WO2020253113A1 - 发票录入方法、装置、设备及计算机存储介质 - Google Patents

发票录入方法、装置、设备及计算机存储介质 Download PDF

Info

Publication number
WO2020253113A1
WO2020253113A1 PCT/CN2019/120910 CN2019120910W WO2020253113A1 WO 2020253113 A1 WO2020253113 A1 WO 2020253113A1 CN 2019120910 W CN2019120910 W CN 2019120910W WO 2020253113 A1 WO2020253113 A1 WO 2020253113A1
Authority
WO
WIPO (PCT)
Prior art keywords
invoice
current
current invoice
image
format
Prior art date
Application number
PCT/CN2019/120910
Other languages
English (en)
French (fr)
Inventor
李锴
Original Assignee
深圳壹账通智能科技有限公司
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 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2020253113A1 publication Critical patent/WO2020253113A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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
    • G06Q10/10Office automation; Time management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/41Analysis of document content
    • G06V30/418Document matching, e.g. of document images
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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, in particular to an invoice entry method, device, equipment and computer storage medium.
  • the state taxation agency collects statistics on various types of invoices.
  • the workers of the state taxation agency organize various types of invoices, they need to manually classify these different types of invoices and then enter them into the computer system. If there are many invoices and many types, and some invoices are even regional, workers need to classify invoices according to invoice types, which is more time-consuming and laborious for workers.
  • the main purpose of this application is to provide an invoice entry method, device, equipment and computer storage medium, aiming to solve the problem that the staff is time-consuming and laborious to manually count invoices due to the large quantity and variety.
  • invoice entry method which includes the following steps:
  • an invoice entry device which includes:
  • the collection module is used to collect the image information of the current invoice
  • An identification module configured to identify the feature point set A of the current invoice format of the current invoice from the image information
  • the comparison module is used to traverse the invoice format images in the image library, collect feature points of the traversed invoice format images, and obtain the feature point set X of the traversed invoice format images;
  • the comparison module is further configured to compare the feature points in the feature point set A with the feature points in the feature point set X;
  • the comparison module is further configured to use the invoice format image corresponding to the feature point set X as the target invoice format image matching the current invoice format if the comparison results are the same;
  • An obtaining module configured to determine the current invoice category corresponding to the current invoice according to the target invoice format image
  • the storage module is used to enter the image information of the current invoice into the storage area corresponding to the current invoice category.
  • this application also proposes a device for entering invoices.
  • the device includes a camera, a memory, a processor, and a computer that is stored on the memory and can be executed on the processor.
  • a read instruction when the computer-readable instruction is executed by the processor, implements the steps of the invoice entry method as described above.
  • this application also proposes a computer storage medium having computer-readable instructions stored thereon, and when the computer-readable instructions are executed by the processor, the above-mentioned invoice entry is realized. Method steps.
  • FIG. 1 is a schematic structural diagram of a device in a hardware operating environment involved in a solution of an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of an invoice entry method according to the application.
  • Fig. 3 is a schematic diagram of each data table of the database in an embodiment of the application
  • FIG. 4 is a schematic flowchart of a second embodiment of an invoice entry method according to the application.
  • FIG. 5 is a schematic flowchart of a third embodiment of an invoice entry method according to the application.
  • FIG. 6 is a schematic flowchart of a fourth embodiment of an invoice entry method according to the application.
  • FIG. 7 is a schematic diagram of each data table of the database in another embodiment of the application.
  • Figure 8 is a structural block diagram of an invoice entry device of this application.
  • FIG. 1 is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the application.
  • the device may include a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005, and a camera 1006.
  • 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 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 WI-FI interface).
  • the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as disk storage.
  • the memory 1005 may also be a storage device independent of the foregoing processor 1001.
  • the camera 1006 is used to collect image information of the invoice.
  • FIG. 1 does not constitute a limitation on the device described in the present application, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components Layout.
  • a memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and computer readable instructions.
  • the device described in this application calls the computer-readable instructions stored in the memory 1005 through the processor 1001, and executes the steps of the invoice entry method.
  • Figure 2 is a schematic flowchart of a first embodiment of an invoice entry method according to this application.
  • the method includes the following steps:
  • Step S10 Collect image information of the current invoice.
  • Step S20 Identify the feature point set A of the current invoice format of the current invoice from the image information.
  • the execution subject of this embodiment is an invoice entry device.
  • the invoice entry device may include a camera for collecting image information of the current invoice.
  • the worker uses the device to collect the image of the current invoice.
  • the feature point set A of the current invoice format of the current invoice is identified in the image information;
  • This embodiment can be implemented based on OpenCV (Open Source Computer Vision Library, open source computer vision library) function to perform grayscale processing on the collected images, and obtain the table line after binarization processing.
  • OpenCV Open Source Computer Vision Library, open source computer vision library
  • Step S30 Traverse the invoice format images in the image library, collect feature points of the traversed invoice format images, and obtain the feature point set X of the traversed invoice format images.
  • this embodiment will summarize the invoice formats of different types of invoices in advance.
  • the format of value-added tax invoices and the format of motor vehicle sales invoices are very different.
  • the background, the image of the white line (or the image of the white background, the black line) is called the form line image, and the built form line image is stored in the image library as the invoice format image.
  • the image database in this embodiment may be a relational database, such as a MySQL database and a SqlServer database.
  • Step S40 Compare the feature points in the feature point set A with the feature points in the feature point set X.
  • Step S50 If the comparison results are the same, the invoice format image corresponding to the feature point set X is used as the target invoice format image matching the current invoice format.
  • Step S60 Determine the current invoice category corresponding to the current invoice according to the target invoice format image.
  • the invoice format image comparison method of this embodiment belongs to the comparison of two-dimensional pictures and two-dimensional pictures. Since different types of invoice formats are in table shape, the similarity of different types of invoice images will be very high. .
  • This embodiment adopts the feature point matching method, that is, when processing the step of "compare the pre-stored invoice format images in the image library according to the current invoice format", the invoice format images in the image library are traversed, and the traversal to To collect the feature point set X of the invoice format, compare the feature point set A of the current invoice format with the feature point set X of the invoice format image.
  • the specific comparison method is: first determine the feature point Set the specific shape a of the current invoice format corresponding to the set A, and then determine the specific shape x of the invoice format image corresponding to the feature point set X, obtain the endpoints of the shape a, and obtain the endpoints of the shape x at the same time, and combine the endpoints and shapes of the shape a
  • the end points of b are connected, for example, the shape a and the shape x are both rectangles, then the four end points of the two rectangles can be connected correspondingly in the order of up, down, left, and right.
  • connection method is: using the connected endpoints as a reference, the characteristic points are connected in the order from left to right and top to bottom.
  • Step S70 Enter the image information of the current invoice into the storage area corresponding to the current invoice category.
  • FIG. 3 is a schematic diagram of each data table of the database of this embodiment.
  • the database of this embodiment will include a database for storing invoice format images.
  • Data table invoice format image table A
  • data table for storing the name of the invoice type invoice category table B
  • multiple data tables for storing invoice image information invoice information table C divided by invoice category
  • invoice category table B includes: invoice category ID (primary key) and invoice category name;
  • invoice format image table A The attributes of the invoice format image table A include: invoice format ID (primary key), invoice format image and invoice category ID (foreign key);
  • the attributes of the invoice information table C include: image information of the invoice (specific invoice content information field) and invoice category ID (foreign key).
  • the invoice entry device when the invoice entry device recognizes the current category of the current invoice, it enters the image information of the current invoice into the storage area corresponding to the current invoice category, that is, enters the image information of the current invoice into the storage area corresponding to the current invoice category. State the invoice information table C corresponding to the current invoice category. Furthermore, it can replace the manual classification of invoices and manually enter the invoice information into the computer. Workers can use the invoice entry device of this program to scan the invoice image information, and then automatically classify the invoice information and store it in the computer system. In, improve the efficiency of workers.
  • the image information of the current invoice is first collected, and the current invoice format of the current invoice is identified from the image information; the invoice format images pre-stored in the picture library are compared according to the current invoice format, and the results are obtained The target invoice format image that matches the invoice format image;
  • this embodiment can automatically classify the invoice information and then store it in the computer system. In turn, it can replace manual classification of invoices and improve the efficiency of workers.
  • step S10 specifically includes:
  • Step S101 Collect image information of the current invoice, identify the current invoice format of the current invoice from the image information, and identify the invoice content information of the current invoice from the image information through optical character recognition technology.
  • this embodiment may adopt optical character recognition technology (OCR, Optical Character Recognition).
  • OCR optical character recognition
  • Recognition Recognize the invoice content information of the current invoice from the image information; that is, use optical technology and computer technology to read out the text printed or written on the current invoice paper and convert it into a computer capable Acceptable and understandable format.
  • Text recognition is a relatively mature technology in the field of computer vision research, and there have been many landing projects in business.
  • the invoice content information includes at least an invoice number, an invoice date and transaction information
  • the transaction information may include buyer information and seller information.
  • the step S70 specifically includes:
  • Step S701 Enter the image information of the current invoice and the invoice content information into the storage area corresponding to the current invoice category.
  • the attributes of the invoice information table C in this embodiment include: image information of the invoice (specific invoice content information field), invoice category ID (foreign key), invoice number, invoice date, transaction information, and other field information.
  • the invoice entry device After the invoice entry device recognizes the current category of the current invoice and the invoice content information, it records the image information of the current invoice and the invoice content information into the storage area corresponding to the current invoice category, That is, the image information of the current invoice and the invoice content information are entered into the invoice information table C corresponding to the current invoice category.
  • the method includes:
  • Step S102 Read the stamp image from the image information of the current invoice, compare the stamp image with a preset stamp, and determine that the current invoice is qualified when the stamp image is the same as the preset stamp invoice.
  • the authenticity of the invoice can be identified based on the invoice information of the current invoice.
  • the red seal without an oval shape is marked with the "National Uniform Invoice Supervision Chapter" at the top of the chapter and the words "produced under the supervision of the local tax bureau” or "produced under the supervision of the State Administration of Taxation" to determine whether the red chapter meets the specifications.
  • step S101 it may also include:
  • Step detecting the connection status between the local network and the server of the State Administration of Taxation, and reading the current invoice number from the invoice content information when the detection result is the communication status;
  • Steps traverse the database of the State Administration of Taxation server according to the current invoice number, and determine that the current invoice is a qualified invoice when it successfully traverses to the same invoice number as the current invoice number.
  • the invoice entry device of this embodiment is synchronized with the database of the State Administration of Taxation.
  • the invoice entry device scans the invoice code of the current invoice, and queries the database of the State Administration of Taxation according to the scanned invoice number. The content indicates that the current invoice is valid, otherwise it is invalid.
  • This embodiment can detect the current invoice in time to determine whether the current invoice is a regular and qualified invoice.
  • FIG. 6 based on the flow diagram of the first embodiment of the above-mentioned invoice entry method, a fourth implementation of an invoice entry method of the present application is proposed.
  • invoice format of the same type in a few regions is different from the conventional invoice format of the same type, we will classify the invoices by type, and will also summarize the invoice format of the same type of invoices in different regions; if the regions are different, but Invoices of the same type have exactly the same format, and they are summarized into an invoice format image.
  • step S60 includes:
  • Step S61 Determine the current invoice category corresponding to the current invoice and the region to which the current invoice belongs according to the target invoice format image.
  • the step S70 includes:
  • Step S71 Enter the image information of the current invoice into a storage area corresponding to the category of the current invoice and the region to which the current invoice belongs.
  • the database system of this embodiment is a relational database.
  • FIG. 7 is a schematic diagram of each data table of the database of this embodiment.
  • the database of this embodiment will include a piece of data for storing invoice format images.
  • Table invoice format image table A
  • data table for storing invoice type names invoice category table B
  • data table for storing invoice area data invoice area table D
  • invoice information table C multiple data tables (invoice information table C) that are used to store invoice image information divided by invoice categories. As shown in the figure, the same field attributes will exist between the data tables, and the same field attributes will be the primary key and Foreign key mapping relationship.
  • invoice category table B includes: invoice category ID (primary key) and invoice category name;
  • the attributes of the invoice information table C include: image information of the invoice (specific invoice content information field) and invoice category ID (foreign key);
  • the attributes of the invoice format image table D include: invoice area and invoice area ID (primary key).
  • the invoice entry device when the invoice entry device recognizes the current category of the current invoice, it enters the image information of the current invoice into the storage area corresponding to the current invoice category, that is, enters the image information of the current invoice into the storage area corresponding to the current invoice category. State the invoice information table C corresponding to the current invoice category. Furthermore, it can replace the manual classification of invoices and manually enter the invoice information into the computer. Workers can use the invoice entry device of this program to scan the invoice image information, and then automatically classify the invoice information and store it in the computer system. In, improve the efficiency of workers.
  • invoices are regional, and the format of invoices in different regions of the same type may be different. Workers also need to classify invoices by region, which is more time-consuming and laborious for workers.
  • the different invoice format images in this embodiment correspond to different invoice categories and invoice regions. That is, this embodiment can identify invoices of the same invoice category and different regions, and enter the image information of the current invoice with the current invoice category and the current invoice category. The storage area corresponding to the region where the invoice belongs.
  • 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 invoice entry method are realized.
  • FIG. 8 is a structural block diagram of a first embodiment of an invoice entry device according to the present application.
  • the device includes:
  • the collection module 10 is used to collect image information of the current invoice
  • the recognition module 20 is configured to recognize the feature point set A of the current invoice format of the current invoice from the image information;
  • the comparison module 30 is used to traverse the invoice format images in the image database, collect feature points of the traversed invoice format images, and obtain the feature point set X of the traversed invoice format images;
  • the comparison module 30 is further configured to compare the feature points in the feature point set A with the feature points in the feature point set X;
  • the comparison module 30 is further configured to, if the comparison result is the same, use the invoice format image corresponding to the feature point set X as the target invoice format image that matches the current invoice format;
  • the obtaining module 40 is configured to determine the current invoice category corresponding to the current invoice according to the target invoice format image
  • the storage module 50 is configured to record the image information of the current invoice into the storage area corresponding to the current invoice category.
  • the invoice entry device of this embodiment can be a program for supporting invoice entry and is loaded in the invoice entry device.
  • the invoice entry device of this embodiment can automatically process invoice information.
  • the classification is then stored in the computer system, which can replace the manual classification of invoices and improve the efficiency of workers.
  • the collection module 10 is also used to collect image information of the current invoice, and identify the current invoice format and invoice content information of the current invoice from the image information through optical character recognition technology.
  • the storage module 50 is further configured to record the image information of the current invoice and the invoice content information into the storage area corresponding to the current invoice category.
  • the acquiring module 40 is further configured to determine the current invoice category corresponding to the current invoice and the region where the current invoice belongs according to the target invoice format image.
  • the storage module 50 is also used to enter the image information of the current invoice into a storage area corresponding to the current invoice category and the region to which the current invoice belongs.
  • This embodiment can identify invoices of the same invoice category and different regions, and enter the image information of the current invoice into the storage area corresponding to the current invoice category and the region to which the current invoice belongs.
  • 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 ROM/RAM, magnetic disk, optical disk).
  • the disk includes several instructions to make a device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the method described in each embodiment of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Library & Information Science (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Character Input (AREA)

Abstract

一种发票录入方法、装置、设备及计算机存储介质,该方法首先采集当前发票的图像信息,从所述图像信息中识别出所述当前发票的当前发票格式;再根据所述当前发票格式对图片库中预存的发票格式图像进行比较,并获取与所述发票格式图像相匹配的目标发票格式图像;然后根据目标发票格式图像确定当前发票对应的当前发票类别;最后将当前发票的图像信息录入与当前发票类别对应的存储区域。能够自动将发票的信息进行分类然后存储到计算机系统中,进而能够代替人工式地对发票分类,提高了工作者的效率。

Description

发票录入方法、装置、设备及计算机存储介质
本申请要求于2019年6月19日提交中国专利局、申请号为201910548140.5、发明名称为“发票录入方法、装置、设备及计算机存储介质”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,尤其涉及一种发票录入方法、装置、设备及计算机存储介质。
背景技术
目前,国家税务机构会对各种类型的发票进行统计,国家税务机构的工作者在整理包括各种不同种类的发票时,需要手动将这些不同种类的发票进行分类,然后将它们录入到计算机系统中,如果发票数量很多、种类也很多,有些发票甚至具有区域性,工作者需要按照发票种类对发票进行分类,这样对工作者来说更加费时费力。
发明内容
本申请的主要目的在于提供了一种发票录入方法、装置、设备及计算机存储介质,旨在解决工作人员在手工统计发票时,由于数量多、种类多,工作人员手工操作起来费时费力的问题。
为实现上述目的,本申请提供了一种发票录入方法,所述方法包括以下步骤:
采集当前发票的图像信息;
从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
此外,为实现上述目的,本申请还提出一种发票录入装置,所述装置包括:
采集模块,用于采集当前发票的图像信息;
识别模块,用于从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
比较模块,用于对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
所述比较模块,还用于将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
所述比较模块,还用于若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
获取模块,用于根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
存储模块,用于将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
此外,为实现上述目的,本申请还提出一种用于发票录入的设备,所述设备包括:摄像头、存储器、处理器及存储在所述存储器上并可在所述处理器上执行的计算机可读指令,所述计算机可读指令被所述处理器执行时,实现如上所述发票录入方法的步骤。
此外,为实现上述目的,本申请还提出一种计算机存储介质,所述计算机存储介质上存储有计算机可读指令,所述计算机可读指令被所述处理器执行时,实现如上所述发票录入方法的步骤。
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设备的结构示意图;
图2为本申请一种发票录入方法第一实施例的流程示意图;
图3为本申请一实施例中的数据库的各个数据表的示意图
图4为本申请一种发票录入方法第二实施例的流程示意图;
图5为本申请一种发票录入方法第三实施例的流程示意图;
图6为本申请一种发票录入方法第四实施例的流程示意图;
图7为本申请又一实施例中的数据库的各个数据表的示意图;
图8为本申请一种发票录入装置的结构框图。
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设备结构示意图。
如图1所示,该设备可以包括:处理器1001,例如CPU,通信总线1002、用户接口1003,网络接口1004,存储器1005,摄像头1006。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),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WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),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。摄像头1006用于对发票的图像信息进行采集。
本领域技术人员可以理解,图1中示出的设备结构并不构成对本申请所述的设备的限定,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。
本申请所述设备通过处理器1001调用存储器1005中存储的计算机可读指令,并执行发票录入方法的步骤。
基于上述硬件结构,提出本申请一种发票录入方法实施例。
参照图2,图2为本申请一种发票录入方法第一实施例的流程示意图。
本实施例中,所述方法包括以下步骤:
步骤S10:采集当前发票的图像信息。
步骤S20:从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A。
具体地,本实施例的执行主体为发票录入设备,所述发票录入设备可以包括一摄像头,用于对当前发票的图像信息进行采集,工作者使用该设备对当前发票进行图像采集,从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
本实施例可以通过基于OpenCV(Open Source Computer Vision Library,开源计算机视觉库)函数对采集到的图像进行灰度处理,在经过二值化处理后得到表格线,
具体地,首先对采集到的图像进行灰度处理,调用OpenCV函数的Canny边缘检测算法在灰度图的基础上进行二值化处理,达成自动阈值的二值化,然后使用霍夫变换,检测出其中的直线,并在直线中,确认出围成一个矩形的区域,然后将这块区域提取出来;然后由获得的表格线得到单元格交点坐标,按坐标对表格图片进行分割,分割成多个单元格图片,交点坐标,这些交点就是当前发票格式的特征点,采集到当前发票格式的特征点集合A即确定当前发票格式的具体形状a。
步骤S30:对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X。
具体地,本实施例会预先对不同类型发票的发票格式进行归纳统计,举个例子,增值税发票的格式和机动车销售发票的表格格式差别很大,我们分别为这两种发票类型建立黑底背景,白色线条的图像(或者白底背景,黑色线条的图像),将其称之为表格线条图像,将建好的表格线条图像作为发票格式图像存储到图像库中。
在具体实现中,本实施例的图像库可以是关系型数据库,如MySQL数据库、SqlServer数据库。
步骤S40:将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对。
步骤S50:若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像。
步骤S60:根据所述目标发票格式图像确定所述当前发票对应的当前发票类别。
可理解的是,本实施例的发票格式图像比对方式属于二维图片与二维图片的比对,由于不同类型的发票格式都是表格形状,因此不同类型的发票图像的相似度会很高。本实施例采用特征点匹配的方式,即在处理“根据所述当前发票格式对图片库中预存的发票格式图像进行比较”的步骤时,对图像库中的发票格式图像遍历,并对遍历到的发票格式图像进行发票格式的特征点集合X的采集,将采集到当前发票格式的特征点集合A与发票格式图像的特征点集合X进行比对,具体地比对方式为:首先确定特征点集合A对应的当前发票格式的具体形状a,然后确定特征点集合X对应的发票格式图像的具体形状x,获取形状a的各个端点,同时获取形状x的各个端点,将形状a的端点和形状b的端点相连,例如形状a和形状x都是矩形,那么可将两个矩形的四个端点按照上、下、左、右的顺序对应连接。
紧接着,将所述特征点集合A与所述特征点集合B中对应的特征点相连,以获取各对应特征点之间的连线,计算各对应特征点之间的连线的长度,如果每条连线的长度近乎相等,则判定形状a和形状b形状相同,也即当前发票格式与图片库中遍历到的发票格式图像相同。
其中,具体地连线方式为:以已经连接的端点为基准,依照从左向右、从上到下的顺序进行特征点连接。
步骤S70:将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
可理解的是,本实施例的数据库系统为关系型数据库,参考图3,图3为本实施例的数据库的各个数据表的示意图,本实施例的数据库会包括一用于存储发票格式图像的数据表(发票格式图像表A)、一用于存储发票种类名称的数据表(发票类别表B),以及按照发票类别划分的多各用于存储发票图像信息的数据表(发票信息表C),如图所示,各数据表之间会存在相同的字段属性,相同的字段属性之间为主键与外键映射关系。
其中,所述发票类别表B的属性包括:发票类别ID(主键)和发票类别名称;
所述发票格式图像表A的属性包括:发票格式ID(主键)、发票格式图像和发票类别ID(外键);
所述发票信息表C的属性包括:发票的图像信息(具体发票内容信息字段)和发票类别ID(外键)。
具体地,当发票录入设备识别出所述当前发票的当前类别时,会将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域,即将所述当前发票的图像信息录入与所述当前发票类别对应的发票信息表C中。进而能够代替人工对发票进行分类后手工式地将发票信息输入到电脑中,工作者可以使用本方案的发票录入设备扫描发票图像信息后,能够自动将该发票的信息分类并存储到录计算机系统中,提高了工作者的效率。
本实施例首先采集当前发票的图像信息,从所述图像信息中识别出所述当前发票的当前发票格式;根据所述当前发票格式对图片库中预存的发票格式图像进行比较,并获取与所述发票格式图像相匹配的目标发票格式图像;
根据目标发票格式图像确定当前发票对应的当前发票类别;最后将当前发票的图像信息录入与当前发票类别对应的存储区域,即本实施例能够自动将发票的信息进行分类然后存储到计算机系统中,进而能够代替人工式地对发票分类,提高了工作者的效率。
进一步地,参考图4,基于上述发票录入方法的第一实施例流程示意图,提出本申请一种发票录入方法的第二实施。
本实施例中,所述步骤S10具体包括:
步骤S101:采集当前发票的图像信息,从所述图像信息中识别出所述当前发票的当前发票格式,并通过光学字符识别技术从所述图像信息中识别出所述当前发票的发票内容信息。
具体地,本实施例可采用光学字符识别技术(OCR,Optical Character Recognition)从所述图像信息中识别出所述当前发票的发票内容信息;即利用光学技术和计算机技术把印在或写在所述当前发票纸上的文字读取出来,并转换成一种计算机能够接受、人又可以理解的格式。文字识别是计算机视觉研究领域的比较成熟的技术,并且在商业中已经有很多落地项目了。其中,所述发票内容信息,至少包括发票编号、开票日期和交易信息,交易信息可以包括是购买方信息和卖方信息。
所述步骤S70具体包括:
步骤S701:将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
具体地,本实施例的所述发票信息表C的属性包括:发票的图像信息(具体发票内容信息字段)、发票类别ID(外键)以及发票编号、开票日期和交易信息等字段信息。
本实施例的当发票录入设备识别出所述当前发票的当前类别以及发票内容信息之后,会将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域,即将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的发票信息表C中。
进一步地,参考图5,基于上述发票录入方法的第二实施例,提出本申请一种发票录入方法的第三实施例。
本实施例中,所述步骤S101之后,包括:
步骤S102:从所述当前发票的图像信息中读取图章图像,将所述图章图像与预设图章进行比较,在所述图章图像与所述预设图章相同时,判断所述当前发票为合格发票。
可理解的是,本实施例在采集当前发票的图像信息的过程中,可以根据识别出当前发票的发票信息来对发票的真伪进行鉴定,例如根据采集到的图像信息判断发票票据上方中间有无椭圆形的红章,章的上方标有“全国统一发票监制章”,章下方标有“地方税务局监制”或者“国家税务局监制”的字样,判断该红章是否符合规范。
进一步地,本实施例中,所述步骤S101之后,也可以包括:
步骤:对本地网络与国家税务局服务器的连接状态进行检测,在检测结果为通讯状态时,从所述发票内容信息中读取当前发票编号;
步骤:根据所述当前发票编号对所述国家税务局服务器的数据库进行遍历,在成功遍历到与所述当前发票编号相同的发票编号时,判断所述当前发票为合格发票。
可理解的是,本实施例的发票录入设备与国家税务局数据库连接保持同步,发票录入设备扫描到当前发票的发票编码,根据扫描到的发票编号对国家税务局数据库进行查询,如果查询到相应的内容,则说明当前发票是有效的,否则是无效的。
此外,工作者在整理众多发票的过程中,难免会碰到“空白”发票,即没有盖章的无效发票,本方案会在采集当前发票的图像信息过程中,对图像中的盖章进行扫码,如果扫码结果发现当前发票没有印章,则说明书此为无效发票,并语音提示工作者。
本实施例能够及时对当前发票进行检测,判断当前发票是否为正规合格发票。
进一步地,参考图6,基于上述发票录入方法的第一实施例流程示意图,提出本申请一种发票录入方法的第四实施。
由于少数地区的同种类发票格式与相同种类常规的发票格式不同,因此我们在按照类型对发票分类的基础上,还会按照不同地区对相同类型的发票进行发票格式进行归纳统计;如果地区不同但是类型相同的发票的格式一模一样,则归纳为一种发票格式图像。
相应地,所述步骤S60,包括:
步骤S61,根据所述目标发票格式图像确定所述当前发票对应的当前发票类别和当前发票所属地区。
所述步骤S70,包括:
步骤S71,将所述当前发票的图像信息录入与所述当前发票类别以及所述当前发票所属地区对应的存储区域。
本实施例,本实施例的数据库系统为关系型数据库,参考图7,图7为本实施例的数据库的各个数据表的示意图,本实施例的数据库会包括一用于存储发票格式图像的数据表(发票格式图像表A)、一用于存储发票种类名称的数据表(发票类别表B)、一用于存储发票地区数据的数据表(发票地区表D)
以及按照发票类别划分的多各用于存储发票图像信息的数据表(发票信息表C),如图所示,各数据表之间会存在相同的字段属性,相同的字段属性之间为主键与外键映射关系。
其中,所述发票类别表B的属性包括:发票类别ID(主键)和发票类别名称;
所述发票格式图像表A的属性包括:发票格式图像、发票格式ID=发票类别ID+发票地区ID;
所述发票信息表C的属性包括:发票的图像信息(具体发票内容信息字段)和发票类别ID(外键);
所述发票格式图像表D的属性包括:发票地区和发票地区ID(主键)。
具体地,当发票录入设备识别出所述当前发票的当前类别时,会将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域,即将所述当前发票的图像信息录入与所述当前发票类别对应的发票信息表C中。进而能够代替人工对发票进行分类后手工式地将发票信息输入到电脑中,工作者可以使用本方案的发票录入设备扫描发票图像信息后,能够自动将该发票的信息分类并存储到录计算机系统中,提高了工作者的效率。
可理解的是,目前可能存在的现象是发票具有区域性,同种类不同地区的发票的格式可能存在差异,工作者还需要按照区域对发票进行分类,这样对应工作者来说更加费时费力。而本实施例不同的发票格式图像对应不同的发票类别和发票所属地区,即本实施例能够针对相同发票类别,不同地区的发票进行识别,按照将当前发票的图像信息录入与当前发票类别以及当前发票所属地区对应的存储区域。
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,实现如上述的发票录入方法的步骤。
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发票录入方法的各个实施例,此处不再赘述。
此外,本申请还提供一种发票录入装置,参照图8,图8为本申请一种发票录入装置第一实施例的结构框图,所述装置包括:
采集模块10,用于采集当前发票的图像信息;
识别模块20,用于从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
比较模块30,用于对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
所述比较模块30,还用于将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
所述比较模块30,还用于若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
获取模块40,用于根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
存储模块50,用于将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
可理解的是,本实施例的一种发票录入装置可以是一种用于支持发票录入的程序,并装载于所述发票录入设备中,本实施例的发票录入装置能够自动将发票的信息进行分类然后存储到计算机系统中,进而能够代替人工式地对发票分类,提高了工作者的效率。
本实施例的发票录入装置的具体实施方式请参照上述发票录入方法实施例,本实施例在此不予赘述。
基于本申请上述发票录入装置第一实施例,提出本申请发票录入装置的第二实施例。
本实施例中,所述采集模块10还用于采集当前发票的图像信息,通过光学字符识别技术从所述图像信息中识别出所述当前发票的当前发票格式和发票内容信息。所述存储模块50还用于将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
基于本申请上述发票录入装置第一实施例,提出本申请发票录入装置的第三实施例。
所述获取模块40,还用于根据所述目标发票格式图像确定所述当前发票对应的当前发票类别和当前发票所属地区。
所述存储模块50,还用于将所述当前发票的图像信息录入与所述当前发票类别以及所述当前发票所属地区对应的存储区域。
本实施例能够针对相同发票类别,不同地区的发票进行识别,按照将当前发票的图像信息录入与当前发票类别以及当前发票所属地区对应的存储区域。
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ROM/RAM、磁碟、光 盘)中,包括若干指令用以使得一台设备(可以是手机,计算机,服务器,空调器,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. 一种发票录入方法,其中,所述方法包括:
    采集当前发票的图像信息;
    从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
    对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
    将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
    若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
    将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
  2. 如权利要求1所述的方法,其中,所述采集当前发票的图像信息的步骤之后,包括:
    通过光学字符识别技术从所述图像信息中识别出所述当前发票的发票内容信息;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
  3. 如权利要求2所述的方法,其中,所述采集当前发票的图像信息的步骤之后,包括:
    从所述当前发票的图像信息中读取图章图像,将所述图章图像与预设图章进行比较,在所述图章图像与所述预设图章相同时,判断所述当前发票为合格发票。
  4. 如权利要求2所述的方法,其中,所述通过光学字符识别技术从所述图像信息中识别出所述当前发票的当前发票格式和发票内容信息的步骤之后,包括:
    对本地网络与国家税务局服务器的连接状态进行检测,在检测结果为通讯状态时,从所述发票内容信息中读取当前发票编号;
    根据所述当前发票编号对所述国家税务局服务器的数据库进行遍历,在成功遍历到与所述当前发票编号相同的发票编号时,判断所述当前发票为合格发票。
  5. 如权利要求1所述的方法,其中,不同的发票格式图像对应不同的发票类别和发票所属地区;
    所述根据所述目标发票格式图像确定所述当前发票对应的当前发票类别的步骤,包括:
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别和当前发票所属地区;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息录入与所述当前发票类别以及所述当前发票所属地区对应的存储区域。
  6. 如权利要求1所述的方法,其中,所述发票内容信息至少包括发票编号、开票日期和交易信息。
  7. 一种发票录入装置,其中,所述装置包括:
    采集模块,用于采集当前发票的图像信息;
    识别模块,用于从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
    比较模块,用于对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
    所述比较模块,还用于将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
    所述比较模块,还用于若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
    获取模块,用于根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
    存储模块,用于将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
  8. 如权利要求7所述的装置,其中,所述采集模块,还用于通过光学字符识别技术从所述图像信息中识别出所述当前发票的发票内容信息;
    所述存储模块,还用于将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
  9. 如权利要求8所述的装置,其中,所述比较模块,还用于从所述当前发票的图像信息中读取图章图像,将所述图章图像与预设图章进行比较,在所述图章图像与所述预设图章相同时,判断所述当前发票为合格发票。
  10. 如权利要求8所述的装置,其中,所述存储模块,还用于对本地网络与国家税务局服务器的连接状态进行检测,在检测结果为通讯状态时,从所述发票内容信息中读取当前发票编号;根据所述当前发票编号对所述国家税务局服务器的数据库进行遍历,在成功遍历到与所述当前发票编号相同的发票编号时,判断所述当前发票为合格发票。
  11. 一种用于发票录入的设备,其中,所述设备包括:摄像头、存储器、处理器及存储在所述存储器上并可在所述处理器上运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;
    采集当前发票的图像信息;
    从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
    对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
    将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
    若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
    将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
  12. 如权利要求11所述的设备,其中,所述所述采集当前发票的图像信息的步骤之后,包括:
    通过光学字符识别技术从所述图像信息中识别出所述当前发票的发票内容信息;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
  13. 如权利要求12所述的设备,其中,所述采集当前发票的图像信息的步骤之后,包括:
    从所述当前发票的图像信息中读取图章图像,将所述图章图像与预设图章进行比较,在所述图章图像与所述预设图章相同时,判断所述当前发票为合格发票。
  14. 如权利要求12所述的设备,其中,所述通过光学字符识别技术从所述图像信息中识别出所述当前发票的当前发票格式和发票内容信息的步骤之后,包括:
    对本地网络与国家税务局服务器的连接状态进行检测,在检测结果为通讯状态时,从所述发票内容信息中读取当前发票编号;
    根据所述当前发票编号对所述国家税务局服务器的数据库进行遍历,在成功遍历到与所述当前发票编号相同的发票编号时,判断所述当前发票为合格发票。
  15. 如权利要求11所述的设备,其中,不同的发票格式图像对应不同的发票类别和发票所属地区;
    所述根据所述目标发票格式图像确定所述当前发票对应的当前发票类别的步骤,包括:
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别和当前发票所属地区;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息录入与所述当前发票类别以及所述当前发票所属地区对应的存储区域。
  16. 一种计算机存储介质,其中,所述计算机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;
    采集当前发票的图像信息;
    从所述图像信息中识别出所述当前发票的当前发票格式的特征点集合A;
    对图像库中的发票格式图像遍历,对遍历到的发票格式图像进行特征点采集,得到遍历到的发票格式图像的特征点集合X;
    将所述特征点集合A中的特征点与所述特征点集合X中的特征点进行比对;
    若比对结果相同,则将所述特征点集合X对应的发票格式图像作为与所述当前发票格式相匹配的目标发票格式图像;
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别;
    将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域。
  17. 如权利要求16所述的计算机可读存储介质,其中,所述采集当前发票的图像信息的步骤之后,包括:
    通过光学字符识别技术从所述图像信息中识别出所述当前发票的发票内容信息;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息和所述发票内容信息录入与所述当前发票类别对应的存储区域。
  18. 如权利要求17所述的计算机可读存储介质,其中,所述采集当前发票的图像信息的步骤之后,包括:
    从所述当前发票的图像信息中读取图章图像,将所述图章图像与预设图章进行比较,在所述图章图像与所述预设图章相同时,判断所述当前发票为合格发票。
  19. 如权利要求17所述的计算机可读存储介质,其中,所述通过光学字符识别技术从所述图像信息中识别出所述当前发票的当前发票格式和发票内容信息的步骤之后,包括:
    对本地网络与国家税务局服务器的连接状态进行检测,在检测结果为通讯状态时,从所述发票内容信息中读取当前发票编号;
    根据所述当前发票编号对所述国家税务局服务器的数据库进行遍历,在成功遍历到与所述当前发票编号相同的发票编号时,判断所述当前发票为合格发票。
  20. 如权利要求16所述的计算机可读存储介质,其中,不同的发票格式图像对应不同的发票类别和发票所属地区;
    所述根据所述目标发票格式图像确定所述当前发票对应的当前发票类别的步骤,包括:
    根据所述目标发票格式图像确定所述当前发票对应的当前发票类别和当前发票所属地区;
    所述将所述当前发票的图像信息录入与所述当前发票类别对应的存储区域的步骤,包括:
    将所述当前发票的图像信息录入与所述当前发票类别以及所述当前发票所属地区对应的存储区域。
PCT/CN2019/120910 2019-06-19 2019-11-26 发票录入方法、装置、设备及计算机存储介质 WO2020253113A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910548140.5 2019-06-19
CN201910548140.5A CN110619056A (zh) 2019-06-19 2019-06-19 发票录入方法、装置、设备及计算机存储介质

Publications (1)

Publication Number Publication Date
WO2020253113A1 true WO2020253113A1 (zh) 2020-12-24

Family

ID=68921635

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/120910 WO2020253113A1 (zh) 2019-06-19 2019-11-26 发票录入方法、装置、设备及计算机存储介质

Country Status (2)

Country Link
CN (1) CN110619056A (zh)
WO (1) WO2020253113A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113205349B (zh) * 2021-04-26 2022-10-25 临沂职业学院 用于发票管理的装置及方法、电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204576535U (zh) * 2014-12-22 2015-08-19 深圳中兴网信科技有限公司 一种票据识别装置
US20160196476A1 (en) * 2014-06-13 2016-07-07 Grg Banking Equipment Co., Ltd. Multi-cue fusion based ticket positioning recognition method and system
CN108717545A (zh) * 2018-05-18 2018-10-30 北京大账房网络科技股份有限公司 一种基于手机拍照的票据识别方法及系统
CN108921240A (zh) * 2018-06-12 2018-11-30 新乡学院 一种发票编码识别分拣系统
CN109726783A (zh) * 2018-12-28 2019-05-07 大象慧云信息技术有限公司 一种基于ocr图像识别技术的发票采集管理系统及方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7783135B2 (en) * 2005-05-09 2010-08-24 Like.Com System and method for providing objectified image renderings using recognition information from images
CN103208004A (zh) * 2013-03-15 2013-07-17 北京英迈杰科技有限公司 票据信息区域自动识别和提取方法及设备
CN105045780B (zh) * 2015-07-15 2017-12-26 广州敦和信息技术有限公司 一种发票字条语义信息的识别方法及装置
CN107633239B (zh) * 2017-10-18 2020-11-03 中电鸿信信息科技有限公司 基于深度学习和ocr的票据分类及票据字段提取方法
CN109635633A (zh) * 2018-10-26 2019-04-16 平安科技(深圳)有限公司 电子装置、票据识别方法及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160196476A1 (en) * 2014-06-13 2016-07-07 Grg Banking Equipment Co., Ltd. Multi-cue fusion based ticket positioning recognition method and system
CN204576535U (zh) * 2014-12-22 2015-08-19 深圳中兴网信科技有限公司 一种票据识别装置
CN108717545A (zh) * 2018-05-18 2018-10-30 北京大账房网络科技股份有限公司 一种基于手机拍照的票据识别方法及系统
CN108921240A (zh) * 2018-06-12 2018-11-30 新乡学院 一种发票编码识别分拣系统
CN109726783A (zh) * 2018-12-28 2019-05-07 大象慧云信息技术有限公司 一种基于ocr图像识别技术的发票采集管理系统及方法

Also Published As

Publication number Publication date
CN110619056A (zh) 2019-12-27

Similar Documents

Publication Publication Date Title
WO2020082562A1 (zh) 字符识别方法、装置、设备及存储介质
WO2020119116A1 (zh) 基于数据分析的医保审核方法、装置、设备和存储介质
WO2020015067A1 (zh) 数据采集方法、装置、设备及存储介质
WO2020034526A1 (zh) 保险录音的质检方法、装置、设备和计算机存储介质
WO2020073495A1 (zh) 基于人工智能的复审方法、装置、设备及存储介质
WO2020186777A1 (zh) 图像检索方法、装置、设备及计算机可读存储介质
WO2022039330A1 (ko) 가상 셀을 이용한 ocr 기반 문서 분석 시스템 및 방법
WO2011021907A2 (en) Metadata tagging system, image searching method and device, and method for tagging a gesture thereof
WO2021003930A1 (zh) 客服录音的质检方法、装置、设备及计算机可读存储介质
WO2019024485A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2020087704A1 (zh) 信贷信息管理方法、装置、设备和存储介质
WO2019132566A1 (ko) 멀티 심도 이미지의 자동 생성 방법
WO2018201638A1 (zh) 基于图像识别的信息采集方法、移动终端及存储介质
WO2020087981A1 (zh) 风控审核模型生成方法、装置、设备及可读存储介质
WO2020119384A1 (zh) 基于大数据分析的医保异常检测方法、装置、设备和介质
WO2020233089A1 (zh) 测试用例生成方法、装置、终端及计算机可读存储介质
EP2435935A2 (en) Method of providing by-viewpoint patent map and system thereof
WO2021012508A1 (zh) Ai影像识别方法、装置、设备及存储介质
WO2020253113A1 (zh) 发票录入方法、装置、设备及计算机存储介质
WO2021027143A1 (zh) 信息推送方法、装置、设备及计算机可读存储介质
WO2020098078A1 (zh) Ocr训练样本的生成方法、装置、设备及可读存储介质
WO2020047960A1 (zh) 数据处理方法、显示装置和计算机可读存储介质
WO2020119175A1 (zh) 医疗费用异常的监控方法、监控服务端及存储介质
WO2020199599A1 (zh) 工作队列的信息展示方法、装置、计算机设备和存储介质
WO2021051557A1 (zh) 基于语义识别的关键词确定方法、装置和存储介质

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: 19933970

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19933970

Country of ref document: EP

Kind code of ref document: A1

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 1205 DATED 29/03/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19933970

Country of ref document: EP

Kind code of ref document: A1