CN111191435A - Method and device for generating report form by using dynamic template of customs report form - Google Patents
Method and device for generating report form by using dynamic template of customs report form Download PDFInfo
- Publication number
- CN111191435A CN111191435A CN201911425613.9A CN201911425613A CN111191435A CN 111191435 A CN111191435 A CN 111191435A CN 201911425613 A CN201911425613 A CN 201911425613A CN 111191435 A CN111191435 A CN 111191435A
- Authority
- CN
- China
- Prior art keywords
- template
- information
- customs
- image
- module
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 9
- 238000012795 verification Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000012856 packing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 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
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Character Input (AREA)
Abstract
The invention provides a method and a device for generating a report form by a dynamic template of a customs report form, wherein the method comprises the following steps: the method comprises the steps of obtaining a customs clearance document image of a single page according to an input original file, identifying characters and characters in the image according to the document image, inputting a character identification result and the customs clearance document image into a classification module, performing preliminary template classification according to a pre-stored customs report basic template, dynamically adjusting the template according to identified character information and positions, comparing the character identification information, the template information and associated document keywords, and outputting an identification result after adjusting the characters and the characters according to a matched basic template. The method has the advantages that the document understanding process of the customs clearance original file is optimized by utilizing the dynamic adjustment mode of the template, the expected recognition result is more accurately output by combining the context verification of the contents of the front page and the back page, the complete declaration file is formed, the accuracy of the final output result is effectively improved, and the labor cost in the customs clearance declaration process is greatly saved.
Description
Technical Field
The invention relates to the field of image recognition and text processing, in particular to a method and a device for generating a report form by using a dynamic template of a customs report form.
Background
The document understanding technology in image processing is a process of converting a file into an image format, and extracting and organizing various types of information contained in the image into structured data such as json or XML through comprehensive processing and analysis of information such as layout analysis, character positions, character recognition content and the like in a document image. Understanding the content in one image and converting the content into structured data is helpful for electronizing documents in the forms of paper or images and the like and providing help for subsequent data sorting and big data analysis.
In customs declaration industry, customs declaration personnel fill in declaration documents, and need to check and compare documents such as invoices, shipping orders, packing orders, sales contracts and the like in a customs declaration original document, so as to extract information of each commodity to be declared, the amount of the commodity, contents such as various logistics packing information and the like.
After the files are compared with each other and checked to be correct, the files are manually input into an electronic declaration system or manually filled in a paper declaration file, and are declared after the contents are confirmed to be correct through verification of a plurality of processes. In the process, a plurality of processes of comparing and checking the data before and after and manually inputting are involved.
The existing electronic customs declaration system or manual filling has the problems that invoice scanning pieces cannot be understood, automatic goods import and export filing is carried out, the time for inputting and verifying before and after is long, and the like.
Disclosure of Invention
In order to realize customs clearance file integration, reduce the time of inputting and checking and improve the customs clearance efficiency, the invention provides a method and a device for generating a report by a dynamic template of a customs clearance report, which comprises the following steps:
a method for generating a report by a dynamic template of a customs report comprises the following steps:
and 4, dynamically adjusting the template by combining the recognized text information and the recognized position, wherein the dynamic adjustment comprises the following steps:
A. dividing the image of the clearance document into a plurality of interested areas to compare with the basic template, comparing the content of the characters and characters of the single interested area with the keywords of the corresponding area in the basic template to judge the basic template with the closest clearance document,
B. if matched keywords are not found in the image and the characters, the boundary of the region of interest is enlarged, the relative position between the regions is adjusted, the semantic analysis is carried out on the characters to judge whether the characters are similar words of the keywords,
C. if the content and the position in the region of interest are matched with the template, the region of interest is reduced, the wrongly-classified irrelevant content is eliminated,
D. comparing the same keyword data in a plurality of associated documents according to the relevance according to the basic template and the association relation of the basic template in the whole set of customs reports,
and 5, comparing the character identification information, the template information and the associated document keywords, adjusting the characters and the characters according to the matched basic template if the identification results of the character identification information, the template information and the associated document keywords are consistent, and outputting the identification result, otherwise, returning to the step 4, and continuously performing dynamic adjustment on the template.
Further, on the basis of the above technical solution, the image, character and character comparison in step a in step 4 is to find out a most similar template according to all the feature parameters, map an area of interest in the template into the input document image according to the image proportion and the relative position of the feature points, compare the similarity between all the text information feature vector codes and the basic template, and compare the area corresponding to the similar text and the relative position relationship between the areas with the basic template, where the similarity is required to reach a threshold value of more than 70%.
Further, on the basis of the above technical solution, the keyword in step 4 is invoice information and/or commodity information.
Further, on the basis of the technical scheme, the invoice information comprises an invoice name, an amount, an invoice body, an invoice number, an invoice date and a commodity name.
Further, on the basis of the above technical solution, the commodity information includes a commodity name, a commodity unit price, a commodity quantity, and a commodity place of origin.
Further, on the basis of the above technical solution, the outputting of the result in step 5 means formatting the output recognition result, and organizing the output recognition result into a declaration file format according to the field name and the recognition result of each region of interest and according to a basic template.
Further, on the basis of the above technical solution, the declaration file format is a json format.
A device for generating a report aiming at a dynamic template for a customs report comprises an image input module, an image processing module, a character recognition module, a storage module, a central processing module and an output module, wherein the image input module is used for acquiring image information of a customs document and transmitting the image information to the image processing module, the image processing module is used for carrying out formatting adjustment on the image information of the customs document and transmitting the processed information to the character recognition module, the character recognition module and the central processing module, the character recognition module is used for recognizing the character information in the image of the customs document and transmitting the processed information to the central processing module, the storage module is used for prestoring a customs report basic template, the central processing module is used for comparing the information with the basic module according to the image processing module, the character recognition module and the character recognition module, generating declaration form information according to a comparison result and transmitting the declaration form information to the output module, and the output module is used for outputting a text according to the declaration form information generated by the central processing module.
The method has the advantages that the document understanding process of the customs clearance original file is optimized by utilizing the dynamic adjustment mode of the template, the expected identification result is more accurately output by combining the context verification of the contents of the front page and the back page, the complete declaration file is formed, the accuracy of the final output result is effectively improved, and the labor cost in the customs clearance declaration process is greatly saved.
Drawings
1. FIG. 1 is a diagram of the steps of the method of the present invention;
2. FIG. 2 is a first diagram of image information according to the method of the present invention;
3. FIG. 3 is a second schematic diagram of image information according to the method of the present invention;
4. FIG. 4 is a third schematic diagram of image information according to the method of the present invention;
5. fig. 5 is a schematic diagram of a module of the device of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
As shown in fig. 1, a method for generating a report by using a dynamic template of a customs report comprises:
and 4, dynamically adjusting the template by combining the recognized text information and the recognized position, wherein the dynamic adjustment comprises the following steps:
A. dividing the image of the clearance document into a plurality of interested areas to compare with the basic template, comparing the content of the characters and characters of the single interested area with the keywords of the corresponding area in the basic template to judge the basic template with the closest clearance document,
B. if matched keywords are not found in the image and the characters, the boundary of the region of interest is enlarged, the relative position between the regions is adjusted, the semantic analysis is carried out on the characters to judge whether the characters are similar words of the keywords,
C. if the content and the position in the region of interest are matched with the template, the region of interest is reduced, the wrongly-classified irrelevant content is eliminated,
D. comparing the same keyword data in a plurality of associated documents according to the relevance according to the basic template and the association relation of the basic template in the whole set of customs reports,
and 5, comparing the character identification information, the template information and the associated document keywords, adjusting the characters and the characters according to the matched basic template if the identification results of the character identification information, the template information and the associated document keywords are consistent, and outputting the identification result, otherwise, returning to the step 4, and continuously performing dynamic adjustment on the template.
With reference to fig. 2, fig. 3, and fig. 4, where fig. 2 is a basic template, fig. 3 is image acquisition document information, after comparing the images, characters, and characters in fig. 3 according to step a of step 4, all feature parameters find the most similar template a in fig. 3, and map the region of interest in the template a into the input image of the document a in fig. 2 according to the image proportion and the relative positions of the feature points, compare the similarity between all text information feature vector codes and the basic template, and compare the relative positional relationship between the regions corresponding to similar texts and the regions with the basic template, where the information of Key1 and Value1 regions in the document a is the same as that of the template a, but there is a print offset region in the document a.
According to the step B, the region of interest boundary is enlarged for the printing offset region in the document A by contrasting the template A, the information matched with the region corresponding to the template A is found after the region is enlarged, the region of interest is adjusted as shown in FIG. 4, the region of interest is reduced to a proper range, and then the irrelevant part is eliminated according to the step C.
According to the step D, calculating and comparing keywords contained in the document A, such as invoice information including invoice name, amount, bill body, invoice number, invoice date, commodity name and the like, and commodity information including commodity name, commodity unit price, commodity quantity, commodity production place and the like, with associated information in other recorded documents, such as the sum of the amounts of all commodities in the invoice is equal to the total amount, the product quantity multiplied by the unit price is equal to the total price of the commodities and the like, and finally confirming that the character identification information, the template information and the associated document keywords are consistent.
And finally, adjusting characters and characters in the document A according to the matched basic template A through the step 5, and outputting a declaration file in a json format.
As shown in fig. 5, an apparatus for generating a report for a dynamic template of a customs report includes an image input module, an image processing module, a character recognition module, a storage module, a central processing module and an output module, where the image input module is configured to obtain image information of a customs document and transmit the image information to the image processing module, the image processing module is configured to perform formatting adjustment on the image information of the customs document and transmit the processed information to the character recognition module, the character recognition module and the central processing module, the character recognition module is configured to recognize character information in the image of the customs document and transmit the processed information to the central processing module, the storage module is configured to pre-store a customs basic report template, the central processing module is used for comparing the information with the basic module according to the image processing module, the character recognition module and the character recognition module, generating declaration form information according to a comparison result and transmitting the declaration form information to the output module, and the output module is used for outputting a text according to the declaration form information generated by the central processing module.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and their full range of equivalents.
Claims (8)
1. A method for generating a report by a dynamic template of a customs report comprises the following steps:
step 1, obtaining a single-page clearance document image of an input original file,
step 2, recognizing characters and characters in the images according to the document images,
step 3, inputting the character recognition result and the customs clearance document image into a classification module, performing primary template classification according to a pre-stored customs report basic template,
and 4, dynamically adjusting the template by combining the recognized text information and the recognized position, wherein the dynamic adjustment comprises the following steps:
A. dividing the image of the clearance document into a plurality of interested areas to compare with the basic template, comparing the content of the characters and characters of the single interested area with the keywords of the corresponding area in the basic template to judge the basic template with the closest clearance document,
B. if matched keywords are not found in the image and the characters, the boundary of the region of interest is enlarged, the relative position between the regions is adjusted, the semantic analysis is carried out on the characters to judge whether the characters are similar words of the keywords,
C. if the content and the position in the region of interest are matched with the template, the region of interest is reduced, the wrongly-classified irrelevant content is eliminated,
D. comparing the same keyword data in a plurality of associated documents according to the relevance according to the basic template and the association relation of the basic template in the whole set of customs reports,
and 5, comparing the character identification information, the template information and the associated document keywords, adjusting the characters and the characters according to the matched basic template if the identification results of the character identification information, the template information and the associated document keywords are consistent, and outputting the identification result, otherwise, returning to the step 4, and continuously performing dynamic adjustment on the template.
2. The method for generating reports using a dynamic template for customs reports as claimed in claim 1, wherein: and B, in the step A of the step 4, the most similar template is found out according to all the characteristic parameters, the region of interest in the template is mapped into the input document image according to the image proportion and the relative position of the characteristic points, the similarity between the characteristic vector codes of all the text information and the basic template is compared, and the relative position relation between the regions and the corresponding regions of the similar text is compared with the basic template, so that the similarity is required to reach a threshold value of more than 70 percent.
3. The method for generating reports using a dynamic template for customs reports as claimed in claim 1, wherein: and 4, the key words in the step 4 are invoice information and/or commodity information.
4. The method for generating reports using a dynamic template for customs reports as claimed in claim 3, wherein: the invoice information comprises an invoice name, an amount, a bill body, an invoice number, an invoice date and a commodity name.
5. The method for generating reports using a dynamic template for customs reports as claimed in claim 3, wherein: the commodity information includes commodity names, commodity unit prices, commodity quantities, and commodity origin.
6. The method for generating reports using a dynamic template for customs reports as claimed in claim 1, wherein: the step 5 of outputting the result means that the output identification result is formatted, and the field name and the identification result of each region of interest are organized into a declaration file format according to a basic template.
7. The method of claim 6, wherein the report generation method is implemented by using a dynamic template for customs reports, and comprises the following steps: the declaration file format is a json format.
8. The device for the method for generating the report by the dynamic template of the customs report of claim 1 comprises an image input module, an image processing module, a character recognition module, a storage module, a central processing module and an output module,
the image input module is used for acquiring the image information of the customs clearance document and transmitting the image information to the image processing module,
the image processing module is used for formatting and adjusting the image information of the clearance documents and transmitting the processed information to the character recognition module, the character recognition module and the central processing module,
the character recognition module is used for recognizing character information in the clearance document image and transmitting the processed information to the central processing module,
the character recognition module is used for recognizing character information in the clearance document image and transmitting the processed information to the central processing module,
the storage module is used for prestoring a customs report form basic template,
the central processing module is used for comparing the information with the basic module according to the image processing module, the character recognition module and the character recognition module, generating declaration form information according to the comparison result and transmitting the declaration form information to the output module,
and the output module is used for outputting a text according to the declaration form information generated by the central processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911425613.9A CN111191435B (en) | 2019-12-25 | 2019-12-25 | Method and device for generating report form by dynamic template for customs report form |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911425613.9A CN111191435B (en) | 2019-12-25 | 2019-12-25 | Method and device for generating report form by dynamic template for customs report form |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111191435A true CN111191435A (en) | 2020-05-22 |
| CN111191435B CN111191435B (en) | 2024-02-06 |
Family
ID=70708107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911425613.9A Active CN111191435B (en) | 2019-12-25 | 2019-12-25 | Method and device for generating report form by dynamic template for customs report form |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191435B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680679A (en) * | 2020-06-03 | 2020-09-18 | 重庆数道科技有限公司 | Automatic document identification method based on OCR |
| CN111881881A (en) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | Machine intelligent text recognition credibility judgment method based on multiple dimensions |
| CN112214184A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | User-defined printing method and device, computer equipment and medium |
| CN113221904A (en) * | 2021-05-13 | 2021-08-06 | 北京惠朗时代科技有限公司 | Semantic associated character recognition method and device |
| CN113553393A (en) * | 2021-06-16 | 2021-10-26 | 北京来也网络科技有限公司 | Processing method and processing device for combining RPA and AI customs information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002157545A (en) * | 2000-11-22 | 2002-05-31 | Nippon Express Co Ltd | Method for reading and transferring document |
| CN106845930A (en) * | 2016-12-30 | 2017-06-13 | 宁波贤晟信息技术有限公司 | One kind declaration data handling system |
| CN108171483A (en) * | 2018-01-29 | 2018-06-15 | 成都易达天下国际贸易有限责任公司 | A kind of EMS declaration systems based on big data |
-
2019
- 2019-12-25 CN CN201911425613.9A patent/CN111191435B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002157545A (en) * | 2000-11-22 | 2002-05-31 | Nippon Express Co Ltd | Method for reading and transferring document |
| CN106845930A (en) * | 2016-12-30 | 2017-06-13 | 宁波贤晟信息技术有限公司 | One kind declaration data handling system |
| CN108171483A (en) * | 2018-01-29 | 2018-06-15 | 成都易达天下国际贸易有限责任公司 | A kind of EMS declaration systems based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 陈界伟,徐蔚然,郭军: "基于多模板匹配和可信度分析的中文文档图像关键词过滤方法" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680679A (en) * | 2020-06-03 | 2020-09-18 | 重庆数道科技有限公司 | Automatic document identification method based on OCR |
| CN111881881A (en) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | Machine intelligent text recognition credibility judgment method based on multiple dimensions |
| CN112214184A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | User-defined printing method and device, computer equipment and medium |
| CN112214184B (en) * | 2020-10-16 | 2023-11-24 | 深圳赛安特技术服务有限公司 | Custom printing method, device, computer equipment and medium |
| CN113221904A (en) * | 2021-05-13 | 2021-08-06 | 北京惠朗时代科技有限公司 | Semantic associated character recognition method and device |
| CN113553393A (en) * | 2021-06-16 | 2021-10-26 | 北京来也网络科技有限公司 | Processing method and processing device for combining RPA and AI customs information |
| WO2022262114A1 (en) * | 2021-06-16 | 2022-12-22 | 北京来也网络科技有限公司 | Rpa and ai combined customs declaration information processing method and processing device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111191435B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191435B (en) | Method and device for generating report form by dynamic template for customs report form | |
| US9454545B2 (en) | Automated field position linking of indexed data to digital images | |
| CN112418812A (en) | Distributed full-link automatic intelligent clearance system, method and storage medium | |
| AU2012213242B2 (en) | System for data extraction and processing | |
| KR101942468B1 (en) | Structured data and unstructured data extraction system and method | |
| CN109002425B (en) | Method for acquiring upstream and downstream relations of enterprise, terminal device and medium | |
| CN112785404A (en) | Invoice issuing management system | |
| CN116244410A (en) | Index data analysis method and system based on knowledge graph and natural language | |
| KR20160127225A (en) | Entry papers creation apparatus and method thereof | |
| TW202018616A (en) | Intelligent accounting system and identification method for accounting documents | |
| EP4168901A1 (en) | System and method for detection and auto-validation of key data in any non-handwritten document | |
| US20220058385A1 (en) | Product labeling review | |
| TWM575887U (en) | Intelligent accounting system | |
| CN114443834A (en) | Method and device for extracting license information and storage medium | |
| CN111563204B (en) | Information extraction method and system | |
| CN117813601A (en) | System and method for enabling relevant data to be extracted from multiple documents | |
| US9727287B2 (en) | Data transfer system, method of transferring data, and system | |
| US10565289B2 (en) | Layout reconstruction using spatial and grammatical constraints | |
| CN112434997A (en) | Date generation device, control method, and non-transitory computer-readable medium | |
| Wattar | Analysis and Comparison of invoice data extraction methods | |
| JP3513806B2 (en) | Real estate registration information filing system | |
| Gunawan et al. | Application Prototype for Scientific Paper Layout Inspection | |
| US20140201223A1 (en) | Intelligent system and method for processing data to provide recognition and extraction of an informative segment | |
| CN115730074A (en) | File classification method and device, computer equipment and storage medium | |
| CN117274993A (en) | Document labeling method, device, equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |