A method and device for converting documentary credit labels

Abstract

The present invention provides a method and apparatus for converting documentary credit labels. The method is as follows: obtain a file to be converted; use a pre-constructed annotation tool to label corresponding labels for each attribute of the file to be converted, obtaining the file to be converted after annotation; replace the attribute name corresponding to each label in the file to be converted after annotation with a target attribute name that conforms to a preset knowledge graph, obtaining structured data. Using the pre-constructed annotation tool to process the file to be converted, making the attribute names of the attributes in the file to be converted conform to the preset knowledge graph, is conducive to unifying the identification standard of the documentary credit bill review model and improving the review accuracy of the bill review engine.

Description

Technical Field

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

[0002] Document examination in a letter of credit refers to a comprehensive service provided by a bank for an exporter under a letter of credit, which integrates document examination and sending documents for negotiation of proceeds.

[0003] Currently, there are many types of documents involved in international documentary credit document examination business. Different customers have different ways of describing documents, and manual marking is required for each examination element in each type of document before the document examination operation can be carried out. Therefore, there are problems of difficult document examination and slow document examination speed. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and device for converting documentary credit labels to solve the problems of difficult document examination and slow document examination speed.

[0005] To achieve the above object, 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 converting documentary credit labels, the method including:

[0007] Obtain a file to be converted, where the file to be converted includes at least an image of a document and a letter of credit;

[0008] Use a marking tool to mark corresponding labels for each attribute of the file to be converted to obtain a marked file to be converted, where the marking tool is pre-constructed based on a label system, a marking level, and a label representation mapping;

[0009] Replace the attribute name corresponding to each label in the marked file to be converted with a target attribute name that conforms to a preset knowledge graph to obtain structured data.

[0010] Preferably, the step of using a marking tool to mark corresponding labels for each attribute of the file to be converted to obtain a marked file to be converted includes:

[0011] Based on the label system and the marking level in the marking tool, obtain the labels corresponding to each attribute of the file to be converted;

[0012] Use the labels to mark the file to be converted to obtain a marked file to be converted.

[0013] Preferably, the step of replacing the attribute name corresponding to each label in the marked file to be converted with a target attribute name that conforms to a preset knowledge graph to obtain structured data includes:

[0014] For each tag in the to-be-converted file after annotation, obtain the target attribute name mapped by the tag from a preset knowledge graph;

[0015] In the to-be-converted file after annotation, replace the attribute name of the attribute corresponding to the tag with the target attribute name to obtain structured data.

[0016] Preferably, before obtaining the to-be-converted file after annotation by using an annotation tool to annotate corresponding tags for each attribute of the to-be-converted file, it further includes:

[0017] Process the image of the document in the to-be-converted file into a text file;

[0018] When the format of the letter of credit in the to-be-converted file is an image, process the image of the letter of credit into a text file.

[0019] Preferably, after obtaining structured data by replacing the attribute name corresponding to each tag in the to-be-converted file after annotation with the target attribute name that conforms to the preset knowledge graph, it further includes:

[0020] Send the structured data to an audit rule engine so that the audit rule engine audits the structured data to obtain an audit result.

[0021] The second aspect of the embodiments of the present invention discloses a conversion device for documentary credit tags, and the device includes:

[0022] An acquisition unit, configured to acquire a to-be-converted file, where the to-be-converted file at least includes an image of a document and a letter of credit;

[0023] An annotation unit, configured to use an annotation tool to annotate corresponding tags for each attribute of the to-be-converted file to obtain a to-be-converted file after annotation, where the annotation tool is pre-constructed based on a tag system, an annotation level, and a tag representation mapping;

[0024] A replacement unit, configured to replace the attribute name corresponding to each tag in the to-be-converted file after annotation with the target attribute name that conforms to the preset knowledge graph to obtain structured data.

[0025] Preferably, the annotation unit includes:

[0026] A first acquisition module, configured to acquire the tags corresponding to each attribute of the to-be-converted file based on the tag system and the annotation level in the annotation tool;

[0027] An annotation module, configured to use the tags to annotate the to-be-converted file to obtain a to-be-converted file after annotation.

[0028] Preferably, the replacement unit includes:

[0029] A second acquisition module, configured to obtain, from a preset knowledge graph, a target attribute name mapped by each tag in the to-be-converted file after annotation;

[0030] A replacement module, configured to replace the attribute name of the attribute corresponding to the tag in the to-be-converted file after annotation with the target attribute name to obtain structured data.

[0031] Preferably, the apparatus further includes:

[0032] A first processing unit, configured to process the image of the document in the to-be-converted file into a text file;

[0033] A second processing unit, configured to process the image of the letter of credit into a text file when the format of the letter of credit in the to-be-converted file is an image.

[0034] Preferably, the apparatus further includes:

[0035] A sending unit, configured to send the structured data to an audit rule engine, so that the audit rule engine audits the structured data to obtain an audit result.

[0036] Based on the above-mentioned method and apparatus for converting documentary credit tags provided by the embodiments of the present invention, the method is as follows: obtaining a to-be-converted file; using a pre-constructed annotation tool to annotate corresponding tags for each attribute of the to-be-converted file to obtain a to-be-converted file after annotation; replacing the attribute name corresponding to each tag in the to-be-converted file after annotation with a target attribute name that conforms to a preset knowledge graph to obtain structured data. Using a pre-constructed annotation tool to process the to-be-converted file, so that the attribute names of the attributes in the to-be-converted file conform to a preset knowledge graph, which is conducive to unifying the identification standard of the document review model for documentary credits and improving the review accuracy of the review engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0038] Figure 1 FIG. is a flowchart of a method for converting documentary credit tags provided by an embodiment of the present invention;

[0039] Figure 2Schematic diagram of a method for converting documentary credit labels provided by an embodiment of the present invention;

[0040] Figure 3 Example diagram of a partial label system provided by an embodiment of the present invention;

[0041] Figure 4 Example diagram of goods elements provided by an embodiment of the present invention;

[0042] Figure 5 Schematic diagram of the relationship between labels and document structures provided by an embodiment of the present invention;

[0043] Figure 6 Another schematic diagram of a method for converting documentary credit labels provided by an embodiment of the present invention;

[0044] Figure 7 Block diagram of the structure of a device for converting documentary credit labels provided by an embodiment of the present invention. Detailed implementation manners

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] In this application, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such a process, method, article or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0047] As can be seen from the background technology, currently, there are many types of documents involved in international letter of credit document review operations. Different customers have different ways of describing documents, and manual marking of the review elements in each type of document is required for document review operations. Therefore, there are problems of difficult document review and slow document review speed.

[0048] Therefore, an embodiment of the present invention provides a method and device for converting documentary credit tags, which includes: obtaining a file to be converted; using a pre-constructed annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining the annotated file to be converted; replacing the attribute name corresponding to each tag in the annotated file to be converted with a target attribute name that conforms to a preset knowledge graph, obtaining structured data. Processing the file to be converted using the annotation tool to make the attribute names of the attributes in the file to be converted conform to the preset knowledge graph is beneficial to unifying the identification standard of the documentary credit document review model and improving the review accuracy of the document review engine.

[0049] Participate Figure 1 , which shows a flowchart of a method for converting documentary credit tags provided by an embodiment of the present invention. The conversion method includes:

[0050] Step S101: Obtain a file to be converted.

[0051] It should be noted that the file to be converted at least includes the image of the document to be reviewed and the letter of credit.

[0052] In the specific implementation process of step S101, obtain a file to be converted that at least includes the image of the document and the letter of credit.

[0053] Step S102: Use an annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining the annotated file to be converted.

[0054] It can be understood that the annotation tool is pre-constructed based on a tag system, an annotation level, and a tag representation mapping. Among them, after the annotation tool is constructed, a preset file is used to train the annotation tool to improve the accuracy of the annotation tool.

[0055] It should be noted that based on the tag system and annotation level in the annotation tool, obtain the tags corresponding to each attribute of the file to be converted, and use the tags to annotate each attribute in the file to be converted, obtaining the annotated file to be converted.

[0056] It can be understood that in the tag tool, the tag system is designed with tag names, attribute names, attribute explanations, attribute value types, and tag descriptions; the annotation level is designed with descriptions for multi-level annotation based on annotation relationships.

[0057] It can be understood that the file to be converted includes the image of the document and the letter of credit in text format and / or the image of the letter of credit. At this time, it is necessary to process the image of the document and the image of the letter of credit into text files.

[0058] In some embodiments, the images of the documents in the file to be converted are processed into text files. When the format of the letter of credit in the file to be converted is an image, the image of the letter of credit is processed into a text file. If the format of the letter of credit in the file to be converted is text, no processing is performed; then, each attribute of the file to be converted in text format is labeled with a corresponding tag using a labeling tool, obtaining the labeled file to be converted.

[0059] In the process of specifically implementing step S102, each attribute of the file to be converted is labeled with a corresponding tag using the tag system and labeling hierarchy in the labeling tool, obtaining the labeled file to be converted.

[0060] Step S103: Replace the attribute name corresponding to each tag in the labeled file to be converted with the target attribute name that conforms to the preset knowledge graph, obtaining structured data.

[0061] It should be noted that for each tag in the labeled file to be converted, the target attribute name mapped by the tag is obtained from the preset knowledge graph, and in the labeled file to be converted, the attribute name of the attribute corresponding to the tag is replaced with the target attribute name, obtaining structured data.

[0062] It can be understood that the preset knowledge graph stores the target attribute names corresponding to each attribute, and each attribute in the file to be converted needs to be labeled with the corresponding target attribute name to facilitate subsequent review and processing of the file to be converted.

[0063] In specific implementation, after replacing the attribute name corresponding to each tag in the labeled file to be converted with the target attribute name that conforms to the preset knowledge graph and obtaining structured data, the structured data is sent to the audit rule engine so that the audit rule engine audits the structured data to obtain an audit result.

[0064] It should be noted that referring to Figure 2 the schematic diagram of a method for converting documentary credit tags provided by the embodiments of the present invention shown, the method for converting documentary credit tags provided by the embodiments of the present invention can be further explained.

[0065] For the tag system, labeling hierarchy, and tag representation mapping included in the above-mentioned labeling tool, the following content is used to explain and illustrate them respectively.

[0066] Explanation of the tag system:

[0067] The tag system design includes tag name, attribute name, attribute explanation, attribute value type, and tag description.

[0068] The label name is an abstract representation of language symbols for the same concept by analyzing hundreds of bills. For example, the main English representations of the letter of credit number include LETTER OF CREDITS NO, LC NO, CREDIT NO, LC NUMBER, L / C NO, etc. These language symbols all have the opportunity to appear in the same set of letter of credit review documents. However, during the business review process, these different language symbols all point to the same concept, that is, the identification attribute of the letter of credit - the letter of credit number. It is necessary to abstract a unified annotation label name that is easy to understand in the practice of letter of credit document review from these different language symbols. For example, the label name of the above-mentioned letter of credit number is LC_NO.

[0069] The attribute name is the formal ontology representation of this label name in the letter of credit document review knowledge graph. For example, the attribute name of LC_NO is creditNumber (camel case naming method of the formal ontology).

[0070] The attribute explanation is the business meaning description of this attribute name.

[0071] The attribute value type refers to the DATA VALUE of this attribute.

[0072] The label description describes where this label is commonly found in the document, what words it usually follows, and some constraints.

[0073] Specifically, please refer to Figure 3 the partial label system example diagram provided by the embodiments of the present invention shown.

[0074] Explanation on the annotation level:

[0075] Since the goods description part of the documentary letter of credit is the most complex content and its business representation is multi-level, it is impossible to obtain the document review data by one-time annotation. Therefore, it is necessary to design the annotation level so that the document to be converted after annotation can be defined and described in line with business conventions. Secondly, the layout of the business document elements involved in the documentary letter of credit is also typeset according to the hierarchical relationship.

[0076] I. Goods description label level

[0077] The goods description label level is divided into three parts: table row structure, goods element entity, and goods element.

[0078] (1) Table row structure

[0079] 1. Design the table structure of the goods description according to the practice. The structure description is as follows in Table 1:

[0080] Table 1

[0081]

[0082]

[0083] (2) Goods element entity

[0084] 1. Annotate the element entity according to the hierarchical concept of goods in the document review knowledge graph.

[0085] 2. According to the specific business labels of each element in the content row of the practice form, such as unit, up and down floating, jointly annotate them in the business label.

[0086] (3) Goods elements

[0087] 1. "QUANTITY" and "MTS" are in the "unit" relationship, which can be seen in Figure 4 the example diagram of goods elements provided by the embodiment of the present invention shown.

[0088] II. Document structure hierarchy

[0089] According to the characteristics of document practice, the document is divided into three parts: the heading, the body, and the ending. The heading part mainly includes the drawer's heading, the document name, and the trading parties on the document. The body part mainly describes the goods. The ending part mainly includes summary information (such as total price, total quantity, total weight) and signing information. When defining the element entity label, each label will be annotated according to the document structure relationship, which can be seen in Figure 5 the schematic diagram of the relationship between the label and the document structure provided by the embodiment of the present invention shown.

[0090] Explanation of label representation mapping:

[0091] In the label design, the label name and the attribute name are a systematic mapping relationship. It is necessary to clarify the concept of the knowledge graph corresponding to the label in the annotation tool. When performing natural language processing, this layer of relationship needs to be output to the review engine, and the review engine triggers the definition through the pre-set rules of the knowledge graph concept for conditional rule review. See Figure 6 another schematic diagram of a method for converting documentary credit labels provided by the embodiment of the present invention shown.

[0092] In the embodiment of the present invention, a file to be converted is obtained, the file to be converted is annotated by using an annotation tool to obtain the annotated file to be converted, and based on the knowledge graph, the attribute name of each label corresponding to the attribute in the annotated file to be converted is replaced with the target attribute name that conforms to the knowledge graph to obtain structured data; the structured data is sent to the review rule engine so that the review rule engine reviews the structured data to obtain a review result. Using the annotation tool to realize the online conversion of documentary credit labels is beneficial to unifying the identification standard of the documentary credit review model and improving the review accuracy of the review engine.

[0093] Corresponding to the method for converting documentary credit labels provided in the embodiment of the present invention described above, refer to Figure 7 , which shows a structural block diagram of a device for converting documentary credit labels provided in the embodiment of the present invention. The conversion device includes: an acquisition unit 701, a marking unit 702, and a replacement unit 703.

[0094] The acquisition unit 701 is configured to acquire a file to be converted, and the file to be converted includes at least an image of a document and a letter of credit.

[0095] The marking unit 702 is configured to use a marking tool to mark corresponding labels for each attribute of the file to be converted, so as to obtain the marked file to be converted. The marking tool is pre-constructed based on a label system, a marking hierarchy, and a label representation mapping.

[0096] The replacement unit 703 is configured to replace the attribute name corresponding to each label in the marked file to be converted with a target attribute name that conforms to a preset knowledge graph, so as to obtain structured data.

[0097] In the embodiment of the present invention, by using a marking tool to convert the labels of the file to be converted into target attribute names that conform to the knowledge graph, it effectively helps to improve the speed of the document examination service for documentary credits and solves the problem of difficult document examination caused by inconsistent customer descriptions.

[0098] Preferably, in combination with Figure 7 , the marking unit 702 includes a first acquisition module and a marking module:

[0099] The first acquisition module is configured to acquire the labels corresponding to each attribute of the file to be converted based on the label system and the marking hierarchy in the marking tool.

[0100] The marking module is configured to use the labels to mark the file to be converted, so as to obtain the marked file to be converted.

[0101] Preferably, in combination with Figure 7 , the replacement unit 703 includes a second acquisition module and a replacement module:

[0102] The second acquisition module is configured to, for each label in the marked file to be converted, acquire the target attribute name mapped by the label from a preset knowledge graph.

[0103] The replacement module is configured to, in the marked file to be converted, replace the attribute name of the attribute corresponding to the label with the target attribute name, so as to obtain structured data.

[0104] Preferably, in combination with Figure 7 , the conversion device further includes a first processing unit and a second processing unit:

[0105] A first processing unit for processing the images of the documents in the file to be converted into text files.

[0106] A second processing unit for processing the image of the letter of credit into a text file when the format of the letter of credit in the file to be converted is an image.

[0107] Preferably, in combination with Figure 7 , the conversion device further includes a sending unit for sending the structured data to an audit rule engine so that the audit rule engine audits the structured data to obtain an audit result.

[0108] In summary, the embodiments of the present invention provide a method and device for converting documentary credit tags. The file to be converted obtained is marked by using a marking tool to obtain the marked file to be converted, and then based on the knowledge graph, the attribute names of the attributes corresponding to each tag in the marked file to be converted are replaced with target attribute names that conform to the knowledge graph. Constructing a marking tool is beneficial to quickly perform tag conversion on documents and letters of credit online, so as to facilitate the subsequent document review operation, which is beneficial to unifying the document review model recognition standard of documentary credits and improving the review accuracy of the document review engine.

[0109] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for a 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 systems and system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0110] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0111] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present invention. Various modifications to these embodiments will be readily 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. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for converting documentary credit labels, characterized in that The method includes: Obtaining a file to be converted, where the file to be converted includes at least an image of a document and a letter of credit in text format, and / or an image of a letter of credit; Using an annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining an annotated file to be converted, where the annotation tool is pre-constructed based on a tag system, an annotation level, and a tag representation mapping; Replacing the attribute name corresponding to each tag in the annotated file to be converted with a target attribute name that conforms to a preset knowledge graph, obtaining structured data; Sending the structured data to an audit rule engine so that the audit rule engine audits the structured data to obtain an audit result; Among them, the step of using an annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining an annotated file to be converted, includes: Based on the tag system and the annotation level in the annotation tool, obtaining the tags corresponding to each attribute of the file to be converted; Using the tags to annotate the file to be converted, obtaining an annotated file to be converted.

2. The method according to claim 1, characterized in that The step of replacing the attribute name corresponding to each tag in the annotated file to be converted with a target attribute name that conforms to a preset knowledge graph, obtaining structured data, includes: For each tag in the annotated file to be converted, obtaining the target attribute name mapped by the tag from a preset knowledge graph; In the annotated file to be converted, replacing the attribute name of the attribute corresponding to the tag with the target attribute name, obtaining structured data.

3. The method according to claim 1, characterized in that, Before using an annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining an annotated file to be converted, it further includes: Processing the image of the document in the file to be converted into a text file; When the format of the letter of credit in the file to be converted is an image, processing the image of the letter of credit into a text file.

4. A conversion device for documentary credit labels, characterized in that, The device includes: An acquisition unit, configured to acquire a file to be converted, where the file to be converted includes at least an image of a document and a letter of credit in text format, and / or an image of a letter of credit; An annotation unit, configured to use an annotation tool to annotate corresponding tags for each attribute of the file to be converted, obtaining an annotated file to be converted, where the annotation tool is pre-constructed based on a tag system, an annotation level, and a tag representation mapping; A replacement unit, configured to replace the attribute name corresponding to each tag in the annotated file to be converted with a target attribute name that conforms to a preset knowledge graph, obtaining structured data; A sending unit, configured to send the structured data to an audit rule engine so that the audit rule engine audits the structured data to obtain an audit result; The annotation unit includes: A first acquisition module, configured to obtain the tags corresponding to each attribute of the file to be converted based on the tag system and the annotation level in the annotation tool; An annotation module, configured to use the tags to annotate the file to be converted, obtaining an annotated file to be converted.

5. The device according to claim 4, characterized in that, The replacement unit includes: A second acquisition module, configured to obtain, for each tag in the labeled file to be converted, a target attribute name mapped by the tag from a preset knowledge graph; A replacement module, configured to replace the attribute name of the attribute corresponding to the tag in the labeled file to be converted with the target attribute name to obtain structured data.

6. The device according to claim 4, characterized in that The apparatus further includes: A first processing unit, configured to process an image of the document in the file to be converted into a text file; A second processing unit, configured to process an image of the letter of credit into a text file when the format of the letter of credit in the file to be converted is an image.

Images