CN111738847B - System and method for matching lenders of same economic service in certificate sheet - Google Patents

System and method for matching lenders of same economic service in certificate sheet Download PDF

Info

Publication number
CN111738847B
CN111738847B CN202010764634.XA CN202010764634A CN111738847B CN 111738847 B CN111738847 B CN 111738847B CN 202010764634 A CN202010764634 A CN 202010764634A CN 111738847 B CN111738847 B CN 111738847B
Authority
CN
China
Prior art keywords
score
node
credit
debit
combination
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
Application number
CN202010764634.XA
Other languages
Chinese (zh)
Other versions
CN111738847A (en
Inventor
沈宏颖
韩世蛟
聂敏
蒋巧兰
杨磊
何法
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Xun Dao Shu Cai Technology Co ltd
Original Assignee
Chengdu Xun Dao Shu Cai Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chengdu Xun Dao Shu Cai Technology Co ltd filed Critical Chengdu Xun Dao Shu Cai Technology Co ltd
Priority to CN202010764634.XA priority Critical patent/CN111738847B/en
Publication of CN111738847A publication Critical patent/CN111738847A/en
Application granted granted Critical
Publication of CN111738847B publication Critical patent/CN111738847B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • G06F16/34—Browsing; Visualisation therefor
    • G06F16/345—Summarisation for human users
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/12—Accounting
    • G06Q40/125—Finance or payroll

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Technology Law (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention relates to the technical field of data statistical analysis, and provides a system and a method for matching lenders of the same economic service in a voucher, wherein in the method for matching the lenders of the same economic service in the voucher, due to a special method of bookkeeping, related information of a project and information of a transaction opposite side are dispersed in the lenders of the same economic service, if a project principal and a transaction object need to be associated, the corresponding relation of the loan needs to be marked, and the purpose can be achieved.

Description

System and method for matching lenders of same economic service in certificate sheet
Technical Field
The invention relates to the field of financial accounting, in particular to a system and a method for matching lenders of the same economic service in a voucher.
Background
In recent years, along with the rapid development of economic business of administrative utilities, financial data volume is rapidly increased, and corresponding financial risks are also continuously increased, so that in a traditional manual auditing mode, an auditing person manually develops auditing business, and the problems of low data efficiency, complex problems, after discovery, narrow attention and the like are faced. In order to reduce the work pressure of the auditors and discover financial risk problems in the process, the new technology of big data and natural language processing is utilized to assist the financial auditors in discovering risks. After a new technology is introduced, how to find the lending parties of an economic business in a large amount of entry data becomes a difficult problem, and the financial accounting lending parties matched with the economic business are very important for establishing a risk early warning model. Therefore, the relationship of the same economic business is automatically mined and matched by using a big data correlation principle.
The financial departments in each company can process a large amount of voucher sheets every day, along with the popularization of the existing electronic office, after a large amount of voucher sheets are recorded into a computer system, financial staff often feel dazzling in processing and statistics, lenders of the same economic service cannot be quickly matched between complicated words and numbers, and when the voucher sheets need to be used in each time, the financial departments need to manually carry out repeated matching by analyzing various abstracts and project contents on the voucher sheets, so that the workload of the financial staff is increased.
Therefore, a method for rapidly processing a large number of financial accounting vouchers is needed, which can rapidly screen out lenders and lenders of the same economic service on the same voucher, and display the borrowers and the lenders, so that subsequent financial staff can visually confirm the matched lenders and lenders, and the office time is saved.
Disclosure of Invention
The invention aims to provide a system and a method for matching lenders of the same economic service in a voucher, which are used for arranging and combining the amounts of the lenders by using the basic principle of 'borrowing must have lending and lending must be equal' in the financial accounting, and using the text analysis technology to score the similarity of the abstracts and finally find the corresponding relation of the lending, so that the system and the method are strong in practicability, ingenious in design and suitable for popularization;
the technical scheme adopted by the invention is as follows: the system for matching the lending parties and the lending parties of the same economic service in the certificate list comprises a processing terminal and a display unit, wherein the processing unit acquires the certificate list data through a financial storage platform, the processing terminal also comprises an importing unit, a processing unit, a communication unit and a storage unit,
starting the import unit, wherein the import unit acquires voucher data in the financial storage platform through a communication unit, a processing model is prestored in the processing unit, the voucher data is sent to the processing model as input, and the output of the processing model is marked voucher data;
the processing model comprises a preprocessing module, a matching module, a scoring module and a screening module, wherein the preprocessing module decomposes voucher data into a single borrower node and a single lender node, and each borrower node and each lender node respectively comprise abstract bytes and project bytes;
the matching module matches the amounts of the plurality of lender nodes in the preprocessing module with the amounts of the plurality of borrower nodes, and combines the nodes of the lenders with the same amount;
the scoring module scores similarity of the summary bytes and the project bytes in the combination;
and the screening module screens out lenders belonging to the same economic service according to the similarity scoring result and sends the lenders to the storage module for storage.
On the other hand, the method for matching the lenders of the same economic service in the certificate list comprises the following steps:
s1: acquiring a plurality of entries of an original voucher, wherein the sum of all debit entries in one voucher is equal to the sum of all credit entries in the voucher, and executing S2;
s2: constructing a set of debit entry data combinations and a set of credit entry data combinations on each original voucher, wherein each entry data combination comprises a single entry or a combination of multiple entries, and each entry only comprises one debit data item or credit data, and executing S3;
s3: establishing a corresponding relation between the debit data and the credit data based on the fact that the amount of the debit entry data combination is equal to the amount of the credit entry data combination, wherein each group of entry data combinations with the same amount of money is defined as a node, establishing a corresponding relation set, and executing S4;
s4: respectively carrying out similarity scoring on the abstracts and the item information of the nodes in the corresponding relation set to obtain score results after the abstracts are scored and score results after the item information is scored, and executing S5;
s5: sorting the new nodes in the corresponding relation set by combining the total score results of the similarity scoring, and executing S6;
s6: and marking the debit data and the credit data of the same economic service, and ending.
Preferably, in S1, a voucher includes a plurality of entry data, and the entry data includes only one DEBIT data or CREDIT data, where the DEBIT data and the CREDIT data include a summary, item information, voucher number and entry number, the DEBIT data further includes a DEBIT amount, the CREDIT data further includes a CREDIT amount, and in S2, the SET of DEBIT entry data combinations is deep _ NODE _ SET, and the SET of CREDIT entry data combinations is CREDIT _ NODE _ SET,
DEBIT_NODE_SET = { DEBIT_NODEj: (DEBIT_ORD_SETj，DEBIT_AMOUNTj) }
CREDIT_NODE_SET ={ CREDIT_NODEi: (CREDIT_ORD_SETi，CREDIT_AMOUNTi) }
wherein the borrow entry data SET DEBIT _ NODE is a NODE of the SET DEBIT _ NODE _ SET of the borrow entry data SET, the borrow entry data SET DEBIT _ NODE comprises a combination DEBIT _ ORD _ SET of the borrow entry numbers and a borrow AMOUNT DEBIT _ AMOUNT, and when N borrow entries exist, the maximum value of j is
Figure 100002_DEST_PATH_IMAGE001
DEBIT _ AMOUNT is the sum of DEBIT AMOUNTs corresponding to DEBIT _ ORD _ SET; the CREDIT-entry-data combination CREDIT _ NODE is a NODE of the SET CREDIT _ NODE _ SET of CREDIT-entry-data combinations, the CREDIT-entry-data combination CREDIT _ NODE contains the combination CREDIT _ ORD _ SET of CREDIT-entry numbers and the CREDIT AMOUNT CREDIT _ AMOUNT,when there are M credit entries, the maximum value of i is
Figure 605740DEST_PATH_IMAGE002
CREDIT _ AMOUNT is the sum of CREDIT AMOUNTs corresponding to CREDIT _ ORD _ SET, where C is defined as the number of combinations, and the calculation formula of the number of combinations is expressed by
Figure 991722DEST_PATH_IMAGE003
For the purpose of example only,
Figure DEST_PATH_IMAGE004
。
preferably, in S3, the sum of money debt _ AMOUNT corresponding to the DEBIT entry data combination debt _ NODE in the SET of DEBIT entry data combinations debt _ NODE _ SET is linked to the original NODE having the same sum of money CREDIT _ AMOUNT corresponding to the CREDIT entry data combination CREDIT _ NODE in the SET of CREDIT entry data combinations CREDIT _ NODE _ SET, and a corresponding relationship SET is obtained.
Preferably, in S4, the process of scoring the similarity of the abstracts includes the following steps:
s41: according to the corresponding relation set in the S3, the abstract combination of each node comprises the abstract of the lender entry corresponding to the node;
s42: the summary processing process includes defining the length of the summary with the shortest character length in the summary combination as L, intercepting all the summaries in the summary combination from left to right to obtain L characters, substituting the character lengths of all the processed summaries into a formula after the summary processing to calculate to obtain processed scores, and executing step S43;
s43: the similarity score of the abstract combination is obtained by adding the score after the abstract processing and the score without the abstract processing.
Preferably, in S43, the similarity SCORE of the summary combination is abstrct _ SCORE, the similarity scoring formula of the processed summary is TRIM _ abstrct _ SCORE, and the similarity scoring formula without the summary processing is ORIGINAL _ abstrct _ SCORE
ABSTRACT_SCORE = TRIM_ABSTRACT_SCORE + ORIGINAL_ABSTRACT_SCORE
TRIM_ABSTRACT_SCORE = 1 - 0.5 × ABSTRACT_COUNT + 0.45 ×DEDUP_ABSTRACT_COUNT
ORIGINAL_ABSTRACT_SCORE = 1 - 0.5 × ABSTRACT_COUNT + 0.15 × DEDUP_ABSTRACT_COUNT
In the formula, DEDUP _ ABSTRACT _ COUNT is the number of the same ABSTRACTs after the abstraction is removed in the abstraction combination, and ABSTRACT _ COUNT is the number of the ABSTRACTs without duplication removal in the abstraction combination.
Preferably, in S4, the process of scoring the similarity of the item information includes the following steps,
s44, according to the corresponding relation set in S3, the project information combination of each node comprises the project information of the lender entry corresponding to the node;
s45: the project information processing process includes defining the length of the project information with the shortest character length in the project information combination as L, intercepting L characters from left to right of all abstracts in the project information combination to obtain all processed character lengths of the project information as L, substituting the L characters into a formula after the project information processing to calculate to obtain a processed score, and executing step S46;
s46: the similarity score of the item information combination is obtained by adding both the post-item-processing score and the non-item-information-processing score, and S5 is executed according to the calculation total similarity scoring formula.
Preferably, in step S46, the similarity SCORE of the item information combination is represented by PROJ _ SCORE, the SCORE formula of the processed item information is represented by TRIM _ PROJ _ SCORE, the similarity SCORE formula of the non-processed item information is represented by origin _ PROJ _ SCORE,
PROJ_SCORE = TRIM_PROJ_SCORE + ORIGINAL_PROJ_SCORE
TRIM_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.45 × DEDUP_PROJ_COUNT
ORIGINAL_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.15 × DEDUP_PROJ_COUNT
TOTAL_SCORE = ABSTRACT_SCORE + PROJ_SCORE × 1.3
in the formula, DEDUP _ PROJ _ COUNT is the number of item information items from which the same item information in the item information combination is removed, and PROJ _ COUNT is the number of item information items from which duplicate information is not removed in the item information combination.
Preferably, relative _ SET = { relative _ NODEk:(DEBIT_ORD_SETn，CREDIT_ORD_SETm，AMOUNTk，ABSTRACT_SETk，ABSTRACT_SCOREk，PROJ_SETk，PROJ_SCOREk，TOTAL_SCOREk)}
In the formula, k is added with 1 from 1 in sequence, the maximum value is equal to the sum of the products of the original NODE number of the SET DEBIT _ NODE _ SET of DEBIT entry data combinations with equal money and the original NODE number of the SET CREDIT _ NODE _ SET of CREDIT entry data combinations, RELATION _ SET is expressed as a corresponding RELATION SET, and the corresponding RELATION SET comprises an updated NODE RELATION _ NODEk、DEBIT score record combination DEBIT _ ORD _ SETn、Credit _ ORD _ SET combined with CREDIT entriesm、Sum of money AMUNTk、Abstract combination ABSTRACT _ SETk、Abstract similarity SCORE ABSTRACT _ SCOREk、Item information combination PROJ _ SETk、Project information similarity SCORE PROJ _ SCOREkAnd TOTAL SCORE TOTAL _ SCOREk。
Preferably, in S6, after the nodes in the corresponding relationship set are sorted according to the total similarity score, the process of marking the same economic service is as follows:
s61: taking out a NODE RELATION _ NODE with the highest total similarity score in a corresponding RELATION SET RELATION _ SET, and storing the NODE RELATION _ NODE in a RESULT SET RESULT _ SET;
s62: deleting the NODE containing the entry number in the relative _ NODE from the relative _ SET;
s63: and repeating the steps of S61 and S62 until the corresponding RELATION SET RELATION _ SET is empty, and obtaining a node SET RESULT _ SET in which the debit entry data combination and the credit entry data combination in each node belong to the same economic service.
Compared with the prior art, the invention has the beneficial effects that:
1. by using the basic principle of financial accounting, data on the voucher is arranged and combined, and related abstracts and project information are scored by using a text similarity technology, so that lenders belonging to the same economic service are quickly found out;
2. the method can process a plurality of loan projects on a plurality of voucher sheets simultaneously, can quickly sort to obtain an accurate result, and can be applied to key models such as 'serial invoice splitting reimbursement', 'splitting reimbursement evades contract processes', 'splitting reimbursement virtual column expenses', 'associated transactions'.
Drawings
Fig. 1 is a flow chart of a method for matching lenders of the same economic transaction in a voucher.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to fig. 1 of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other implementations made by those of ordinary skill in the art based on the embodiments of the present invention are obtained without inventive efforts.
Example 1:
the system for matching the lending parties and the lending parties of the same economic service in the certificate list comprises a processing terminal and a display unit, wherein the processing unit acquires the certificate list data through a financial storage platform, the processing terminal also comprises an importing unit, a processing unit, a communication unit and a storage unit,
starting the import unit, wherein the import unit acquires voucher data in the financial storage platform through a communication unit, a processing model is prestored in the processing unit, the voucher data is sent to the processing model as input, and the output of the processing model is marked voucher data;
the processing model comprises a preprocessing module, a matching module, a scoring module and a screening module, wherein the preprocessing module decomposes voucher data into a single borrower node and a single lender node, and each borrower node and each lender node respectively comprise abstract bytes and project bytes;
the matching module matches the amounts of the plurality of lender nodes in the preprocessing module with the amounts of the plurality of borrower nodes, and combines the nodes of the lenders with the same amount;
the scoring module scores similarity of the summary bytes and the project bytes in the combination;
and the screening module screens out lenders belonging to the same economic service according to the similarity scoring result and sends the lenders to the storage module for storage.
In summary, the working principle of this embodiment is that, the voucher data is called from the cloud through the system, and the voucher data is processed through the preprocessing model, so that the worker can directly obtain the lending parties of the same economic service in a very short time, and manual identification and matching of the text content on numerous lenders and lenders are not needed, which is more humanized.
Example 2:
the method for matching the lender and the lender of the same economic service in the certificate list comprises the following steps:
s1: acquiring a plurality of entries of an original voucher, wherein the sum of all debit entries in one voucher is equal to the sum of all credit entries in the voucher, and executing S2;
s2: constructing a set of debit entry data combinations and a set of credit entry data combinations on each original voucher, wherein each entry data combination comprises a single entry or a combination of multiple entries, and each entry only comprises one debit data item or credit data, and executing S3;
s3: establishing a corresponding relation between the debit data and the credit data based on the fact that the amount of the debit entry data combination is equal to the amount of the credit entry data combination, wherein each group of entry data combinations with the same amount of money is defined as a node, establishing a corresponding relation set, and executing S4;
s4: respectively carrying out similarity scoring on the abstracts and the item information of the nodes in the corresponding relation set to obtain score results after the abstracts are scored and score results after the item information is scored, and executing S5;
s5: sorting the new nodes in the corresponding relation set by combining the total score results of the similarity scoring, and executing S6;
s6: and marking the debit data and the credit data of the same economic service, and ending.
It should be noted that in S1, one voucher includes multiple entry data, and the entry data includes only one debit data or credit data, where the debit data and the credit data both include an abstract, item information, a voucher number, and an entry number, the debit data further includes a debit amount, and the credit data further includes a credit amount.
It is to be noted that ORD _ SET = { ORD = { (ORD)1，ORD2，...，ORDN+M And fourthly, the debit entry quantity is N, and the credit entry quantity is M.
It is noted that in the step S2, the SET of DEBIT record data SETs is DEBIT _ NODE _ SET, the SET of CREDIT record data SETs is CREDIT _ NODE _ SET,
DEBIT_NODE_SET = { DEBIT_NODEj: (DEBIT_ORD_SETj，DEBIT_AMOUNTj) }
CREDIT_NODE_SET ={ CREDIT_NODEi: (CREDIT_ORD_SETi，CREDIT_AMOUNTi) }
wherein the borrow entry data SET DEBIT _ NODE is a NODE of the SET DEBIT _ NODE _ SET of the borrow entry data SET, the borrow entry data SET DEBIT _ NODE comprises a combination DEBIT _ ORD _ SET of the borrow entry numbers and a borrow AMOUNT DEBIT _ AMOUNT, and when N borrow entries exist, the maximum value of j is
Figure 177984DEST_PATH_IMAGE001
DEBIT _ AMOUNT is the sum of DEBIT AMOUNTs corresponding to DEBIT _ ORD _ SET; the CREDIT entry data SET CREDIT _ NODE is a NODE of the SET CREDIT _ NODE _ SET of CREDIT entry data SETs, the CREDIT entry data SET CREDIT _ NODE contains the combination CREDIT _ ORD _ SET of CREDIT entry numbers and the CREDIT AMOUNT CREDIT _ AMOUNT, when there are M CREDIT entries, the maximum value of i is
Figure 42034DEST_PATH_IMAGE002
CREDIT _ AMOUNT is the sum of CREDIT AMOUNTs corresponding to CREDIT _ ORD _ SET, where C is defined as the number of combinations, and the calculation formula of the number of combinations is expressed by
Figure 325248DEST_PATH_IMAGE003
For the purpose of example only,
Figure 350973DEST_PATH_IMAGE004
。
entry numbers and other data tables in voucher form of Table 1S 1
Figure DEST_PATH_IMAGE006
In table 1, the debit entry number is 2; the number of lender entries is 3.
It should be noted that, referring to table 2, table 2 is a SET debt _ NODE _ SET of the borrowed entry data combination in the embodiment:
TABLE 2 set of borrowed entry data combinations
Figure DEST_PATH_IMAGE007
Referring to Table 3, Table 3 is a SET CREDIT _ NODE _ SET of CREDIT entry data combinations in the example:
TABLE 3 set of lender entry data combinations
Figure DEST_PATH_IMAGE008
It should be noted that in step S3, the original NODEs having the same sum of money debt _ AMOUNT corresponding to the DEBIT entry data combination debt _ NODE in the SET of DEBIT entry data combinations debt _ NODE _ SET and the same sum of money CREDIT _ AMOUNT corresponding to the CREDIT entry data combination CREDIT _ NODE in the SET of CREDIT entry data combinations CREDIT _ NODE _ SET are linked, and a new SET of DEBIT correspondence relationship relaton _ SET is obtained.
Please refer to table 4, wherein table 4 is a set of lender correspondences:
TABLE 4 node set of lender correspondences
Figure DEST_PATH_IMAGE009
It should be noted that in S4, the process of scoring the similarity of the abstracts includes the following steps:
s41: according to the corresponding RELATION SET relationship _ SET in S3, the summary combination of each node includes all the summaries recorded by the lender in the node;
s42: the summary processing process includes defining the length of the summary with the shortest character length in the summary combination as L, intercepting all the summaries in the summary combination from left to right to obtain L characters, substituting the character lengths of all the processed summaries into a formula after the summary processing to calculate to obtain processed scores, and executing step S43;
s43: the similarity score of the abstract combination is obtained by adding the score after the abstract processing and the score without the abstract processing.
It should be noted that in S43, the similarity SCORE of the summary combination is abstrct _ SCORE, the similarity scoring formula of the processed summary is TRIM _ abstrct _ SCORE, and the similarity scoring formula without summary processing is ORIGINAL _ abstrct _ SCORE
ABSTRACT_SCORE = TRIM_ABSTRACT_SCORE + ORIGINAL_ABSTRACT_SCORE
TRIM_ABSTRACT_SCORE = 1-0.5×ABSTRACT_COUNT+0.45×DEDUP_ABSTRACT_COUNT
ORIGINAL_ABSTRACT_SCORE = 1-0.5×ABSTRACT_COUNT+0.15×DEDUP_ABSTRACT_COUNT
In the formula, DEDUP _ ABSTRACT _ COUNT is the number of the same ABSTRACTs after the abstraction is removed in the abstraction combination, and ABSTRACT _ COUNT is the number of the ABSTRACTs without duplication removal in the abstraction combination.
It should be noted that, in this embodiment, for example, (1) the calculation of TRIM _ abstrct _ SCORE
RELATION_NODE5The method comprises 5 ABSTRACTs, ABSTRACT _ COUNT = 5, wherein the ABSTRACT with the shortest ABSTRACT character length is 'XXX department plum XX service charge', and has 12 characters in total, after being intercepted, the ABSTRACT is 5 same 'XXX department plum XX service charge', and after being deduplicated, DEDUP _ ABSTRACT _ COUNT = 1.
TRIM_ABSTRACT_SCORE = 1 - 0.5 × 5 + 0.45 × 1 = -1.05。
It is worth mentioning that (2) the ORIGINAL _ ABSTRACT _ SCORE is calculated
RELATION_NODE5There are 5 digests, ABSTRACT _ COUNT = 5, and the same "XXX department plum XX reports service charge (running water 20190001)", "XXX department plum XX reports service charge", and the rest "XXX department plum XX reports service charge (running water 20190001)", "XXX department plum XX reports service charge withholds tax" 3 digests, so DEDUP depup _ ABSTRACT _ COUNT = 3.
TRIM_ABSTRACT_SCORE = 1 - 0.5 × 5 + 0.15 × 3 = -1.05。
(3) Calculating ABSTRACT _ SCORE
ABSTRACT_SCORE = -1.05 - 1.05 = -2.1
It should be noted that, referring to table 5, table 5 shows the results after scoring the similarity of the abstracts:
table 5 summary similarity scored results
Figure DEST_PATH_IMAGE011
It should be noted that in S4, the process of similarity scoring for the project information includes the following steps,
s44, according to the corresponding RELATION SET RELATION _ SET in S3, the item information combination of each node comprises all the item information recorded by the lender in the node;
s45: the project information processing process includes defining the length of the project information with the shortest character length in the project information combination as L, intercepting L characters from left to right of all abstracts in the project information combination to obtain all processed character lengths of the project information as L, substituting the L characters into a formula after the project information processing to calculate to obtain a processed score, and executing step S46;
s46: the similarity score of the item information combination is obtained by adding both the post-item information processing score and the non-item information processing score.
It should be noted that in step S46, the similarity SCORE of the item information combination is represented by PROJ _ SCORE, the SCORE formula of the processed item information is represented by TRIM _ PROJ _ SCORE, and the similarity SCORE formula of the non-processed item information is represented by origin _ PROJ _ SCORE,
PROJ_SCORE = TRIM_PROJ_SCORE + ORIGINAL_PROJ_SCORE
TRIM_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.45 × DEDUP_PROJ_COUNT
ORIGINAL_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.15 × DEDUP_PROJ_COUNT
in the formula, DEDUP _ PROJ _ COUNT is the quantity of item information after the same item information in the item information combination is removed, and PROJ _ COUNT is the quantity of item information without duplication in the item information combination;
with relative _ NODE in Table 65The method for scoring similarity of project information is explained as an example.
It is worth mentioning that (1) the TRIM _ PROJ _ SCORE is calculated
RELATION_NODE5There are 5 items of information, PROJ _ COUNT =4, the item information character lengths are all 3, the same "PROJ 05" is culled, and there are remaining 3 items of information, PROJ01 "," PROJ05 ", and" PROJ08 ", DEDUP _ PROJ _ COUNT =3 after deduplication.
TRIM_PROJ_SCORE = 1 - 0.5 × 4 + 0.45 × 3 = 0.35
(2) Calculating ORIGINAL _ PROJ _ SCORE
RELATION_NODE5There are 5 items of information, PROJ _ COUNT =4, so DEDUP _ PROJ _ COUNT =3 after deduplication.
ORIGINAL_PROJ_SCORE = 1 - 0.5 × 4 + 0.15 × 3 = -0.55
(3) Calculating PROJ _ SCORE
PROJ_SCORE = 0.35 - 0.55 = -0.20
Please refer to table 6, wherein table 6 shows the result of item information similarity score:
TABLE 6 results after item information similarity scoring
Figure 257487DEST_PATH_IMAGE013
It is worth noting that TOTAL _ SCORE = ABSTRACT _ SCORE + prog _ SCORE × 1.3
TOTAL_SCORE = -2.1 + （-0.20）× 1.3 = -2.3
Referring to table 7, table 7 is the total similarity score results:
table 7 Total similarity score results
Figure 659649DEST_PATH_IMAGE015
It is to be noted that relative _ SET = { relative _ NODEk:(DEBIT_ORD_SETn，CREDIT_ORD_SETm，AMOUNTk，ABSTRACT_SETk，ABSTRACT_SCOREk，PROJ_SETk，PROJ_SCOREk，TOTAL_SCOREk)}
Wherein k is added 1 in sequence starting from 1, the maximum value is equal to the sum of the products of the original NODE number of the SET DEBIT _ NODE _ SET with equal amount of DEBIT entry data combination and the original NODE number of the combined CREDIT _ NODE _ SET with CREDIT entry data combination, RELATION _ SET is expressed as an updated NODE SET, and the updated NODE SET comprises the updated NODE RELATION _ NODEkDEBIT score record combination DEBIT _ ORD _ SETnCREDIT entry combination CREDIT _ ORD _ SETmSum of money after combination AMOUNTk、Abstract combination ABSTRACT _ SETk、Abstract similarity SCORE ABSTRACT _ SCOREk、Item information combination PROJ _ SETk、Project information similarity SCORE PROJ _ SCOREkAnd TOTAL SCORE TOTAL _ SCORE; m ranges from 1 to i; n ranges from 1 to j, provided thatj =3, n may be only 1, only 2, only 3, or 1, 2, or 3, and the AMOUNT of money is the AMOUNT of money of both lenders, i.e., AMOUNT = DEBIT _ AMOUNT = CREDIT _ AMOUNT.
It should be noted that in S6, after the updated nodes corresponding to the total similarity score are sorted, the process of marking the same economic service is as follows
S61: taking out the NODE relative _ NODE with the highest total similarity score in the correspondence SET relative _ SET, and storing the NODE relative _ NODE in the RESULT SET RESULT _ SET, please refer to table 8, where table 8 is data of RESULT _ SET:
TABLE 8 RESULT _ SET data
Figure DEST_PATH_IMAGE017
S62: deleting the NODE containing the entry number in the relative _ NODE from the relative _ SET1The entry numbers included in the list are 1 and 2, and the nodes with entry numbers including 1 and 2 are removed from the original SET, please refer to table 9, where table 9 is related _ SET after one round of removal:
TABLE 9 RELATION _ SET after one round of culling
Figure DEST_PATH_IMAGE019
S63: repeating S61 and S62 until the corresponding RELATION SET RELATION _ SET is empty, obtaining a NODE SET RESULT _ SET, wherein the debit entry data combination and the credit entry data combination in each NODE belong to the same economic service, and taking the RELATION _ NODE with the highest total similarity score from the RELATION _ SET4Put into RESULT _ SET, please refer to Table 10, wherein Table 10 is the data of RESULT _ SET,
TABLE 10 RESULT _ SET data
Figure DEST_PATH_IMAGE021
RELATION_NODE4Middle ladleEntry numbers 3 and (4, 5), and the nodes with entry numbers 3, 4, 5 are removed from the original SET, and after the previous step is completed, relative _ SET is empty, and RESULT _ SET is the final RESULT, please refer to table 11, where table 11 is the data of the last borrower:
TABLE 11 data of last RESULT _ SET
Figure DEST_PATH_IMAGE023
The voucher in this example is illustrated to contain two economic services, item 1 being a debit with entry number 1 and a credit with entry number 2, item 2 being a debit with entry number 3 and a credit with entry number 4, 5.
It should be noted that, in the S6, when two lenders of the same economic service are matched, multiple marking manners may be used for displaying, and the format of the marking may also be retained or substituted for the original voucher to facilitate retrieval and use.
In summary, the implementation principle of the embodiment is as follows: the method model is used for one part of the analysis and monitoring of the financial system, the original document of the certificate sheet recorded in the financial account-reporting system is directly called, the original document of the certificate sheet comprises a plurality of certificate sheets, the model integrates data on the single certificate sheet respectively, and concretely, the certificate sheet comprises debit amount and debit abstract, credit amount and credit abstract, each amount comprises corresponding use description, namely abstract, each abstract and amount are together classified into a entry number, each entry number in the model occupies one line, the debit entry number and the credit entry number are arranged from top to bottom, the entry numbers are 0, 1, 2, 3 and 4 … … from top to bottom, after the entry numbers of the debit and credit parties are combined respectively, the debit and credit parties with the same amount are connected, and then the abstract and item information of the debit and credit parties are similarly graded, the lender with the highest similarity score is the same economic service, at the moment, the lender of the same economic service is screened out without manual judgment and is automatically completed, and the marked data is used for subsequent calling and taking of the system.

Claims (8)

1. The system for matching the lending parties of the same economic service in the voucher comprises a processing terminal and a display unit, wherein the processing terminal acquires voucher data through a financial storage platform, and is characterized in that the processing terminal also comprises an importing unit, a processing unit, a communication unit and a storage unit,
starting the import unit, wherein the import unit acquires voucher data in the financial storage platform through a communication unit, a processing model is prestored in the processing unit, the voucher data is sent to the processing model as input, and the output of the processing model is marked voucher data;
the processing model comprises a preprocessing module, a matching module, a scoring module and a screening module, wherein the preprocessing module decomposes voucher data into a single borrower node and a single lender node, and each borrower node and each lender node respectively comprise abstract bytes and project bytes;
the matching module matches the amounts of the plurality of lender nodes in the preprocessing module with the amounts of the plurality of borrower nodes, and combines the nodes of the lenders with the same amount;
the scoring module scores similarity of the summary bytes and the project bytes in the combination, wherein the process of scoring similarity of the summary comprises the following steps:
s41: the abstract combination of each node comprises the abstract of the lender entry corresponding to the node;
s42: the summary processing process includes defining the length of the summary with the shortest character length in the summary combination as L, intercepting all the summaries in the summary combination from left to right to obtain L characters, substituting the character lengths of all the processed summaries into a formula after the summary processing to calculate to obtain processed scores, and executing step S43;
s43: the similarity score of the abstract combination is obtained by adding the score after the abstract processing and the score without the abstract processing;
the process of similarity scoring for project information includes the following steps,
s44, the project information combination of each node comprises the project information of the lender entry corresponding to the node;
s45: the project information processing process includes defining the length of the project information with the shortest character length in the project information combination as L, intercepting L characters from left to right of all abstracts in the project information combination to obtain all processed character lengths of the project information as L, substituting the L characters into a formula after the project information processing to calculate to obtain a processed score, and executing step S46;
s46: the similarity score of the project information combination is obtained by adding the score after the project processing and the score without the project information processing, and a total similarity scoring formula is calculated;
and the screening module screens out lenders belonging to the same economic service according to the similarity scoring result and sends the lenders to the storage unit for storage.
2. The method for matching the lender and the lender of the same economic service in the certificate list is characterized by comprising the following steps:
s1: acquiring a plurality of entries of an original voucher, wherein the sum of all debit entries in one voucher is equal to the sum of all credit entries in the voucher, and executing S2;
s2: constructing a set of debit entry data combinations and a set of credit entry data combinations on each original voucher, wherein each entry data combination comprises a single entry or a combination of multiple entries, and each entry only comprises one debit data item or credit data, and executing S3;
s3: establishing a corresponding relation between the debit data and the credit data based on the fact that the amount of the debit entry data combination is equal to the amount of the credit entry data combination, wherein each group of entry data combinations with the same amount of money is defined as a node, establishing a corresponding relation set, and executing S4;
s4: respectively carrying out similarity scoring on the abstracts and the item information of the nodes in the corresponding relation set to obtain score results after the abstracts are scored and score results after the item information is scored, wherein the process of carrying out similarity scoring on the abstracts comprises the following steps:
s41: according to the corresponding relation set in the S3, the abstract combination of each node comprises the abstract of the lender entry corresponding to the node;
s42: the summary processing process includes defining the length of the summary with the shortest character length in the summary combination as L, intercepting all the summaries in the summary combination from left to right to obtain L characters, substituting the character lengths of all the processed summaries into a formula after the summary processing to calculate to obtain processed scores, and executing step S43;
s43: the similarity score of the abstract combination is obtained by adding the score after the abstract processing and the score without the abstract processing;
the process of similarity scoring for project information includes the following steps,
s44, according to the corresponding relation set in S3, the project information combination of each node comprises the project information of the lender entry corresponding to the node;
s45: the project information processing process includes defining the length of the project information with the shortest character length in the project information combination as L, intercepting L characters from left to right of all abstracts in the project information combination to obtain all processed character lengths of the project information as L, substituting the L characters into a formula after the project information processing to calculate to obtain a processed score, and executing step S46;
s46: the similarity score of the project information combination is obtained by adding the score after the project processing and the score without the project information processing, and S5 is executed according to the total similarity scoring formula;
s5: sorting the new nodes in the corresponding relation set by combining the total score results of the similarity scoring, and executing S6;
s6: and marking the debit data and the credit data of the same economic service, and ending.
3. The method of claim 2, wherein in step S1, a voucher includes a plurality of entries, and the entries include only one DEBIT data or CREDIT data, wherein the DEBIT data and the CREDIT data include a summary, item information, voucher number and entry number, the DEBIT data further includes a DEBIT amount, the CREDIT data further includes a CREDIT amount, and in step S2, the SET of DEBIT entry data combinations is DEBIT _ NODE _ SET, the SET of CREDIT entry data combinations is CRDIT _ NODE _ SET,
DEBIT_NODE_SET = { DEBIT_NODEj : (DEBIT_ORD_SETj，DEBIT_AMOUNTj) }
CREDIT_NODE_SET ={ CREDIT_NODEi : (CREDIT_ORD_SETi，CREDIT_AMOUNTi) }
wherein the borrow entry data SET DEBIT _ NODE is a NODE of the SET DEBIT _ NODE _ SET of the borrow entry data SET, the borrow entry data SET DEBIT _ NODE comprises a combination DEBIT _ ORD _ SET of the borrow entry numbers and a borrow AMOUNT DEBIT _ AMOUNT, and when N borrow entries exist, the maximum value of j is
Figure DEST_PATH_IMAGE001
The definition of C is the number of combinations, the calculation formula of the number of combinations is as follows,
Figure 261135DEST_PATH_IMAGE002
DEBIT _ AMOUNT is the sum of DEBIT AMOUNTs corresponding to DEBIT _ ORD _ SET; the CREDIT entry data SET CREDIT _ NODE is a NODE of the SET CREDIT _ NODE _ SET of CREDIT entry data SETs, the CREDIT entry data SET CREDIT _ NODE comprisingThe combination CRDIT _ ORD _ SET with CREDIT entry number and CREDIT AMOUNT CRDIT _ AMOUNT, when there are M CREDIT entries, the maximum value of i is
Figure DEST_PATH_IMAGE003
The CREDIT _ AMOUNT is the sum of CREDIT AMOUNTs corresponding to the CREDIT _ ORD _ SET.
4. The method of matching lenders of the same economic transaction in a voucher 3, wherein in step S3, the sum of money debt _ AMOUNT corresponding to the DEBIT entry data SET debt _ NODE in the SET of DEBIT entry data SETs debt _ NODE _ SET is linked with the original NODE having the same sum of money CREDIT _ AMOUNT corresponding to the CREDIT entry data SET CREDIT _ NODE in the SET of CREDIT entry data SETs CREDIT _ NODE _ SET, and the corresponding relation SET is obtained.
5. The method of matching lenders of the same economic transaction in a voucher 4 wherein the similarity SCORE of the summary combination is abstrct _ SCORE, the similarity SCORE formula of the processed summary is TRIM _ abstrct _ SCORE, and the similarity SCORE formula without the summary processing is ORIGINAL _ abstrct _ SCORE in S43
ABSTRACT_SCORE = TRIM_ABSTRACT_SCORE + ORIGINAL_ABSTRACT_SCORE
TRIM_ABSTRACT_SCORE = 1 - 0.5 × ABSTRACT_COUNT + 0.45 ×DEDUP_ABSTRACT_COUNT
ORIGINAL_ABSTRACT_SCORE = 1 - 0.5 × ABSTRACT_COUNT + 0.15 × DEDUP_ABSTRACT_COUNT
In the formula, the summary _ abstrct _ COUNT in the processed summary similarity scoring formula TRIM _ abstrct _ SCORE is the number of the same ABSTRACTs after all the ABSTRACTs are cut from left to right and the same ABSTRACTs are removed, the summary _ abstrct _ COUNT in the similarity scoring formula origin _ abstrct _ SCORE without the summary processing is the number of the same ABSTRACTs after the abstraction is removed in the ABSTRACT combination, and the abstrct _ COUNT is the number of the unreleased ABSTRACTs in the ABSTRACT combination.
6. The method for matching lenders of the same economic service in a voucher according to claim 5, wherein the similarity SCORE of the item information combination is PROJ _ SCORE, the SCORE formula of the processed item information is TRIM _ PROJ _ SCORE, the similarity SCORE formula without processing the item is ORIGINAL _ PROJ _ SCORE in step S46,
PROJ_SCORE = TRIM_PROJ_SCORE + ORIGINAL_PROJ_SCORE
TRIM_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.45 × DEDUP_PROJ_COUNT
ORIGINAL_PROJ_SCORE = 1 - 0.5 × PROJ_COUNT + 0.15 × DEDUP_PROJ_COUNT
TOTAL_SCORE = ABSTRACT_SCORE + PROJ_SCORE × 1.3
in the formula, the depth _ PROJ _ COUNT in the scoring formula TRIM _ PROJ _ SCORE of the processed item information is obtained by cutting all item information from left to right by L characters, and then removing the same quantity of item information, the depth _ PROJ _ COUNT in the similarity scoring formula origin _ PROJ _ SCORE without processing the item is obtained by removing the same quantity of item information in the combination, the PROJ _ COUNT is the quantity of unremoved item information in the item information combination, and the TOTAL similarity SCORE is TOTAL.
7. Method for matching lenders to the same economic transaction in a voucher according to any of claims 2 to 6, characterized in that relative _ SET = { relative _ NODE =k:(DEBIT_ORD_SETn，CREDIT_ORD_SETm，AMOUNTk，ABSTRACT_SETk，ABSTRACT_SCOREk，PROJ_SETk，PROJ_SCOREk，TOTAL_SCOREk)}
In the formula, k is added with 1 from 1 in sequence, the maximum value is equal to the sum of the products of the original NODE number of the SET DEBIT _ NODE _ SET of DEBIT entry data combinations with equal money and the original NODE number of the SET CREDIT _ NODE _ SET of CREDIT entry data combinations, RELATION _ SET is expressed as a corresponding RELATION SET, and the corresponding RELATION SET comprises an updated NODE RELATION _ NODEkDEBIT score record combination DEBIT _ ORD _ SETnCREDIT entry combination CREDIT _ ORD _ SETmSum of money AMOUNTkAbstract combination ABSTRACT _ SETkAbstract similarity SCORE ABSTRACT _ SCOREkPROJ _ SET for item information combinationkItem information similarity SCORE PROJ _ SCOREkAnd TOTAL SCORE TOTAL _ SCOREk。
8. The method for matching lenders of the same economic service in a voucher according to claim 7, wherein in S6, after the nodes in the corresponding relationship set are sorted according to the total similarity score, the process of marking the same economic service is as follows:
s61: taking out a NODE RELATION _ NODE with the highest total similarity score in a corresponding RELATION SET RELATION _ SET, and storing the NODE RELATION _ NODE in a RESULT SET RESULT _ SET;
s62: deleting the NODE containing the entry number in the relative _ NODE from the relative _ SET;
s63: and repeating the steps of S61 and S62 until the corresponding RELATION SET RELATION _ SET is empty, and obtaining a node SET RESULT _ SET in which the debit entry data combination and the credit entry data combination in each node belong to the same economic service.
CN202010764634.XA 2020-08-03 2020-08-03 System and method for matching lenders of same economic service in certificate sheet Active CN111738847B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010764634.XA CN111738847B (en) 2020-08-03 2020-08-03 System and method for matching lenders of same economic service in certificate sheet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010764634.XA CN111738847B (en) 2020-08-03 2020-08-03 System and method for matching lenders of same economic service in certificate sheet

Publications (2)

Publication Number Publication Date
CN111738847A CN111738847A (en) 2020-10-02
CN111738847B true CN111738847B (en) 2020-11-20

Family

ID=72656894

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010764634.XA Active CN111738847B (en) 2020-08-03 2020-08-03 System and method for matching lenders of same economic service in certificate sheet

Country Status (1)

Country Link
CN (1) CN111738847B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1188941A (en) * 1996-10-21 1998-07-29 三星电子株式会社 Accounting processor and method for automated management control system
US7640199B1 (en) * 2006-11-03 2009-12-29 Promontory Interfinancial Network, Llc Auditing and reconciling custodial accounts
JP2011065363A (en) * 2009-09-16 2011-03-31 Soumubu:Kk Automatic journalizing system
CN104715415A (en) * 2013-12-13 2015-06-17 徐国良 Loan Matching Platform System
CN107194723A (en) * 2017-05-17 2017-09-22 中国科学技术大学 The bi-directional matching of loaning bill project and lender recommend method in network petty load
CN110046980A (en) * 2019-04-24 2019-07-23 合肥智海科技服务有限公司 A kind of financial data generation system and method
CN110941652A (en) * 2019-12-05 2020-03-31 中投摩根信息技术（北京）有限责任公司 Analysis method of bank flow data
CN111461859A (en) * 2019-03-14 2020-07-28 配对宝有限公司 Loan pairing system and method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5338954B1 (en) * 2012-07-13 2013-11-13 日本電気株式会社 Deposit / withdrawal log analysis device, deposit / withdrawal log analysis method, and deposit / withdrawal log analysis program
CN111383086A (en) * 2018-12-29 2020-07-07 华润置地控股有限公司 Contract payment financial certificate management method and system thereof
CN110458675B (en) * 2019-07-24 2022-12-23 北京一诺前景财税科技有限公司 Bill voucher generating method based on big data
CN110796531A (en) * 2019-10-29 2020-02-14 浪潮云信息技术有限公司 Web-based accounting voucher generation method and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1188941A (en) * 1996-10-21 1998-07-29 三星电子株式会社 Accounting processor and method for automated management control system
US7640199B1 (en) * 2006-11-03 2009-12-29 Promontory Interfinancial Network, Llc Auditing and reconciling custodial accounts
JP2011065363A (en) * 2009-09-16 2011-03-31 Soumubu:Kk Automatic journalizing system
CN104715415A (en) * 2013-12-13 2015-06-17 徐国良 Loan Matching Platform System
CN107194723A (en) * 2017-05-17 2017-09-22 中国科学技术大学 The bi-directional matching of loaning bill project and lender recommend method in network petty load
CN111461859A (en) * 2019-03-14 2020-07-28 配对宝有限公司 Loan pairing system and method
CN110046980A (en) * 2019-04-24 2019-07-23 合肥智海科技服务有限公司 A kind of financial data generation system and method
CN110941652A (en) * 2019-12-05 2020-03-31 中投摩根信息技术（北京）有限责任公司 Analysis method of bank flow data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
如何正确选择会计分录中的借贷方;王卓然;《中国国际财经(中英文)》;20180308(第05期);51 *

Also Published As

Publication number Publication date
CN111738847A (en) 2020-10-02

Similar Documents

Publication Publication Date Title
US7937303B2 (en) Grants management system
US8306986B2 (en) Method, system, and computer program product for linking customer information
US20040064404A1 (en) Computer-based method for automatic remote coding of debtor credit databases with bankruptcy filing information
JP2008515094A (en) Systems, software, and methods for searching a database in a forensic accounting environment
CN109670945B (en) Comprehensive risk early warning decision platform based on big data
CN110851667A (en) Integrated analysis method and tool for multi-source large data
CN114510735B (en) Role management-based intelligent shared financial management method and platform
CN107908733A (en) A kind of querying method of global trade data, apparatus and system
JP2018116566A (en) Accounting processing system, accounting processing method and accounting processing program
US8485435B2 (en) System and method of financial instrument processing with duplicate item detection
CN111738847B (en) System and method for matching lenders of same economic service in certificate sheet
CN108734021B (en) Financial loan big data risk assessment method and system based on privacy-removing data
CN115858470B (en) Policy and regulation file matching method, system, server and storage medium
CN112214557A (en) Data matching classification method and device
CN110941652A (en) Analysis method of bank flow data
TW200411453A (en) Budget and financial analysis management system and method
CN110766091B (en) Method and system for identifying trepanning loan group partner
CN111402054A (en) Risk judgment method and system for equity financing platform
CN111091454A (en) Financial public opinion recommendation method based on knowledge graph
CN102024242A (en) Method and system for processing customer information in bank credit management
WO2022149222A1 (en) Journalization device, journalization method, journalization display method, and journalization display program
CN115456765A (en) Bank fund flow data processing method and system
CN117575384A (en) Enterprise data processing method, enterprise data processing device, computer equipment and storage medium
Stevanović Data science as decision making support for creating successful crowdfunding campaigns: Lessons learned from Kickstarter
CN104091285A (en) Method for automatically recognizing quoted prices of bonds

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