasted on the inbound postal items.
  • a conveyor such as a conveyor belt
  • image capture equipment such as a camera
  • the image acquisition device transmits the collected paper order information corresponding to the electronic pictures of each inbound postal item to the inspection system in this embodiment, and the inspection system performs processing in accordance with the above-mentioned steps, which can quickly and accurately Extract the item information of each inbound postal item.
  • image collection equipment can be set around the transmission device, and
  • the conveyor belt for placing inbound postal items can be made of transparent material, so that no matter which direction the paper order information pasted on the inbound postal items is located, the paper order information can be captured when passing through the collection area to obtain the paper The electronic picture corresponding to the quality order information.
  • the inspection system may obtain the ID number of the purchaser by identifying the image identification code on the photographed electronic picture.
  • Step S20 using the contact method to issue an identity authentication notification to the purchaser, so as to obtain audio and video information containing the biometric information of the purchaser.
  • the identity authentication notification issued to the purchase in this embodiment is specifically issued in the form of a short message to the corresponding mobile phone number installed.
  • the identity authentication notification issued to the purchase in this embodiment is specifically issued in the form of a short message to the corresponding mobile phone number installed.
  • the user terminal of the mobile phone card In the user terminal of the mobile phone card.
  • the purchaser's biometric information can be collected.
  • the identity verification notice issued to the purchaser is specifically It carries a uniform resource locator (Uniform Resource Locator, URL), so that after receiving the identity authentication notification, the purchaser directly clicks on the URL to display a biometric collection interface on the user terminal.
  • URL Uniform Resource Locator
  • step S20 above can be specifically refined into the following two steps:
  • the URL is sent to the reserved mobile phone number of the purchaser by means of short messages.
  • the URL can be sent by mail or instant messaging.
  • the URL is sent to the user terminal logging in the mailbox or instant messaging account.
  • a biometric information collection interface pops up on the user interface of the user terminal that receives the uniform resource locator to record the biological information of the purchaser.
  • the audio and video information of the feature information are included in the uniform resource locator.
  • biometric information collection interface is based on Hyper Text Markup Language (Hyper Text Markup Language). Language, HTML) pre-compiled.
  • HTML Hyper Text Markup Language
  • HTML Hyper Text Markup Language
  • the fifth development version of HTML which is commonly referred to as H5, is preferred.
  • H5 has the characteristics of simplicity, extensibility, platform independence, versatility, portability, etc., no matter what system the mobile terminal used by the buyer is, the developer can develop the above-mentioned biometric information through one development
  • the interface realizes the use of multiple platforms, which not only facilitates the operation of buyers, but also greatly simplifies the workload of developers.
  • Step S30 Receive the audio and video information, extract the buyer's biometric information from the audio and video information, and determine the buyer's true identity information based on the biometric information.
  • biometric information that can identify the buyer's identity, such as facial feature information, iris feature information, voiceprint feature information, etc. Therefore, all the information is extracted from the audio and video information.
  • a suitable biometric information extraction model can be selected according to the preset type of biometric information to be extracted, and the biometric information of the purchaser can be extracted from the audio and video information. .
  • biometric information that needs to be extracted is facial feature information or voiceprint feature information as an example
  • the operation of extracting the buyer's biometric information from the audio and video information is specifically described:
  • the extracted biological feature information is facial feature information
  • the buyer’s facial feature information can be extracted from the audio and video information, and the extracted facial feature information
  • the characteristic information serves as the biological characteristic information.
  • the extracted biological feature information is voiceprint feature information
  • the buyer’s voiceprint feature information can be extracted from the audio and video information, and the extracted The obtained voiceprint feature information is used as the biological feature information.
  • the audio and video information containing the biometric information specifically, live detection technology can be used, that is, the content that needs to be read by the buyer is randomly displayed on the above biometric collection interface, so that the buyer reads the random
  • live detection technology can be used, that is, the content that needs to be read by the buyer is randomly displayed on the above biometric collection interface, so that the buyer reads the random
  • video information and voice information containing the facial image of the purchaser are recorded, and audio and video information containing the biometric information of the purchaser is obtained.
  • the biological characteristic information extraction model of sum is selected, and the required biological characteristic information is extracted from the audio and video information.
  • the contact method is used to issue an identity authentication notice carrying the address for collecting facial feature information to the purchaser.
  • the video information needs to include the purchaser's facial image.
  • facial feature extraction is performed on the facial image in the video information to obtain the facial feature information of the purchaser.
  • the facial feature information extraction model may be specifically obtained by using a convolutional neural network algorithm to train the facial feature information in the face sample data obtained in advance.
  • the method of constructing the facial feature information extraction model can be roughly as follows:
  • a training model is constructed according to the facial feature information in the face sample data.
  • the training model is trained until a certain face image data is input, and the desired face feature information can be obtained, then the training of the training model can be completed.
  • the training model at this moment is the facial feature information extraction model.
  • the convolution kernel in the training model is a convolution kernel of size
  • the convolution kernel in order to increase the network depth of the training model and at the same time increase the training speed as much as possible, can be split into two Convolution kernel of size.
  • the face sample data can also be normalized to reduce the convolution kernel in each convolution layer and the fully connected layer as the output layer in the training process. The number of nodes to simplify various calculations in the training process.
  • the collected audio and video information needs to include the image information of the buyer's finger. Then, by analyzing and processing the image information of the finger, the fingerprint feature information of the buyer is extracted.
  • the above-mentioned operation of determining the real identity information of the purchaser based on the biometric information it may specifically be the use of big data analysis technology to combine the currently determined biometric information with the biometric information stored in a large database. The information is compared to determine the real identity information of the buyer.
  • biometric information as facial feature information
  • the operation of determining the buyer's identity information based on the biometric information may be roughly as follows:
  • a face feature analysis model can be constructed in advance, and then by inputting the determined face feature information into the face feature analysis model, the face feature analysis model can compare the face feature information with The facial feature information corresponding to a large number of users with known identity information stored in the large database is compared one by one, so as to find out a face feature information with a high similarity to the input facial feature information, and compare the facial feature information.
  • the identity information corresponding to the information serves as the real identity information of the purchaser.
  • this higher similarity can also be compared with the preset
  • the threshold value is compared, and if it is greater than the threshold value, the identity information corresponding to the facial feature information is used as the real identity information of the purchaser.
  • a person skilled in the art can set it as required, for example, set it to 50% or even higher.
  • Step S40 The reserved identity information is compared with the real identity information, and if the reserved identity information matches the real identity information, the inbound postal item is put into the warehouse.
  • the operation of putting the inbound postal item into the warehouse means that the inbound postal item is qualified and can be put into the warehouse. , And then transfer to domestic logistics to send to the buyer.
  • the identity verification-based item storage method automatically obtains the item information of the inbound postal item when an inbound postal item is received, and obtains the item information from the item information. Extract the buyer’s contact information and reserved identity information, and then use the contact method to issue an identity authentication notice to the buyer, and then obtain audio and video information containing the buyer’s biometric information, and then obtain Extracting the biometric information of the buyer from the audio and video information, and determining whether the buyer is real or not according to the biometric information, and finally comparing the reserved identity information with the real identity information When it is determined that the reserved identity information matches the real identity information, the inbound postal item is put into the warehouse.
  • the entire verification process does not require the intervention of customs personnel, which not only ensures the accuracy of the inspection results, but also greatly improves the inspection efficiency of inbound postal items, thereby realizing the rapid speed of all inbound postal items. Check.
  • FIG. 4 is a schematic flowchart of a second embodiment of a method for warehousing an item based on identity verification according to this application.
  • the method for warehousing items based on identity verification in this embodiment further includes:
  • Step S404 Obtain historical shopping records of the purchaser in a preset period according to the real identity information.
  • step S404 is obtained from the entry postal article record table.
  • the real ID number of the purchaser traverse the record of inbound postal items.
  • the preset period is obtained. For example, the purchase history of the purchaser corresponding to the real ID number in the past month.
  • the content recorded in the historical shopping record can be preset by a person skilled in the art according to business needs. For example, it can include the number, quantity, and time of each inbound postal item purchased by the buyer. , The item information of each inbound postal item, etc., may also include the total number of times and total quantity of all inbound postal items purchased by the buyer.
  • Step S405 Determine whether the shopper is eligible for purchase based on the historical shopping records and preset purchase qualification evaluation criteria.
  • step S402 is executed to store the inbound postal items into the warehouse; if it is determined through the judgment that the buyer is not qualified to purchase, then execute Step S403: Detain the inbound postal item, and use the contact method to issue an operation of an item detention notice to the purchaser.
  • this embodiment uses the purchase qualification evaluation criteria to set according to different identity information.
  • the buyer’s qualification criteria for this type of buyer can be set as follows: the number of inbound mail items allowed to be purchased is large, and the number of purchases within the specified time is large;
  • the purchase qualification criteria for this type of purchaser can be set as: the number of inbound mail items allowed to be purchased is relatively small, and the number of purchases within the specified time is relatively small.
  • step S402 is executed to store the inbound postal article in the warehouse If the first quantity is greater than the second quantity, step S403 is performed to detain the inbound postal items, and use the contact method to issue an operation of detaining items to the purchaser.
  • the so-called “ant move” specifically refers to a smuggling method, which mainly has the following characteristics:
  • the purchaser's real identity information can also be compared with The item information of the inbound postal items is stored in the inbound postal item record table in the form of key-value pairs, so that the next time the purchaser’s inbound postal items are received, the buyer’s Whether the purchase is legal.
  • the embodiments of the present application also provide a computer-readable storage medium, and the computer-readable storage medium may be a non-volatile readable storage medium.
  • the computer-readable storage medium of the present application stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the above-mentioned identity verification-based article storage method are realized.
  • the method implemented when the computer-readable instruction is executed can refer to the various embodiments of the method for warehousing an item based on identity verification in this application, which will not be repeated here.
  • FIG. 5 is a structural block diagram of a first embodiment of an article storage device based on identity verification in this application.
  • the device for warehousing items based on identity verification proposed in the embodiment of the present application includes:
  • the extraction module 5001 is used to obtain article information of inbound postal articles, and extract the contact information and reserved identity information of the purchaser from the article information;
  • the sending module 5002 is used to use the contact information , Issue an identity authentication notice to the purchaser to obtain audio and video information containing the biometric information of the purchaser;
  • the determining module 5003 is configured to receive the audio and video information, and from the audio and video information Extract the biological characteristic information of the purchaser, and determine the true identity information of the purchaser according to the biological characteristic information;
  • the comparison module 5004 is used to compare the reserved identity information and the real identity information In contrast, if the reserved identity information matches the real identity information, the inbound postal item is put into the warehouse.
  • each virtual function module of the above-mentioned identity verification-based article storage device is stored in the memory 1005 of the identity verification-based article storage device shown in FIG. 1, and is used to implement all the functions of computer-readable instructions; When the module is executed by the processor 1001, it can complete the function of the entire process of warehousing items based on identity verification.
  • the extraction module includes:
  • a photographing unit configured to photograph the paper order information pasted on the inbound postal items to obtain an electronic picture corresponding to the paper order information
  • the recognition unit is configured to use optical character recognition technology to perform optical character recognition on the electronic picture, and determine the computer text corresponding to each character in the electronic picture;
  • the sorting unit is used for sorting the computer text corresponding to each character according to the sequence of each character in the electronic picture to obtain the item information of the inbound postal article.
  • the sending module includes:
  • a uniform resource locator sending unit configured to use the contact method to deliver the uniform resource locator to the purchaser;
  • the recording unit is configured to pop up a biometric information collection interface on the user interface of the user terminal that receives the uniform resource locator when the purchaser triggers the uniform resource locator to record the biometric characteristics of the purchaser
  • the audio and video information of the information
  • biometric information collection interface is pre-compiled based on hypertext markup language.
  • the determining module includes:
  • the facial feature information extraction unit is used to extract the buyer’s facial feature information from the audio and video information according to a pre-built facial feature information extraction model, and use the extracted facial feature information as the Biometric information.
  • the determining module further includes:
  • the voiceprint feature information extraction unit is used to extract the buyer's voiceprint feature information from the audio and video information according to a pre-built voiceprint feature information extraction model, and use the extracted voiceprint feature information as the Biometric information.
  • the device for warehousing items based on identity verification further includes: a picture preprocessing module, which is used to perform grayscale processing on the electronic picture to obtain a grayscale picture; Performing binarization processing on the degree picture to obtain a binary picture from which interference information is removed; performing noise reduction processing on the binary picture to obtain an electronic picture to be identified;
  • the step of performing noise reduction processing on the binary picture to obtain the electronic picture to be recognized includes:
  • the preset area is an area determined by taking a position corresponding to the current pixel as a center and a radius by using a preset length;
  • the RGB color value corresponding to the current pixel is converted to the RGB color value corresponding to the black pixel to complete the reduction of the binary image Noise processing to obtain the electronic picture to be identified;
  • the RGB color value corresponding to the current pixel is converted to the RGB color value corresponding to the white pixel to complete the reduction of the binary image Noise processing to obtain the electronic picture to be identified;
  • the step of using optical character recognition technology to perform optical character recognition on the electronic picture and determining the computer text corresponding to each character in the electronic picture includes:
  • the device for warehousing items based on identity verification further includes: a judging module; the judging module is configured to obtain historical shopping records of the purchaser in a preset period according to the real identity information; Judging whether the shopper is qualified to purchase based on the historical shopping records and preset purchase qualification evaluation criteria;
  • the following steps are performed: the operation of storing the inbound postal items in the warehouse; if the shopper is not qualified to purchase, the inbound postal items are detained and all State the contact information, and issue a notice of item detention to the buyer.
  • each module in the above-mentioned identity verification-based article storage device corresponds to each step in the embodiment of the above-mentioned identity verification-based article storage method, and its functions and realization processes are not repeated here.
  • the method of the embodiment can be implemented by means of software plus a necessary general hardware platform, of course, it can also be implemented by hardware, but the former is a better implementation in many cases.
  • the application s The essence of the technical solution or the part that contributes to the existing technology can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium (such as Read Only Memory). Memory, ROM)/RAM, disk, optical
  • the disk includes several instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Multimedia (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Computer Security & Cryptography (AREA)
  • Development Economics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Character Discrimination (AREA)

Abstract

一种基于身份验证的物品入库方法、装置、设备及存储介质。该方法包括:获取进境邮递物品的物品信息,从物品信息中提取购买者的联系方式和预留身份信息(S10);采用联系方式,向购买者下发身份认证通知,以获取包含购买者的生物特征信息的音视频信息(S20);接收音视频信息,从音视频信息中提取购买者的生物特征信息,并根据生物特征信息,确定购买者的真实身份信息(S30);将预留身份信息和真实身份信息进行对比,若预留身份信息和真实身份信息匹配,则将进境邮递物品入库(S40)。通过上述方式,大大提升了对进境邮递物品的查验效率,从而实现了对全部进境邮递物品的快速查验,并保证了查验结果的准确性。

Description

基于身份验证的物品入库方法、装置、设备及存储介质
本申请要求于2019年5月21日提交中国专利局、申请号为201910428318.2、发明名称为“基于身份验证的物品入库方法、装置、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术领域,尤其涉及一种基于身份验证的物品入库方法、装置、设备及存储介质。
背景技术
随着互联网经济的蓬勃发展,网购已成为人们当前主要的购物方式,特别是随着国际和国内物流行业的快速发展,越来越多的居民开始通过海外电商平台或者代购的方式购买海外物品,因此海关进境邮递物品呈现快速发展的趋势。
但是,由于进境邮递物品的种类繁多、查验信息复杂。并且,相对于传统邮递物品(国内邮递物品),进境邮递物品需要监察征税和特定物品布控情况,因而传统的抽查方式,显然无法保证所有进境邮递物品的合法性。
并且,现有的抽查方式,由于需要依靠海关工作人员人工核实购买者的身份信息,在核实成功后才会对进件邮递物品进行入库操作,因而入库效率也相对较低。
所以,亟需提供一种能够方便、快速的对进境邮递物品的购买者进行身份验证的方法,以提升对进境邮递物品的查验效率和查验结果的准确性。
发明内容
本申请的主要目的在于提供一种基于身份验证的物品入库方法、装置、设备及存储介质,旨在提升对进境邮递物品的查验效率,以实现对全部进境邮递物品的快速查验,并保证查验结果的准确性。
为实现上述目的,本申请提供了一种基于身份验证的物品入库方法,所述方法包括以下步骤:
获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
此外,为实现上述目的,本申请还提出一种基于身份验证的物品入库装置,所述装置包括:
提取模块,用于获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
发送模块,用于采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
确定模块,用于接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
对比模块,用于将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
此外,为实现上述目的,本申请还提出一种基于身份验证的物品入库设备,所述设备包括:存储器、处理器及存储在所述存储器上并可被所述处理器执行的计算机可读指令,其中所述计算机可读指令被所述处理器执行时,实现如上文所述的基于身份验证的物品入库方法的步骤。
此外,为实现上述目的,本申请还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有计算机可读指令,其中所述计算机可读指令被处理器执行时,实现如上文所述的基于身份验证的物品入库方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其他特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
图1是本申请实施例方案涉及的硬件运行环境的基于身份验证的物品入库设备的结构示意图;
图2为本申请基于身份验证的物品入库方法第一实施例的流程示意图;
图3为本申请基于身份验证的物品入库方法第一实施例中步骤S40的具体实现流程示意图;
图4为本申请基于身份验证的物品入库方法第二实施例的流程示意图;
图5为本申请基于身份验证的物品入库装置第一实施例的结构框图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。
参照图1,图1为本申请实施例方案涉及的硬件运行环境的基于身份验证的物品入库设备结构示意图。
如图1所示,该基于身份验证的物品入库设备可以包括:处理器1001,例如中央处理器(Central Processing Unit,CPU),通信总线1002、用户接口1003,网络接口1004,存储器1005。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如无线保真(WIreless-FIdelity,WI-FI)接口)。存储器1005可以是高速的随机存取存储器(Random Access Memory,RAM)存储器,也可以是稳定的非易失性存储器(Non-Volatile Memory,NVM),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解,图1中示出的结构并不构成对基于身份验证的物品入库设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图1所示,作为一种计算机可读存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及计算机可读指令。
在图1所示的基于身份验证的物品入库设备中,网络接口1004主要用于与网络服务器进行数据通信;用户接口1003主要用于与用户进行数据交互;本申请基于身份验证的物品入库设备中的处理器1001、存储器1005可以设置在基于身份验证的物品入库设备中,所述基于身份验证的物品入库设备通过处理器1001调用存储器1005中存储的计算机可读指令,并执行本申请实施例提供的基于身份验证的物品入库方法。
本申请实施例提供了一种基于身份验证的物品入库方法,参照图2,图2为本申请一种基于身份验证的物品入库方法第一实施例的流程示意图。
本实施例中,所述基于身份验证的物品入库方法包括以下步骤:
步骤S10,获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息。
具体的说,本实施例中的执行主体为预先构建的用于对进境邮递物品进行查验的系统。在实际应用中,该系统可以部署在为海关办公所提供的海关服务器,并配合相应的采集设备(如摄像头),实现对进境邮递物品的物品信息的采集,从而使该查验系统能够进行后续身份验证操作。
此外,关于本实施例中所说的联系方式,通常为购买者的手机号码;所述预留身份信息,通常为所送购买者的身份证号码和用户姓名。
应当理解的是,由于身份证号码较为隐私,因而为了避免泄露所述购买者的预留的身份证号码,通常会将所述身份证号码转换为其他形式的标识码,比如二维码或条形码等图像识别码。然后,通过扫码枪或者其他扫描设备对所述图像识别码进行扫描,进而识别出图像识别码中携带的身份证号码。
此外,值得一提的是,由于在实际应用中,所述进境邮递物品的物品信息通常是记录在粘贴在所述进境邮递物品外包装上的纸质订单中的,因而为了能够快速准确的获取到所述物品信息,在获取所述进境邮递物品的物品信息时,具体可以采用光学字符识别(Optical Character Recognition,OCR)技术,从所述纸质订单中提取所述物品信息。
为了便于理解,以下针对采用OCR技术提取所述物品信息的操作进行具体说明:
(1)拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片。
应当理解的是,在邮件物品时,物流公司会在物品的包装袋或包装箱上粘贴物流单,而物流单上通常会填写者收件人姓名(即本实施例中所说的购买者的姓名)、收件地址、收件人电话、购买的物品名称、数量等信息。
因此,通过拍摄所述进境邮递物品上粘贴的纸质订单信息,便可得到携带有上述信息的电子图片。
(2)采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字。
具体的说,所述光学字符识别(Optical Character Recognition,OCR)技术,是指电子设备(例如扫描仪或数码相机)检查纸上打印的字符,通过检测暗、亮的模式确定其形状,然后用字符识别方法将形状翻译成计算机文字的过程。即,针对印刷体字符,采用光学的方式将纸质文档中的文字转换成为黑白点阵的图像文件,并通过识别软件将图像中的文字转换成文本格式,供文字处理软件进一步编辑加工的技术。
由于OCR技术的使用已经较为成熟,因而在具体实现中,本领域的技术人员可以通过查找OCR技术的相关文档,自行实现,此处不再赘述。
此外,应当理解的是,上述所说的计算机文字即为计算机设备能够识别的文字。
(3)根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
进一步地,为了保证提取所述物品信息的精确度,在采用光学字符识别技术,对所述电子图片进行光学字符识别,提取出所述电子图片中的字符之前,还可以先执行以下操作:首先对所述电子图片进行图像预处理操作,比如灰度处理、二值化处理、降噪等处理操作,得到待识别电子图片;然后,再采用OCR技术对所述待识别电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字。
为了便于理解,本实施例给出一种具体的图像预处理方式,其具体实现流程大致如下:
(a)对所述电子图片进行灰度处理,得到灰度图片。
由于一般的文字识别方法,需要处理的是对应的灰度图像。因此,为了保证最终得到的计算机文字的准确性,需要先将彩色的电子图片进行灰度处理,在进行其他的预处理。
具体的,目前常见的彩色图像有BMP、JPG等格式,其颜色表示多采用RGB色彩空间上的三维矢量。每个像素点均由取值范围为0~255的三元分量描述,数据的大小表示该基色的取值,最终由三种基色混合表示。而灰度图像是通过灰度级Gray Level表示的,所以转换过程可以被理解为是一个三维矢量到一个一维矢量的投影操作。
此外,常用的灰度处理方法有最大值法,即选择R、G、B三基色中最大的值作为灰度值,其函数表达式为:R=G=B=max(R,G,B);平均值法,选取R、G、B的平均值,其函数表达式为:R=G=B=max(R,G,B)/3;权平均法,该方法是目前使用较多的灰度处理方法。具体是对三种基色按照不同的比例(权值)求和,然后投影到一维空间。
由于上述三种方法的使用均相当成熟,在具体实现中,本领域的技术人员可以通过查找相关资料自行实现,此处不再赘述。
(b)对所述灰度图片进行二值化处理,得到去除干扰信息的二值图片。
具体的说,由于扫描设备输入或文档本身的原因,使得经过灰度处理后的图像会存在一个模糊的背景,由于这些背景会对文字设备产生较大的干扰。因此,需要对所述灰度图像进行二值化处理,以去除这些干扰,使得处理后的结果形成只有0和1形式的二值图像,以便计算机的识别与处理。
关于,二值图像(Binary Image),具体是指将图像上的每一个像素只有两种可能的取值或灰度等级状态,人们经常用黑白、B&W、单色图像表示二值图像。也就是说,二值图像中的任何像素不是0就是1,再无其他过渡的灰度值。
(c)对所述二值图片进行降噪处理,得到待识别电子图片。
应当理解的是,在实际应用中,虽然进行二值化处理后得到的二值图片是白底黑字的图片(其对应的数字矩阵仅有0和1组成),但是在白底黑字的图片中往往存在一些干扰像素点,比如说在一堆密集的黑色像素点中存在的少许白色像素点,或者在一堆白色像素点中存在的少许黑色像素点。虽然这些少许的白色像素点和黑色像素点不会影响图片整体内容,但是会影响对主要特征的提取,因此为了保证后续提取的字符的轮廓特征的准确性,需要对二值化处理得到的二值图片进行降噪处理,实现将一堆密集的黑色像素点中存在的少许白色像素点转换为黑色像素点,或者一堆密集的白色像素点中存在的少许黑色像素点转换为白色像素点。
为了便于理解对所述二值图片进行的降噪处理,本实施例给出一种具体的实现方式,大致如下:
(c1)对所述二值图片中的像素点进行遍历,获取遍历到的当前像素点的RGB颜色值。
具体的说,因为当前二值图片是经过二值化处理的,而二值化处理后的图片是一个白底黑字的图片(对应的数字矩阵仅包括0和1) ,因而该二值图片中的任意一个像素点对应的RGB颜色值不是黑色就是白色。
相应地,若遍历到的当前像素点的RGB颜色值为(255,255,255),则表明当前像素点为白色像素点;若遍历到的当前像素点的RGB颜色值为(0,0,0),则表明当前像素点为黑色像素点。
(c2)获取预设区域内第一阈值数目的参考像素点。
具体的说,在本实施例中所说的预设区域是以所述当前像素点对应的位置为圆心,以预设长度为半径确定的区域。
此外,值得一提的是,由于在实际应用中,一个像素点周围通常会有8个像素点,故此处所说的第一阈值数目可以是8。
(c3)分别获取各参考像素点的RGB颜色值,根据各参考像素点的RGB颜色值确定对应的参考像素点的颜色,所述颜色为黑色或白色。
(c4)根据各参考像素点的颜色对各参考像素点进行分类,得到黑色像素点集合和白色像素点集合。
(c5)统计所述黑色像素点集合中的黑色像素点的数量和所述白色像素点集合中的白色像素点的数量。
(c6)分别将所述黑色像素点的数量和所述白色像素点的数量与预设的第二阈值数目进行比较。
具体的说,为了保证降噪操作的合理性,此次优选将第二阈值数目设置为大于第一阈值数目的一半,比如在第一阈值数目为8的时候,第二阈值数目优选为大于等于5,且小于8的整数,比如5,6或者7。
相应地,若所述黑色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述黑色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片;若所述白色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述白色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片。
应当理解的是,以上给出的仅为一种对二值图片进行降噪处理的具体实现方式,对本申请的技术方案并不构成任何限定,在实际应用中,本领域的技术人员可以根据需要进行设置,此处不做限制。
进一步地,所述采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字的操作,具体如下:
遍历所所述待识别电子图片中的字符,提取遍历到的当前字符的轮廓特征;
将所述当前字符的轮廓特征与预先构建的特征模板库中的模板进行模板粗分类和模板细匹配,确定所述当前字符对应的计算机文字。
需要说明的是,上述所说的预先构建的特征模板库中存储的模板中主要记录有不同字符的轮廓特征。
相应地,模板中每一个已知字符的轮廓特征都会对应一个确定的计算机文字。
因而,通过将所述当前字符的轮廓特征与预先构建的特征模板库中的模板进行模板粗分类和模板细匹配,便可以确定所述当前字符对应的计算机文字。
为了便于理解,采用OCR技术获取进境邮递物品的物品信息的方式,以下结合实例进行说明:
比如,在进境邮递物品到达海关港口后,通过将进境邮递物品依次放置到安装有图像采集设备(如摄像头)的传送装置(如传送带)上,这样进境邮递物品在传送的过程中,便会被拍摄到所述进境邮递物品上粘贴的纸质订单信息。
接着,由图像采集装置将采集到的各进境邮递物品的纸质订单信息对应电子图片传送至本实施例中的查验系统,由查验系统按照上述几个步骤进行处理,便可以快速、准确的提取到各进境邮递物品的物品信息。
此外,值得一提的是,在实际应用中,为了保证可以拍摄到传输装置上放置的进境邮递物品的纸质订单信息对应的电子图片,可以在传送装置的四周均设置图像采集设备,且设置放置进境邮递物品的传送带可以选用透明材质,这样无论进境邮递物品上粘贴的纸质订单信息位于哪一方向,在穿过采集区域时都可以拍摄到纸质订单信息,得到所述纸质订单信息对应的电子图片。
进一步地,如果需要根据粘贴在进境邮递物品上的图像识别码提取用户的身份证号码等信息,还可以在传送装置上安装扫码设备,这样在进境邮递物品通过时,便可以同时获取到所述购买者的身份证号码。
还或者,可以由查验系统通过识别拍摄的电子图片上的图像识别码得到所述购买者的身份证号码。
应当理解的是,以上仅为举例说明,对本申请的技术方案并不构成任何限定,在具体应用中,本领域的技术人员可以根据需要进行设置,本申请对此不做限制。
步骤S20,采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息。
具体的说,由于预留的联系方式大多为购买者的手机号码,因而本实施例中向所述购买下发的身份认证通知,具体是以短信的方式下发至安装有所述手机号码对应的手机卡的用户终端中。
并且,为了方便所述购买者使用,且无需所述购买者安装照任何身份验证软件,便可以实现对购买者生物特征信息的采集,本实施例中下发给购买者的身份认证通知中具体携带有用于采集所述购买者生物特征信息统一资源定位符(Uniform Resource Locator,URL),这样购买者在接收到所述身份认证通知后,直接点击所述URL便会在所述用户终端上显示一个生物特征采集的界面。
也就是说,在实际应用中,上述步骤S20中的操作具体可以细化为以下两个步骤:
(1)采用所述联系方式,向所述购买者下发所述统一资源定位符。
具体的说,在本实施例中即为以短信的方式,将所述URL发送至所述购买者的预留的手机号码。
此外,应当理解的是,在实际应用中,如果所述购买者预留的联系方式为邮箱或即时通信账号,则在发送所述URL时,具体可以是以邮件或即时通信消息的方式,将所述URL发送至登录所述邮箱或即时通信账号的用户终端。
(2)监控所述购买者对所述统一资源定位符的触发操作。
相应地,在监控到所述购买者触发所述统一资源定位符时,则在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息。
需要说明的是,上述所说的生物特征信息采集界面是基于超文本标记语言(Hyper Text Markup Language,HTML)预先编译的,在本实施例中优选HTML的第5个开发版本,即通常所说的H5。
由于H5具有简易性、可扩展性、与平台无关性、通用性、可移植性等特点,因而无论购买者使用的移动终端是什么系统,开发人员都可以通过一次开发,使得上述生物特征信息采集界面实现多平台的使用,从而在方便购买者操作的同时,也大大简化了开发人员的工作量。
步骤S30,接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息。
具体的说,在实际应用中,能够标识购买者身份的生物特征信息有多种类型,比如人脸特征信息、虹膜特征信息、声纹特征信息等,因而在从所述音视频信息中提取所述购买者的生物特征信息的时候,具体可以根据预先设置的需要提取的生物特征信息的类型,选择适合的生物特征信息提取模型,从所述音视频信息中提取所述购买者的生物特征信息。
应当理解的是,由于本实施例中获取的是包含所述购买者生物特征信息的音视频信息,因而优选从所述音视频信息中提取所述购买者的人脸特征信息,或者声纹特征信息,还或者虹膜特征信息。
为了便于理解,本实施例中以需要提取的生物特征信息为人脸特征信息或声纹特征信息为例,对从所述音视频信息中提取所述购买者的生物特征信息的操作进行具体说明:
在提取的生物特征信息为人脸特征信息时,具体可以根据预先构建的人脸特征信息提取模型,从所述音视频信息中提取所述购买者的人脸特征信息,并将提取到的人脸特征信息作为所述生物特征信息。
相应地,在提取的生物特征信息为声纹特征信息时,具体可以根据预先构建的声纹特征信息提取模型,从所述音视频信息中提取所述购买者的声纹特征信息,并将提取到的声纹特征信息作为所述生物特征信息。
进一步地,为了防止他人预先录制音视频信息,冒名顶替。在录制包含所述生物特征信息的音视频信息时,具体可以采用活体检测技术,即在上述生物特征采集界面随机显示需要所述购买者朗读的内容,从而在所述购买者读取所述随机显示内容的过程中,录制包含所述购买者人脸图想的视频信息和语音信息,进而得到包含所述购买者生物特征信息的音视频信息。然后根据需要提取的生物特征信息,选择和的生物特征信息提取模型,从所述音视频信息中提取需要的生物特征信息。
为了便于理解,以下以获取的生物特征信息为人脸特征信息为例,结合具体实例进行说明:
首先,采用所述联系方式,向所述购买者下发携带有人脸特征信息采集地址的身份认证通知。
然后,接收所述购买者在触发所述人脸特征信息采集地址对应的人脸特征信息采集界面上的采集按钮后,读取随机预设内容时的视频信息。
应当理解是,为了保证后续能够从所述视频信息中能够提取到所述购买者的人脸特征信息,所述视频信息需要包含所述购买者的人脸图像。
最后,基于预设的人脸特征信息提取模型,对所述视频信息中的人脸图像进行人脸特征提取,得到所述购买者的人脸特征信息。
需要说明的是,在本实施例中,所述人脸特征信息提取模型具体可以采用卷积神经网络算法对预先获取的人脸样本数据中的人脸特征信息训练获得的。
关于构建所述人脸特征信息提取模型的方式,大致可以如下所述:
首先,根据所述人脸样本数据中的人脸特征信息构建训练模型。
然后,基于所述卷积神经网络算法,对所述训练模型进行训练,直到输入某一人脸图像数据,可以得到想要的人脸特征信息为止,便可以完成对所述训练模型的训练。
相应地,此刻的训练模型便是所述人脸特征信息提取模型。
进一步地,在实际应用中,为了增加训练模型的网络深度,使得训练出的人脸特征信息提取模型的提取精度更加准确,在采用所述卷积神经网络算法,对所述训练模型进行训练之前,还可以先对所述训练模型中的初始卷积核进行拆分。
比如,在训练模型中的初始卷积核为一个尺寸为的卷积核时,为了增加训练模型的网络深度,同时尽可能的提升训练速度,可以将所述的卷积核拆分为两个尺寸为的卷积核。
进一步地,为了加速后续训练过程中人脸特征信息提取模型的收敛速度,并且在一定程度上提升人脸特征信息提取模型的泛化能力(机器学习算法对新鲜样本的适应能力),在根据所述人脸样本数据构建所述训练模型之前,还可以对所述人脸样本数据进行归一化处理,从而缩小训练过程中每层卷积层中卷积核以及作为输出层的全连接层中的节点数,进而简化训练过程中的各种计算。
应当理解的是,以上给出的仅为一种构建人脸征信息提取模型的具体实现方式,在实际应用中,本领域的技术人员可以根据需要提取的生物特征信息,选取合适的机器学习算法,对从各大数据平台收集到的样本数据进行训练获得,具体的构建方式本领域的技术人员可以参考其选取的具体机器学习算法的文档,此处不再赘述。
此外,在实际应用中,如果需要根据所述购买者的指纹特征信息来确定所述购买者的真实身份信息,则在采集的音视频信息中需要包括所述购买者手指的图像信息。然后,通过对所述手指的图像信息的分析处理,提取出所述购买者的指纹特征信息。
应当理解的是,以上仅为举例说明,对本申请的技术方案并不构成任何限定,在具体应用中,本领域的技术人员可以根据需要进行设置,本申请对此不做限制。
此外,关于上述所说的根据所述生物特征信息,确定所述购买者的真实身份信息的操作,具体可以是利用大数据分析技术,将当前确定的生物特征信息与大数据库中存储的生物特征信息进行比对,从而确定所述购买者的真实身份信息。
关于上述所说的大数据库,可以是预先构建的,也可以直接与各大数据平台对接,此处不做限制。
仍以所述生物特征信息为人脸特征信息为例,则所述根据所述生物特征信息,确定所述购买者的真是身份信息的操作,大致可以如下:
为了方便,可以预先构建一个人脸特征分析模型,然后通过将确定的人脸特征信息输入到所述人脸特征分析模型中,使得所述人脸特征分析模型可以将所述人脸特征信息与大数据库中存储的众多身份信息已知的用户对应的人脸特征信息进行逐个对比,从而找出与一个与输入的人脸特征信息相似度较高的人脸特征信息,并将该人脸特征信息对应的身份信息作为所述购买者的真实身份信息。
进一步地,为了保证确定的真实身份信息的准确性,在将所述人脸特征信息对应的身份信息作为所述购买者的真实身份信息之前,还可以将这个较高的相似度与预设的阈值进行比较,如果大于阈值,则将该人脸特征信息对应的身份信息作为所述购买者的真实身份信息。
关于上述阈值的设置,可以有本领域的技术人员根据需要进行设置,比如设置为50%,甚至更高。
步骤S40,将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
具体的说,此处所说的在所述预留身份信息与所述真实身份信息匹配时,将所述进境邮递物品入库的操作,是指所述进境邮递物品查验合格,可以入库,然后转国内物流发送给所述购买者。
应当理解的是,以上给出的仅为一直具体的实现方式,对本申请的技术方案并不构成任何限定,在实际应用中,本领域的技术人员可以根据需要进行设置,此处不做限制。
通过上述描述不难发现,本实施例中提供的基于身份验证的物品入库方法,在接收到进境邮递物品时,通自动获取所述进境邮递物品的物品信息,并从所述物品信息中提取购买者的联系方式和预留身份信息,接着通过采用所述联系方式,向所述购买者下发身份认证通知,进而获取包含所述购买者的生物特征信息的音视频信息,然后从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息确定所述购买者的真实是否信息,最终通过将所述预留身份信息与所述真实身份信息进行对比,在确定所述预留身份信息与所述真实身份信息匹配时,才将所述进境邮递物品入库。通过这种身份验证方式,使得整个验证过程都无需海关人员介入,不仅保证了查验结果的准确性,也大大提升了对进境邮递物品的查验效率,从而实现了对全部进境邮递物品的快速查验。
参考图4,图4为本申请一种基于身份验证的物品入库方法第二实施例的流程示意图。
基于上述第一实施例,本实施例基于身份验证的物品入库方法在所述步骤S402之前,还包括:
步骤S404,根据所述真实身份信息,获取所述购买者在预设周期内的历史购物记录。
应当理解的是,在实际应用中,为了便于查询进出海关的进境邮递物品的相关信息,通常会预先构建一个用于存储进境邮递物品的物品信息以及购买进境邮递物品的购买者的身份信息的记录表,为了便于描述,以下称为“进境邮递物品记录表”。
相应地,所述步骤S404中的操作,便是从所述进境邮递物品记录表中获取。
比如,根据所述购买者的真实身份证号码,在所述进境邮递物品记录中进行遍历,当遍历到与所述真实身份证号码对应的身份证号码时,便获取出预设周期内,比如近一个月所述真实身份证号码对应的购买者的历史购买记录。
需要说明的是,所述历史购物记录中记录的内容,可以根据业务需要,由本领域的技术人员预先设置,比如可以包括所述购买者购买的每一种进境邮递物品的次数、数量、时间、每一种进境邮递物品的物品信息等,还可以包括所述购买者购买的所有进境邮递物品的总次数,以及总数量。
步骤S405,根据所述历史购物记录和预设的购买资格评判标准,判断所述购物者是否具备购买资格。
具体的说,若通过判断,确定所述购物者具备购买资格,则执行步骤S402,将所述进境邮递物品入库的操作;若通过判断,确定所述购买者不具备购买资格,则执行步骤S403,扣留所述进境邮递物品,并采用所述联系方式,向所述购买者下发物品扣留通知的操作。
为了便于理解步骤S405中的操作,本实施例以所述购买资格评判标准根据不同身份信息设置。
比如,在购买者的身份信息为企业或者商家时,可以设置这类购买者的购买者资格评判标准为:允许购买的进境邮递物品数量较大,规定时间内的购买次数较多;在购买者的身份信息为个人时,可以设置这类购买者的购买资格评判标准为:允许购买的进境邮递物品的数量相对较小,规定时间内的购买次数也相对较少。
具体的设置方式,本领域的技术人员可以根据实际情况进行设置,此处不做限制。
相应地,所述根据所述历史购物记录和预设的购买资格评判标准,判断所述购物者是否具备购买资格的操作,大致如下:
对所述历史购物记录进行遍历,统计所述购买者购买的进件邮递物品的第一数量;
读取所述购买资格评判标准中规定的所述进件邮递物品的允许购买的第二数量;
将所述第一数量与所述第二数量进行对比,若所述第一数量不大于(小于或等于)所述第二数量,则执行步骤S402,将所述进境邮递物品入库的操作;若所述第一数量大于所述大二数量,则执行步骤S403,扣留所述进境邮递物品,并采用所述联系方式,向所述购买者下发物品扣留通知的操作。
应当理解的是,以上给出的仅为一种根据所述历史购物记录和预设的购买资格评判标准,判断所述购物者是否具备购买资格的具体实现方式,对本申请的技术方案并不构成任何限制,在实际应用中,本领域的技术人员可以根据需要进行设置,此处不做限制。
通过上述描述不难发现,本实施例中提供的基于身份验证的物品入库方法,在确定所述预留身份信息和所述真实身份信息匹配后,将所述进境邮递物品入库之前,通过获取所述购买者的历史购物记录,并根据所述历史购物记录和预设的购买资格评判标准判断所述购买者是否具备购买资格,然后根据判断结果决定是否将所述进境邮递物品入库,从而有效防止了“水客”以“蚂蚁搬家”的方式走私进境邮递物品。
为了便于理解,以下分别对“蚂蚁搬家”和“水客”进行解释。
所谓“蚂蚁搬家”,具体是指一种走私方式,这种走私方式主要具有如下所述的特征:
(1)货物由货主向境外采购;
(2)货物已经销售或待售;
(3)货物进境是由已经查实的确定或未被查实不确定的“水客”分多次携带进境;
(4)当事人或货主不能证明商品已经缴税。
所谓“水客”,历史上大多数时候指贩运货物的行商。但随着中国改革开放的发展,现在更多的是泛指经常在大陆、香港、澳门之间来回的,并随身携带着产品进来,或出去的人,他们少则带上几罐奶粉,多则整车整船,价值达数亿元的走私过关。
此外,值得一提的是,在实际应用中,为了方便海关人员后续查验,在确定当前进境邮递物品合法,所述购买者具备购买资格后,还可以将所述购买者的真实身份信息与所述进境邮递物品的物品信息以键值对的方式,存储到所述进境邮递物品记录表中,从而在下次收到所述购买者的进境邮递物品时,确定所述购买者的购买行为是否合法。
此外,本申请实施例还提供一种计算机可读存储介质,所述计算机可读存储介质可以为非易失性可读存储介质。
本申请计算机可读存储介质上存储有计算机可读指令,其中所述计算机可读指令被处理器执行时,实现如上述的基于身份验证的物品入库方法的步骤。
其中,该计算机可读指令被执行时所实现的方法可参照本申请基于身份验证的物品入库方法的各个实施例,此处不再赘述。
参照图5,图5为本申请基于身份验证的物品入库装置第一实施例的结构框图。
如图5所示,本申请实施例提出的基于身份验证的物品入库装置包括:
提取模块5001、发送模块5002、确定模块5003和对比模块5004。
其中,所述提取模块5001,用于获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;所述发送模块5002,用于采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;所述确定模块5003,用于接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;所述对比模块5004,用于将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
应当理解的是,上述基于身份验证的物品入库装置的各虚拟功能模块存储于图1所示基于身份验证的物品入库设备的存储器1005中,用于实现计算机可读指令的所有功能;各模块被处理器1001执行时,可完成基于身份验证的物品入库的全流程的功能。
进一步地,所述提取模块包括:
拍摄单元,用于拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片;
识别单元,用于采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字;
排序单元,用于根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
进一步地,在所述身份认证通知中携带有用于采集所述购买者生物特征信息统一资源定位符时,所述发送模块包括:
统一资源定位符发送单元,用于采用所述联系方式,向所述购买者下发所述统一资源定位符;
监控单元,用于监控所述购买者对所述统一资源定位符的触发操作;
录制单元,用于在所述购买者触发所述统一资源定位符时,在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息;
其中,所述生物特征信息采集界面基于超文本标记语言预先编译。
进一步地,在所述生物特征信息为人脸特征信息时,所述确定模块包括:
人脸特征信息提取单元,用于根据预先构建的人脸特征信息提取模型,从所述音视频信息中提取所述购买者的人脸特征信息,并将提取到的人脸特征信息作为所述生物特征信息。
进一步地,在所述生物特征信息为声纹特征信息时,所述确定模块还包括:
声纹特征信息提取单元,用于根据预先构建的声纹特征信息提取模型,从所述音视频信息中提取所述购买者的声纹特征信息,并将提取到的声纹特征信息作为所述生物特征信息。
进一步地,所述基于身份验证的物品入库装置,还包括:图片预处理模块,所述图片预处理模块,用于对所述电子图片进行灰度处理,得到灰度图片;对所述灰度图片进行二值化处理,得到去除干扰信息的二值图片;对所述二值图片进行降噪处理,得到待识别电子图片;
其中,所述对所述二值图片进行降噪处理,得到待识别电子图片的步骤,包括:
对所述二值图片中的像素点进行遍历,获取遍历到的当前像素点的RGB颜色值;
获取预设区域内第一阈值数目的参考像素点,所述预设区域为以所述当前像素点对应的位置为圆心,以预设长度为半径确定的区域;
分别获取各参考像素点的RGB颜色值,根据各参考像素点的RGB颜色值确定对应的参考像素点的颜色,所述颜色为黑色或白色;
根据各参考像素点的颜色对各参考像素点进行分类,得到黑色像素点集合和白色像素点集合;
统计所述黑色像素点集合中的黑色像素点的数量和所述白色像素点集合中的白色像素点的数量;
分别将所述黑色像素点的数量和所述白色像素点的数量与预设的第二阈值数目进行比较;
若所述黑色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述黑色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片;
若所述白色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述白色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片;
其中,所述采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字的步骤,包括:
遍历所述待识别电子图片中的字符,提取遍历到的当前字符的轮廓特征;
将所述当前字符的轮廓特征与预先构建的特征模板库中的模板进行模板粗分类和模板细匹配,确定所述当前字符对应的计算机文字,所述模板中记录有字符的轮廓特征,所述字符的轮廓特征与所述计算机文字之间存在对应关系。
进一步地,所述基于身份验证的物品入库装置,还包括:判断模块;所述判断模块,用于根据所述真实身份信息,获取所述购买者在预设周期内的历史购物记录;根据所述历史购物记录和预设的购买资格评判标准,判断所述购物者是否具备购买资格;
相应地,若所述购物者具备购买资格,则执行步骤:将所述进境邮递物品入库的操作;若所述购物者不具备购买资格,则扣留所述进境邮递物品,并采用所述联系方式,向所述购买者下发物品扣留通知。
其中,上述基于身份验证的物品入库装置中各个模块的功能实现与上述基于身份验证的物品入库方法实施例中各步骤相对应,其功能和实现过程在此处不再一一赘述。
此外,需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述 实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通 过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的 技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体 现出来,该计算机软件产品存储在一个存储介质(如只读存储器(Read Only Memory,ROM)/RAM、磁碟、光 盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于身份验证的物品入库方法,其中,所述方法包括以下步骤:
    获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
    采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
    接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
    将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
  2. 如权利要求1所述的方法,其中,所述获取进境邮递物品的物品信息的步骤,包括:
    拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片;
    采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字;
    根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
  3. 如权利要求2所述的方法,其中,所述采用光学字符识别技术,对所述电子图片进行光学字符识别,提取出所述电子图片中的字符的步骤之前,所述方法还包括以下步骤:
    对所述电子图片进行灰度处理,得到灰度图片;
    对所述灰度图片进行二值化处理,得到去除干扰信息的二值图片;
    对所述二值图片进行降噪处理,得到待识别电子图片;
    其中,所述对所述二值图片进行降噪处理,得到待识别电子图片的步骤,包括:
    对所述二值图片中的像素点进行遍历,获取遍历到的当前像素点的RGB颜色值;
    获取预设区域内第一阈值数目的参考像素点,所述预设区域为以所述当前像素点对应的位置为圆心,以预设长度为半径确定的区域;
    分别获取各参考像素点的RGB颜色值,根据各参考像素点的RGB颜色值确定对应的参考像素点的颜色,所述颜色为黑色或白色;
    根据各参考像素点的颜色对各参考像素点进行分类,得到黑色像素点集合和白色像素点集合;
    统计所述黑色像素点集合中的黑色像素点的数量和所述白色像素点集合中的白色像素点的数量;
    分别将所述黑色像素点的数量和所述白色像素点的数量与预设的第二阈值数目进行比较;
    若所述黑色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述黑色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片;
    若所述白色像素点的数量大于所述第二阈值数目,则将所述当前像素点对应的RGB颜色值转换为所述白色像素点对应的RGB颜色值,完成对所述二值图片的降噪处理,得到所述待识别电子图片;
    其中,所述采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字的步骤,包括:
    遍历所述待识别电子图片中的字符,提取遍历到的当前字符的轮廓特征;
    将所述当前字符的轮廓特征与预先构建的特征模板库中的模板进行模板粗分类和模板细匹配,确定所述当前字符对应的计算机文字,所述模板中记录有字符的轮廓特征,所述字符的轮廓特征与所述计算机文字之间存在对应关系。
  4. 如权利要求1所述的方法,其中,所述身份认证通知中携带有用于采集所述购买者生物特征信息统一资源定位符;
    所述采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息的步骤,包括:
    采用所述联系方式,向所述购买者下发所述统一资源定位符;
    监控所述购买者对所述统一资源定位符的触发操作;
    在所述购买者触发所述统一资源定位符时,在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息;
    其中,所述生物特征信息采集界面基于超文本标记语言预先编译。
  5. 如权利要求4所述的方法,其中,所述生物特征信息为人脸特征信息;
    所述从所述音视频信息中提取所述购买者的生物特征信息的步骤,包括:
    根据预先构建的人脸特征信息提取模型,从所述音视频信息中提取所述购买者的人脸特征信息,并将提取到的人脸特征信息作为所述生物特征信息。
  6. 如权利要求4所述的方法,其中,所述生物特征信息为声纹特征信息;
    所述从所述音视频信息中提取所述购买者的生物特征信息的步骤,包括:
    根据预先构建的声纹特征信息提取模型,从所述音视频信息中提取所述购买者的声纹特征信息,并将提取到的声纹特征信息作为所述生物特征信息。
  7. 如权利要求1所述的方法,其中,所述将所述进境邮递物品入库的步骤之前,所述方法还包括以下步骤:
    根据所述真实身份信息,获取所述购买者在预设周期内的历史购物记录;
    根据所述历史购物记录和预设的购买资格评判标准,判断所述购物者是否具备购买资格;
    若所述购物者具备购买资格,则执行步骤:将所述进境邮递物品入库的操作;
    若所述购物者不具备购买资格,则扣留所述进境邮递物品,并采用所述联系方式,向所述购买者下发物品扣留通知。
  8. 一种基于身份验证的物品入库装置,其中,所述装置包括:
    提取模块,用于获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
    发送模块,用于采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
    确定模块,用于接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
    对比模块,用于将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
  9. 如权利要求8所述的基于身份验证的物品入库装置,其中,所述提取模块包括:
    拍摄单元,用于拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片;
    识别单元,用于采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字;
    排序单元,用于根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
  10. 如权利要求8所述的基于身份验证的物品入库装置,其中,所述身份认证通知中携带有用于采集所述购买者生物特征信息统一资源定位符;所述发送模块包括:
    统一资源定位符发送单元,用于采用所述联系方式,向所述购买者下发所述统一资源定位符;
    监控单元,用于监控所述购买者对所述统一资源定位符的触发操作;
    录制单元,用于在所述购买者触发所述统一资源定位符时,在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息;
    其中,所述生物特征信息采集界面基于超文本标记语言预先编译。
  11. 如权利要求10所述的基于身份验证的物品入库装置,其中,所述生物特征信息为人脸特征信息;所述确定模块包括:
    人脸特征信息提取单元,用于根据预先构建的人脸特征信息提取模型,从所述音视频信息中提取所述购买者的人脸特征信息,并将提取到的人脸特征信息作为所述生物特征信息。
  12. 如权利要求10所述的基于身份验证的物品入库装置,其中,所述生物特征信息为声纹特征信息;所述确定模块还包括:
    声纹特征信息提取单元,用于根据预先构建的声纹特征信息提取模型,从所述音视频信息中提取所述购买者的声纹特征信息,并将提取到的声纹特征信息作为所述生物特征信息。
  13. 一种基于身份验证的物品入库设备,其中,所述设备包括:存储器、处理器及存储在所述存储器上并可被所述处理器执行的计算机可读指令,其中所述计算机可读指令被所述处理器执行时,实现如下步骤:
    获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
    采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
    接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
    将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
  14. 如权利要求13所述的基于身份验证的物品入库设备,其中,所述获取进境邮递物品的物品信息的步骤,包括:
    拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片;
    采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字;
    根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
  15. 如权利要求13所述的基于身份验证的物品入库设备,其中,所述身份认证通知中携带有用于采集所述购买者生物特征信息统一资源定位符;
    所述采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息的步骤,包括:
    采用所述联系方式,向所述购买者下发所述统一资源定位符;
    监控所述购买者对所述统一资源定位符的触发操作;
    在所述购买者触发所述统一资源定位符时,在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息;
    其中,所述生物特征信息采集界面基于超文本标记语言预先编译。
  16. 如权利要求15所述的基于身份验证的物品入库设备,其中,所述生物特征信息为人脸特征信息;
    所述从所述音视频信息中提取所述购买者的生物特征信息的步骤,包括:
    根据预先构建的人脸特征信息提取模型,从所述音视频信息中提取所述购买者的人脸特征信息,并将提取到的人脸特征信息作为所述生物特征信息。
  17. 如权利要求15所述的基于身份验证的物品入库设备,其中,所述生物特征信息为声纹特征信息;
    所述从所述音视频信息中提取所述购买者的生物特征信息的步骤,包括:
    根据预先构建的声纹特征信息提取模型,从所述音视频信息中提取所述购买者的声纹特征信息,并将提取到的声纹特征信息作为所述生物特征信息。
  18. 一种计算机可读存储介质,其中,所述计算机可读存储介质上存储有计算机可读指令,其中所述计算机可读指令被处理器执行时,实现如下步骤:
    获取进境邮递物品的物品信息,从所述物品信息中提取购买者的联系方式和预留身份信息;
    采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息;
    接收所述音视频信息,从所述音视频信息中提取所述购买者的生物特征信息,并根据所述生物特征信息,确定所述购买者的真实身份信息;
    将所述预留身份信息和所述真实身份信息进行对比,若所述预留身份信息和所述真实身份信息匹配,则将所述进境邮递物品入库。
  19. 如权利要求18所述的计算机可读存储介质,其中,所述获取进境邮递物品的物品信息的步骤,包括:
    拍摄所述进境邮递物品上粘贴的纸质订单信息,得到所述纸质订单信息对应的电子图片;
    采用光学字符识别技术,对所述电子图片进行光学字符识别,确定所述电子图片中各字符对应的计算机文字;
    根据各字符在所述电子图片中的排列顺序,对各字符对应的计算机文字进行排列,得到所述进境邮递物品的物品信息。
  20. 如权利要求18所述的计算机可读存储介质,其中,所述身份认证通知中携带有用于采集所述购买者生物特征信息统一资源定位符;
    所述采用所述联系方式,向所述购买者下发身份认证通知,以获取包含所述购买者的生物特征信息的音视频信息的步骤,包括:
    采用所述联系方式,向所述购买者下发所述统一资源定位符;
    监控所述购买者对所述统一资源定位符的触发操作;
    在所述购买者触发所述统一资源定位符时,在接收所述统一资源定位符的用户终端的用户界面弹出生物特征信息采集界面,以录制包含所述购买者的生物特征信息的音视频信息;
    其中,所述生物特征信息采集界面基于超文本标记语言预先编译。
PCT/CN2019/122321 2019-05-21 2019-12-02 基于身份验证的物品入库方法、装置、设备及存储介质 Ceased WO2020233076A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910428318.2 2019-05-21
CN201910428318.2A CN110288286A (zh) 2019-05-21 2019-05-21 基于身份验证的物品入库方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020233076A1 true WO2020233076A1 (zh) 2020-11-26

Family

ID=68002315

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/122321 Ceased WO2020233076A1 (zh) 2019-05-21 2019-12-02 基于身份验证的物品入库方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN110288286A (zh)
WO (1) WO2020233076A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114327517A (zh) * 2021-12-29 2022-04-12 深圳市驱动人生科技股份有限公司 软件驱动的实现方法及系统
CN117522281A (zh) * 2024-01-05 2024-02-06 山东通广电子股份有限公司 一种基于视觉识别的工器具出入库管理方法及系统
CN118552999A (zh) * 2024-07-12 2024-08-27 北京诺君安信息技术股份有限公司 边检一体机用的生物特征采集方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110288286A (zh) * 2019-05-21 2019-09-27 深圳壹账通智能科技有限公司 基于身份验证的物品入库方法、装置、设备及存储介质
CN111523647B (zh) * 2020-04-26 2023-11-14 南开大学 网络模型训练方法及装置、特征选择模型、方法及装置
CN111931774B (zh) * 2020-09-27 2020-12-18 耀方信息技术(上海)有限公司 药品数据的入库方法及系统
CN112581062B (zh) * 2020-12-25 2025-01-10 同方威视科技江苏有限公司 基于关系挖掘的快件收发组织发现方法及相关设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407968A (zh) * 2016-08-25 2017-02-15 深圳市启明星电子商务有限公司 一种跨境电商快速身份识别方法及其识别系统
CN107093044A (zh) * 2017-04-06 2017-08-25 杭州天翔东捷运物流有限公司 一种跨境个人物品身份验证方法及其系统
CN107180177A (zh) * 2016-03-10 2017-09-19 阿里巴巴集团控股有限公司 获取用户信息的方法和装置
CN107404381A (zh) * 2016-05-19 2017-11-28 阿里巴巴集团控股有限公司 一种身份认证方法和装置
CN110288286A (zh) * 2019-05-21 2019-09-27 深圳壹账通智能科技有限公司 基于身份验证的物品入库方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107180177A (zh) * 2016-03-10 2017-09-19 阿里巴巴集团控股有限公司 获取用户信息的方法和装置
CN107404381A (zh) * 2016-05-19 2017-11-28 阿里巴巴集团控股有限公司 一种身份认证方法和装置
CN106407968A (zh) * 2016-08-25 2017-02-15 深圳市启明星电子商务有限公司 一种跨境电商快速身份识别方法及其识别系统
CN107093044A (zh) * 2017-04-06 2017-08-25 杭州天翔东捷运物流有限公司 一种跨境个人物品身份验证方法及其系统
CN110288286A (zh) * 2019-05-21 2019-09-27 深圳壹账通智能科技有限公司 基于身份验证的物品入库方法、装置、设备及存储介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114327517A (zh) * 2021-12-29 2022-04-12 深圳市驱动人生科技股份有限公司 软件驱动的实现方法及系统
CN114327517B (zh) * 2021-12-29 2022-07-29 深圳市驱动人生科技股份有限公司 软件驱动的实现方法及系统
CN117522281A (zh) * 2024-01-05 2024-02-06 山东通广电子股份有限公司 一种基于视觉识别的工器具出入库管理方法及系统
CN117522281B (zh) * 2024-01-05 2024-04-16 山东通广电子股份有限公司 一种基于视觉识别的工器具出入库管理方法及系统
CN118552999A (zh) * 2024-07-12 2024-08-27 北京诺君安信息技术股份有限公司 边检一体机用的生物特征采集方法

Also Published As

Publication number Publication date
CN110288286A (zh) 2019-09-27

Similar Documents

Publication Publication Date Title
WO2020233076A1 (zh) 基于身份验证的物品入库方法、装置、设备及存储介质
WO2020138745A1 (en) Image processing method, apparatus, electronic device and computer readable storage medium
WO2016013914A1 (ko) 상품 정보를 제공하고 표시하는 방법, 장치, 시스템 및 컴퓨터 프로그램
WO2018166099A1 (zh) 信息泄露检测方法及装置、服务器及计算机可读存储介质
WO2018074870A1 (ko) 이미지 인증을 이용한 증강현실 객체 제공 방법 및 제공 서버
WO2018008881A1 (ko) 단말장치 및 서비스서버, 그 장치에 의해 수행되는 진단분석 서비스를 제공하기 위한 방법 및 프로그램과, 그 프로그램이 기록된 컴퓨터 판독 가능 기록매체
WO2023106572A1 (ko) 가상 자산 부정 거래 탐지를 위한 탐지 모델의 학습 방법, 탐지 모델을 이용한 가상 자산 부정 거래의 탐지 방법 및 이들을 수행하는 장치 및 컴퓨터 프로그램
WO2020032567A1 (en) Electronic device for providing information on item based on category of item
WO2020207038A1 (zh) 基于人脸识别的人数统计方法、装置、设备及存储介质
WO2021210918A1 (en) Electronic device for sending cryptocurrency to blockchain account and method for operating the same
WO2020091253A1 (ko) 전자 장치 및 전자 장치의 제어 방법
WO2021066541A1 (ko) 신분증 인식 방법 및 장치
WO2014137118A1 (ko) 역경매를 이용한 가맹점 추천 방법과 장치
EP3649460A1 (en) Apparatus for optimizing inspection of exterior of target object and method thereof
WO2020116988A1 (ko) 영상 분석 장치, 영상 분석 방법 및 기록 매체
WO2022039330A1 (ko) 가상 셀을 이용한 ocr 기반 문서 분석 시스템 및 방법
WO2020233055A1 (zh) 基于活体检测的产品推广方法、装置、设备及存储介质
WO2022169045A1 (ko) 학습된 딥러닝 모델을 이용한 cfu 인식 방법
WO2023022537A1 (ko) Ai 기반 차량 디스크 불량 검출 시스템
EP3991123A1 (en) Method and apparatus for generating structured relation information based on a text input
WO2023146195A1 (ko) 이미지를 분류하는 서버 및 그 동작 방법
WO2023234619A1 (ko) 메타버스 창고 상에서 상품 유통 관리 방법 및 이러한 방법을 수행하는 장치
WO2011068315A4 (ko) 최대 개념강도 인지기법을 이용한 최적의 데이터베이스 선택장치 및 그 방법
WO2022244997A1 (en) Method and apparatus for processing data
WO2022119136A1 (ko) 스크린샷 이미지로부터 태그 정보를 추출하는 방법 및 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19930050

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25/02/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19930050

Country of ref document: EP

Kind code of ref document: A1