CN113420657A - Intelligent verification method and device, computer equipment and storage medium - Google Patents
Intelligent verification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113420657A CN113420657A CN202110695907.4A CN202110695907A CN113420657A CN 113420657 A CN113420657 A CN 113420657A CN 202110695907 A CN202110695907 A CN 202110695907A CN 113420657 A CN113420657 A CN 113420657A
- Authority
- CN
- China
- Prior art keywords
- target
- recognition
- file
- text
- identified
- 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.)
- Pending
Links
- 238000012795 verification Methods 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 84
- 238000004590 computer program Methods 0.000 claims description 18
- 238000011144 upstream manufacturing Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 8
- 238000012546 transfer Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012015 optical character recognition Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The embodiment of the invention discloses an intelligent verification method, an intelligent verification device, computer equipment and a storage medium. The method comprises the following steps: acquiring a target file to be identified; performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text; acquiring verification data corresponding to the target file to be identified; comparing the verification data with the target identification text to obtain a comparison result; and generating a verification result according to the comparison result. According to the scheme, the obtained target file to be recognized can be automatically and quickly recognized according to the preset recognition template and the preset recognition algorithm, the target recognition text is obtained, automatic verification is conducted according to the target recognition text and the verification information, and the verification efficiency is high.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent verification method, an intelligent verification device, computer equipment and a storage medium.
Background
The authenticity verification of the assets in the supply chain business is very important, wherein the registration and inquiry are carried out in a dynamic production financing unified registration platform (hereinafter referred to as a network) of a Chinese people's bank credit investigation center as one step of operation necessary in the asset transaction.
In the traditional supply chain business operation, when the authenticity of customer assets needs to be verified, special early warning personnel of a company needs to acquire corresponding customer information in a middle-log-in network for manual check so as to check whether the maintained customer information is consistent with the information acquired from the middle-log-in network, and manual early warning before transaction is realized.
Disclosure of Invention
The embodiment of the invention provides an intelligent verification method, an intelligent verification device, computer equipment and a storage medium, which can realize automatic verification and improve verification efficiency.
In a first aspect, an embodiment of the present invention provides an intelligent verification method, which includes:
acquiring a target file to be identified;
performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text;
acquiring verification data corresponding to the target file to be identified;
comparing the verification data with the target identification text to obtain a comparison result;
and generating a verification result according to the comparison result.
In a second aspect, an embodiment of the present invention further provides an intelligent verification apparatus, which includes:
the first acquisition unit is used for acquiring a target file to be identified;
the identification unit is used for carrying out text identification processing on the target file to be identified according to a preset identification template and a preset identification algorithm to obtain a target identification text;
the second acquisition unit is used for acquiring verification data corresponding to the target file to be identified;
the comparison unit is used for comparing the verification data with the target identification text to obtain a comparison result;
and the first generating unit is used for generating a verification result according to the comparison result.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the above method when executing the computer program.
In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores a computer program, the computer program including program instructions, which when executed by a processor, implement the above method.
The embodiment of the invention provides an intelligent verification method, an intelligent verification device, computer equipment and a storage medium. Wherein the method comprises the following steps: acquiring a target file to be identified; performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text; acquiring verification data corresponding to the target file to be identified; comparing the verification data with the target identification text to obtain a comparison result; and generating a verification result according to the comparison result. According to the scheme, the obtained target file to be recognized can be automatically and quickly recognized according to the preset recognition template and the preset recognition algorithm, the target recognition text is obtained, automatic verification is conducted according to the target recognition text and the verification information, and the verification efficiency is high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of an intelligent verification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an intelligent verification method according to an embodiment of the present invention;
FIG. 3 is a schematic view of a sub-flow of an intelligent verification method according to an embodiment of the present invention;
FIG. 4 is a schematic view of another sub-flow of the intelligent verification method according to the embodiment of the present invention;
FIG. 5 is a schematic block diagram of an intelligent verification apparatus provided by an embodiment of the present invention;
FIG. 6 is a schematic block diagram of an intelligent verification apparatus according to another embodiment of the present invention;
FIG. 7 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the invention provides an intelligent verification method, an intelligent verification device, computer equipment and a storage medium.
The execution main body of the intelligent verification method can be the intelligent verification device provided by the embodiment of the invention or computer equipment integrated with the intelligent verification device, wherein the intelligent verification device can be realized in a hardware or software mode, the computer equipment can be a terminal or a server, and the terminal can be a smart phone, a tablet computer, a palm computer, a notebook computer or the like.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of the intelligent verification method according to the embodiment of the present invention. The intelligent verification method is applied to the computer device in fig. 1, and in some embodiments, the computer device may download a target file to be identified from a medium log-in network; then, performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text; acquiring verification data corresponding to a target file to be identified; comparing the verification data with the target identification text to obtain a comparison result; and finally generating a verification result according to the comparison result.
Fig. 2 is a schematic flow chart of the intelligent verification method according to an embodiment of the present invention, which is illustrated by taking a server as an execution subject. As shown in fig. 2, the method includes the following steps S110-150.
And S110, acquiring a target file to be identified.
In this embodiment, the file representation types of the target file to be recognized include: PDF files, PDF scanning pieces, Excel files and/or pictures and the like, wherein the file content types of the target files to be identified comprise: invoices, contracts, and/or other mid-log files, etc., wherein a mid-log file is a file registered by a user in a mid-log network.
In some embodiments, when the user needs to verify the invoice, the user may upload the invoice to the server, so that the server obtains the target file to be identified, and then perform automatic invoice verification through the server, wherein the user may upload multiple invoices to the server at the same time and perform invoice verification at the same time, and the document expression type of the invoice includes a PDF scan, an Excel file, and/or a picture, etc.
In other embodiments, when the user needs to verify the information recorded in the server by the user according to the information in the mid-log, the server may call the mid-log query interface, and automatically download the required mid-log registration file, so that the server obtains the target file to be identified, where the file representation type of the mid-log registration file includes a PDF file and/or a picture, and the like.
In some embodiments, as shown in fig. 3, when the target file to be recognized is a picture, step S110 includes:
and S111, acquiring the original file to be identified.
In some embodiments, the original file to be identified may be an original invoice file uploaded by a user, an original mid-registration file acquired by a server in a mid-registration network, or the like.
When the document expression type of the original document to be recognized is a picture, the picture is processed by multi-aspect transmission and the like at upstream, so that the resolution ratio of the picture is low, the picture is fuzzy, and the accuracy of subsequent text extraction is influenced.
S112, determining whether the resolution of the original file to be identified is smaller than a preset resolution threshold, if so, executing a step S113, and if not, executing a step S114.
In order to reduce the problem of low accuracy of subsequently extracting a text due to low resolution of the original file to be recognized, in this embodiment, the resolution of the original file to be recognized needs to be determined, and a picture with a resolution lower than a resolution threshold is defined as a blurred picture, which is not easy to extract the text.
And S113, inputting the original file to be recognized into a preset resolution improvement network model for resolution processing to obtain the target file to be recognized.
In this embodiment, when the resolution of the original to-be-recognized file is smaller than a preset resolution threshold, the original to-be-recognized file needs to be input into a preset resolution improving network model for resolution processing, so as to improve the resolution of the original to-be-recognized file, and obtain a target to-be-recognized file, where the preset resolution improving network model is a trained resolution improving network model, and the resolution improving network model may be used to improve the resolution of a picture, and where the resolution improving network model may be a Convolutional Neural Network (CNN).
And S114, determining the original file to be identified as the target file to be identified.
In this embodiment, when the resolution of the original file to be recognized is greater than or equal to the preset resolution threshold, it indicates that the definition of the original file to be recognized is high enough, and the resolution does not need to be improved.
And S120, performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text.
In some embodiments, as shown in fig. 4, S120 comprises:
s121, determining a target identification template and a target identification algorithm of the target file to be identified according to the file type of the target file to be identified.
The file type in this embodiment includes a file representation type and a file content type, and specifically, in this embodiment, a target identification template of a target file to be identified is determined according to the file content type of the target file to be identified, and a target identification algorithm of the target file to be identified is determined according to the file representation type of the target file to be identified.
In some embodiments, when acquiring the target file to be identified, the server also acquires file content type information and file representation type information corresponding to the target file to be identified, for example, the file representation type of the target file to be identified is a picture, and the file content type of the target file to be identified is an invoice.
In other embodiments, if the server does not obtain the file content type information and the file expression type information corresponding to the target file to be recognized when obtaining the target file to be recognized, at this time, the server further needs to perform specific analysis on the target file to be recognized to obtain the file content type information and the file expression type information of the target file to be recognized, specifically, the file content type information may be determined according to a file name of the target file to be recognized or a top of the file content, and the file expression type information may be determined by analyzing a suffix of the target file name to be recognized.
The target identification template in this embodiment is a template capable of reflecting the position of the key information in the target file to be identified, that is, the information of the target file to be identified is filled according to the template type of the target identification template, for example, the invoice template includes an invoice code, an invoice number, an invoice invoicing date, position information of the invoice without tax amount, a check code, buyer information and sales information, when the invoice code in the invoice needs to be identified, only the position corresponding to the invoice code needs to be acquired at this time, and then text identification is performed on the position.
The target Recognition algorithm in this embodiment is an algorithm that can perform text Recognition processing on a file of a corresponding file representation type, for example, the file representation type is a picture, at this time, the target Recognition algorithm may be Optical Character Recognition (OCR), if the text representation type is Excel, the target Recognition algorithm may be an Excel text extraction method, if the text representation type is PDF, the target Recognition algorithm may be a PDF text analysis algorithm, and the like.
And S122, determining the target position of the target file to be recognized according to the target recognition template.
For example, when the server needs to acquire the invoice code, the invoice invoicing date buyer information and the sales information in the invoice, the target positions corresponding to the invoice code, the invoice invoicing date buyer information and the sales information in the invoice can be determined according to the target identification template, wherein the target positions are positions needing text identification processing, and other positions do not need text identification processing, so the identification efficiency of the text identification processing can be improved.
And S123, performing text recognition processing on the target position according to a target recognition algorithm to obtain a target recognition text.
After the target position to be subjected to text recognition and the corresponding target recognition algorithm are determined, the embodiment performs text recognition processing on the target position according to the target recognition algorithm to obtain a target recognition text, for example, obtain an invoice code in an invoice, invoice invoicing date buyer information and sales information.
In some embodiments, there may be some places where there is an identification error in the initial identification text recognized by the server, for example, a "company" is recognized as "public", so after the initial identification text is obtained, correction processing needs to be performed on the initial identification text to improve the accuracy of text identification, in this case, S120 further specifically includes: performing text recognition processing on a target position according to a target recognition algorithm to obtain an initial recognition text, performing word segmentation processing on the initial recognition text to obtain a plurality of segmented words, performing correction processing on the segmented words according to a preset word bank to obtain target segmented words, and finally determining the target recognition text according to the target segmented words.
After the initial recognition text is obtained, word segmentation processing needs to be performed on the initial recognition text to obtain a plurality of corresponding words, and the words are corrected according to a preset word bank, wherein specifically, the correction rule is as follows: if the corresponding participles exist in the word stock, the corresponding participles do not need to be corrected, the participles are directly determined as target participles, if the corresponding participles do not exist in the word stock, the participles closest to the participle vector in the word stock need to be determined as target participles, and finally, the target recognition texts are combined according to the recognized participles.
In some embodiments, the image in the target identification text acquired by the server may be skewed, and the size of the image may be too large or too small, so that the angle correction processing needs to be performed on the target identification text at this time to obtain a first target identification text; then, carrying out size adjustment processing on the first target recognition text to obtain a second target recognition text; in this case, in step S120, text recognition processing is performed on the second target file to be recognized according to the recognition template and the recognition algorithm, so as to obtain a target recognition text.
In some embodiments, when the target to-be-identified file includes a plurality of target to-be-identified subfiles, the server may simultaneously determine a target identification template and a target identification algorithm, where the target identification template and the target identification algorithm correspond to a file type of each of the plurality of target to-be-identified subfiles respectively; and starting multithreading processing, and then performing text recognition processing on the corresponding target sub-files to be recognized through each thread according to the target recognition template and the target recognition algorithm to respectively obtain the target recognition text of each target sub-file to be recognized.
For example, when a user uploads invoices (pictures, excels and PDF scanning pieces) with various file types to a server for verification, the server respectively starts recognition algorithms corresponding to the pictures, the excels and the PDF scanning pieces to extract texts of the corresponding invoices, wherein if the invoices are the PDF scanning pieces, the invoices pictures are firstly intercepted from the PDF scanning pieces, and then the intercepted invoices pictures are subjected to OCR recognition.
In some embodiments, when the server finds that the same invoice or contract is associated by a plurality of assets according to the target identification text, the server judges that the invoice or contract has a repeated registration condition, and sends out an early warning.
And S130, acquiring verification data corresponding to the target file to be identified.
In some embodiments, if the document to be verified is an invoice and the invoice is verified, at this time, before verification data corresponding to the target document to be recognized is obtained, the tax bureau system may be invoked to verify the authenticity of the invoice, after the verification passes, verification data maintained by the user in the server is obtained, and then whether the verification data is consistent with text information in the invoice is compared, for example, whether user information and amount data in the invoice are consistent with user information and amount data in the verification information is verified.
In other embodiments, if the document to be verified is contract information, and the purpose is to verify the authenticity of the contract information, the document to be identified may be an accessory downloaded from a network, and the verification data is data (such as contract information) entered by the user and required to be verified in the server, for example, verifying transferor and transferee information in the contract information, and at this time, the authenticity of the transferor and transferee information may be verified according to the data (target identification text) acquired from the network.
And S140, comparing the verification data with the target identification text to obtain a comparison result.
In this embodiment, the verification data and the target identification text are compared, and whether the information in the verification data and the information in the target identification text are consistent is checked.
For example, it is verified whether the user information and the amount data in the invoice match the user information and the amount data in the verification information, or whether the data in the contract (verification data) match the data registered in the mid-log (target identification text) or not.
S150, generating a verification result according to the comparison result.
In this embodiment, if it is determined according to the comparison result that the information in the verification data and the information in the target identification text are consistent, the verification passes, and at this time, an early warning does not need to be sent out.
In some embodiments, the method further includes monitoring an upstream file corresponding to the target file to be identified; and when the upstream file is changed, generating change early warning information.
In some embodiments, the upstream file corresponding to the target file to be identified is a corresponding file registered in the mid-log network, and when the file is changed in the mid-log network (for example, during the extension period and the logout), an early warning message needs to be generated to remind the user of the change.
In summary, in the embodiment of the present invention, a target file to be identified is first obtained; then, performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text; then acquiring verification data corresponding to the target file to be identified; comparing the verification data with the target identification text to obtain a comparison result; and finally generating a verification result according to the comparison result. According to the scheme, the obtained target file to be recognized can be automatically and quickly recognized according to the preset recognition template and the preset recognition algorithm, the recognition text is obtained, manual recognition is not needed, the recognition speed is high, full-automatic intelligent verification is achieved according to the recognition text and verification information, and the verification efficiency is high.
For ease of understanding, two specific application examples will be provided below to describe the intelligent verification method of the present invention:
scene one: check the invoice
1) The invoice verification operation page of the user in the operation terminal corresponding to the server uploads the invoice needing verification according to page guidance, and the server supports three uploading modes: the method comprises the steps of picture, Excel import and PDF scanning, and the three modes all support batch uploading of a plurality of invoices. The method comprises the steps that a user uploads invoices to a server in batches, the server starts multithreading, if the invoices are scanned by PDF, PDF file analysis is firstly carried out, the invoices in the PDF files are cut into one invoice picture, then OCR picture recognition service is called to recognize the invoice picture, invoice 5 elements (such as invoice codes, invoice numbers, invoice invoicing dates, invoices do not contain tax amount and check codes) are extracted, invoice repeatability inspection is firstly carried out after OCR recognition is successful, and if the invoices are used by other assets, the invoices are prompted to be reused.
2) Verifying the invoice in batch: after the invoice is uploaded and the invoice text information is extracted, the user can check the invoice in batches, in order to improve the user experience, the server adopts a multithreading mode, calls a tax system interface in batches to check the invoice, records the check result into a table, verifies that the buyer and seller extracting the invoice are matched with the buyer and seller of the asset bottom contract, and prompts the user if the buyer and seller and the invoice are inconsistent.
3) The invoice is analyzed, the invoice associated with the asset is analyzed and counted through different dimensions, the automatic check is performed on the invoice amount, the invoice type and the invoice price by combining the enterprise operation condition (verification data), and whether the invoice is matched with the asset or not is automatically judged (including: 1. whether the invoicing time is within the validity period of the asset, 2, whether the asset amount is consistent with the invoice amount, and 3, whether the asset bottom layer type is matched with the invoice type).
4) After the invoice is successfully verified, the invoice is automatically monitored in a pool, in the asset financing transfer process, the server monitors the invoice in an abnormal way in the whole process before the asset is not due, if the invoice is verified on another platform or the invoice is invalidated, the server can monitor and warn the invoice in real time, and the warning information is pushed to the user in the modes of mails, station letters and WeChat public numbers, so that the user can obtain the warning information in time.
In the first scenario, the server can realize intelligent invoice verification and early warning service, support batch uploading of invoice pictures and PDF invoice scanning files, the system adopts a multithreading mode, performs OCR in batches to identify relevant invoice factors, then automatically calls a tax system interface to perform automatic invoice verification, automatically detects whether the invoice is reused or not during invoice verification, and can verify whether the buyer and seller of the invoice are consistent with the buyer and seller of the contract at the bottom of the asset, automatically perform intelligent identification and verification with the historical operating condition of the enterprise, the price of the main business and the main trading partner, meanwhile, the invoice is monitored in a pool, and if the invoice is verified in other systems or is invalidated, the abnormal early warning can be carried out in real time, this may allow the user to be more secure for the funder during the transfer of the supply chain assets, and also improve the invoice validation efficiency and customer satisfaction.
Scene two: automatic matching early warning is carried out according to data and assets in middle-climbing network
1) And clicking the login query according to the page guide by the user on an operation page in the operation terminal corresponding to the server, calling a middle login query interface by the server, and automatically querying and downloading the middle login registration file.
2) The server analyzes the mid-registration PDF file and dynamically extracts relevant mid-registration data including mid-registration description, transfer contract and amount, transferor, transferee and the like.
3) And the server performs intelligent matching on the invoice and the contract number associated with the asset according to the extracted related registration data to register a query result, judges whether the invoice and the contract are repeatedly registered, and reminds in real time if the invoice and the contract are repeatedly registered.
4) The server automatically processes and marks the registration records of change, extension and logout, and the user can intuitively inquire which registration records are valid and which are invalid and logout.
5) When repeated early warning risks appear during login, the server marks the prominent color on the dangerous well registration records, so that the users can see the records of the dangerous early warning at a glance through the corresponding terminals, and real-time intelligent early warning is achieved.
6) In the process of asset transfer and financing, before assets are not settled (for example, core enterprises do not pay), the server monitors the registration condition of the assets registered in the middle in real time, and once the registration record is changed or cancelled or the registration condition is repeated, the server carries out real-time early warning and carries out early warning reminding in various modes such as mails, station letters, WeChat public numbers and the like.
7) In the financing transfer process of the assets, the server automatically acquires the related information of the assets, including the information of a transferor, a transferee, a transfer amount, a contract number, a contract name, a contract expiration date and the like, automatically fills the mid-registration information, calls a mid-registration service interface, and completes the automatic registration of the assets.
8) The server can analyze whether the business operation state of the enterprise is matched with the registered assets or not by counting the registered assets and the fund amount of the enterprise within a period of time, and timely warns if the business operation state of the enterprise is not matched with the registered assets.
In the second scenario, the server supports the user to automatically perform mid-registration and mid-registration query in the asset transfer process, intelligently identifies mid-registration certification documents, performs anti-repeat verification on invoices and contracts associated with assets, performs intelligent risk early warning on risky assets, supports batch downloading of mid-registration documents and analysis texts and performs automatic matching early warning with assets, reduces labor cost, can monitor mid-registration, and can automatically perform risk early warning when the mid-registration is changed, and is cancelled or repeated, so that a capital party can be more confident in the supply chain asset transfer process, and is assured to be successful.
Fig. 5 is a schematic block diagram of an intelligent verification apparatus according to an embodiment of the present invention. As shown in fig. 5, the present invention also provides an intelligent verification apparatus corresponding to the above intelligent verification method. The intelligent verification apparatus includes a unit for performing the above-described intelligent verification method, and the apparatus may be configured in a terminal or a server. Specifically, referring to fig. 5, the intelligent verification apparatus includes a first obtaining unit 501, an identifying unit 502, a second obtaining unit 503, a comparing unit 504, and a first generating unit 505, wherein:
a first obtaining unit 501, configured to obtain a target file to be identified;
the identification unit 502 is configured to perform text identification processing on the target file to be identified according to a preset identification template and a preset identification algorithm to obtain a target identification text;
a second obtaining unit 503, configured to obtain verification data corresponding to the target file to be identified;
a comparison unit 504, configured to compare the verification data with the target identification text to obtain a comparison result;
a first generating unit 505, configured to generate a verification result according to the comparison result.
In some embodiments, the identifying unit 502 is specifically configured to:
determining a target identification template and a target identification algorithm of the target file to be identified according to the file type of the target file to be identified;
determining the target position of the target file to be identified according to the target identification template;
and performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text.
In some embodiments, the identifying unit 502 is further specifically configured to:
performing text recognition processing on the target position according to the target recognition algorithm to obtain an initial recognition text;
performing word segmentation processing on the initial recognition text to obtain a plurality of words;
correcting the participles according to a preset word bank to obtain target participles;
and determining the target recognition text according to the target word segmentation.
In some embodiments, when the target file to be identified is a picture, the first obtaining unit 501 is specifically configured to:
acquiring an original file to be identified;
determining whether the resolution of the original file to be identified is smaller than a preset resolution threshold value;
if the resolution of the original file to be recognized is smaller than the resolution threshold, inputting the original file to be recognized into a preset resolution improvement network model for resolution processing to obtain the target file to be recognized;
and if the resolution of the original file to be identified is greater than or equal to the resolution threshold, determining the original file to be identified as the target file to be identified.
In some embodiments, the target file to be recognized includes a plurality of target sub-files to be recognized, and the recognition unit 502 is specifically configured to:
determining a target identification template and a target identification algorithm which respectively correspond to the file type of each target to-be-identified sub-file in the plurality of target to-be-identified sub-files;
and starting multi-thread processing, and performing text recognition processing on the corresponding target sub-files to be recognized through each thread according to the target recognition template and the target recognition algorithm to respectively obtain target recognition texts of the target sub-files to be recognized.
Fig. 6 is a schematic block diagram of an intelligent verification apparatus according to another embodiment of the present invention. As shown in fig. 6, the intelligent verification apparatus of the present embodiment is added with a correction unit 506, an adjustment unit 507, a monitoring unit 508, and a second generation unit 509 in addition to the above-mentioned embodiment.
A correcting unit 506, configured to perform angle correction processing on the target recognition text to obtain a first target recognition text;
an adjusting unit 507, configured to perform size adjustment processing on the first target recognition text to obtain a second target recognition text;
at this time, the identifying unit 502 is specifically configured to:
and performing text recognition processing on the second target file to be recognized according to the recognition template and the recognition algorithm to obtain the target recognition text.
A monitoring unit 508, configured to monitor an upstream file corresponding to the target file to be identified;
a second generating unit 509, configured to generate change warning information when the upstream file is changed.
It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of the above-mentioned intelligent verification apparatus and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.
The above-mentioned intelligent verification apparatus may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present invention. The computer device 700 may be a terminal or a server, where the terminal may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 7, the computer device 700 includes a processor 702, memory, and a network interface 705 coupled via a system bus 701, where the memory may include a non-volatile storage medium 703 and an internal memory 704.
The non-volatile storage medium 703 may store an operating system 7031 and a computer program 7032. The computer program 7032 comprises program instructions that, when executed, cause the processor 702 to perform an intelligent verification method.
The processor 702 is configured to provide computing and control capabilities to support the operation of the overall computer device 700.
The internal memory 704 provides an environment for the execution of a computer program 7032 on the non-volatile storage medium 703, which computer program 7032, when executed by the processor 702, causes the processor 702 to perform an intelligent verification method.
The network interface 705 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing device 700 to which aspects of the present invention may be applied, and that a particular computing device 700 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 702 is configured to run a computer program 7032 stored in the memory to perform the steps of:
acquiring a target file to be identified;
performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text;
acquiring verification data corresponding to the target file to be identified;
comparing the verification data with the target identification text to obtain a comparison result;
and generating a verification result according to the comparison result.
In some embodiments, when implementing the step of performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the processor 702 specifically implements the following steps:
determining a target identification template and a target identification algorithm of the target file to be identified according to the file type of the target file to be identified;
determining the target position of the target file to be identified according to the target identification template;
and performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text.
In some embodiments, when implementing the step of performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text, the processor 702 specifically implements the following steps:
performing text recognition processing on the target position according to the target recognition algorithm to obtain an initial recognition text;
performing word segmentation processing on the initial recognition text to obtain a plurality of words;
correcting the participles according to a preset word bank to obtain target participles;
and determining the target recognition text according to the target word segmentation.
In some embodiments, when the step of obtaining the target file to be identified is implemented when the target file to be identified is a picture, the processor 702 specifically implements the following steps:
acquiring an original file to be identified;
determining whether the resolution of the original file to be identified is smaller than a preset resolution threshold value;
if the resolution of the original file to be recognized is smaller than the resolution threshold, inputting the original file to be recognized into a preset resolution improvement network model for resolution processing to obtain the target file to be recognized;
and if the resolution of the original file to be identified is greater than or equal to the resolution threshold, determining the original file to be identified as the target file to be identified.
In some embodiments, before implementing the step of performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the processor 702 further implements the following steps:
carrying out angle correction processing on the target recognition text to obtain a first target recognition text;
carrying out size adjustment processing on the first target recognition text to obtain a second target recognition text;
the text recognition processing is carried out on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, and the method comprises the following steps:
and performing text recognition processing on the second target file to be recognized according to the recognition template and the recognition algorithm to obtain the target recognition text.
In some embodiments, when the processor 702 implements that the target file to be recognized includes a plurality of target sub-files to be recognized, and performs text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the following steps are specifically implemented:
determining a target identification template and a target identification algorithm which respectively correspond to the file type of each target to-be-identified sub-file in the plurality of target to-be-identified sub-files;
and starting multi-thread processing, and performing text recognition processing on the corresponding target sub-files to be recognized through each thread according to the target recognition template and the target recognition algorithm to respectively obtain target recognition texts of the target sub-files to be recognized.
In some embodiments, after the step of obtaining the target file to be identified is implemented, the processor 702 further implements the following steps:
monitoring an upstream file corresponding to the target file to be identified;
and when the upstream file is changed, generating change early warning information.
It should be appreciated that, in embodiments of the present invention, the Processor 702 may be a Central Processing Unit (CPU), and the Processor 702 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions. The program instructions, when executed by the processor, cause the processor to perform the steps of:
acquiring a target file to be identified;
performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text;
acquiring verification data corresponding to the target file to be identified;
comparing the verification data with the target identification text to obtain a comparison result;
and generating a verification result according to the comparison result.
In some embodiments, when the processor executes the program instruction to implement the step of performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the following steps are specifically implemented:
determining a target identification template and a target identification algorithm of the target file to be identified according to the file type of the target file to be identified;
determining the target position of the target file to be identified according to the target identification template;
and performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text.
In some embodiments, when the processor executes the program instruction to implement the step of performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text, the following steps are specifically implemented:
performing text recognition processing on the target position according to the target recognition algorithm to obtain an initial recognition text;
performing word segmentation processing on the initial recognition text to obtain a plurality of words;
correcting the participles according to a preset word bank to obtain target participles;
and determining the target recognition text according to the target word segmentation.
In some embodiments, when the processor executes the program instructions to implement the step of obtaining the target file to be recognized when the target file to be recognized is a picture, the following steps are specifically implemented:
acquiring an original file to be identified;
determining whether the resolution of the original file to be identified is smaller than a preset resolution threshold value;
if the resolution of the original file to be recognized is smaller than the resolution threshold, inputting the original file to be recognized into a preset resolution improvement network model for resolution processing to obtain the target file to be recognized;
and if the resolution of the original file to be identified is greater than or equal to the resolution threshold, determining the original file to be identified as the target file to be identified.
In some embodiments, before the step of executing the program instruction to implement text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the processor specifically implements the following steps:
carrying out angle correction processing on the target recognition text to obtain a first target recognition text;
carrying out size adjustment processing on the first target recognition text to obtain a second target recognition text;
the text recognition processing is carried out on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, and the method comprises the following steps:
and performing text recognition processing on the second target file to be recognized according to the recognition template and the recognition algorithm to obtain the target recognition text.
In some embodiments, when the processor executes the program instruction to implement that the target to-be-recognized file includes a plurality of target to-be-recognized sub-files, and performs text recognition processing on the target to-be-recognized file according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the following steps are specifically implemented:
determining a target identification template and a target identification algorithm which respectively correspond to the file type of each target to-be-identified sub-file in the plurality of target to-be-identified sub-files;
and starting multi-thread processing, and performing text recognition processing on the corresponding target sub-files to be recognized through each thread according to the target recognition template and the target recognition algorithm to respectively obtain target recognition texts of the target sub-files to be recognized.
In some embodiments, after the step of obtaining the target file to be identified is implemented by the processor executing the program instructions, the following steps are implemented:
monitoring an upstream file corresponding to the target file to be identified;
and when the upstream file is changed, generating change early warning information.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent verification method, comprising:
acquiring a target file to be identified;
performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text;
acquiring verification data corresponding to the target file to be identified;
comparing the verification data with the target identification text to obtain a comparison result;
and generating a verification result according to the comparison result.
2. The method according to claim 1, wherein the performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text comprises:
determining a target identification template and a target identification algorithm of the target file to be identified according to the file type of the target file to be identified;
determining the target position of the target file to be identified according to the target identification template;
and performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text.
3. The method according to claim 2, wherein the performing text recognition processing on the target position according to the target recognition algorithm to obtain the target recognition text comprises:
performing text recognition processing on the target position according to the target recognition algorithm to obtain an initial recognition text;
performing word segmentation processing on the initial recognition text to obtain a plurality of words;
correcting the participles according to a preset word bank to obtain target participles;
and determining the target recognition text according to the target word segmentation.
4. The method according to claim 1, wherein when the target file to be recognized is a picture, the acquiring the target file to be recognized comprises:
acquiring an original file to be identified;
determining whether the resolution of the original file to be identified is smaller than a preset resolution threshold value;
if the resolution of the original file to be recognized is smaller than the resolution threshold, inputting the original file to be recognized into a preset resolution improvement network model for resolution processing to obtain the target file to be recognized;
and if the resolution of the original file to be identified is greater than or equal to the resolution threshold, determining the original file to be identified as the target file to be identified.
5. The method according to claim 4, wherein before performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, the method further comprises:
carrying out angle correction processing on the target recognition text to obtain a first target recognition text;
carrying out size adjustment processing on the first target recognition text to obtain a second target recognition text;
the text recognition processing is carried out on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text, and the method comprises the following steps:
and performing text recognition processing on the second target file to be recognized according to the recognition template and the recognition algorithm to obtain the target recognition text.
6. The method according to claim 1, wherein the target file to be recognized comprises a plurality of target sub-files to be recognized, and performing text recognition processing on the target file to be recognized according to a preset recognition template and a preset recognition algorithm to obtain a target recognition text comprises:
determining a target identification template and a target identification algorithm which respectively correspond to the file type of each target to-be-identified sub-file in the plurality of target to-be-identified sub-files;
and starting multi-thread processing, and performing text recognition processing on the corresponding target sub-files to be recognized through each thread according to the target recognition template and the target recognition algorithm to respectively obtain target recognition texts of the target sub-files to be recognized.
7. The method according to any one of claims 1 to 6, wherein after the target file to be identified is obtained, the method further comprises:
monitoring an upstream file corresponding to the target file to be identified;
and when the upstream file is changed, generating change early warning information.
8. An intelligent verification device, comprising:
the first acquisition unit is used for acquiring a target file to be identified;
the identification unit is used for carrying out text identification processing on the target file to be identified according to a preset identification template and a preset identification algorithm to obtain a target identification text;
the second acquisition unit is used for acquiring verification data corresponding to the target file to be identified;
the comparison unit is used for comparing the verification data with the target identification text to obtain a comparison result;
and the first generating unit is used for generating a verification result according to the comparison result.
9. A computer arrangement, characterized in that the computer arrangement comprises a memory having stored thereon a computer program and a processor implementing the method according to any of claims 1-7 when executing the computer program.
10. A storage medium, characterized in that the storage medium stores a computer program comprising program instructions which, when executed by a processor, implement the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695907.4A CN113420657A (en) | 2021-06-23 | 2021-06-23 | Intelligent verification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110695907.4A CN113420657A (en) | 2021-06-23 | 2021-06-23 | Intelligent verification method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113420657A true CN113420657A (en) | 2021-09-21 |
Family
ID=77716145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110695907.4A Pending CN113420657A (en) | 2021-06-23 | 2021-06-23 | Intelligent verification method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420657A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115017272A (en) * | 2022-08-09 | 2022-09-06 | 盛业信息科技服务(深圳)有限公司 | Intelligent verification method and device based on registration data |
| CN116959018A (en) * | 2023-06-05 | 2023-10-27 | 简单汇信息科技(广州)有限公司 | OCR-based intelligent checking method, system and equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500179A (en) * | 2013-09-09 | 2014-01-08 | 国家电网公司 | Data source change early warning method |
| CN109472918A (en) * | 2018-10-12 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Invoice validation method, financing checking method, device, equipment and medium |
| CN109919147A (en) * | 2019-03-04 | 2019-06-21 | 上海宝尊电子商务有限公司 | The method of text identification in drop for clothing image |
| CN110751143A (en) * | 2019-09-26 | 2020-02-04 | 中电万维信息技术有限责任公司 | Electronic invoice information extraction method and electronic equipment |
| CN111105548A (en) * | 2019-12-13 | 2020-05-05 | 远光软件股份有限公司 | Batch checking device and method for value-added tax special invoices |
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN111461070A (en) * | 2020-04-29 | 2020-07-28 | Oppo广东移动通信有限公司 | Text recognition method and device, electronic equipment and storage medium |
| CN111950560A (en) * | 2020-08-21 | 2020-11-17 | 广州宝钢南方贸易有限公司 | Invoice checking device and method |
| CN112784220A (en) * | 2020-06-12 | 2021-05-11 | 深圳市迪博企业风险管理技术有限公司 | Paper contract tamper-proof verification method and system |
| CN112966671A (en) * | 2021-04-22 | 2021-06-15 | 深圳鼎盛电脑科技有限公司 | Contract detection method and device, electronic equipment and storage medium |
-
2021
- 2021-06-23 CN CN202110695907.4A patent/CN113420657A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103500179A (en) * | 2013-09-09 | 2014-01-08 | 国家电网公司 | Data source change early warning method |
| CN109472918A (en) * | 2018-10-12 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Invoice validation method, financing checking method, device, equipment and medium |
| CN109919147A (en) * | 2019-03-04 | 2019-06-21 | 上海宝尊电子商务有限公司 | The method of text identification in drop for clothing image |
| CN110751143A (en) * | 2019-09-26 | 2020-02-04 | 中电万维信息技术有限责任公司 | Electronic invoice information extraction method and electronic equipment |
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN111105548A (en) * | 2019-12-13 | 2020-05-05 | 远光软件股份有限公司 | Batch checking device and method for value-added tax special invoices |
| CN111461070A (en) * | 2020-04-29 | 2020-07-28 | Oppo广东移动通信有限公司 | Text recognition method and device, electronic equipment and storage medium |
| CN112784220A (en) * | 2020-06-12 | 2021-05-11 | 深圳市迪博企业风险管理技术有限公司 | Paper contract tamper-proof verification method and system |
| CN111950560A (en) * | 2020-08-21 | 2020-11-17 | 广州宝钢南方贸易有限公司 | Invoice checking device and method |
| CN112966671A (en) * | 2021-04-22 | 2021-06-15 | 深圳鼎盛电脑科技有限公司 | Contract detection method and device, electronic equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115017272A (en) * | 2022-08-09 | 2022-09-06 | 盛业信息科技服务(深圳)有限公司 | Intelligent verification method and device based on registration data |
| CN115017272B (en) * | 2022-08-09 | 2022-11-04 | 盛业信息科技服务(深圳)有限公司 | Intelligent verification method and device based on registration data |
| CN116959018A (en) * | 2023-06-05 | 2023-10-27 | 简单汇信息科技(广州)有限公司 | OCR-based intelligent checking method, system and equipment |
| CN116959018B (en) * | 2023-06-05 | 2024-02-23 | 简单汇信息科技(广州)有限公司 | OCR-based intelligent checking method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10332118B2 (en) | Efficient prevention of fraud | |
| EP3440591B1 (en) | Improving optical character recognition (ocr) accuracy by combining results across video frames | |
| AU2020200058B2 (en) | Image quality assessment and improvement for performing optical character recognition | |
| AU2013379776B2 (en) | Presentation of image of source of tax data through tax preparation application | |
| JP6528147B2 (en) | Accounting data entry support system, method and program | |
| US20140270404A1 (en) | Efficient prevention of fraud | |
| CN108256591B (en) | Method and apparatus for outputting information | |
| US8326041B2 (en) | Machine character recognition verification | |
| US20140270409A1 (en) | Efficient prevention of fraud | |
| CN112651841B (en) | Online business handling method, online business handling device, server and computer readable storage medium | |
| CN113420657A (en) | Intelligent verification method and device, computer equipment and storage medium | |
| CN111382740A (en) | Text picture analysis method and device, computer equipment and storage medium | |
| US11100572B1 (en) | Customer verification and account creation systems and methods | |
| EP3425544B1 (en) | System and method for processing a digital transaction | |
| AU2020369152A1 (en) | Docket analysis methods and systems | |
| WO2019027970A1 (en) | Mobile application for automatic information synthesis | |
| CN112001818A (en) | Contract verification method and device, computer equipment and storage medium | |
| CN111507850A (en) | Authority guaranteeing method and related device and equipment | |
| CN115408727A (en) | Intelligent data auditing method, device, equipment and medium | |
| CN113066223A (en) | Automatic invoice verification method and device | |
| WO2024065374A1 (en) | Automated verification of documents related to accounts within a service provider network | |
| CN115410309A (en) | Invoice checking method and system | |
| CN113449673A (en) | Certificate identification and verification method and device | |
| JP5598388B2 (en) | Document creation device, document creation method, document creation program | |
| CN113342937A (en) | Confirmation processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210921 |
|
| WD01 | Invention patent application deemed withdrawn after publication |