CN112991037A - Credit certificate 46 domain analysis method and device - Google Patents
Credit certificate 46 domain analysis method and device Download PDFInfo
- Publication number
- CN112991037A CN112991037A CN202110177529.0A CN202110177529A CN112991037A CN 112991037 A CN112991037 A CN 112991037A CN 202110177529 A CN202110177529 A CN 202110177529A CN 112991037 A CN112991037 A CN 112991037A
- Authority
- CN
- China
- Prior art keywords
- sentence
- bill
- document
- credit
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for analyzing a 46-domain letter of credit, wherein the method comprises the following steps: classifying each sentence contained in the credit card 46 field, and determining a bill type corresponding to each sentence; extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence; and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence. The method determines the bill type by classifying each sentence contained in the credit certificate 46 field, further extracts the bill element contained in each sentence and the corresponding bill element value, and finally establishes the corresponding relation among the bill type, the bill element and the bill element value, thereby improving the analysis efficiency of the credit certificate 46 field.
Description
Technical Field
The invention relates to the technical field of information extraction, in particular to a credit card 46 domain analysis method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The letter of credit is the settlement certificate which is applied by an importer to a financial institution and takes an exporter as a beneficiary, the exporter needs to deliver goods within the shipping date specified by the letter of credit, and documents which conform to the regulation of the letter of credit are submitted to a designated bank within the specified delivery period to obtain payment. A letter of credit often involves multiple participants, including applicants, beneficiaries, issuing lines, advising lines, etc., and is typically circulated between the participants in the form of a swift message. In order to electronically process the letter of credit, the content of the letter of credit needs to be analyzed and understood. The swift message of the letter of credit is semi-structured data, and takes the message MT700 for issuing the letter of credit as an example, which includes dozens of fields such as 27 fields (number of pages/total number of pages), 40 fields (letter of credit type), 20 fields (letter of credit number), 31C (date of issuing), 31D (expiration date/validity), 52A/D (issuing bank), 50 (applicant), 59 (beneficiary), 45 fields (description of goods), 46 fields (requirement of document), and the like. Where 46 fields are one of the core contents of a letter of credit that describes the document requirements of a letter of credit submission in a natural language, examples are as follows:
:46A:DOCUMENTS REQUIRED
+SIGNED COMMERCIAL INVOICE IN TRIPLICATE
+FULL SET OF CLEAN ON BOARD OCEAN BILLS OF LADING MADE OUT TO THE ORDER OF INDUSTRIAL BANK OF KOREA MARKED FREIGHT PREPAID AND NOTIFY APPLICANT
+FULL SET OF INSURANCE POLICIES OR CERTIFICATES,ENDORSED IN BLANK FOR 110PCT OF INVOICE VALUE,STIPULATING CLAIMS TO BE PAYABLE IN KOREA IN THE CURRENCY OF THE DRAFT COVERING INSTITUTE CARGO CLAUSES:ALL RISKS
+PACKING LIST IN TRIPLICATE
+CERTIFICATE OF ORIGIN IN DUPLICATE。
because the content of the credit card 46 is rich, the expression form is unstructured and has no fixed paradigm, in the prior art, when the credit card message is analyzed, the 46 domain is often stored as a whole, the specifically expressed content of the credit card message is not analyzed, and the credit card message is split and understood manually during subsequent processing, so that the workload and the complexity of subsequent manual understanding and processing of the 46 domain are increased, and the analysis efficiency of the credit card 46 domain is reduced.
Therefore, the prior art has the problem of low resolution efficiency of the letter of credit 46 domain.
Disclosure of Invention
The embodiment of the invention provides a method for analyzing a credit card 46 domain, which is used for improving the efficiency of analyzing the credit card 46 domain, and the method for analyzing the credit card 46 domain comprises the following steps:
classifying each sentence contained in the credit card 46 field, and determining a bill type corresponding to each sentence;
extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence;
and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence.
The embodiment of the present invention further provides a device for analyzing the domain of a credit card 46, which is used to improve the efficiency of analyzing the domain of the credit card 46, and the device for analyzing the domain of the credit card 46 includes:
the classification module is used for classifying each sentence contained in the credit card 46 field and determining the bill type corresponding to each sentence;
the extraction module is used for extracting the bill elements contained in each sentence and the corresponding bill element values thereof according to the bill type corresponding to each sentence 1301;
and the relation establishing module is used for establishing the corresponding relation among the bill type, the bill element and the bill element value of each sentence.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the credit card 46 domain analysis method.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for resolving the domain of the letter of credit 46 is stored in the computer-readable storage medium.
In the embodiment of the invention, each sentence contained in the credit card 46 field is classified, and the bill type corresponding to each sentence is determined; extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence; and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence. According to the embodiment of the invention, the receipt type is determined by classifying each sentence contained in the credit certificate 46 field, the receipt element contained in each sentence and the corresponding receipt element value are further extracted, and finally, the corresponding relation among the receipt type, the receipt element and the receipt element value is established, so that the analysis efficiency of the credit certificate 46 field is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart illustrating an implementation of a domain resolution method for a letter of credit 46 according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an implementation of step 101 in a domain resolution method for a letter of credit 46 according to an embodiment of the present invention;
fig. 3 is a flowchart of another implementation of step 101 in the domain resolution method for the letter of credit 46 according to the embodiment of the present invention;
fig. 4 is a flowchart of another implementation of step 101 in the domain resolution method for the letter of credit 46 according to the embodiment of the present invention;
FIG. 5 is a flowchart illustrating an implementation of step 102 in a domain resolution method for a letter of credit 46 according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating another implementation of step 102 in a domain resolution method for a letter of credit 46 according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating still another implementation of step 102 in a domain resolution method for letter of credit 46 according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating another implementation of step 102 in a domain resolution method for a letter of credit 46 according to an embodiment of the present invention;
FIG. 9 is a functional block diagram of a domain resolution apparatus for letter of credit 46 according to an embodiment of the present invention;
fig. 10 is a block diagram illustrating a structure of a classification module 901 in a domain resolution apparatus for a letter of credit 46 according to an embodiment of the present invention;
fig. 11 is another structural block diagram of a classification module 901 in the domain resolution apparatus for letter of credit 46 according to the embodiment of the present invention;
fig. 12 is a block diagram of another structure of a classification module 901 in the domain resolution apparatus for the letter of credit 46 according to the embodiment of the present invention;
fig. 13 is a block diagram illustrating an extracting module 902 of the domain parsing apparatus for the letter of credit 46 according to the embodiment of the present invention;
fig. 14 is another block diagram of the extracting module 902 in the domain parsing apparatus for letter of credit 46 according to the embodiment of the present invention;
fig. 15 is a block diagram illustrating another structure of an extracting module 902 in the domain parsing apparatus for letter of credit 46 according to the embodiment of the present invention;
fig. 16 is a block diagram of another structure of the extracting module 902 in the domain analyzing device for letter of credit 46 according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Fig. 1 shows an implementation flow of a domain resolution method for a letter of credit 46 provided by an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the following details are described below:
as shown in fig. 1, the domain resolution method for the letter of credit 46 includes:
102, extracting a receipt element contained in each sentence and a value of the corresponding receipt element according to the receipt type corresponding to each sentence;
and 103, establishing a corresponding relation among the bill type, the bill element and the value of the bill element of each sentence.
The essence of the domain content of the letter of credit 46 is a description of the document requirements submitted by the client under the letter of credit, and when the document is analyzed, the document should be analyzed by taking the document as a dimension in order to be closer to the business scene reality and the business instance. The letter of credit 46 field contains several sentences, each of which has and only describes one type of document requirement. The types OF documents described in the letter OF credit 46 field mainly include INVOICE (INVOICE), Draw (DRAFT), BILL OF LADING (BILL OF LADING), box BILL (PACKING LIST), INSURANCE POLICY (insurant POLICY), certificate OF origin (CERTIFICATE OF ORIGIN), AIR BILL OF LADING (AIR WAYBILL), rental BILL OF LADING (CHARTER BILL OF LADING), proof OF quality inspection (CERTIFICATE OF QUALITY), proof OF quantity (CERTIFICATE OF QUANTITY), proof OF analysis (CERTIFICATE OF ANALYSIS), and the like.
Thus, in parsing the LC 46 field, each sentence contained in the LC 46 field is first classified to determine the document type to which each sentence corresponds. After sentence classification is complete, the specific requirements for which document type each sentence in the LC 46 field is. In the previous example, the sentence starts with "+", which is:
:46A:DOCUMENTS REQUIRED
+ SIGNED command INVOICE IN TRIPLICATE-a request for an INVOICE (command INVOICE);
+ FULL SET OF CLEAN ON BOARD OCEAN BILLS OF LADING MADE OUT TO THE ORDER OF INDUSTRIAL BANK OF KOREA MARKED FREIGHT PREPAID AND NOTIFY APPLICATION- -a requirement for a bill OF LADING (BILLS OF LADING);
+ FULL OF INSURANCE POLICIES OR CERTIFICATES, ENDORSED IN BLANK FOR 110PCT OF INVOLICE VALUE, STIPULATING CLAIMS TO BE PAYABLE IN KOREA IN THE CURRENCE OF THE DRAFT COVERING INSULATITE CARGO CLAUSES-ALL RISKS-requirement FOR INSURANCE POLICIES (INSURANCE POLICIES OR CERTIFICATES);
+ PACKING LIST IN TRIPLICATE-the requirement for a box sheet (PACKING LIST);
+ CERTIFICATE OF ORIGIN IN DUPLICATE- -requirement for certification of origin (CERTIFICATE OF ORIGIN).
It can be seen that the documents corresponding to the sentences contained in the letter of credit 46 field mainly include invoice type, bill of lading type, insurance policy type, box policy type, origin type, and so on.
After the bill type corresponding to the sentence is determined, the content of the sentence is analyzed, and the bill requirement is actually the requirement on one or more bill elements on the bill. And then extracting the document elements contained in each sentence and the values of the document elements corresponding to the document elements according to the document type corresponding to each sentence.
As an example OF THE above requirement "FULL SET OF CLEAN ON BOARD OCEAN BILLS OF LADING MADE OUT TO THE ORDER OF INDUSTRIAL BANK OF KOREA MARKED FREIGHT PREPAID AND NOTIFY APPLICATION" for a bill OF LADING (BILLS OF LANDING), THE analysis shows that THE clause actually makes a requirement for THE following elements ON THE bill OF LADING:
a copy number requirement for bill of lading (FULL SET);
bill of lading CLEAN or not (clear ON BOARD);
bill OF lading consignee request (TO THE ORDER OF outstanding BANK OF KOREA);
bill of lading freight requirements (FREIGHT PREPAID);
bill of lading notifier (APPLICANT)
Similarly, other sentences in the example can be understood by splitting as such:
+ signal common logic input IN TRIPLICATE; [ invoice signature request (SIGNED), invoice copy request (IN TRIPLICATE) ]
+ FULL SET OF inertial measurements OR CERTIFICATES, ENDORSED IN BLANK FOR 110PCT OF INVOLICE VALUE, STIPULATING CLAIMS TO BE PAYABLE IN KOREA IN THE CURRENTY OF THE DRAFT COVERING INSTITUTE CARGO CLAUSES: ALL RISKS; [ FULL SET, insurance endorsement requirements (ENDORSED IN BLANK), insurance sum requirements (110PCT OF INVOIICE VALUE), insurance claim ground requirements (KOREA), insurance CURRENCY requirements (IN THE CURRENCE OF THE DRAFT), insurance policy risk class requirements (COVERING INSTITUTE CARGO CLAUSES: ALL RISKS) ]
+ PACKING LIST IN TRIPLICATE; [ case single copy requirements IN TRIPLICATE ]
+ CERTIFICATE OF ORIGIN IN DUPLICATE; [ requirement for number of parts of origin (IN DUCLICATE) ]
Thus, in terms of a request for a certain type of document in the letter of credit 46 field, the request for the document element can be extracted according to the expression pattern of the sentence. Taking the bill OF lading as an example, the bill OF lading includes elements such as LANGUAGE (LANGUAGE), bill Number (NO), ISSUE DATE (ISSUE DATE), ship-in DATE (ON bound DATE), ship-out DATE (SHIPMENT DATE), SHIPPER (ship), CONSIGNEE (CONSIGNEE), CARRIER (CARRIER), consignor (ISSUER), SIGNER (SIGNER), PORT OF shipment (PORT OF load), PORT OF DISCHARGE (PORT OF DISCHARGE), cargo (commodify), number OF bills (NUM), clear or not bill (CLEAN), Freight (FEE), notifier (NOTIFY PARTY), ENDORSEMENT (doenrsten), and SIGN or not bill.
By consolidating all terms of the existing letter of credit 46 domain relating to the bill of lading requirements, the following expression pattern is obtained, along with possible expressions for each element of the pattern in which the bill of lading elements relating to the requirements are a subset of the above listed face elements:
<NUM>OF<SIGN><CLAEN>BILL OF LADING MADE OUT<CONSIGNEE>MARKED<FEE>ENDORSED<ENDORSEMENT>AND NOTIFY<NOTIFYPARTY>MARKED SHIPPER<SHIPPER>MARKED<SHIPPED DATE>ISSUED BY<ISSUER>SIGNED BY<SIGNER>
possible expressions of document number NUM include: (IN)2ORIGINAL (S) (OF); (IN)3COPY (IES) Or (OF); (IN) ONE NON-NEGOTIABLE COPY (IES) (OF); (IN) applying (OF); (IN) TRIPLICATE(OF); (IN) FULL SET (OF); (IN) FULL SET OF THREE (OF); (IN) FULL SET 3/3 (OF); (IN) THE FOR; (IN)3/3ORIGINAL (OF); FULL SET OF ORIGINAL;
whether a possible representation of signature SIGN is required includes: SIGNED; MANUALLY SIGNED
Possible expressions of whether CLEAN clear is required include: CLEAN ON BOARD; CLEAN "ON BOARD"; CLEAN SHIPPED ON BOARD; CLEAN "SHIPPED ON BOARD"; CLEAN
Possible expressions for the CONSIGNEE CONSIGNEE include: TO (THE) ORDER (OF) APPLICANT/TO (THE) ORDER (OF) ISSUING BANK/TO (THE) ORDER (OF) OPENING BANK/TO (THE) ORDER (OF) SHIPPER/TO (THE) ORDER (OF) A specific BANK or company
Possible expressions for freight FEE include: FREIGHT PREPAID, respectively; FREIGHT TO COLLECT; f, FREIGHT: a COLLECT; FREIGHT COLLECT; FCL/FCL; fresh PAYABLE AT destruction;
possible expressions of endorsement ENDORSEMNT include: BLANK ENDORSED, DRAWN AND/N/OR ENDORSED TO THE ORDER OF A specific bank OR company, BLANK ENDORSED BY SHIPPER
Possible expression patterns of NOTIFYPARTY of the notified party: APPLICANT/PARTY AS L/C APPLICANT/ISSUING BANK/OPENING BANK/a specific BANK or company/APPLICANT WITH FULL ADDRESS AS INDICATED (IN THIS L/C)/THE APPLICANT' S FULL NAME AND ADDRESS/XXX (ADDRESS, SEE FILED 50)/APPLICANT WITH FULL ADDRESS/SAME AS CONSIGNEE
SHIPPER (ship) possible expression: SHIPPER XXXX;
possible expressions of shipping date (SHIPPED DATE): SHIPPED ON BOARD DATE;
presenting a possible expression mode of human ISSUER: ISSUED BY CARRIER/a specific company
Possible expression patterns of SIGNERs (SIGNER): signal BY THE CARRIER OR THEIR AGENT;
when a sentence related to the bill drawing requirement appears, the sentence is matched with the expression mode and the possible value of each element, so that the specific requirement of the sentence can be disassembled, namely, the corresponding relation among the bill type, the bill element and the bill element value of each sentence is finally established.
For example, "FULL SET OF CLEAN ON round tubes OF LADING MADE OUT TO THE ORDER OF THE summary OF summary BANK OF key MARKED FREIGHT PREPAID AND NOTIFY application" can be finally resolved as:
field, bill type, bill element and bill element value
46.BILL OF LADING REQUIRE.NUM＝FULL SET
46.BILL OF LADING REQUIRE.CLEAN＝CLEAN ON BOARD
46.BILL OF LADING REQUIRE.CONSIGNEE＝TO THE ORDER OF INDUSTRIAL BANK OF KOREA
46.BILL OF LADING REQUIRE.FEE＝FREIGHT PREPAID
46.BILL OF LADING REQUIRE.NOTIFY PARTY＝APPLICANT
By this, parsing of the relevant sentences of the bill of credit 46 field bill of lading in the example is completed. Other types of documents require sentences to be processed according to the same logic, and finally, the analysis and storage of all contents in the 46 fields in the letter of credit message are completed.
In the embodiment of the invention, each sentence contained in the credit card 46 field is classified, and the bill type corresponding to each sentence is determined; extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence; and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence. According to the embodiment of the invention, the receipt type is determined by classifying each sentence contained in the credit certificate 46 field, the receipt element contained in each sentence and the corresponding receipt element value are further extracted, and finally, the corresponding relation among the receipt type, the receipt element and the receipt element value is established, so that the analysis efficiency of the credit certificate 46 field is improved.
Fig. 2 shows an implementation flow of step 101 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve the accuracy of determining the document type, as shown in fig. 2, in step 101, classifying each sentence contained in the field of the letter of credit 46, and determining the document type corresponding to each sentence includes:
Although each sentence contained in the LC 46 field is a requirement for only one type of document, the sentences may refer to the names of other types of documents and thus cannot be classified with simple rules. In the embodiment of the invention, the TF-IDF weighting technology and a naive Bayes classification model are used for classifying the sentences. TF-IDF (Term Frequency-Inverse Document Frequency) is a weighting technique commonly used in information processing, which calculates the degree of importance of a word in the entire corpus based on the number of times the word appears in a sentence and the Frequency of documents appearing in the entire corpus. Naive bayes classification is a series of simple probabilistic classifiers based on the use of bayesian theorem under strong independence between assumed features. The TF-IDF weighting technology and the naive Bayes classification model are used for classifying the sentences, so that the bill type corresponding to each sentence contained in the credit card 46 field can be more accurately determined.
In the embodiment of the invention, each sentence contained in the credit card 46 field is classified by using the TF-IDF weighting model and the naive Bayes classification model, and the bill type corresponding to each sentence is determined, so that the accuracy of determining the bill type can be improved.
Fig. 3 illustrates another implementation flow of step 101 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve the accuracy of determining the document type, as shown in fig. 3, in step 101, classifying each sentence contained in the field of the letter of credit 46, and determining the document type corresponding to each sentence includes:
In addition, each sentence contained in the letter of credit 46 field can be classified through natural language processing technology to determine the bill type corresponding to each sentence contained in the letter of credit 46 field, so that the bill type corresponding to each sentence contained in the letter of credit 46 field can be more accurately determined.
In the embodiment of the invention, each sentence contained in the credit card 46 field is classified by utilizing natural language processing, and the bill type corresponding to each sentence is determined, so that the accuracy of determining the bill type can be improved.
Fig. 4 shows a further implementation flow of step 101 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve the accuracy of determining the document type, as shown in fig. 4, classifying each sentence contained in the letter of credit 46 field, and determining the document type corresponding to each sentence includes:
In addition, each sentence contained in the letter of credit 46 field can be classified through the trained neural network model so as to determine the bill type corresponding to each sentence contained in the letter of credit 46 field, and the bill type corresponding to each sentence contained in the letter of credit 46 field can be more accurately determined.
The process of training the neural network model comprises the following steps: dividing sentences contained in the field of the historical letter of credit 46 into a training set and a test set; training the neural network model by using a training set, and verifying the accuracy of the trained neural network model by using a testing set; and terminating the training when the iteration termination condition is met, and obtaining the trained neural network model. The iteration termination condition is met, including that the iteration number reaches the preset iteration number or the accuracy of the neural network model is not less than the preset accuracy.
The preset iteration number is a preset iteration number, and a person skilled in the art may preset the preset iteration number according to an actual situation and a specific requirement, for example, the preset iteration number may be preset to 10 ten thousand, and it is understood that a person skilled in the art may also preset other values than the preset iteration number to 10 ten thousand, for example, 8 ten thousand or 11 ten thousand, which is not limited in particular by the embodiment of the present invention.
The preset accuracy is a preset accuracy, and a person skilled in the art may preset the preset accuracy according to an actual situation and a specific requirement, for example, the preset accuracy may be preset to 96%, and it is understood that a person skilled in the art may also preset other values than the preset accuracy to 96%, for example, 94% or 98%, which is not limited in particular by the embodiment of the present invention.
In the embodiment of the invention, each sentence contained in the letter of credit 46 field is classified by using the trained neural network model, the bill type corresponding to each sentence is determined, and the accuracy of determining the bill type can be improved.
Fig. 5 illustrates an implementation flow of step 102 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the following details are described below:
in an embodiment of the present invention, in order to further improve the domain parsing efficiency of the letter of credit 46, as shown in fig. 5, step 102, according to the document type corresponding to each sentence, extracting document elements and corresponding document element values contained in each sentence, includes:
and 504, acquiring a bill element value corresponding to the bill element contained in each sentence according to the bill element contained in each sentence and the element value data table.
When extracting the document elements and the corresponding document element values contained in each sentence, the type element data table and the element value data table can be configured in the database in advance. The type element data table comprises a document type and a document element and also comprises a corresponding relation between the document type and the document element. One document type may correspond to a plurality of document elements. The element value data table comprises document elements and document element values and also comprises corresponding relations between the document elements and the document element values.
Specifically, according to the bill type corresponding to each sentence, a preset type element data table is directly obtained from a database, each sentence is compared with the type element data table, the bill elements contained in each sentence are extracted, then according to the bill elements contained in each sentence, a preset element value data table is directly obtained from the database, and through the element value data table, the individual element value contained in each sentence is compared with the element value data table, so that the bill element value corresponding to each bill element contained in each sentence is obtained.
In the embodiment of the invention, a pre-configured type element data table is directly obtained from a database, and then document elements contained in each sentence are extracted; and then, a pre-configured element value data table is directly obtained from the database so as to obtain the document element value corresponding to the document element contained in each sentence, and the analysis efficiency of the credit card 46 domain can be further improved.
Fig. 6 shows another implementation flow of step 102 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve flexibility of configuration of the type element data table and/or the element value data table, as shown in fig. 6, on the basis of the method steps shown in fig. 5, step 102 is to extract a document element and a document element value corresponding to the document element included in each sentence according to a document type corresponding to each sentence, and further includes:
When the type element data table and/or the element value data table are configured, the type element data table and/or the element value data table may be configured based on a received configuration instruction, for example, a click operation or a drag operation, or a configuration modification instruction may modify contents in the configured type element data table and/or the element value data table, for example, add an item, delete an item, or modify contents of an item, so as to improve flexibility of configuration of the type element data table and/or the element value data table.
In the embodiment of the invention, the type element data table and/or the element value data table are configured according to the received configuration instruction, so that the flexibility of configuration of the type element data table and/or the element value data table can be improved.
Fig. 7 illustrates a further implementation flow of step 102 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to further improve the domain parsing efficiency of the letter of credit 46, as shown in fig. 7, in step 102, extracting, according to the document type corresponding to each sentence, document elements and corresponding document element values included in each sentence, includes:
701, acquiring a preset corresponding relation data table from a database according to the bill type corresponding to each sentence; the corresponding relation data table comprises corresponding relations among the bill types, the bill elements, the bill element values and the bill types, and the bill elements and the bill element values;
and step 702, obtaining the document elements contained in each sentence and the corresponding document element values thereof according to the document type corresponding to each sentence and the corresponding relation data table.
The type element data table and the element value data table can be combined to form a corresponding relation data table, the corresponding relation data table comprises a document type, a document element value, a corresponding relation between the document type and the document element, and a corresponding relation between the document element and the document element value.
Specifically, after extracting the document elements and the corresponding document element values contained in each sentence, a preset corresponding relation data table is directly obtained from the database, and the document elements and the corresponding document element values contained in each sentence are directly extracted through the corresponding relation data table, so that the analysis efficiency of the credit certificate 46 domain can be further improved.
In the embodiment of the invention, the preset corresponding relation data table is directly obtained from the database according to the bill type corresponding to each sentence, and the bill element contained in each sentence and the value of the corresponding bill element are obtained according to the bill type corresponding to each sentence and the corresponding relation data table, so that the analysis efficiency of the credit certificate 46 field can be further improved.
Fig. 8 shows a further implementation flow of step 102 in the domain resolution method for the letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve flexibility of configuration of the correspondence data table, as shown in fig. 8, on the basis of the method steps shown in fig. 7, step 102 is to extract a document element included in each sentence and a value of the document element corresponding to the document element according to a document type corresponding to each sentence, and further includes:
When configuring the corresponding relationship data table, the corresponding relationship data table may be configured based on a received configuration instruction, for example, a configuration instruction such as a click operation or a drag operation, or a content in the configured corresponding relationship data table may be modified based on a configuration modification instruction, for example, an item is added, an item is deleted, or a content of a certain item is modified, so as to improve flexibility of configuration of the corresponding relationship data table.
In the embodiment of the invention, the corresponding relation data table is configured according to the received configuration instruction, so that the flexibility of the configuration of the corresponding relation data table can be improved.
The embodiment of the present invention further provides a device for analyzing the domain of the letter of credit 46, as described in the following embodiments. Since the principle of solving the problem of these apparatuses is similar to the domain resolution method of the letter of credit 46, the implementation of these apparatuses can be referred to the implementation of the method, and the repeated descriptions are omitted.
Fig. 9 shows functional modules of a domain resolution apparatus for a letter of credit 46 provided in an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
referring to fig. 9, each module included in the domain resolution apparatus for the letter of credit 46 is used to execute each step in the embodiment corresponding to fig. 1, and specific reference is made to fig. 1 and the related description in the embodiment corresponding to fig. 1, which are not repeated herein. In the embodiment of the present invention, the domain analysis device for the letter of credit 46 includes a classification module 901, an extraction module 902, and a relationship establishing module 903.
The classification module 901 is configured to classify each sentence included in the letter of credit 46 field, and determine a document type corresponding to each sentence.
The extracting module 902 is configured to extract, according to the document type corresponding to each sentence 1301, document elements included in each sentence and corresponding document element values thereof.
And the relation establishing module 903 is used for establishing the corresponding relation among the bill type, the bill element and the bill element value of each sentence.
In the embodiment of the present invention, the classification module 901 classifies each sentence contained in the domain of the letter of credit 46, and determines the document type corresponding to each sentence; the extracting module 902 extracts the document elements contained in each sentence and the corresponding document element values thereof according to the document type corresponding to each sentence; the relationship establishing module 903 establishes a corresponding relationship among the document type, the document elements and the values of the document elements of each sentence. According to the embodiment of the invention, the receipt type is determined by classifying each sentence contained in the credit certificate 46 field, the receipt element contained in each sentence and the corresponding receipt element value are further extracted, and finally, the corresponding relation among the receipt type, the receipt element and the receipt element value is established, so that the analysis efficiency of the credit certificate 46 field is improved.
Fig. 10 shows a structural schematic diagram of a classification module 901 in a domain resolution device for letters of credit 46 provided by an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve accuracy of determining a type of a document, referring to fig. 10, each unit included in the classification module 901 is configured to execute each step in the embodiment corresponding to fig. 2, specifically please refer to fig. 2 and related descriptions in the embodiment corresponding to fig. 2, which are not described herein again. In this embodiment of the present invention, the classifying module 901 includes a first classifying unit 1001.
The first classification unit 1001 is configured to classify each sentence included in the letter of credit 46 domain by using a TF-IDF weighting model and a naive bayesian classification model, and determine a receipt type corresponding to each sentence.
In the embodiment of the present invention, the first classification unit 1001 classifies each sentence included in the credit card 46 domain by using the TF-IDF weighting model and the naive bayes classification model, and determines the receipt type corresponding to each sentence, thereby improving the accuracy of determining the receipt type.
Fig. 11 shows another structural schematic diagram of a classification module 901 in a domain resolution apparatus for letters of credit 46 provided by an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve accuracy of determining a document type, referring to fig. 11, each unit included in the classification module 901 is configured to execute each step in the embodiment corresponding to fig. 3, specifically please refer to fig. 3 and related descriptions in the embodiment corresponding to fig. 3, which are not described herein again. In this embodiment of the present invention, the classifying module 901 includes a second classifying unit 1101.
The second classification unit 1101 is configured to classify each sentence included in the letter of credit 46 field by using natural language processing, and determine a receipt type corresponding to each sentence.
In the embodiment of the present invention, the second classification unit 1101 classifies each sentence included in the letter of credit 46 field by using natural language processing, and determines the bill type corresponding to each sentence, so that the accuracy of determining the bill type can be improved.
Fig. 12 shows a schematic structural diagram of a classification module 901 in a domain resolution apparatus for letters of credit 46 according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which is detailed as follows:
referring to fig. 12, each module included in the classification module 901 is used to execute each step in the embodiment corresponding to fig. 4, specifically please refer to fig. 4 and the related description in the embodiment corresponding to fig. 4, which is not repeated herein. In this embodiment of the present invention, the classifying module 901 includes a third classifying unit 1201.
A third classification unit 1201, configured to classify each sentence included in the letter of credit 46 domain by using the trained neural network model, and determine a document type corresponding to each sentence.
Wherein, the process of training the neural network model comprises the following steps:
dividing sentences contained in the field of the historical letter of credit 46 into a training set and a test set;
training the neural network model by using a training set, and verifying the accuracy of the trained neural network model by using a testing set;
and terminating the training when the iteration termination condition is met, and obtaining the trained neural network model.
In the embodiment of the present invention, the third classification unit 1201 classifies each sentence included in the letter of credit 46 domain by using the trained neural network model, and determines the bill type corresponding to each sentence, so that the accuracy of determining the bill type can be improved.
Fig. 13 shows a schematic structure of the extracting module 902 in the domain parsing apparatus for letter of credit 46 according to the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which are detailed as follows:
in an embodiment of the present invention, in order to further improve the domain resolution efficiency of the credit card 46, referring to fig. 13, each unit included in the extracting module 902 is configured to execute each step in the embodiment corresponding to fig. 5, specifically please refer to fig. 5 and the related description in the embodiment corresponding to fig. 5, which is not described herein again. In this embodiment of the present invention, the extracting module 902 includes a first data table obtaining unit 1301, a document element extracting unit 1302, a second data table obtaining unit 1303, and a document element value obtaining unit 1304.
A first data table obtaining unit 1301, configured to obtain a pre-configured type element data table from a database according to a document type corresponding to each sentence; the type element database comprises the type of the document, the document elements and the corresponding relation between the type of the document and the document elements.
The document element extracting unit 1302 is configured to extract document elements included in each sentence according to the document type and the type element data table corresponding to each sentence.
A second data table obtaining unit 1303, configured to obtain a pre-configured element value data table from the database according to the document elements included in each sentence; the element value data table comprises document elements, document element values and corresponding relations between the document elements and the document element values.
And a document element value obtaining unit 1304, configured to obtain, according to the document elements and the element value data table included in each sentence, document element values corresponding to the document elements included in each sentence.
In the embodiment of the present invention, the first data table obtaining unit 1301 directly obtains a pre-configured type element data table from a database, and the document element extracting unit 1302 extracts document elements included in each sentence; then, the second data table obtaining unit 1303 directly obtains the preconfigured element value data table from the database, and the document element value obtaining unit 1304 obtains the document element value corresponding to the document element contained in each sentence, so that the resolution efficiency of the credit card 46 domain can be further improved.
Fig. 14 shows another structural schematic diagram of the extracting module 902 in the domain parsing apparatus for letter of credit 46 provided by the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to improve flexibility of configuration of the type element data table and/or the element value data table, referring to fig. 14, each unit included in the extracting module 902 is configured to execute each step in the embodiment corresponding to fig. 6, specifically refer to fig. 6 and related descriptions in the embodiment corresponding to fig. 6, and details are not repeated here. In the embodiment of the present invention, on the basis of the module structure shown in fig. 13, the extracting module 902 further includes a first configuration unit 1401.
A first configuration unit 1401, configured to configure the type element data table and/or the element value data table according to the received configuration instruction.
In this embodiment of the present invention, the first configuration unit 1401 configures the type element data table and/or the element value data table according to the received configuration instruction, and can improve the flexibility of the configuration of the type element data table and/or the element value data table.
Fig. 15 shows a schematic diagram of a further structure of the extracting module 902 in the domain parsing apparatus for letter of credit 46 according to the embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
in an embodiment of the present invention, in order to further improve the domain resolution efficiency of the letter of credit 46, referring to fig. 15, each module included in the extracting module 902 is configured to execute each step in the embodiment corresponding to fig. 7, and please refer to fig. 7 and the related description in the embodiment corresponding to fig. 7 specifically, which is not described herein again. In the embodiment of the present invention, the extracting module 902 includes a third data table obtaining unit 1501 and an extracting unit 1502.
A third data table obtaining unit 1501, configured to obtain a pre-configured correspondence data table from a database according to a document type corresponding to each sentence; the corresponding relation data table comprises corresponding relations among the bill types, the bill elements, the bill element values and the bill types, and the bill elements and the bill element values.
The extracting unit 1502 is configured to obtain document elements included in each sentence and corresponding document element values thereof according to the document type and the corresponding relationship data table corresponding to each sentence.
In this embodiment of the present invention, the third data table obtaining unit 1501 directly obtains a pre-configured correspondence data table from the database according to the document type corresponding to each sentence, and the extracting unit 1502 obtains the document elements included in each sentence and the corresponding document element values thereof according to the document type corresponding to each sentence and the correspondence data table, which can further improve the resolution efficiency of the credit card 46 domain.
Fig. 16 shows a schematic structural diagram of an extracting module 902 in a domain parsing apparatus for letter of credit 46 according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, which is detailed as follows:
in an embodiment of the present invention, in order to improve flexibility of configuration of the corresponding relationship data table, referring to fig. 16, each unit included in the extracting module 902 is configured to execute each step in the embodiment corresponding to fig. 8, specifically please refer to fig. 8 and the related description in the embodiment corresponding to fig. 8, which is not described herein again. In the embodiment of the present invention, on the basis of the above module structure shown in fig. 15, the extracting module 902 further includes a second configuration unit 1601.
The second configuring unit 1601 is configured to configure the corresponding relationship data table according to the received configuration instruction.
In the embodiment of the present invention, the second configuration unit 1601 configures the corresponding relationship data table according to the received configuration instruction, so that the flexibility of the configuration of the corresponding relationship data table can be improved.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the credit card 46 domain analysis method.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the method for resolving the domain of the letter of credit 46 is stored in the computer-readable storage medium.
In summary, in the embodiment of the present invention, each sentence included in the domain of the letter of credit 46 is classified, and the document type corresponding to each sentence is determined; extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence; and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence. According to the embodiment of the invention, the receipt type is determined by classifying each sentence contained in the credit certificate 46 field, the receipt element contained in each sentence and the corresponding receipt element value are further extracted, and finally, the corresponding relation among the receipt type, the receipt element and the receipt element value is established, so that the analysis efficiency of the credit certificate 46 field is improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (18)
1. A method for resolving a credit 46 field, comprising:
classifying each sentence contained in the credit card 46 field, and determining a bill type corresponding to each sentence;
extracting document elements contained in each sentence and corresponding document element values according to the document type corresponding to each sentence;
and establishing the corresponding relation among the bill type, the bill elements and the bill element values of each sentence.
2. The method for parsing the domain of letters of credit 46 of claim 1, wherein classifying each sentence contained in the domain of letters of credit 46 and determining the type of document corresponding to each sentence comprises:
and classifying each sentence contained in the credit card 46 domain by using a TF-IDF weighting model and a naive Bayes classification model, and determining a bill type corresponding to each sentence.
3. The method for parsing the domain of letters of credit 46 of claim 1, wherein classifying each sentence contained in the domain of letters of credit 46 and determining the type of document corresponding to each sentence comprises:
each sentence contained in the LC 46 field is classified using natural language processing to determine the document type corresponding to each sentence.
4. The method for parsing the domain of letters of credit 46 of claim 1, wherein classifying each sentence contained in the domain of letters of credit 46 and determining the type of document corresponding to each sentence comprises:
and classifying each sentence contained in the letter of credit 46 field by using the trained neural network model, and determining the bill type corresponding to each sentence.
5. The method for analyzing the domain of the letter of credit 46 of claim 1, wherein extracting the document elements contained in each sentence and the values of the document elements corresponding to the document elements according to the document type corresponding to each sentence comprises:
acquiring a pre-configured type element data table from a database according to the bill type corresponding to each sentence; the type element database comprises a document type, a document element and a corresponding relation between the document type and the document element;
extracting the document elements contained in each sentence according to the document type and the type element data table corresponding to each sentence;
acquiring a pre-configured element value data table from a database according to the document elements contained in each sentence; the element value data table comprises document elements, document element values and corresponding relations between the document elements and the document element values;
and acquiring the bill element value corresponding to the bill element contained in each sentence according to the bill element contained in each sentence and the element value data table.
6. The method for analyzing the domain of letters of credit 46 of claim 5, wherein extracting document elements contained in each sentence and corresponding document element values thereof according to the document type corresponding to each sentence, further comprises:
and configuring a type element data table and/or an element value data table according to the received configuration instruction.
7. The method for analyzing the domain of the letter of credit 46 of claim 1, wherein extracting the document elements contained in each sentence and the values of the document elements corresponding to the document elements according to the document type corresponding to each sentence comprises:
acquiring a preset corresponding relation data table from a database according to the bill type corresponding to each sentence; the corresponding relation data table comprises corresponding relations among the bill types, the bill elements, the bill element values and the bill types, and the bill elements and the bill element values;
and acquiring the document elements contained in each sentence and the corresponding document element values thereof according to the document type corresponding to each sentence and the corresponding relation data table.
8. The method for analyzing the domain of letters of credit 46 of claim 7, wherein extracting document elements contained in each sentence and corresponding document element values thereof according to the document type corresponding to each sentence, further comprises:
and configuring a corresponding relation data table according to the received configuration instruction.
9. A credit 46 field resolution device, comprising:
the classification module is used for classifying each sentence contained in the credit card 46 field and determining the bill type corresponding to each sentence;
the extraction module is used for extracting the bill elements contained in each sentence and the corresponding bill element values thereof according to the bill type corresponding to each sentence 1301;
and the relation establishing module is used for establishing the corresponding relation among the bill type, the bill element and the bill element value of each sentence.
10. The apparatus for parsing a letter of credit 46 of claim 9 wherein the classification module comprises:
and the first classification unit is used for classifying each sentence contained in the credit card 46 domain by utilizing the TF-IDF weighting model and the naive Bayesian classification model and determining the bill type corresponding to each sentence.
11. The apparatus for parsing a letter of credit 46 of claim 9 wherein the classification module comprises:
and the second classification unit is used for classifying each sentence contained in the credit card 46 field by using natural language processing and determining the bill type corresponding to each sentence.
12. The apparatus for parsing a letter of credit 46 of claim 9 wherein the classification module comprises:
and the third classification unit is used for classifying each sentence contained in the letter of credit 46 field by using the trained neural network model and determining the bill type corresponding to each sentence.
13. The apparatus for parsing a letter of credit 46 of claim 9, wherein the extracting module comprises:
the first data table acquisition unit is used for acquiring a pre-configured type element data table from a database according to the bill type corresponding to each sentence; the type element database comprises a document type, a document element and a corresponding relation between the document type and the document element;
the document element extraction unit is used for extracting document elements contained in each sentence according to the document type corresponding to each sentence and the type element data table;
the second data table acquisition unit is used for acquiring a pre-configured element value data table from the database according to the document elements contained in each sentence; the element value data table comprises document elements, document element values and corresponding relations between the document elements and the document element values;
and the bill element value obtaining unit is used for obtaining the bill element value corresponding to the bill element contained in each sentence according to the bill element contained in each sentence and the element value data table.
14. The apparatus for parsing a letter of credit 46 of claim 13, wherein the extracting module further comprises:
and the first configuration unit is used for configuring the type element data table and/or the element value data table according to the received configuration instruction.
15. The apparatus for parsing a letter of credit 46 of claim 9, wherein the extracting module comprises:
the third data table acquisition unit is used for acquiring a preset corresponding relation data table from the database according to the bill type corresponding to each sentence; the corresponding relation data table comprises corresponding relations among the bill types, the bill elements, the bill element values and the bill types, and the bill elements and the bill element values;
and the extraction unit is used for acquiring the document elements contained in each sentence and the corresponding document element values thereof according to the document type corresponding to each sentence and the corresponding relation data table.
16. The apparatus for parsing a letter of credit 46 of claim 15, wherein the extracting module further comprises:
and the second configuration unit is used for configuring the corresponding relation data table according to the received configuration instruction.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the LC 46 domain resolution method of any of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium storing a computer program for executing the domain resolution method for the letter of credit 46 according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110177529.0A CN112991037A (en) | 2021-02-07 | 2021-02-07 | Credit certificate 46 domain analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110177529.0A CN112991037A (en) | 2021-02-07 | 2021-02-07 | Credit certificate 46 domain analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112991037A true CN112991037A (en) | 2021-06-18 |
Family
ID=76392558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110177529.0A Pending CN112991037A (en) | 2021-02-07 | 2021-02-07 | Credit certificate 46 domain analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991037A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114219443A (en) * | 2021-12-16 | 2022-03-22 | 中国建设银行股份有限公司 | Document data processing method, device and equipment |
-
2021
- 2021-02-07 CN CN202110177529.0A patent/CN112991037A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114219443A (en) * | 2021-12-16 | 2022-03-22 | 中国建设银行股份有限公司 | Document data processing method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yoon | A study on the transformation of accounting based on new technologies: Evidence from Korea | |
| US11195008B2 (en) | Electronic document data extraction | |
| US20230004888A1 (en) | Ai-augmented auditing platform including techniques for applying a composable assurance integrity framework | |
| CN105243117B (en) | A kind of data processing system and method | |
| US11720615B2 (en) | Self-executing protocol generation from natural language text | |
| US20080201157A1 (en) | Methods, systems, and computer software utilizing xbrl to electronically link the accounting records of multi-period contracts and multi-period loans and grants for management | |
| CN114202755A (en) | Transaction background authenticity auditing method and system based on OCR (optical character recognition) and NLP (non-line segment) technologies | |
| CN112801777B (en) | Automatic processing method, system, electronic equipment and storage medium for bank letter | |
| US11915279B2 (en) | Automated invoice management system and platform | |
| CN110956166A (en) | Bill marking method and device | |
| Gullkvist | Towards paperless accounting and auditing | |
| CN112991037A (en) | Credit certificate 46 domain analysis method and device | |
| Malviya et al. | The changing face of accounting: Prospects and issues in the application of artificial intelligence | |
| US20210287301A1 (en) | Accelerated intelligent enterprise including timely vendor spend analytics | |
| CN114861622A (en) | Documentary credit generating method, documentary credit generating device, documentary credit generating equipment, storage medium and program product | |
| Faboyede et al. | The impact of extensible business reporting language education and adoption on stock exchange development: a focus on Nigeria | |
| US11055795B1 (en) | Methods, systems, and computer program products for linking data schemas to electronic tax return | |
| CN113537964A (en) | Application form processing method, device, storage medium and device | |
| Doultani et al. | Smart Underwriting-A Personalised Virtual Agent | |
| Rudžionis et al. | Identifying irregular financial operations using accountant comments and natural language processing techniques | |
| CN111144409A (en) | Order following, accepting and examining processing method and system | |
| CN112634048A (en) | Anti-money laundering model training method and device | |
| CN112766892A (en) | Method and device for combining fund ratio of RPA and AI and electronic equipment | |
| US8694433B1 (en) | Image cashletter processing with reject repair deferral | |
| Wattar | Analysis and Comparison of invoice data extraction methods |
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 |