CN110097329B - Information auditing method, device, equipment and computer readable storage medium - Google Patents
Information auditing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110097329B CN110097329B CN201910205659.3A CN201910205659A CN110097329B CN 110097329 B CN110097329 B CN 110097329B CN 201910205659 A CN201910205659 A CN 201910205659A CN 110097329 B CN110097329 B CN 110097329B
- Authority
- CN
- China
- Prior art keywords
- auditing
- audit
- text
- content
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000012550 audit Methods 0.000 claims abstract description 500
- 239000000463 material Substances 0.000 claims abstract description 151
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000012015 optical character recognition Methods 0.000 claims description 28
- 239000012634 fragment Substances 0.000 claims description 24
- 238000002372 labelling Methods 0.000 claims description 11
- 230000001960 triggered effect Effects 0.000 claims description 6
- 230000000052 comparative effect Effects 0.000 claims 2
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013136 deep learning model Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000000977 initiatory effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Character Discrimination (AREA)
Abstract
The invention provides an information auditing method, which comprises the following steps: extracting text information in the auditing material image based on an OCR extraction technology, and slicing the text information based on a preset slicing rule to obtain one or more text segments; comparing each text segment with a preset label, acquiring a first audit label in the text segment based on a comparison result, and acquiring a first audit content in the text segment or audit material image; determining a second check tag matched with each first check tag based on pre-stored association information of the text segment first check tag and the second check tag of the input information; and comparing and auditing the auditing contents corresponding to the first auditing label with the auditing contents corresponding to the matched second auditing label in the text segment, or generating first comparison auditing information for the auditing personnel to conduct manual auditing. The invention also provides an information auditing device, equipment and a computer readable storage medium. The invention can improve the information auditing efficiency.
Description
Technical Field
The present invention relates to the field of transaction auditing technologies, and in particular, to an information auditing method, apparatus, device, and computer readable storage medium.
Background
At present, in the transaction approval process, the input information submitted by a user when the user initiates approval and related audit file materials are generally required to be compared and audited. For example, in the examination of real estate registration, it is necessary to compare and examine the input information, such as the name or address, at the time of registration initiation with the information in the image of the examination material, such as the real estate card or the identity card, uploaded at the time of registration initiation. In the prior art, transaction approval is generally carried out by adopting a manual mode, and in the auditing process, the review needs to be switched back and forth between the input information and the image of the auditing material, so that the auditing efficiency is very low.
Disclosure of Invention
The invention mainly aims to provide an information auditing method, device, equipment and computer readable storage medium, aiming at improving information auditing efficiency.
In order to achieve the above object, the present invention provides an information auditing method, comprising the steps of:
extracting text information in the auditing material image based on an OCR optical character recognition extraction technology, and slicing the text information based on preset slicing rules of the auditing material to obtain one or more text segments of the auditing material;
Comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image;
determining a second check tag matched with each first check tag based on pre-stored association information of the text segment first check tag and the second check tag of the input information;
and comparing and checking the checking content corresponding to the first checking label in the text segment with the checking content corresponding to the matched second checking label, or generating first comparison checking information based on the first checking label in the text segment and the corresponding first checking content, and the first comparison checking information generated by the matched second checking label and the corresponding second checking content, so that the auditor can check manually.
Optionally, the first audit content is first text audit content extracted from the text segment, the second audit content is second text audit content input by the user based on the second audit tag, and the step of comparing and auditing the audit content corresponding to the first audit tag in the text segment with the audit content corresponding to the matched second audit tag includes:
Comparing the first text audit content with the second text audit content to determine whether the first text audit content and the second text audit content are consistent;
if the first text audit content and the second text audit content are inconsistent, judging that the comparison audit of the first text audit content and the second text audit content is not passed.
Optionally, the first audit content is an image audit content extracted from the audit material image, the second audit content is a second text audit content input by a user based on the second audit tag, and the step of generating first comparison audit information based on the first audit tag and the corresponding first audit content in the text segment, and the matched second audit tag and the corresponding second audit content for the auditor to perform manual audit includes:
and generating first comparison audit information based on the first audit label and the corresponding image audit content and the matched second audit label and the corresponding second audit content so as to enable an auditor to conduct manual audit.
Optionally, the step of determining that the first audit content and the second audit content do not pass includes:
and based on the first audit content and the second comparison audit information in the second audit Rong Shengcheng, which do not pass the comparison audit, the auditor can conduct manual audit.
Optionally, the step of providing the auditor with the manual audit based on the first audit content and the second comparison audit information Rong Shengcheng in the second audit that the comparison audit does not pass includes:
determining a first position of the first text audit content in the audit material image based on the position of the first text audit content in the text information, and determining a second position of the corresponding second text audit content in the input information;
performing auditing and labeling on first text auditing contents in the auditing material image based on the first position, and performing auditing and labeling on second text auditing contents in the input information based on the second position;
generating second comparison audit information based on the annotated audit material image and the annotated input information for manual audit by an auditor;
and when an audit result submitting instruction triggered by an auditor is received, determining a final audit result of the input information based on the audit result submitting instruction.
Optionally, the method for performing audit annotation at least comprises the following steps: highlighting the text of the check content, setting the text of the check content to a preset font color, or underlining the text of the check content.
Optionally, the step of slicing the text information based on the preset slicing rule of the audit material to obtain one or more text segments of the audit material includes:
comparing the text information with the preset label, and determining a third position of a third check label matched with the preset label in the text information;
and slicing the text information based on the third position to obtain text fragments corresponding to each third check label.
In addition, in order to achieve the above object, the present invention also provides an information auditing apparatus, including:
the slicing module is used for extracting the text information in the auditing material image based on the OCR optical character recognition extraction technology, and slicing the text information based on the preset slicing rule of the auditing material to obtain one or more text fragments of the auditing material;
the comparison module is used for comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image;
The determining module is used for determining a second check tag matched with each first check tag based on pre-stored association information of the first check tag of the text segment and the second check tag of the input information;
the auditing module is used for comparing and auditing the auditing contents corresponding to the first auditing label in the text segment with the auditing contents corresponding to the matched second auditing label, or generating first comparison auditing information based on the first auditing label in the text segment and the corresponding first auditing content, and the first comparison auditing information generated by the matched second auditing label and the corresponding second auditing content, so that the auditor can conduct manual auditing.
In addition, in order to achieve the above object, the present invention also provides an information auditing apparatus, which includes a processor, a memory, and an information auditing program stored on the memory and executable by the processor, wherein the information auditing program, when executed by the processor, implements the steps of the information auditing method as described above.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium having stored thereon an information auditing program, wherein the information auditing program, when executed by a processor, implements the steps of the information auditing method as described above.
The invention provides an information auditing method, device, equipment and computer readable storage medium, wherein the information auditing method comprises the following steps: extracting text information in the auditing material image based on an OCR optical character recognition extraction technology, and slicing the text information based on preset slicing rules of the auditing material to obtain one or more text segments of the auditing material; comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image; determining a second check tag matched with each first check tag based on pre-stored association information of the text segment first check tag and the second check tag of the input information; and comparing and checking the checking content corresponding to the first checking label in the text segment with the checking content corresponding to the matched second checking label, or generating first comparison checking information based on the first checking label in the text segment and the corresponding first checking content, and the first comparison checking information generated by the matched second checking label and the corresponding second checking content, so that the auditor can check manually. According to the method, the OCR technology can be utilized to convert the auditing material image into the text format to obtain text information of the text format of the auditing material, the text information of the auditing material can be sliced into text fragments corresponding to auditing matters based on a preset slicing rule, auditing labels and auditing contents in the text fragments can be respectively extracted based on preset labels, the auditing labels of the same auditing matters in the input information can be determined based on prestored associated information, and the auditing modes of comparison auditing are replaced by auditing modes of comparison auditing of the auditing contents corresponding to the auditing labels of the text fragments and the input information, so that auditing efficiency is improved; or generating comparison audit information based on the audit label matched in the text segment and the input information or audit content corresponding to the matched audit label, so that switching comparison between audit materials and the input information can be avoided, and audit efficiency is improved.
Drawings
FIG. 1 is a schematic hardware structure of an information auditing apparatus according to an embodiment of the present invention;
FIG. 2 is a flowchart of a first embodiment of an information auditing method according to the present invention;
FIG. 3 is a flowchart of a second embodiment of the information auditing method of the present invention;
FIG. 4 is a flowchart of a third embodiment of an information auditing method according to the present invention;
FIG. 5 is a flowchart of a fourth embodiment of an information auditing method according to the present invention;
FIG. 6 is a flowchart of a fifth embodiment of an information auditing method according to the present invention;
fig. 7 is a schematic diagram of a functional module of the information auditing apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The information auditing method related to the embodiment of the invention is mainly applied to information auditing equipment, and the information auditing equipment can be personal computers (personal computer, PC), portable computers, mobile terminals and other equipment with data processing functions.
Referring to fig. 1, fig. 1 is a schematic hardware structure of an information auditing apparatus according to an embodiment of the present invention. In an embodiment of the present invention, the information auditing device may include a processor 1001 (e.g., central processing unit Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communications between these components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM) or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may alternatively be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration shown in fig. 1 is not limiting of the invention and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
With continued reference to FIG. 1, memory 1005, which is one type of computer-readable storage medium in FIG. 1, may include an operating system, a network communication module, and an information auditing program. In fig. 1, the network communication module may be used to connect to a server and perform data communication with the server; and the processor 1001 may call the information auditing program stored in the memory 1005 and execute the information auditing method provided by the embodiment of the present invention.
The embodiment of the invention provides an information auditing method.
Referring to fig. 2, fig. 2 is a flowchart of a first embodiment of the information auditing method according to the present invention.
At present, in the transaction approval process, the input information submitted by a user when the user initiates approval and related audit file materials are generally required to be compared and audited. For example, in the examination of real estate registration, it is necessary to compare and examine the input information, such as the name or address, at the time of registration initiation with the information in the image of the examination material, such as the real estate card or the identity card, uploaded at the time of registration initiation. In the prior art, transaction approval is generally carried out by adopting a manual mode, and in the auditing process, the review needs to be switched back and forth between the input information and the image of the auditing material, so that the auditing efficiency is very low.
In this embodiment, the information auditing method includes the following steps:
step S10, extracting text information in the auditing material image based on an OCR optical character recognition extraction technology, and slicing the text information based on preset slicing rules of the auditing material to obtain one or more text segments of the auditing material;
the invention is mainly applied to the technical field of transaction approval, such as the technical field of house property transaction approval. The information auditing method of the invention can be executed by a preset information auditing system. In this embodiment, the management system or the server is connected to the information input and uploading system, and performs information auditing processing on the data of the information input and uploading system.
The auditing material comprises paper materials such as a house property certificate, an identity card, a mortgage contract or a trade contract. The audit materials can be photographed or scanned to obtain images of the audit materials. For example, when it is required to audit the contents of the matters such as "proof rights or matters", "rights person (applicant)" or "obligator" of the real estate certificate, the related personnel, such as the sponsor or auditor of the transaction approval, scan the audit materials containing the contents of the matters to obtain the corresponding audit material images, and upload the obtained audit material images to the information audit system. And after the information auditing system obtains the auditing material image, extracting text information in the auditing material image based on an OCR optical character recognition extraction technology. The OCR technology of this embodiment is an abbreviation (Optical Character Recognition) for optical character recognition, which converts characters in various notes, newspapers, books, manuscripts, and other printed matters into image information by scanning or other optical input methods, converts the image information into usable computer input technology by using the character recognition technology, converts characters in paper documents into image files of black-and-white dot matrixes by adopting an optical method, and converts characters in images into text formats by using recognition software. The method can be applied to the fields of inputting and processing bank notes, a large amount of text data, file files and texts, and is suitable for automatic scanning recognition and long-term storage of a large amount of note forms in the industries of banks, tax and the like. In the text extraction process, the extracted text is arranged based on the extraction sequence and the relative positions of the extracted text in the audit material images.
After obtaining the text information in the image of the auditing material, slicing the obtained text information based on a preset slice of the auditing material to obtain one or more text segments of the auditing material, wherein each text segment corresponds to one auditing item, for example, for a house property certificate, the auditing item can comprise auditing items such as a house owner or a house sitting. Different audit materials correspond to different text typesetting formats or page layouts, and in general, typesetting formats or page layouts of audit materials of the same type are relatively uniform, so that different slicing rules can be set for text information of different audit materials, and the slicing rules are configured in an information audit system. The preset slicing rules may be determined in advance based on the position of the item content text in the page layout of the audit material, for example based on the paragraph, specific line number, or field of the item content in the audit material. For a slicing rule determined based on the page position, determining the position of the item content in a preset rule in the slicing process, and intercepting the characters of each item content based on the position of the item content to obtain the character fragments of the item content.
Further, the preset slicing rules may also be determined based on audit labels. Specifically, the audit tag may be set in advance based on an actual field of the contents of the matter of the audit material, for example, for the audit material property certificate, the audit tag "house owner" or "house sitting" or the like, and the "buyer" or "seller" or the like in the house business contract may be set, and the set audit tag is configured in the audit rule. For the preset slicing rule based on the auditing label, in the slicing process, the preset label of the auditing material and the text information of the auditing material can be compared and matched, the text matched with the preset auditing label in the text information of the auditing material is identified, the position of the text in the text information is determined, and then the contents of the items such as the certification right or item, the right person (applicant) or the obligator are sliced respectively based on the material preset slicing rule. In general, the page layout of the different audit materials is relatively uniform, and the preset slicing rules may be determined based on the page position of the item content in the audit material, for example, based on the paragraph or specific line number range of the item content in the audit material. For a slicing rule determined based on a page position, in the slicing process, firstly, the position of the item content in a preset rule is based, and the image fragment of each item content is intercepted based on the position of the item content. Further, the preset slicing rule may be determined based on the position of the audit tag information, specifically, preset audit tag fields, such as "right person", "obligator" or "proof right or item", may be pre-stored in the preset slicing rule, in the slicing process, text information matched with the preset audit tag field may be determined first from the material image, and the position of the matched text information in the image may be determined, for each audit tag field, the beginning text line where the audit tag field is located is determined, the previous line where the next audit tag field is located is an ending text line, the image segment between the beginning text line and the ending text line is intercepted, or the audit tag field is taken as the beginning field, the last text before the next audit tag field is taken as the ending field, and the image segment between the beginning field and the ending field is intercepted.
For the text in each image segment, the text can be divided into audit tag text and audit content text, where audit tag text refers to text indicating audit content category, for example, fields such as "right person", "obligator" or "proof right or item" in step S10; the auditing content text refers to specific text content corresponding to each auditing label, and also is content to be audited, specifically, the complete text of the image segment corresponding to the auditing label text, namely "right person", is "right person: li Xiaoming ", li Xiaoming" is audit content text. For example, for various types of audit materials, audit tag information for the audit type may be preset and stored at a preset location. After the characters of the image fragments are extracted, comparing and matching the characters of the image fragments with the characters in the preset positions, determining audit tag characters in the characters of the image fragments, and taking the rest characters as audit content characters. For an identity card, the audit tag text that may be extracted may include: "identification card number", "name", "address" and "year of birth", etc.; for a real estate trade contract, the extracted audit tag text may include: "seller" or "buyer" and the like; for a property certificate, the audit tag text that can be extracted can include: "House ownership", "sharing" or "House sitting", etc.
Further, for audit materials with a page layout in a table form, such as a property certificate, a preset slicing rule can be determined based on the table form of the audit materials, and text information can be extracted for slicing according to the slicing rule based on the table form. In this embodiment, a table template may be created based on the table format of the audit material in advance, and identification codes may be added to each cell in the table template, for example, a cell number is added, and a slicing rule based on the cell number is set, for example, it may be set that a combination of characters in the extracted cell 1 and the cell 2 is used as a text segment, characters in the cell 3 and the cell 4 are used as a text segment … …, in the process of extracting characters from the audit material image by using OCR, table lines in the audit material image are identified at the same time, a table of the audit material is obtained based on the identified table lines, and the extracted characters and the table thereof are obtained, and an OCR extraction table corresponding to the audit material image is obtained, wherein in the OCR extraction table, the OCR extracted character information and the table are included, and the extracted character information and the table is typeset based on the positional relationship of the OCR-identified characters and the table cells. After the OCR extraction form is obtained, the text segment of the slice is obtained based on the form coding of the cell and the extraction combination rule of the text.
Step S20, comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image;
in this embodiment, the preset label, that is, the audit label set based on the actual field of the item content of the audit material, is consistent with the label definition in the slicing rule based on the audit label in step S10. For each audit material, one or more audit tags can be preset as preset tags as required. After the text fragments are obtained, the text in the text fragments is compared with the preset labels one by one, and a text field consistent with one of the preset labels in the text fragments, namely a first check label, is determined. The first audit tag in this embodiment is a text field extracted from a text segment of the audit material and matched with a preset tag. After the first audit tag is obtained, the text fields except the first audit tag in the text segment are used as first audit content, namely audit content extracted from the text segment in the audit material. Specifically, the text segment extracted from the property certificate may include "house ownership Li Xiaoming", and the preset tag in the property certificate of the auditing material may include "house ownership", "house seating" and "sharing condition", and in the process of performing contrast matching, the "house ownership Li Xiaoming" may be compared with tag fields such as "house ownership", "house seating" and "sharing condition", respectively, and then it may be determined that the first auditing tag corresponding to the text segment "house ownership Li Xiaoming" is "house ownership", and the field "Li Xiaoming" other than the first auditing tag is the first auditing content.
Step S30, determining a second check tag matched with each first check tag based on pre-stored association information of the first check tag of the text segment and the second check tag of the input information;
the input information refers to application information input by a user in an input interface in a system in the process of applying for real estate transaction registration. The input information comprises name information of a property owner, identification information such as an identification card number and the like, address information of the property and the like, and property occupation area information. The audit labels in the input information correspond to the required information items in the input interface, namely, second audit labels, such as 'rights names' or 'identity card numbers', and the audit contents in the input information are text information input by a user in an edit box of each required information item. The required information items to be compared and audited can be associated with audit tag characters in advance based on audit requirements, and association information between the first audit tag and the second audit tag is generated and stored in a preset association information storage position. After the first audit label and the first audit content of the text segment of the audit material are obtained, pre-stored association information comprising the first audit label is determined, and a second audit label corresponding to the first audit label in the pre-stored association information is determined. Specifically, in this embodiment, the first audit tag "house owner" and the second audit tag "right person name" may be associated in advance, association information of the "house owner" and the "right person name" may be generated, and the association information may be stored in a preset storage location. When the first audit tag 'house ownership' is obtained, determining that a second audit tag matched with the first audit tag is 'right person name' based on the association relation.
And S40, comparing and checking the checking content corresponding to the first checking label in the text segment with the checking content corresponding to the matched second checking label, or generating first comparison checking information based on the first checking label in the text segment and the corresponding first checking content, and the matched second checking label and the corresponding second checking content, so as to enable the auditor to conduct manual checking.
Based on step S30, after determining the second audit tag corresponding to the first audit tag, respectively obtaining audit contents corresponding to the two audit tags, and comparing the obtained audit contents or generating first comparison audit information based on the first audit tag and the corresponding first audit content, and the second audit tag and the corresponding second audit content, so as to enable an auditor to perform manual audit. In the embodiment, the auditing content of the specific auditing matters can be compared and audited in advance according to the requirement, the matters outside the comparison and audit are manually audited, and the auditing content is a printed character body with standard character body characteristics, so that the identification and comparison are convenient, and the comparison and audit can be carried out; and for the audit content of the handwriting, the identification and the comparison audit are inconvenient, and the comparison audit information can be generated for the auditor to conduct manual audit, such as the handwritten signature of related personnel.
In the embodiment, text information in an audit material image is extracted based on an OCR optical character recognition extraction technology, and the text information is sliced based on a preset slicing rule of the audit material, so that one or more text segments of the audit material are obtained; comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image; determining a second check tag matched with each first check tag based on pre-stored association information of the text segment first check tag and the second check tag of the input information; and comparing and checking the checking content corresponding to the first checking label in the text segment with the checking content corresponding to the matched second checking label, or generating first comparison checking information based on the first checking label in the text segment and the corresponding first checking content, and the first comparison checking information generated by the matched second checking label and the corresponding second checking content, so that the auditor can check manually. According to the method, the OCR technology can be utilized to convert the auditing material image into the text format to obtain text information of the text format of the auditing material, the text information of the auditing material can be sliced into text fragments corresponding to auditing matters based on a preset slicing rule, auditing labels and auditing contents in the text fragments can be respectively extracted based on preset labels, the auditing labels of the same auditing matters in the input information can be determined based on prestored associated information, and the auditing modes of comparison auditing are replaced by auditing modes of comparison auditing of the auditing contents corresponding to the auditing labels of the text fragments and the input information, so that auditing efficiency is improved; or generating comparison audit information based on the audit label matched in the text segment and the input information or audit content corresponding to the matched audit label, so that switching comparison between audit materials and the input information can be avoided, and audit efficiency is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a second embodiment of the information auditing method according to the present invention.
Based on the above embodiment, in this embodiment, the first audit content is first text audit content extracted from the text segment, the second audit content is second text audit content entered by a user based on the second audit tag, and the step of comparing and auditing the audit content corresponding to the first audit tag in the text segment with the audit content corresponding to the matched second audit tag includes:
s50, comparing the first text audit content with the second text audit content to determine whether the first text audit content and the second text audit content are consistent;
based on the above embodiment, in this embodiment, the first audit content is the first text audit content extracted from the text segment, that is, the remaining text content in the text segment except for the first audit tag, such as "Li Xiaoming" in the first embodiment. The second auditing content is text information content input by the user based on a second auditing label in the information input interface, namely the second text auditing content. In this embodiment, after determining the second audit tag that matches the first audit tag, the first text audit content corresponding to the first audit tag is compared with the second text audit content corresponding to the corresponding matched second audit tag, and whether the first text audit content and the second text audit content are consistent is determined.
And step S60, if the first text audit content and the second text audit content are inconsistent, judging that the comparison audit of the first text audit content and the second text audit content is not passed.
Based on step S50, if the first text audit content is consistent with the second text audit content, it is determined that the first text audit content and the second text audit content pass. If the first text audit content is inconsistent with the second text audit content, judging that the first text audit content and the second text audit content are not passed. Specifically, for example, if the first text audit content is "Li Xiaoming" and the second text audit content is "Zhang Xiaodong", it is determined that the comparison audit of the first text audit content and the second text audit content is not passed. And if the second text audit content is Li Xiaoming, determining that the first text audit content and the second text audit content pass the audit.
Further, step S60 is followed by:
and step S80, based on the first audit content and the second comparison audit information Rong Shengcheng in the second audit, the comparison audit is not passed, so that the auditor can conduct manual audit.
In this embodiment, if the first text audit content and the second text audit content pass the comparison audit, the first audit tag and the corresponding first text audit content, and the second audit tag and the corresponding second text audit content may generate comparison audit information for the auditor to perform manual audit. And determining the final auditing result of the auditing content according to the auditing result submitted by the auditor. If the first text audit content and the second text audit content pass the comparison audit, determining that the final audit result of the audit content is audit passing.
In this embodiment, the first audit content is a first text audit content extracted from the text segment, the second audit content is a second text audit content entered by a user based on the second audit label, and the first text audit content and the second text audit content are compared to determine whether they are consistent; if the first text audit content and the second text audit content are inconsistent, judging that the comparison audit of the first text audit content and the second text audit content is not passed. By the method, when the first verification content and the second verification content are text verification content, the corresponding text verification content can be directly compared and verified, and verification efficiency is improved.
Further, fig. 4 is a flowchart of a third embodiment of the information auditing method according to the present invention.
Based on the above embodiment, in this embodiment, the first audit content is an image audit content extracted from the audit material image, the second audit content is a second text audit content input by a user based on the second audit tag, and the step of generating first comparison audit information based on the first audit tag and the corresponding first audit content in the text segment, and the matched second audit tag and the corresponding second audit content, for the auditor to perform manual audit includes:
And step S70, generating first comparison audit information based on the first audit label and the corresponding image audit content and the matched second audit label and the corresponding second audit content so as to enable an auditor to conduct manual audit.
Based on the above embodiment, in this embodiment, the first audit content is an image audit content extracted from an audit material image. The handwriting word image can be acquired in advance, handwriting label information is added to the acquired handwriting word image, a training set for deep learning is constructed based on the word image and the handwriting label information, then the word image in the training set is used as input of a deep learning model, corresponding handwriting label information is used as output of the deep learning model, and the deep learning model for recognizing the handwriting word is obtained through training. For the audit material image with the handwritten characters, the audit material image can be input into a trained deep learning model for recognizing the handwritten characters, the handwritten characters in the audit material image are recognized by using the deep learning model, and the picture area where the handwritten characters are located is intercepted based on the preset size parameters. And then determining the extracted audit label in a preset area near the handwritten text as a first audit label of the image audit content, then determining a second audit label corresponding to the first audit label and a second text audit content corresponding to the second audit label based on pre-stored associated information, and classifying the first audit label and the corresponding image audit content determined in the step and the second audit label and the corresponding second text audit content into two discrete display columns in the same page for the auditor to carry out manual audit.
In this embodiment, the first audit content is an image audit content extracted from the audit material image, the second audit content is a second text audit content input by a user based on the second audit tag, first comparison audit information is generated based on the first audit tag and the corresponding image audit content, and the matched second audit tag and the corresponding second audit content, so that an auditor can conduct manual audit, the method can be applied to extraction of handwriting audit content inconvenient for text information extraction, and by extracting the image audit content from the audit material image, comparison audit information is generated based on the image audit content, so that audit can be conducted by the auditor, identification and extraction of specific unsuitable extracted text audit content can be avoided, error audit content can be obtained, and error audit content can be obtained.
Further, fig. 5 is a flowchart of a fourth embodiment of the information auditing method of the present invention.
Based on the above embodiment, in the present embodiment, step S80 includes:
step S90, determining a first position of the first text audit content in the audit material image based on the position of the first text audit content in the text information, and determining a second position of a corresponding second text audit content in the input information;
In this embodiment, the position of each text segment in the text information may be determined during the process of slicing the text information, the position of the first text audit content in the text information may be determined based on the position of the text segment in the text information, and the position of the first text audit content in the audit material image may be further determined based on the position of the first text audit content in the text information, i.e. the first position. And then determining the position of the second text audit content corresponding to the matching second audit label corresponding to the first audit label based on the second audit label, and determining the position of the second text audit content in the display information of the input information.
Step S100, performing an audit mark on first text audit contents in the audit material image based on the first position, and performing an audit mark on second text audit contents in the input information based on the second position, where the method for performing the audit mark at least includes: highlighting the characters of the check content, setting the characters of the check content to be a preset font color or adding underlining to the characters of the check content;
based on step S90, after determining the position of the first text audit content in the audit material image, where the first text audit content fails the audit, and the position of the corresponding second text audit content in the input information, the audit label is performed on the first text audit content and the second text audit content, so as to prompt the auditor to perform manual audit based on the audit label. In this embodiment, the method for auditing and labeling the auditing content includes highlighting the text corresponding to the auditing content, or setting the text of the auditing content to a preset font color, for example, red, or adding an underline to the text of the auditing content, such as a lower line or an lower wavy line.
Step S110, generating second contrast audit information based on the annotated audit material images and the annotated input information for the auditor to conduct manual audit;
after the first text audit content and the second text audit content which are not passed by audit are marked, second comparison audit information is generated based on the audit material image subjected to audit marking and the input information subjected to audit marking so as to be used for manual audit by an auditor. In this embodiment, the second comparison audit information refers to the audit material image after the audit labeling and the comparison audit information generated by the input information. In this embodiment, the second comparison audit information may be obtained by classifying the annotated audit material image and the annotated input information in different display columns of the same page.
And step S120, when an audit result submitting instruction triggered by an auditor is received, determining a final audit result of the input information based on the audit result submitting instruction.
After the second comparison information is generated, an auditor can trigger to check the second comparison audit information to be manually audited through a check function button preset in the information audit system, and then trigger a submission instruction corresponding to the audit result based on the actual manual audit result. Specifically, if the actual manual auditing result is auditing passing, triggering an auditing result submitting instruction of auditing passing through a preset auditing passing function button; and triggering an audit result submitting instruction for failing to audit based on a preset function button of failing to audit if the actual manual audit result is failing to audit. When an auditing result submitting instruction triggered by an auditor is received, the information auditing system acquires a manual auditing result determined by the auditor from the auditing result submitting instruction, and sets the extracted manual auditing result as a final auditing result of the input information.
In this embodiment, a first position of the first text audit content in the audit material image is determined based on a position of the first text audit content in the text information, and a second position of a corresponding second text audit content in the input information is determined; performing auditing and labeling on first text auditing contents in the auditing material image based on the first position, and performing auditing and labeling on second text auditing contents in the input information based on the second position; generating second comparison audit information based on the annotated audit material image and the annotated input information for manual audit by an auditor; and when an audit result submitting instruction triggered by an auditor is received, determining a final audit result of the input information based on the audit result submitting instruction. Through the method, when the audit contents which do not pass the audit exist, the audit contents are marked based on the positions of the audit contents which do not pass the audit in the original audit material images or the input information, and the comparison audit information is generated based on the marked audit material images and the marked input information, so that the audit personnel can conveniently conduct manual audit, and the audit efficiency is improved.
Further, fig. 6 is a flowchart of a fifth embodiment of the information auditing method according to the present invention.
Based on the foregoing embodiment, in this embodiment, the step of slicing the text information based on the preset slicing rule of the audit material to obtain one or more text segments of the audit material includes:
step S130, comparing the text information with the preset label, and determining a third position of a third check label matched with the preset label in the text information;
based on the above-described embodiments, in the present embodiment, the audit tag may be set in advance based on the actual field of the content of the matter of the audit material, for example, for the audit material property certificate, the audit tag "house owner" or "house sitting" or the like, and the "buyer" or "seller" or the like in the house business contract may be set, and the set audit tag is configured in the audit rule. For the preset slicing rule based on the auditing label, in the slicing process, the preset label of the auditing material and the text information of the auditing material can be compared and matched, the text matched with the preset auditing label in the text information of the auditing material is identified, the position of the text in the text information is determined, and then the contents of the items such as the certification right or item, the right person (applicant) or the obligator are sliced respectively based on the material preset slicing rule. In general, the page layout of the different audit materials is relatively uniform, and the preset slicing rules may be determined based on the page position of the item content in the audit material, for example, based on the paragraph or specific line number range of the item content in the audit material.
And S140, slicing the text information based on the third position to obtain text fragments corresponding to each third audit label.
In the slicing process, firstly, based on the position of the item content in the preset rule, and based on the position of the item content, the image fragment of each item content is intercepted. Further, the preset slicing rule may be determined based on the position of the audit tag information, specifically, preset audit tag fields, such as "right person", "obligator" or "proof right or item", may be pre-stored in the preset slicing rule, in the slicing process, text information matched with the preset audit tag field may be determined first from the material image, and the position of the matched text information in the image may be determined, for each audit tag field, the beginning text line where the audit tag field is located is determined, the previous line where the next audit tag field is located is an ending text line, the image segment between the beginning text line and the ending text line is intercepted, or the audit tag field is taken as the beginning field, the last text before the next audit tag field is taken as the ending field, and the image segment between the beginning field and the ending field is intercepted.
In an embodiment, comparing the text information with the preset label, and determining a third position of a third check label matched with the preset label in the text information; and slicing the text information based on the third position to obtain text fragments corresponding to each third check label. By the method, the text information is precisely sliced based on the preset label, and the accurate text fragments are obtained.
In addition, the embodiment of the invention also provides an information auditing device.
Referring to fig. 7, fig. 7 is a schematic functional block diagram of a first embodiment of an information auditing apparatus according to the present invention.
In this embodiment, the information auditing apparatus includes:
the slicing module 10 is used for extracting text information in the image of the auditing material based on the OCR optical character recognition extraction technology, and slicing the text information based on preset slicing rules of the auditing material to obtain one or more text segments of the auditing material;
the comparison module 20 is configured to compare each text segment with a preset label corresponding to an audit material, obtain a first audit label in the text segment based on a comparison result, and obtain a first audit content in the text segment or audit material image;
A determining module 30, configured to determine a second audit tag that matches each first audit tag based on pre-stored association information of the text segment first audit tag and the second audit tag of the input information;
the auditing module 40 is configured to compare and audit the auditing content corresponding to the first auditing label in the text segment with the auditing content corresponding to the matched second auditing label, or generate first comparison auditing information based on the first auditing label in the text segment and the corresponding first auditing content, and the first comparison auditing information generated by the matched second auditing label and the corresponding second auditing content, so as to enable an auditor to perform manual auditing.
Wherein, each virtual function module of the information auditing device is stored in the memory 1005 of the information auditing device shown in fig. 1, and is used for implementing all functions of the information auditing program; each module, when executed by the processor 1001, improves information auditing efficiency.
Further, the auditing module is further configured to:
comparing the first text audit content with the second text audit content to determine whether the first text audit content and the second text audit content are consistent;
if the first text audit content and the second text audit content are inconsistent, judging that the comparison audit of the first text audit content and the second text audit content is not passed.
Further, the auditing module is further configured to:
and generating first comparison audit information based on the first audit label and the corresponding image audit content and the matched second audit label and the corresponding second audit content so as to enable an auditor to conduct manual audit.
Further, the auditing module is further configured to:
and based on the first audit content and the second comparison audit information in the second audit Rong Shengcheng, which do not pass the comparison audit, the auditor can conduct manual audit.
Further, the auditing module is further configured to:
determining a first position of the first text audit content in the audit material image based on the position of the first text audit content in the text information, and determining a second position of the corresponding second text audit content in the input information;
performing auditing and labeling on first text auditing contents in the auditing material image based on the first position, and performing auditing and labeling on second text auditing contents in the input information based on the second position;
generating second comparison audit information based on the annotated audit material image and the annotated input information for manual audit by an auditor;
And when an audit result submitting instruction triggered by an auditor is received, determining a final audit result of the input information based on the audit result submitting instruction.
Further, the slicing module is further configured to:
comparing the text information with the preset label, and determining a third position of a third check label matched with the preset label in the text information;
and slicing the text information based on the third position to obtain text fragments corresponding to each third check label.
In addition, the embodiment of the invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention stores an information auditing program, wherein the information auditing program, when executed by a processor, implements the steps of the information auditing method described above.
The method implemented when the information auditing program is executed may refer to various embodiments of the information auditing method of the present invention, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. The information auditing method is characterized by comprising the following steps:
extracting text information in the auditing material image based on an OCR optical character recognition extraction technology, and slicing the text information based on preset slicing rules of the auditing material to obtain one or more text segments of the auditing material;
comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image;
determining a second check tag matched with each first check tag based on pre-stored association information of the text segment first check tag and the second check tag of the input information;
comparing and auditing the auditing contents corresponding to the first auditing label in the text segment with the auditing contents corresponding to the matched second auditing label, or generating first comparison auditing information based on the first auditing label in the text segment and the corresponding first auditing content, and the first comparison auditing information with the matched second auditing label and the corresponding second auditing content so as to enable an auditor to conduct manual auditing;
the method comprises the steps of obtaining one or more text segments of the auditing material, wherein the text information is sliced based on a preset slicing rule of the auditing material, and the method further comprises the following steps:
Determining an audit tag based on an actual field corresponding to the item content of the audit material, and configuring a preset slicing rule according to the audit tag;
the step of slicing the text information based on the preset slicing rule of the auditing material to obtain one or more text segments of the auditing material comprises the following steps:
matching the text information with the audit tag in the preset slicing rule, and determining matched text information matched with the audit tag in the text information;
determining a target position of the matched text information in the text information, and slicing the text information based on the target position to obtain one or more text fragments of the auditing material;
the step of comparing and auditing the auditing contents corresponding to the first auditing label in the text segment with the auditing contents corresponding to the matched second auditing label, or generating first comparison auditing information based on the first auditing label in the text segment and the corresponding first auditing contents, and the first comparison auditing information generated by the matched second auditing label and the corresponding second auditing contents, so as to enable an auditor to conduct manual auditing, comprises the following steps:
when the auditing content corresponding to the first auditing label in the text segment is preset auditing content, comparing and auditing the auditing content corresponding to the first auditing label in the text segment with the auditing content corresponding to the matched second auditing label;
And when the auditing content corresponding to the first auditing label in the text segment is not the preset auditing content, generating first comparison auditing information based on the first auditing label and the corresponding first auditing content in the text segment, and the matched second auditing label and the corresponding second auditing content, so as to enable an auditor to conduct manual auditing.
2. The information auditing method of claim 1, wherein the first auditing content is first text auditing content extracted from the text segment, the second auditing content is second text auditing content entered by a user based on the second auditing label, and the step of comparing auditing content corresponding to the first auditing label with auditing content corresponding to the matched second auditing label in the text segment comprises:
comparing the first text audit content with the second text audit content to determine whether the first text audit content and the second text audit content are consistent;
if the first text audit content and the second text audit content are inconsistent, judging that the comparison audit of the first text audit content and the second text audit content is not passed.
3. The information auditing method of claim 1, wherein the first auditing content is an image auditing content extracted from the auditing material image, the second auditing content is a second text auditing content entered by a user based on the second auditing tag, and the step of generating first comparison auditing information for an auditor to manually audit based on the first auditing tag and the corresponding first auditing content in the text segment, and the matched second auditing tag and the corresponding second auditing content comprises:
And generating first comparison audit information based on the first audit label and the corresponding image audit content and the matched second audit label and the corresponding second audit content so as to enable an auditor to conduct manual audit.
4. The information auditing method of claim 2, wherein the step of determining that the first audit content and the second audit content do not pass comprises:
and based on the first audit content and the second comparison audit information in the second audit Rong Shengcheng, which do not pass the comparison audit, the auditor can conduct manual audit.
5. The method of information auditing of claim 4, wherein the step of providing for manual auditing by an auditor based on first audit content that the comparative auditing does not pass and second comparative audit information within a second audit Rong Shengcheng includes:
determining a first position of the first text audit content in the audit material image based on the position of the first text audit content in the text information, and determining a second position of the corresponding second text audit content in the input information;
performing auditing and labeling on first text auditing contents in the auditing material image based on the first position, and performing auditing and labeling on second text auditing contents in the input information based on the second position;
Generating second comparison audit information based on the annotated audit material image and the annotated input information for manual audit by an auditor;
and when an audit result submitting instruction triggered by an auditor is received, determining a final audit result of the input information based on the audit result submitting instruction.
6. The information auditing method of claim 5, wherein the method for conducting audit labeling comprises at least: highlighting the text of the check content, setting the text of the check content to a preset font color, or underlining the text of the check content.
7. An information auditing apparatus, characterized in that the information auditing apparatus includes:
the slicing module is used for extracting the text information in the auditing material image based on the OCR optical character recognition extraction technology, and slicing the text information based on the preset slicing rule of the auditing material to obtain one or more text fragments of the auditing material;
the comparison module is used for comparing each text segment with a preset label corresponding to the auditing material, acquiring a first auditing label in the text segment based on a comparison result, and acquiring first auditing content in the text segment or the auditing material image;
The determining module is used for determining a second check tag matched with each first check tag based on pre-stored association information of the first check tag of the text segment and the second check tag of the input information;
the auditing module is used for comparing and auditing the auditing contents corresponding to the first auditing label in the text segment with the auditing contents corresponding to the matched second auditing label, or generating first comparison auditing information based on the first auditing label in the text segment and the corresponding first auditing content and the matched second auditing label and the corresponding second auditing content so as to enable an auditor to conduct manual auditing;
the slicing module is further used for determining an audit tag based on an actual field corresponding to the item content of the audit material, and configuring a preset slicing rule according to the audit tag;
the slicing module is further configured to:
matching the text information with the audit tag in the preset slicing rule, and determining matched text information matched with the audit tag in the text information;
determining a target position of the matched text information in the text information, and slicing the text information based on the target position to obtain one or more text fragments of the auditing material;
The auditing module is further used for:
when the auditing content corresponding to the first auditing label in the text segment is preset auditing content, comparing and auditing the auditing content corresponding to the first auditing label in the text segment with the auditing content corresponding to the matched second auditing label;
and when the auditing content corresponding to the first auditing label in the text segment is not the preset auditing content, generating first comparison auditing information based on the first auditing label and the corresponding first auditing content in the text segment, and the matched second auditing label and the corresponding second auditing content, so as to enable an auditor to conduct manual auditing.
8. An information auditing apparatus, characterized in that it comprises a processor, a memory, and an information auditing program stored on the memory and executable by the processor, wherein the information auditing program, when executed by the processor, implements the steps of the information auditing method of any of claims 1 to 6.
9. A computer readable storage medium, wherein an information auditing program is stored on the computer readable storage medium, wherein the information auditing program, when executed by a processor, implements the steps of the information auditing method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910205659.3A CN110097329B (en) | 2019-03-16 | 2019-03-16 | Information auditing method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910205659.3A CN110097329B (en) | 2019-03-16 | 2019-03-16 | Information auditing method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110097329A CN110097329A (en) | 2019-08-06 |
| CN110097329B true CN110097329B (en) | 2023-11-14 |
Family
ID=67443385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910205659.3A Active CN110097329B (en) | 2019-03-16 | 2019-03-16 | Information auditing method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097329B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490181B (en) * | 2019-08-14 | 2022-04-22 | 北京思图场景数据科技服务有限公司 | Form filling and auditing method, device and equipment based on OCR (optical character recognition) technology and computer storage medium |
| CN110705559B (en) * | 2019-10-09 | 2022-07-08 | 杭州高达软件系统股份有限公司 | Steel information recording method, device and equipment based on steel label image recognition |
| CN111079173A (en) * | 2019-11-15 | 2020-04-28 | 湖北瑞致和科技有限公司 | Financial expenditure approval system |
| CN111144416A (en) * | 2019-12-25 | 2020-05-12 | 中国联合网络通信集团有限公司 | Information processing method and device |
| CN111401854A (en) * | 2020-03-24 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Information processing method and device |
| CN111709855A (en) * | 2020-06-17 | 2020-09-25 | 中国银行股份有限公司 | Fund escrow method, device, storage medium and equipment based on OCR |
| CN111753817B (en) * | 2020-06-28 | 2024-01-26 | 国网数字科技控股有限公司 | Information processing method and device, electronic equipment and computer readable storage medium |
| CN112001640A (en) * | 2020-08-26 | 2020-11-27 | 中国银行股份有限公司 | Method and system for centralized and parallel processing of counter transactions of commercial bank |
| CN112182502A (en) * | 2020-09-07 | 2021-01-05 | 支付宝(杭州)信息技术有限公司 | Compliance auditing method, device and equipment |
| CN112863184B (en) * | 2021-01-12 | 2022-11-11 | 山西省交通运输运行监测与应急处置中心 | Traffic information management system |
| CN113297836A (en) * | 2021-05-28 | 2021-08-24 | 善诊(上海)信息技术有限公司 | Image report label evaluation method and device, computer equipment and storage medium |
| CN115034877A (en) * | 2022-05-26 | 2022-09-09 | 重庆银行股份有限公司 | Loan mortgage information processing method and device and computer equipment |
| CN115034876A (en) * | 2022-05-26 | 2022-09-09 | 重庆银行股份有限公司 | Loan information auditing method and device based on OCR (optical character recognition) technology and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654057A (en) * | 2015-12-31 | 2016-06-08 | 中国建设银行股份有限公司 | Picture auditing system and picture auditing method based on picture contents |
| CN107067044A (en) * | 2017-05-31 | 2017-08-18 | 北京空间飞行器总体设计部 | A kind of finance reimbursement unanimous vote is according to intelligent checks system |
| CN107067228A (en) * | 2017-03-31 | 2017-08-18 | 南京钧元网络科技有限公司 | A kind of hand-held authentication intelligent checks system and its checking method |
| CN108198591A (en) * | 2017-12-28 | 2018-06-22 | 泰康保险集团股份有限公司 | For the method and apparatus of remote upload document |
| CN108830512A (en) * | 2018-08-20 | 2018-11-16 | 华润守正招标有限公司 | A kind of user's registration checking method, device and the equipment of e-bidding bid platform |
| CN109377397A (en) * | 2018-11-07 | 2019-02-22 | 中国平安财产保险股份有限公司 | Insurance business list checking method, device, computer equipment and storage medium |
-
2019
- 2019-03-16 CN CN201910205659.3A patent/CN110097329B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654057A (en) * | 2015-12-31 | 2016-06-08 | 中国建设银行股份有限公司 | Picture auditing system and picture auditing method based on picture contents |
| CN107067228A (en) * | 2017-03-31 | 2017-08-18 | 南京钧元网络科技有限公司 | A kind of hand-held authentication intelligent checks system and its checking method |
| CN107067044A (en) * | 2017-05-31 | 2017-08-18 | 北京空间飞行器总体设计部 | A kind of finance reimbursement unanimous vote is according to intelligent checks system |
| CN108198591A (en) * | 2017-12-28 | 2018-06-22 | 泰康保险集团股份有限公司 | For the method and apparatus of remote upload document |
| CN108830512A (en) * | 2018-08-20 | 2018-11-16 | 华润守正招标有限公司 | A kind of user's registration checking method, device and the equipment of e-bidding bid platform |
| CN109377397A (en) * | 2018-11-07 | 2019-02-22 | 中国平安财产保险股份有限公司 | Insurance business list checking method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110097329A (en) | 2019-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097329B (en) | Information auditing method, device, equipment and computer readable storage medium | |
| US9626555B2 (en) | Content-based document image classification | |
| US20210192129A1 (en) | Method, system and cloud server for auto filing an electronic form | |
| CN109101469B (en) | Extracting searchable information from digitized documents | |
| US20120189999A1 (en) | System and method for using optical character recognition to evaluate student worksheets | |
| CN112101367A (en) | Text recognition method, image recognition and classification method and document recognition processing method | |
| US9710769B2 (en) | Methods and systems for crowdsourcing a task | |
| CN111914597B (en) | Document comparison identification method and device, electronic equipment and readable storage medium | |
| CN111612081B (en) | Training method, device, equipment and storage medium for recognition model | |
| US20190384971A1 (en) | System and method for optical character recognition | |
| CN111310750B (en) | Information processing method, device, computing equipment and medium | |
| CN113935710A (en) | Contract auditing method and device, electronic equipment and storage medium | |
| JP6694587B2 (en) | Image reading device and program | |
| CN110750964A (en) | Information adding method and related device | |
| CN113868411A (en) | Contract comparison method and device, storage medium and computer equipment | |
| CN110929725B (en) | Certificate classification method, device and computer readable storage medium | |
| CN114626341A (en) | Document conversion method, device and storage medium | |
| US20230351103A1 (en) | Methods and systems for automatically validating filled-out application forms against one or more verification documents | |
| US10606928B2 (en) | Assistive technology for the impaired | |
| CN110751140A (en) | Character batch recognition method and device and computer equipment | |
| JPWO2008114451A1 (en) | Confirmation support system and computer program | |
| JP3513806B2 (en) | Real estate registration information filing system | |
| US20210064867A1 (en) | Information processing apparatus and non-transitory computer readable medium | |
| CN114495145B (en) | Policy and document extraction method, device, equipment and storage medium | |
| JPH10134141A (en) | Device and method for document collation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |