A method and device for processing documentary letter of credit

Abstract

The present invention provides a method and device for processing a documentary credit. The method comprises: when receiving an audit request sent by a client and carrying an audit mark and a document to be audited, extracting elements to be audited from the document to be audited; merging the elements to be audited and preset audit rules to obtain merged data; generalizing the merged data using a preset knowledge graph to obtain structured data; and sending the structured data to an audit rule engine so that the audit rule engine audits the structured data to obtain an audit result of the document to be audited. The audit rule engine is used to audit documents and documents, documents and letters of credit, with simple operation and short processing time, thereby improving the processing efficiency of documentary credits.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for processing a documentary letter of credit. Background Art

[0002] Document review under a letter of credit refers to the service of collective document review provided by the bank to exporters under a letter of credit. When reviewing documents under a letter of credit, it is necessary to follow international practices and practical rules, and to review documents in accordance with the principles of "consistency between documents", "consistency between documents and certificates", and "consistency with rules".

[0003] Currently, the main method for reviewing letters of credit is offline review by business experts, who conduct the review and output the review results. This method is complicated and takes a long time to process, resulting in low efficiency in letter of credit review. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for processing a documentary letter of credit to solve the problem of low efficiency in letter of credit review.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A first aspect of an embodiment of the present invention discloses a method for processing a documentary letter of credit, the method comprising:

[0007] When receiving an audit request sent by a client and carrying an audit mark and a document to be audited, extracting the audit elements from the document to be audited, wherein the audit mark is used to indicate that the audit request is a single audit request or a document audit request, the single audit request is used to audit a document and a document, and the document audit request is used to audit a document and a letter of credit;

[0008] Merging the elements to be reviewed and the preset review rules to obtain combined data;

[0009] Generalizing the combined data using a preset knowledge graph to obtain structured data;

[0010] The structured data is sent to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited.

[0011] Preferably, the step of merging the elements to be audited and the preset audit rules to obtain the merged data includes:

[0012] When the audit identifier indicates that the audit request is a single audit request, obtaining a first audit rule corresponding to the single audit from preset audit rules;

[0013] Merging the to-be-audited element with the first audit rule to obtain first merged data;

[0014] When the audit identifier indicates that the audit request is a document audit request, obtaining a second audit rule corresponding to the document audit from preset audit rules;

[0015] The to-be-audited element is combined with the second audit rule to obtain second combined data.

[0016] Preferably, the step of generalizing the merged data using a preset knowledge graph to obtain structured data includes:

[0017] For each of the elements to be reviewed in the merged data, according to the representation rules corresponding to the elements to be reviewed in the preset knowledge graph, the elements to be reviewed are disambiguated to obtain structured data.

[0018] Preferably, the sending of the structured data to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the to-be-audited file includes:

[0019] When the audit identifier indicates that the audit request is a single audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the single audit rule to obtain a first audit result of the to-be-audited file;

[0020] When the audit identifier indicates that the audit request is a document audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the document to be audited.

[0021] Preferably, after sending the structured data to the audit rule engine so that the audit rule engine audits the structured data and obtains the audit result of the to-be-audited file, the method further includes:

[0022] The audit result of the file to be audited is sent to the client.

[0023] A second aspect of an embodiment of the present invention discloses a device for processing a documentary letter of credit, the device comprising:

[0024] an extracting unit, configured to extract the to-be-audited elements from the to-be-audited file upon receiving an audit request sent by a client and carrying an audit identifier and the to-be-audited file, wherein the audit identifier is used to indicate that the audit request is a single audit request or a document audit request, the single audit request is used to audit the document and the document, and the document audit request is used to audit the document and the letter of credit;

[0025] A merging unit, used to merge the elements to be reviewed and the preset review rules to obtain merged data;

[0026] A generalization unit, used to generalize the combined data using a preset knowledge graph to obtain structured data;

[0027] The audit unit is used to send the structured data to the audit rule engine, so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited.

[0028] Preferably, the merging unit comprises:

[0029] A first acquisition module, configured to acquire a first audit rule corresponding to the single audit from preset audit rules when the audit identifier indicates that the audit request is a single audit request;

[0030] A first merging module, used for merging the to-be-audited element with the first audit rule to obtain first merged data;

[0031] A second acquisition module, configured to acquire a second audit rule corresponding to the document audit from preset audit rules when the audit identifier indicates that the audit request is a document audit request;

[0032] The second merging module is used to merge the to-be-audited element with the second audit rule to obtain second merged data.

[0033] Preferably, the generalization unit comprises:

[0034] The disambiguation module is used to disambiguate each of the elements to be reviewed in the merged data according to the representation rules corresponding to the elements to be reviewed in the preset knowledge graph to obtain structured data.

[0035] Preferably, the review unit includes:

[0036] A first audit module, configured to send the structured data to an audit rule engine when the audit identifier indicates that the audit request is a single audit request, so that the audit rule engine audits the structured data according to a single audit rule to obtain a first audit result of the to-be-audited file;

[0037] The second audit module is used to send the structured data to the audit rule engine when the audit identifier indicates that the audit request is a document audit request, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the document to be audited.

[0038] Preferably, the device further comprises:

[0039] The sending unit is used to send the audit result of the file to be audited to the client.

[0040] Based on the above-mentioned embodiment of the present invention, a method and device for processing a documentary credit is provided. The method is as follows: when receiving an audit request sent by a client carrying an audit mark and a document to be audited, extracting the elements to be audited from the document to be audited; merging the elements to be audited and the preset audit rules to obtain merged data; generalizing the merged data using a preset knowledge graph to obtain structured data; sending the structured data to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the document to be audited. The audit rule engine is used to audit documents and documents, documents and letters of credit, which is simple to operate and takes a short processing time, thereby improving the processing efficiency of documentary credits. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0042] Figure 1 A flowchart of a method for processing a documentary letter of credit provided by an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of an audit provided by an embodiment of the present invention;

[0044] Figure 3 A structural block diagram of a documentary credit processing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0047] As can be seen from the background technology, the main method of letter of credit review is currently offline review by business experts, who review and output the review results. This method is complicated and takes a long time to process, resulting in low efficiency of letter of credit review.

[0048] Therefore, the embodiment of the present invention provides a method and device for processing documentary credits. When receiving an audit request sent by a client carrying an audit mark and a file to be audited, extract the audit elements from the file to be audited; merge the audit elements and the preset audit rules to obtain merged data; generalize the merged data using a preset knowledge graph to obtain structured data; send the structured data to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited. After processing the audit elements in the file to be audited, the audit is performed using the audit rule engine, thereby improving the audit efficiency.

[0049] join Figure 1 , which shows a flowchart of a method for processing a documentary credit provided by an embodiment of the present invention, the processing method comprising:

[0050] Step S101: when receiving a review request sent by a client and carrying a review mark and a document to be reviewed, extracting the review elements from the document to be reviewed.

[0051] It should be noted that the audit mark is used to indicate whether the audit request is a single audit request or a document audit request. A single audit request is used to audit a document and a bill, and a document audit request is used to audit a document and a letter of credit.

[0052] In some embodiments, the document review includes reviewing documents and letters of credit, and also includes reviewing documents and UCP600\ISBP745\PRACTICE.

[0053] It can be understood that when the audit mark indicates that the audit request is a single audit request, the documents to be audited are documents and documents; when the audit mark indicates that the audit request is a document audit request, the documents to be audited are documents and letters of credit.

[0054] For example, the elements to be reviewed in a letter of credit (entities agreed in the letter of credit) include: letter of credit applicant, letter of credit beneficiary, letter of credit commodity description, letter of credit shipment, letter of credit price terms, letter of credit amount, letter of credit consignee, letter of credit notify party, letter of credit insured, letter of credit issuer, letter of credit insurance amount, and letter of credit insurance type terms.

[0055] The elements to be reviewed in the document (document fact entities) include: document beneficiary, document applicant, document commodity description, document shipment, document price terms, document amount, document consignee, document notify party, document insured, document issuer, document insurance amount, and document insurance type terms.

[0056] Step S102: Merge the elements to be reviewed and the preset review rules to obtain merged data.

[0057] It can be understood that the preset review rules are regular expressions with logical symbols obtained by processing international customary review rules and the review experience of business review experts.

[0058] It should be noted that the preset audit rules include document type, audit item category, audit item description, audit item data anchor value (defined according to business practices and rules), audit item data source, audit type (document audit, single audit), trigger type, trigger basis, audit logic, audit basis, audit item output description and audit rule expression.

[0059] For example, please refer to some preset audit rules shown in Tables 1 to 5:

[0060] Table 1

[0061]

[0062] Table 2

[0063]

[0064] Table 3

[0065]

[0066]

[0067] Table 4

[0068]

[0069] It should be noted that, when the audit identifier indicates that the audit request is a single audit request, the first audit rule corresponding to the single audit is obtained from the preset audit rules; the element to be audited is merged with the first audit rule to obtain the first merged data.

[0070] For example, the first audit rule includes: (i) Date trigger:

[0071] 1. Unconditional equality. (1) The document shows the date of shipment. (2) The document shows the date of issuance of other documents.

[0072] 2. Conditional equality. (1) Other documents show the invoice date. For example: when the issuer of the packing list or weight list is the beneficiary, the invoice date of the packing list or weight list is exactly the same as the invoice; when the exporter (EXPORTER) on the certificate of origin is the beneficiary, the invoice date shown on the certificate of origin must be consistent with the invoice date; when the exporter (EXPORTER) / consignor (CONSIGNOR) on the certificate of analysis is the beneficiary, the invoice date shown on the certificate of analysis must be consistent with the invoice date.

[0073] (II) Amount trigger:

[0074] 1. Unconditional equality. The document shows the amount data on other documents, such as the invoice showing the premium information stated in the insurance policy.

[0075] 2. Calculation logic: For example, when the letter of credit does not specify the insured amount, INSURED AMT ≥ GROSS VALUE OF GOODS * 110%.

[0076] (III) Number trigger:

[0077] 1. Unconditional equality. The document shows the identification number of other documents, such as the letter of credit number of the invoice.

[0078] 2. Conditional equality. (1) Display INV NO, VOYAGE NO or FLIGHT NO. For example, when the issuer of the packing list or weight list is the beneficiary, the invoice number of the packing list or weight list is exactly the same as the invoice number on the invoice, and the VOYAGE NO and FLIGHT NO are consistent with the transport document; when the exporter (EXPORTER) on the certificate of origin is the beneficiary, it must be consistent with the invoice and transport document; when the exporter (EXPORTER) / consignor (CONSIGNOR) on the certificate of analysis is the beneficiary, it must be consistent with the invoice and transport document.

[0079] (IV) Mark trigger: The transport document shows N / M or specific mark content. When other documents quote the mark, it must be strictly consistent with the transport document, or AS PER INV NO must be consistent with the invoice number on the invoice.

[0080] When the audit mark indicates that the audit request is a document audit request, a second audit rule corresponding to the document audit is obtained from the preset audit rules; the element to be audited is merged with the second audit rule to obtain second merged data.

[0081] For example, for the review of documents and letters of credit, the second review rule includes: 1. The entity of the document is consistent with the entity agreed in the letter of credit. For example, the name of the beneficiary of the invoice must be consistent with the name of the beneficiary of the letter of credit. 2. The entity of the document is in the entity area agreed in the letter of credit. For example, if the letter of credit stipulates that the port of shipment is ANY PORT IN CHINA, then the port of shipment of the bill of lading is within the area specified in the letter of credit. 3. The entity of the document is within the entity range agreed in the letter of credit. For example, if the letter of credit stipulates that the letter of credit amount is USD10,000, an increase of 10% is allowed, and partial shipment is not allowed, then the invoice amount must be between USD10,000 and USD11,000.

[0082] For example, for document and UCP600\ISBP745\PRACTICE audit, the second audit rule includes:

[0083] 1. The elements in the document must exist. For example, UCP600 ARTICLE 18A(i) states that "the commercial invoice must appear to be issued by the beneficiary". First, based on the knowledge graph of documentary credits, commercial invoices have the attribute of issuer. When describing this business rule, the second review rule is designed. The relationship between commercial invoices and issuers in the graph is that commercial invoices must have issuers, and the data instantiated by the issuer is the beneficiary of the credit.

[0084] 2. Specify the named entity in the document. For example, UCP600 Article 18A(ii) states that "commercial invoices must be issued in the name of the applicant". First, based on the knowledge graph of documentary credits, commercial invoices have the attribute of the name ...

[0085] 3. Specify the constraints of document elements. For example, UCP600 ARTICLE 14(i) states that "the document date may be earlier than the issuance date of the letter of credit, but not later than the presentation date". First, based on the knowledge graph of documentary credit, documents have the attributes of document issuance date, letter of credit issuance date and presentation date. When designing the system review rule to describe this business rule, it is to establish a temporal logic, a unified document issuance date constraint under the presentation date. For example, it can be expressed as ALL DOCS ISSUE DATE≤PRESENTATION DATE.

[0086] In the specific implementation of step S102, the elements to be reviewed in the review file are merged with the corresponding preset review rules to obtain merged data.

[0087] Step S103: Use the preset knowledge graph to generalize the merged data to obtain structured data.

[0088] It should be noted that the preset knowledge graph is used to generalize the merged data. Specifically, for each element to be reviewed in the merged data, the element to be reviewed is disambiguated according to the representation rules corresponding to the element to be reviewed in the preset knowledge graph to obtain structured data.

[0089] For example, the beneficiary is defined as BENEFICIARY in the preset knowledge graph, and its synonyms include SELLER, BENE, etc. When a set of documents is submitted, the beneficiary description of each document will be different, some are described as SELLER, some are described as BENE, and some are described as BENEFICIARY. Since the beneficiary names appearing in all documents need to be reviewed, the beneficiary descriptions of all documents must be uniformly mapped to BENEFICIARY specified in the preset knowledge graph during the review.

[0090] It is understandable that the preset knowledge graph specifies the representation rules corresponding to each element to be reviewed.

[0091] Step S104: Send the structured data to the audit rule engine, so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited.

[0092] It should be noted that when the audit identifier indicates that the audit request is a single audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the single audit rule to obtain the first audit result of the file to be audited.

[0093] When the audit identifier indicates that the audit request is a document audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the document to be audited.

[0094] In the specific implementation of step S104, the structured data is sent to the audit rule engine, and the audit rule engine is used to audit the structured data to obtain the audit result of the file to be audited. The audit process can be seen in Figure 2 A schematic diagram of an audit provided by an embodiment of the present invention is shown.

[0095] In a specific implementation, after obtaining the audit result of the file to be audited, the audit result of the file to be audited is sent to the client.

[0096] The audit rules used by the audit rule engine are explained in the following content:

[0097] The audit rule types mainly include:

[0098] 1. Four arithmetic operations: such as numerical equality, numerical comparison or numerical calculation, etc.

[0099] 2. Object comparison: such as comparison of the consistency and non-contradiction of goods.

[0100] 3. Address inclusion rules: If the letter of credit requires a Chinese port, other documents should be specific ports.

[0101] 4. Production rules: such as rules with causal relationships such as "if...then..."

[0102] 5. Document element existence category: For example, a certain statement must be included in the letter of credit text (for this type of document review scenario, consider conducting review and judgment in the program instead of building document review rules).

[0103] 6. Reference consistency category: For example, a document needs to contain information about other documents (for this type of document review scenario, consider conducting review and judgment in the program instead of building document review rules).

[0104] It should be noted that the audit rules are represented in the audit rule engine in the form of audit operators. The representation of the audit operators is explained in Table 5 below:

[0105] Table 5

[0106]

[0107]

[0108]

[0109]

[0110] It is understandable that the triggering rules for auditing using the audit rule engine include:

[0111] 1. Non-production rules check the formal expression elements involved in the rules and convert them into path queries on the instance graph. If an instance node is matched, it means that the element exists. When all the elements involved in the rule exist, it means that the rule triggering conditions are met, and the matched instance data is substituted into the operator for calculation.

[0112] 2. Production rules first check whether the expression in the if condition operator is true. If it is true, execute the subsequent expression, otherwise execute the expression in else. The expression can be expressed in the form of a single element, such as BillLadingClause.Shipper, which indicates the existence of the element; it can be a single rule expression or multiple rule expressions, which are combined expressions through And, Or, and Not logical operators.

[0113] In the embodiment of the present invention, offline document review knowledge and international document review rules are represented as structured data, and the review rule engine is used to implement online documentary credit processing operations, which is simple to operate and fast in processing, thereby improving the processing efficiency of documentary credits.

[0114] Corresponding to the method for processing a documentary credit provided by the above embodiment of the present invention, see Figure 3 , shows a structural block diagram of a documentary credit processing device provided by an embodiment of the present invention, the processing device includes: an extraction unit 301, a merging unit 302, a generalization unit 303 and an audit unit 304.

[0115] The extraction unit is used to extract the elements to be reviewed from the files to be reviewed when receiving an audit request sent by a client and carrying an audit mark and files to be reviewed, wherein the audit mark is used to indicate that the audit request is a single audit request or a document audit request, the single audit request is used to audit the documents and the documents, and the document audit request is used to audit the documents and the letter of credit.

[0116] The merging unit is used to merge the elements to be audited and the preset audit rules to obtain merged data.

[0117] The generalization unit is used to generalize the merged data using the preset knowledge graph to obtain structured data.

[0118] The audit unit is used to send the structured data to the audit rule engine so that the audit rule engine audits the structured data and obtains the audit result of the file to be audited.

[0119] In an embodiment of the present invention, when an audit request carrying an audit identifier and a file to be audited is received from a client, the elements to be audited in the file to be audited are extracted and processed into structured data, and the structured data is audited using an audit rule engine to implement online audit of the file to be audited, thereby obtaining an audit result and improving the processing efficiency of the file to be audited.

[0120] Preferably, combined Figure 3 , the merging unit includes:

[0121] The first acquisition module is used to acquire a first audit rule corresponding to the single audit from preset audit rules when the audit identifier indicates that the audit request is a single audit request.

[0122] The first merging module is used to merge the elements to be reviewed with the first review rules to obtain first merged data.

[0123] The second acquisition module is used to acquire a second audit rule corresponding to the document audit from preset audit rules when the audit identifier indicates that the audit request is a document audit request.

[0124] The second merging module is used to merge the elements to be reviewed with the second review rules to obtain second merged data.

[0125] Preferably, combined Figure 3 , the generalization unit includes:

[0126] The disambiguation module is used to disambiguate each element to be reviewed in the merged data according to the representation rules corresponding to the element to be reviewed in the preset knowledge graph to obtain structured data.

[0127] Preferably, combined Figure 3 , the audit units include:

[0128] The first audit module is used to send the structured data to the audit rule engine when the audit identifier indicates that the audit request is a single audit request, so that the audit rule engine audits the structured data according to the single audit rule to obtain a first audit result of the file to be audited.

[0129] The second audit module is used to send the structured data to the audit rule engine when the audit identifier indicates that the audit request is a document audit request, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the file to be audited.

[0130] Preferably, combined Figure 3 The processing device also includes: a sending unit, which is used to send the review result of the file to be reviewed to the client.

[0131] In summary, the embodiments of the present invention provide a method and device for processing documentary letters of credit, which utilize an audit rule engine to audit documents and documents, documents and letters of credit, with simple operation and short processing time, thereby improving the processing efficiency of documentary letters of credit.

[0132] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0133] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0134] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing a documentary letter of credit, characterized in that: The method comprises: When receiving an audit request sent by a client and carrying an audit mark and a document to be audited, extracting the audit elements from the document to be audited, wherein the audit mark is used to indicate that the audit request is a single audit request or a document audit request, the single audit request is used to audit a document and a document, and the document audit request is used to audit a document and a letter of credit; Merging the elements to be reviewed and the preset review rules to obtain combined data; The preset audit rules include audit types and audit rule expressions; the audit types include document audit and single audit; Generalizing the combined data using a preset knowledge graph to obtain structured data; The structured data is sent to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited.

2. The method according to claim 1, characterized in that The step of merging the elements to be reviewed and the preset review rules to obtain the combined data includes: When the audit identifier indicates that the audit request is a single audit request, obtaining a first audit rule corresponding to the single audit from preset audit rules; Merging the to-be-audited element with the first audit rule to obtain first merged data; When the audit identifier indicates that the audit request is a document audit request, obtaining a second audit rule corresponding to the document audit from preset audit rules; The to-be-audited element is combined with the second audit rule to obtain second combined data.

3. The method according to claim 1, characterized in that The method of generalizing the merged data using a preset knowledge graph to obtain structured data includes: For each of the elements to be reviewed in the merged data, according to the representation rules corresponding to the elements to be reviewed in the preset knowledge graph, the elements to be reviewed are disambiguated to obtain structured data.

4. The method according to claim 1, characterized in that: The sending of the structured data to the audit rule engine so that the audit rule engine audits the structured data to obtain the audit result of the to-be-audited file includes: When the audit identifier indicates that the audit request is a single audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the single audit rule to obtain a first audit result of the to-be-audited file; When the audit identifier indicates that the audit request is a document audit request, the structured data is sent to the audit rule engine, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the document to be audited.

5. The method according to claim 1, characterized in that The method further includes sending the structured data to the audit rule engine so that the audit rule engine audits the structured data and obtains the audit result of the to-be-audited file: The audit result of the file to be audited is sent to the client.

6. A device for processing documentary credit, characterized in that: The device comprises: an extracting unit, configured to extract the to-be-audited elements from the to-be-audited file upon receiving an audit request sent by a client and carrying an audit identifier and the to-be-audited file, wherein the audit identifier is used to indicate that the audit request is a single audit request or a document audit request, the single audit request is used to audit the document and the document, and the document audit request is used to audit the document and the letter of credit; A merging unit, used for merging the elements to be audited and the preset audit rules to obtain the merged data; the preset audit rules include the audit type and the audit rule expression; the audit type includes the document audit and the single audit; A generalization unit, used to generalize the combined data using a preset knowledge graph to obtain structured data; The audit unit is used to send the structured data to the audit rule engine, so that the audit rule engine audits the structured data to obtain the audit result of the file to be audited.

7. The device according to claim 6, characterized in that The merging unit comprises: A first acquisition module, configured to acquire a first audit rule corresponding to the single audit from preset audit rules when the audit identifier indicates that the audit request is a single audit request; A first merging module, used for merging the to-be-audited element with the first audit rule to obtain first merged data; A second acquisition module, configured to acquire a second audit rule corresponding to the document audit from preset audit rules when the audit identifier indicates that the audit request is a document audit request; The second merging module is used to merge the to-be-audited element with the second audit rule to obtain second merged data.

8. The device according to claim 6, characterized in that The generalization unit comprises: The disambiguation module is used to disambiguate each of the elements to be reviewed in the merged data according to the representation rules corresponding to the elements to be reviewed in the preset knowledge graph to obtain structured data.

9. The device according to claim 6, characterized in that The review unit includes: A first audit module, configured to send the structured data to an audit rule engine when the audit identifier indicates that the audit request is a single audit request, so that the audit rule engine audits the structured data according to a single audit rule to obtain a first audit result of the to-be-audited file; The second audit module is used to send the structured data to the audit rule engine when the audit identifier indicates that the audit request is a document audit request, so that the audit rule engine audits the structured data according to the document audit rule to obtain a second audit result of the document to be audited.

10. The device according to claim 6, characterized in that The device also includes: The sending unit is used to send the audit result of the file to be audited to the client.

Images