CN117093548B - Bidding management auditing system - Google Patents
Bidding management auditing system Download PDFInfo
- Publication number
- CN117093548B CN117093548B CN202311359635.6A CN202311359635A CN117093548B CN 117093548 B CN117093548 B CN 117093548B CN 202311359635 A CN202311359635 A CN 202311359635A CN 117093548 B CN117093548 B CN 117093548B
- Authority
- CN
- China
- Prior art keywords
- comparison
- text
- file
- auditing
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims abstract description 36
- 238000002372 labelling Methods 0.000 claims abstract description 29
- 238000007726 management method Methods 0.000 claims abstract description 13
- 230000006855 networking Effects 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000012550 audit Methods 0.000 claims description 19
- 238000005516 engineering process Methods 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 9
- 238000000034 method Methods 0.000 abstract description 6
- 230000010365 information processing Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract 1
- 238000012797 qualification Methods 0.000 description 7
- 230000005856 abnormality Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a bidding management auditing system, which belongs to the technical field of information processing, and comprises a networking data acquisition module for acquiring corresponding enterprise information according to the enterprise information required to be acquired; the auditing analysis module is used for auditing the enterprise information according to the enterprise information and auditing the comparison item according to the comparison item file; the picture extraction module extracts pictures in the file; the annotation recognition and analysis module recognizes annotation information in the picture and analyzes character information corresponding to the annotation information to obtain annotation habit; the labeling habit comparison module compares labeling habits of pictures in the file, when one item of labeling habits in one item of labeling information are the same, a score is accumulated, and when the score exceeds a set score threshold value, the picture is judged to be abnormal. According to the method, the character information is obtained through analysis of the identification picture marking information, and then integral calculation is carried out on the same marking habit, so that whether abnormal conditions such as serial marks exist or not is judged according to the marking habit.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a bid and tender management auditing system.
Background
In the bidding process, the bidding documents of each large bidding enterprise are required to be audited, the traditional auditing mode needs to manually review each bidding document one by one to record, calculate, analyze and compare a large amount of data, and when the bidding projects are more and the bidding enterprises are more, the manual auditing cannot achieve the non-missing auditing of the massive bidding documents and cannot achieve the accurate calculation and analysis in massive and complex-relation data.
The invention patent with the application number of CN202110166523.3 discloses a bidding auditing method and system based on a data mining analysis technology, bidding auditing key information is automatically extracted from bidding business files and technical scheme files through OCR (optical character recognition) and text extraction technologies, and bidding enterprises and projects with bidding violations such as exchange bidding agents and technical scheme mines are intelligently identified from the bidding key information by utilizing data mining technologies such as association analysis and text mining. The patent only realizes text auditing of business files and technical files, but cannot audit the configuration drawings of the business files or the technical files, only generally recognizes the structure and the color of an image picture in the traditional image comparison, and for the sake of clear explanation, usually carries out information labeling in the file configuration drawings, and labeling habits of all people are different, so that the labeling habits can reflect the similarity among the files to a certain extent and further reflect whether abnormal conditions such as serial labels exist or not, and therefore, a bidding management auditing system is required to audit the labeling information of the pictures.
Disclosure of Invention
The invention provides a bidding management auditing system for solving the technical problems in the prior art, which comprises the following steps: the project configuration module and the project auditing module are used for carrying out project configuration;
the project configuration module comprises: a comparison item configuration module and a file template acquisition module;
the comparison item configuration module is used for selecting one or more items from the comparison items for comparison; the comparison items comprise business files and technical files;
the file template acquisition module is used for acquiring a corresponding comparison item file template according to the selected comparison item; the comparison item file template comprises a business file template and a technical file template;
the project auditing module comprises: the system comprises a networking data acquisition module and an audit analysis module;
the networking data acquisition module is used for acquiring corresponding enterprise information according to the enterprise information to be acquired;
the auditing analysis module is used for auditing the enterprise information according to the enterprise information and auditing the comparison item according to the comparison item file;
the comparison item auditing comprises business technology auditing; the business technology audit comprises picture comparison;
the auditing analysis module comprises a picture extraction module, a labeling identification and analysis module and a labeling habit comparison module;
the picture extraction module is used for extracting pictures in the business files and/or the technical files;
the annotation recognition and analysis module is used for recognizing annotation information in the picture and analyzing character information corresponding to the annotation information to obtain annotation habits;
the marking habit comparison module is used for comparing the marking habits of the pictures in the business files and/or the technical files of each enterprise, accumulating a score when one item of marking habits in one item of marking information are the same, and judging the picture as a marking abnormal picture when the score exceeds a set score threshold; if the ratio of the number of the marked abnormal images in the current comparison and the number of the images in the file exceeds a set abnormal threshold, judging that the enterprise has the abnormal image marking.
Further, the labeling information comprises Chinese labeling, english labeling and digital labeling; the character information comprises fonts, character spacing, font size and a guiding mode; the labeling habit comprises font habit, interval habit, size habit and guiding mode habit.
Further, the label recognition and analysis module recognizes character label information in the picture and analyzes the character label information, specifically:
converting the picture into a gray level picture and performing binarization processing to obtain a preprocessed image;
recognizing characters in the preprocessed image by using an OCR algorithm to obtain Unicode codes, and analyzing the Unicode codes to obtain font sizes;
recognizing the fonts of the characters in the preprocessed image through a font library;
the pixel pitch of the character is obtained by proportionally calculating the pixel size of the preprocessed image, wherein the pixel pitch is the word pitch.
Further, the business technology audit further comprises text comparison, the business files and/or the technical files of the enterprises are compared with other enterprises one by one to analyze the text similarity, the text similarity is analyzed once again in each comparison, and if the text similarity in any text comparison exceeds a set business technology similarity threshold, the text is judged to be abnormal.
Further, the audit analysis module further includes:
the filtering word stock is used for storing stop words and industry terms;
the similar keyword analysis module is used for analyzing the similarity of keywords;
the similarity text analysis module is used for analyzing the similarity of the text;
the text similarity is an average value of the keyword similarity and the text similarity.
Further, the keyword similarity analysis module analyzes the keyword similarity, specifically:
extracting keywords with occurrence times exceeding a set first threshold value from texts, filtering the stop words and industry terms through the filtering word bank, and taking the keywords as abnormal keywords if the keywords with the same word meaning as the keywords in the comparison texts and occurrence times exceeding a set second threshold value exist in the keywords of the current texts in the current comparison; and taking the ratio of the abnormal keyword number to the keyword number of the current text as the keyword similarity of the current text in the current text comparison.
Further, the similarity text analysis module analyzes the similarity of the text, specifically:
dividing a plurality of text segments from the text, performing word segmentation on the text segments, and then performing word frequency statistics to construct word frequency vectors; and calculating the cosine value of the word frequency vector of the current text segment and the cosine value of the word frequency vector of the comparison text segment, and if the cosine value is larger than a preset cosine threshold value, taking the current text segment as an abnormal text segment, wherein the ratio of the number of the abnormal text segments of the current text to the total number of the text segments of the current text as the similarity of the text segments of the current text in the current text comparison.
Further, the project auditing module further comprises a first judging module for identifying whether the file format, the file name and the file content of the uploaded comparison item file are correct according to the uploaded enterprise list and the selected comparison item.
Further, the file names include company names and comparison item names;
the first judging module identifies whether the file name of the uploaded comparison item file is correct or not, specifically: identifying whether the company name is the same as the company name of the current uploading channel, and identifying whether the comparison item name is the same as the comparison item name of the current uploading channel;
the first judging module identifies whether the file content of the uploaded comparison item file is correct or not, specifically: and acquiring a corresponding comparison item file template according to the comparison item name of the uploaded comparison item file, and identifying whether the file content of the uploaded comparison item file is matched with the corresponding comparison item file template or not, if so, the file content of the uploaded comparison item file is correct.
Further, the alignment item further includes: quotation documents, personnel lists and invoices; the comparison item file template also comprises a quotation file template, a personnel list template and an invoice template; the comparison item auditing further comprises: price auditing, personnel auditing and invoice auditing.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps of carrying out annotation habit analysis of picture annotation information through an annotation recognition and analysis module and an annotation habit comparison module to obtain annotation abnormal pictures, and judging whether picture annotation abnormality exists according to the quantity occupation ratio of the annotation abnormal pictures;
through setting the filtering word library, stop words and industry terms are filtered when keyword similarity comparison is carried out, accuracy of keyword similarity analysis is improved, meanwhile, similarity of the text is analyzed by combining a similarity text analysis module, text similarity is obtained through comprehensive calculation, and accuracy of text similarity analysis is further improved;
and the first judging module is used for identifying whether the file format, the file name and the file content of the uploaded comparison item file are correct according to the uploaded enterprise list and the selected comparison item, so that manual check is avoided, and the auditing efficiency is improved.
Drawings
FIG. 1 is a system block diagram of a bid management auditing system of the present invention;
FIG. 2 is an illustration of the present invention for a direction mode;
FIG. 3 is a block diagram of an audit analysis module according to an embodiment of the present invention.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, the bid management auditing system provided by the present invention includes: the project configuration module and the project auditing module are used for carrying out project configuration;
the project configuration module comprises: a comparison item configuration module and a file template acquisition module;
the comparison item configuration module is used for selecting one or more items from the comparison items for comparison; the comparison items comprise business files and technical files;
the file template acquisition module is used for acquiring a corresponding comparison item file template according to the selected comparison item; the comparison item file template comprises a business file template and a technical file template;
the comparison item file template is uploaded by the user, and file formats supported by the business file template and the technical file template comprise: doc, docx and pdf.
The project auditing module comprises: the system comprises a networking data acquisition module and an audit analysis module;
the networking data acquisition module is used for acquiring corresponding enterprise information according to the enterprise information to be acquired;
the enterprise information items comprise industrial and commercial information, judicial risk information and qualification information;
the business information comprises enterprise basic information, enterprise stakeholder information and historical main personnel; the basic information of the enterprise comprises addresses, contact ways, mailboxes, legal person information and the like;
the judicial risk information comprises historical legal litigation, executed persons, belief-losing persons, administrative punishment information and suspected actual control persons; the administrative penalty information comprises current penalty information and historical penalty information;
the qualification information includes business license, tax registration information, general taxpayer information, business credit rating, administrative license, tax rating and industry qualification information; the industry qualification information is a professional qualification certificate required by the industry of the enterprise, such as a professional qualification certificate required by the industries of construction, finance, information technology and the like, and the professional capability and qualification of the enterprise in the related field are proved.
According to the scheme, the networking data acquisition module can select to acquire the required enterprise information, for example, a user selects to acquire the enterprise basic information and the enterprise stakeholder information, and then the networking data acquisition module acquires the enterprise basic information and the enterprise stakeholder information of the enterprise in the auditing project through network inquiry.
And the auditing analysis module is used for auditing the enterprise information according to the enterprise information and auditing the comparison item according to the comparison item file.
The enterprise information auditing is to perform auditing comparison according to the acquired enterprise information, such as whether enterprises have administrative penalties, whether enterprises have mutual control, whether the main personnel of different enterprises are the same, and the like.
The comparison item auditing comprises business technology auditing; the business technology audit comprises picture comparison;
the auditing analysis module comprises a picture extraction module, a labeling identification and analysis module and a labeling habit comparison module;
the picture extraction module is used for extracting pictures in the business files and/or the technical files;
the annotation recognition and analysis module is used for recognizing annotation information in the picture and analyzing character information corresponding to the annotation information to obtain annotation habits;
the marking habit comparison module is used for comparing the marking habits of the pictures in the business files and/or the technical files of each enterprise, accumulating a score when one item of marking habits in one item of marking information are the same, and judging the picture as a marking abnormal picture when the score exceeds a set score threshold; if the ratio of the number of the marked abnormal images in the current comparison and the number of the images in the file exceeds a set abnormal threshold, judging that the enterprise has the abnormal image marking.
The labeling information comprises Chinese labeling, english labeling and digital labeling; the character information comprises fonts, character spacing, font size and a guiding mode; the labeling habit comprises font habit, interval habit, size habit and guiding mode habit.
The character information with the most frequency of each marking information is used as the marking habit of the character information, for example, in all pictures of a certain business file or technical file, the character information with the most frequency of marking by Chinese characters of regular script is used as the font habit of the Chinese marking of the file.
The annotation recognition and analysis module recognizes character annotation information in the picture and analyzes the character annotation information, and specifically comprises the following steps:
converting the picture into a gray level picture and performing binarization processing to obtain a preprocessed image;
recognizing characters in the preprocessed image by using an OCR algorithm to obtain Unicode codes, and analyzing the Unicode codes to obtain font sizes;
recognizing the fonts of the characters in the preprocessed image through a font library;
the pixel space of the character is obtained through the proportional calculation of the pixel size of the preprocessed image, and the pixel space is the character space;
the guiding mode is a mode that a certain structure in the picture points to corresponding marking information, for example, as shown in fig. 2, marking information 1 is directly marked in the structure corresponding to the picture in the left diagram of fig. 2, and the structure is connected with the marking information 1 by using a guiding line in the right diagram of fig. 2;
in some embodiments, the business technology audit further includes text comparison, comparing the business document and/or the technical document of the enterprise with other enterprises one by one to analyze the text similarity, re-analyzing the text similarity once each time, and if the text similarity in any text comparison exceeds a set business technology similarity threshold, determining that the text is abnormal.
For example, the similarity threshold of business technology is set to be 30%, three enterprises A, B, C perform text comparison on technical files, text similarity between A and B is 50% when A and C are compared, text similarity between A and C is required to be analyzed again and independently, text similarity between A and C is 20%, text similarity between B and C is 35%, and text anomalies exist in A, B, C.
Referring to fig. 3, the audit analysis module further includes:
the filtering word stock is used for storing stop words, industry terms and template sentences; the term used for stopping is common words and words without actual meaning, such as "this", "some", and the like;
the similar keyword analysis module is used for keyword similarity analysis, and specifically comprises the following steps:
extracting keywords with occurrence times exceeding a set first threshold value and filtered by using the stop words and industry terms through the filtering word bank from the text, and taking the keywords as abnormal keywords if the keywords in the current text have the same word meaning as the keywords in other comparison texts and the occurrence times exceeding a set second threshold value; and taking the ratio of the number of abnormal keywords of the current text to the number of keywords as the keyword similarity.
The similarity text analysis module is used for text similarity analysis and specifically comprises the following steps:
dividing a plurality of text segments from the text, performing word segmentation on the text segments, and then performing word frequency statistics to construct word frequency vectors; and calculating the cosine value of the word frequency vector of the current text segment and the cosine value of the word frequency vector of the comparison text segment, and if the cosine value is larger than a preset cosine threshold value, taking the current text segment as an abnormal text segment, wherein the ratio of the number of the abnormal text segments of the current text to the total number of the text segments of the current text as the similarity of the text segments of the current text in the current text comparison.
For example, the text A is "I like football, does not like basketball", and the text B is "I does not like football, does not like basketball"; the text A is "I1, like 2, football 1, not 1, basketball 1, also 0" obtained through word segmentation and word frequency statistics, and the text B is "I1, like 2, football 1, not 2, basketball 1, also 1"; the word frequency vector of the text A is [1,2,1,1,1,0], the word frequency vector of the text B is [1,2,1,2,1,1], and the cosine value of the word frequency vector of the text A and the cosine value of the word frequency vector of the text B are about 0.9, so that in the current text comparison, the abnormal text of each text of the text A and the text B are obtained.
The text similarity is an average value of the keyword similarity and the text similarity.
In some embodiments, the project auditing module further includes a first judging module, configured to identify whether the file format, the file name and the file content of the uploaded comparison item file are correct according to the uploaded enterprise list and the selected comparison item.
The first judging module identifies whether the file name of the uploaded comparison item file is correct or not, specifically: identifying whether the company name is the same as the company name of the current uploading channel, and identifying whether the comparison item name is the same as the comparison item name of the current uploading channel, if so, the file name is correct;
for example, the technical file uploading channel of company a uploads the comparison item file, if the file name is "company a-technical file", the file name of the comparison item file is correct, and if the file name is "company B-technical file" or "company a-business file", the file name is correct.
The first judging module identifies whether the file content of the uploaded comparison item file is correct or not, specifically: and acquiring a corresponding comparison item file template according to the comparison item name of the uploaded comparison item file, and identifying whether the file content of the uploaded comparison item file is matched with the corresponding comparison item file template or not, if so, the file content of the uploaded comparison item file is correct.
The file formats supported by the business file and the technical file include: doc, docx and pdf.
The first judging module also identifies whether the comparison item file is absent, and it is required to be noted that when the comparison item file is identified to be absent, the system can still continue to audit and analyze the comparison items of all enterprises which are not absent.
In some embodiments, the alignment further comprises: quotation documents, personnel lists and invoices; the comparison item file template also comprises a quotation file template, a personnel list template and an invoice template; the comparison item auditing further comprises: price auditing, personnel auditing and invoice auditing.
The file formats supported by the quotation file template and the personnel list file template comprise: xls and xlsx. The file formats supported by the quotation file and the personnel list file comprise: xls and xlsx; the file formats supported by the invoice comprise: jpg, jpeg, png, doc, docx and pdf.
The system also comprises a quotation configuration module which is started when the comparison item selected by the comparison item configuration module is detected to contain quotation file comparison and the comparison item file template acquisition module acquires a quotation file template;
the quotation configuration module comprises:
the quotation contrast item selection module is used for selecting quotation contrast items to be configured;
the cell ring selection module is used for ring selecting corresponding cells on the quotation file template according to the quotation comparison items selected and configured;
the second judging module is used for identifying the row and column positions of the selected cells, storing position data, judging whether the filled cells are numerical values or not according to the quotation comparison items, if not, reporting errors, and carrying out re-modification, circling or re-uploading of a new quotation file template by a user;
the quotation comparison term comprises a maximum limit price, a multi-grid maximum limit price, a calculation formula and a regularity difference;
when the price comparison item selection module selects to configure the maximum price, a cell is selected in a circle and the maximum threshold value is set for the cell;
when the quotation comparison item selection module selects to configure a multi-grid maximum price, more than one cell is selected in a circling mode, and a maximum threshold value is set for each cell independently;
the first judging module further judges whether the numerical value of the circled cell is calculated according to a preset formula or not when the quotation comparison item selecting module selects the configuration calculation formula; each cell requiring formula calculation is provided with a corresponding preset formula.
Price quotation auditing, inquiring a cell at a corresponding position according to the position data stored by the second judging module, analyzing whether the content of the cell is a numerical value or not, and if not, judging that the abnormality exists; if yes, comparing whether the highest threshold value corresponding to the cell is exceeded, and if yes, displaying that the highest limit value is exceeded; meanwhile, whether a formula corresponding to a cell calculated by the required formula is consistent with a preset formula corresponding to the cell is analyzed, and if the formula is inconsistent with the preset formula, the abnormality exists.
When the quotation auditing is used for carrying out the regularity difference analysis, the ratio calculation can be carried out on all corresponding cells needing the regularity difference analysis of two enterprises one by one to analyze whether similar ratios exist or not, and if the number of the similar ratios exceeds a set threshold value of the number of the similar ratios, the regularity quotation exists between the two enterprises.
Personnel auditing, namely carrying out personnel name comparison according to personnel list files of all enterprises, and judging that personnel abnormality exists in two enterprises if the number of identical personnel names appearing in personnel lists between the two enterprises exceeds a set threshold value of identical personnel names;
checking the invoice, verifying whether the invoice exists by inquiring the invoice code and/or the invoice number of the invoice, comparing whether the invoice numbers of the invoice are the same, and judging that the invoice of the corresponding enterprise is abnormal if the invoice with the same invoice number exists;
in some embodiments, the bidding management auditing system further comprises an auditing report generation and storage module and a mailbox configuration and sending module;
the auditing report generation and storage module is used for generating and storing an auditing report according to the auditing results of enterprise information auditing and comparison item auditing;
and the mailbox configuration and sending module is used for storing a plurality of mailbox addresses and selecting an audit report from the audit report generation and storage module to send the audit report to the mailbox addresses required to be sent.
All embodiments of the inventive arrangements can be combined with one another to form new embodiments.
The invention has the beneficial effects that: the method comprises the steps of carrying out annotation habit analysis of picture annotation information through an annotation recognition and analysis module and an annotation habit comparison module to obtain annotation abnormal pictures, and judging whether picture annotation abnormality exists according to the quantity occupation ratio of the annotation abnormal pictures;
through setting the filtering word library, stop words and industry terms are filtered when keyword similarity comparison is carried out, accuracy of keyword similarity analysis is improved, meanwhile, similarity of the text is respectively analyzed by combining a similarity text analysis module, text similarity is obtained through comprehensive calculation, and accuracy of text similarity analysis is further improved;
and the first judging module is used for identifying whether the file format, the file name and the file content of the uploaded comparison item file are correct according to the uploaded enterprise list and the selected comparison item, so that manual check is avoided, and the auditing efficiency is improved.
It will be apparent to those skilled in the art from this disclosure that various other changes and modifications can be made which are within the scope of the invention as defined in the appended claims.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (5)
1. A bid management auditing system, comprising: the project configuration module and the project auditing module are used for carrying out project configuration;
the project configuration module comprises: a comparison item configuration module and a file template acquisition module;
the comparison item configuration module is used for selecting one or more items from the comparison items for comparison; the comparison items comprise business files and technical files;
the file template acquisition module is used for acquiring a corresponding comparison item file template according to the selected comparison item; the comparison item file template comprises a business file template and a technical file template;
the project auditing module comprises: the system comprises a networking data acquisition module and an audit analysis module;
the networking data acquisition module is used for acquiring corresponding enterprise information according to the enterprise information to be acquired;
the auditing analysis module is used for auditing the enterprise information according to the enterprise information and auditing the comparison item according to the comparison item file;
the comparison item auditing comprises business technology auditing; the business technology audit comprises picture comparison;
the auditing analysis module comprises a picture extraction module, a labeling identification and analysis module and a labeling habit comparison module;
the picture extraction module is used for extracting pictures in the business files and/or the technical files;
the annotation recognition and analysis module is used for recognizing annotation information in the picture and analyzing character information corresponding to the annotation information to obtain annotation habits;
the marking habit comparison module is used for comparing the marking habits of the pictures in the business files and/or the technical files of each enterprise, accumulating a score when one item of marking habits in one item of marking information are the same, and judging the picture as a marking abnormal picture when the score exceeds a set score threshold; if the ratio of the number of the marked abnormal images in the current comparison and the number of the images in the file exceeds a set abnormal threshold, judging that the enterprise has abnormal image marking;
the labeling information comprises Chinese labeling, english labeling and digital labeling; the character information comprises fonts, character spacing, font size and a guiding mode; the labeling habit comprises font habit, interval habit, size habit and guiding mode habit;
the business technology audit further comprises text comparison, the business files and/or the technical files of the enterprises are compared with other enterprises one by one to analyze the text similarity, the text similarity is analyzed once again in each comparison, and if the text similarity in any text comparison exceeds a set business technology similarity threshold value, the text is judged to be abnormal;
the audit analysis module further comprises:
the filtering word stock is used for storing stop words and industry terms;
the similar keyword analysis module is used for analyzing the similarity of keywords;
the similarity text analysis module is used for analyzing the similarity of the text;
the text similarity is an average value of the keyword similarity and the text similarity;
the similar keyword analysis module analyzes keyword similarity, specifically:
extracting keywords with occurrence times exceeding a set first threshold value from texts, filtering the stop words and industry terms through the filtering word bank, and taking the keywords as abnormal keywords if the keywords with the same word meaning as the keywords in the comparison texts and occurrence times exceeding a set second threshold value exist in the keywords of the current texts in the current comparison; taking the ratio of the number of abnormal keywords of the current text to the number of keywords as the similarity of keywords of the current text in the current text comparison;
the similarity text analysis module analyzes the similarity of the text, and specifically comprises the following steps:
dividing a plurality of text segments from the text, performing word segmentation on the text segments, and then performing word frequency statistics to construct word frequency vectors; and calculating the cosine value of the word frequency vector of the current text segment and the cosine value of the word frequency vector of the comparison text segment, and if the cosine value is larger than a preset cosine threshold value, taking the current text segment as an abnormal text segment, wherein the ratio of the number of the abnormal text segments of the current text to the total number of the text segments of the current text as the similarity of the text segments of the current text in the current text comparison.
2. The bid management auditing system of claim 1, wherein the annotation recognition and analysis module recognizes character annotation information in a picture and analyzes the character annotation information, specifically:
converting the picture into a gray level picture and performing binarization processing to obtain a preprocessed image;
recognizing characters in the preprocessed image by using an OCR algorithm to obtain Unicode codes, and analyzing the Unicode codes to obtain font sizes;
recognizing the fonts of the characters in the preprocessed image through a font library;
the pixel pitch of the character is obtained by proportionally calculating the pixel size of the preprocessed image, wherein the pixel pitch is the word pitch.
3. The bid management auditing system of claim 1, wherein said project auditing module further comprises a first judging module for identifying whether the file format, file name and file content of the uploaded comparison item file are correct based on the uploaded enterprise list and the selected comparison item.
4. The bid management auditing system of claim 3, in which said file names include company names and alignment item names;
the first judging module identifies whether the file name of the uploaded comparison item file is correct or not, specifically: identifying whether the company name is the same as the company name of the current uploading channel, and identifying whether the comparison item name is the same as the comparison item name of the current uploading channel;
the first judging module identifies whether the file content of the uploaded comparison item file is correct or not, specifically: and acquiring a corresponding comparison item file template according to the comparison item name of the uploaded comparison item file, and identifying whether the file content of the uploaded comparison item file is matched with the corresponding comparison item file template or not, if so, the file content of the uploaded comparison item file is correct.
5. The bid management auditing system of claim 1, wherein said comparison term further comprises: quotation documents, personnel lists and invoices; the comparison item file template also comprises a quotation file template, a personnel list template and an invoice template; the comparison item auditing further comprises: price auditing, personnel auditing and invoice auditing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311359635.6A CN117093548B (en) | 2023-10-20 | 2023-10-20 | Bidding management auditing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311359635.6A CN117093548B (en) | 2023-10-20 | 2023-10-20 | Bidding management auditing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117093548A CN117093548A (en) | 2023-11-21 |
| CN117093548B true CN117093548B (en) | 2024-01-26 |
Family
ID=88773890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311359635.6A Active CN117093548B (en) | 2023-10-20 | 2023-10-20 | Bidding management auditing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117093548B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES2398829A1 (en) * | 2012-12-05 | 2013-03-22 | Tkt Brainpower, S.L. | Ink cartridge (Machine-translation by Google Translate, not legally binding) |
| CN108848337A (en) * | 2018-06-12 | 2018-11-20 | 中国联合网络通信集团有限公司 | Long-range auditing method, device, terminal and the computer storage medium of line project |
| WO2020187118A1 (en) * | 2019-03-18 | 2020-09-24 | 智慧芽信息科技(苏州)有限公司 | Page presentation method and apparatus |
| WO2021017372A1 (en) * | 2019-08-01 | 2021-02-04 | 中国科学院深圳先进技术研究院 | Medical image segmentation method and system based on generative adversarial network, and electronic equipment |
| CN112800113A (en) * | 2021-02-04 | 2021-05-14 | 天津德尔塔科技有限公司 | Bidding auditing method and system based on data mining analysis technology |
| CN112906817A (en) * | 2021-03-16 | 2021-06-04 | 中科海拓(无锡)科技有限公司 | Intelligent image labeling method |
| CN114462960A (en) * | 2022-01-07 | 2022-05-10 | 武汉理工大学 | Automatic qualification auditing method and system in electronic bidding |
| CN114639173A (en) * | 2022-05-18 | 2022-06-17 | 国网浙江省电力有限公司 | OCR technology-based intelligent auditing method and device for checking and certifying materials |
| CN115309582A (en) * | 2021-05-07 | 2022-11-08 | 中国移动通信集团有限公司 | Data auditing method and device, electronic equipment and storage medium |
| CN115795000A (en) * | 2023-02-07 | 2023-03-14 | 南方电网数字电网研究院有限公司 | Joint similarity algorithm comparison-based enclosure identification method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7260568B2 (en) * | 2004-04-15 | 2007-08-21 | Microsoft Corporation | Verifying relevance between keywords and web site contents |
-
2023
- 2023-10-20 CN CN202311359635.6A patent/CN117093548B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES2398829A1 (en) * | 2012-12-05 | 2013-03-22 | Tkt Brainpower, S.L. | Ink cartridge (Machine-translation by Google Translate, not legally binding) |
| CN108848337A (en) * | 2018-06-12 | 2018-11-20 | 中国联合网络通信集团有限公司 | Long-range auditing method, device, terminal and the computer storage medium of line project |
| WO2020187118A1 (en) * | 2019-03-18 | 2020-09-24 | 智慧芽信息科技(苏州)有限公司 | Page presentation method and apparatus |
| WO2021017372A1 (en) * | 2019-08-01 | 2021-02-04 | 中国科学院深圳先进技术研究院 | Medical image segmentation method and system based on generative adversarial network, and electronic equipment |
| CN112800113A (en) * | 2021-02-04 | 2021-05-14 | 天津德尔塔科技有限公司 | Bidding auditing method and system based on data mining analysis technology |
| CN112906817A (en) * | 2021-03-16 | 2021-06-04 | 中科海拓(无锡)科技有限公司 | Intelligent image labeling method |
| CN115309582A (en) * | 2021-05-07 | 2022-11-08 | 中国移动通信集团有限公司 | Data auditing method and device, electronic equipment and storage medium |
| CN114462960A (en) * | 2022-01-07 | 2022-05-10 | 武汉理工大学 | Automatic qualification auditing method and system in electronic bidding |
| CN114639173A (en) * | 2022-05-18 | 2022-06-17 | 国网浙江省电力有限公司 | OCR technology-based intelligent auditing method and device for checking and certifying materials |
| CN115795000A (en) * | 2023-02-07 | 2023-03-14 | 南方电网数字电网研究院有限公司 | Joint similarity algorithm comparison-based enclosure identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117093548A (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887153B (en) | Finance and tax processing method and system | |
| US20200019767A1 (en) | Document classification system | |
| US20180268448A1 (en) | System and methods of an expense management system based upon business document analysis | |
| US9025890B2 (en) | Information classification device, information classification method, and information classification program | |
| CN111125343A (en) | Text analysis method and device suitable for human-sentry matching recommendation system | |
| US11501344B2 (en) | Partial perceptual image hashing for invoice deconstruction | |
| JP2007172077A (en) | Image search system, method thereof, and program thereof | |
| US20210256097A1 (en) | Determination of intermediate representations of discovered document structures | |
| CN115599885A (en) | Document full-text retrieval method and device, computer equipment, storage medium and product | |
| US20130218913A1 (en) | Parsing tables by probabilistic modeling of perceptual cues | |
| US20230205800A1 (en) | System and method for detection and auto-validation of key data in any non-handwritten document | |
| CN114492323A (en) | Method and device for detecting enclosing and bidding behavior based on electronic bidding document comparison | |
| CN114495139A (en) | Operation duplicate checking system and method based on image | |
| CN113469005A (en) | Recognition method of bank receipt, related device and storage medium | |
| TW202018616A (en) | Intelligent accounting system and identification method for accounting documents | |
| CN117093548B (en) | Bidding management auditing system | |
| KR102392644B1 (en) | Apparatus and method for classifying documents based on similarity | |
| Slavin et al. | Models and methods flexible documents matching based on the recognized words | |
| Bureš et al. | Automatic information extraction from scanned documents | |
| CN115482075A (en) | Financial data anomaly analysis method and device, electronic equipment and storage medium | |
| CN114495138A (en) | Intelligent document identification and feature extraction method, device platform and storage medium | |
| Blomqvist et al. | Reading the ransom: Methodological advancements in extracting the swedish wealth tax of 1571 | |
| CN113763143A (en) | Auditing processing method, computer equipment and storage device | |
| CN111967246A (en) | Error correction method for shopping bill recognition result | |
| US20230055042A1 (en) | Partial Perceptual Image Hashing for Document Deconstruction |
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 |