CN115601129A - Supply chain financial asset auditing method, device, equipment and medium - Google Patents
Supply chain financial asset auditing method, device, equipment and medium Download PDFInfo
- Publication number
- CN115601129A CN115601129A CN202211156964.6A CN202211156964A CN115601129A CN 115601129 A CN115601129 A CN 115601129A CN 202211156964 A CN202211156964 A CN 202211156964A CN 115601129 A CN115601129 A CN 115601129A
- Authority
- CN
- China
- Prior art keywords
- financial asset
- image data
- information
- target
- opinion
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19107—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/1918—Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Abstract
The application relates to an artificial intelligence technology, and provides a supply chain financial asset auditing method, device, equipment and medium, wherein the method comprises the following steps: carrying out image recognition on the financial asset image data to obtain position information and character information of each line of text box; performing multi-mode information extraction on the financial asset image data according to the identified information to obtain target information; carrying out validity check on the financial asset image data by using the target information; if the validity is verified, sending target information to the configuration platform; inquiring the target opinion from the audit opinion set according to the feedback data of the configuration platform aiming at the target information; sending the target opinions to a configuration platform; the target opinion is fed back when selected. According to the method and the device, automatic verification of the supply chain financial assets can be achieved by combining character recognition and multi-mode information extraction, verification efficiency is improved, meanwhile, verification opinions can be generated, verification of the supply chain financial assets is assisted, and verification efficiency is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a supply chain financial asset auditing method, device, equipment and medium.
Background
In the field of supply chain finance, particularly for cross-border supply chain finance, a company applying for loan needs to upload document images such as invoices, customs reports, contracts, purchase orders and bills to prove the authenticity of transactions.
Currently, for the loan data, a loan institution generally adopts a manual review mode. Because the data is various, the number of the elements needing to be compared is also large, the manual review mode is time-consuming and labor-consuming, the review efficiency is low, and mistakes are easy to make.
Disclosure of Invention
The embodiment of the application provides a supply chain financial asset auditing method, a supply chain financial asset auditing device, computer equipment and a storage medium, and aims to solve the problems of low supply chain financial asset data auditing efficiency and high possibility of errors.
In a first aspect, an embodiment of the present application provides a supply chain financial asset auditing method, which includes:
in response to a received auditing request for financial asset image data, performing image recognition on the financial asset image data to obtain position information and character information of each line of text box in the financial asset image data;
performing multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text box to obtain target information;
carrying out validity check on the financial asset image data by using the target information;
responding to the fact that the financial asset image data passes the validity check, and sending the target information to a configuration platform;
responding to feedback data of the configuration platform for the target information, and inquiring a target opinion from a pre-configured audit opinion set according to the feedback data;
sending the target opinion to the configuration platform;
and feeding back the target opinion in response to a selection instruction of the target opinion.
In a second aspect, an embodiment of the present application provides a supply chain financial asset auditing apparatus, which includes:
the identification unit is used for responding to a received auditing request for the financial asset image data, carrying out image identification on the financial asset image data and obtaining position information and character information of each line of text box in the financial asset image data;
the extraction unit is used for performing multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text frame to obtain target information;
the checking unit is used for carrying out validity checking on the financial asset image data by utilizing the target information;
the sending unit is used for responding to the fact that the financial asset image data passes the validity check and sending the target information to a configuration platform;
the query unit is used for responding to feedback data of the configuration platform aiming at the target information and querying the target opinion from a pre-configured audit opinion set according to the feedback data;
the sending unit is further configured to send the target opinion to the configuration platform;
and the feedback unit is used for responding to a selection instruction of the target opinion and feeding back the target opinion.
In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the supply chain financial asset auditing method described in the first aspect is implemented.
In a fourth aspect, the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the supply chain financial asset auditing method according to the first aspect.
The embodiment of the application provides a supply chain financial asset auditing method, device, equipment and medium, which can be used for realizing automatic verification of supply chain financial assets by combining character recognition and multi-mode information extraction, improving verification efficiency, and generating auditing opinions to assist in auditing the supply chain financial assets and improve auditing efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an application scenario of a supply chain financial asset auditing method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a supply chain financial asset auditing method according to an embodiment of the present disclosure;
FIG. 3 is a schematic block diagram of a supply chain financial asset auditing apparatus provided by an embodiment of the present application;
fig. 4 is a schematic block diagram of a computer device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a supply chain financial asset auditing method according to an embodiment of the present application; fig. 2 is a schematic flow chart of a supply chain financial asset auditing method according to an embodiment of the present application, where the supply chain financial asset auditing method is implemented in a server and is executed by application software installed in the server.
As shown in fig. 2, the method includes steps S101 to S107.
S101, responding to a received auditing request for the financial asset image data, and carrying out image recognition on the financial asset image data to obtain position information and character information of each line of text box in the financial asset image data.
In this embodiment, the technical solution may be described with a server as an execution subject. The user end (such as an intelligent terminal like a smart phone or a tablet computer) used by a user can perform data interaction with the server, specifically, the server provides a supply chain financial asset auditing platform, and the user end can log in the supply chain financial asset auditing platform. And a user interaction interface of the supply chain financial asset auditing platform is displayed on a terminal interface of the user side, and at least one picture uploading interface exists in the user interaction interface. When a user selects a certain image as financial asset image data and uploads the image data to the server from the image uploading interface, subsequent supply chain financial asset examination and verification can be carried out in the server.
In this embodiment, the request for approval may be triggered by the loan applicant. Specifically, when a loan applicant uploads the financial asset image data, the request for auditing is determined to be triggered. The financial asset image data may be in a format of jpg, png or pdf.
In this embodiment, an OCR (Optical Character Recognition) technique may be adopted to perform image Recognition on the financial asset image data.
For example: character recognition can be performed on the financial asset image data by adopting a DBNet model so as to detect text information in the financial asset image data and generate positioning information of the text. Further, single line of text information of the located text is extracted by using a CRNN (Convolutional recurrent neural Network) to obtain position information and character information of each line of text box in the financial asset image data.
And S102, performing multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text box to obtain target information.
For example: the SDMGR model can be adopted to read the position information and the character information of the text box to obtain the field to which the text box belongs, namely, the text box is regarded as a node, and the label of each node and the relation between two adjacent nodes are obtained through a graph neural network.
Specifically, the obtaining of the target information by performing multi-modal information extraction on the financial asset image data according to the position information and the character information of each line of text box includes:
performing feature extraction on the character information based on the position information of each line of text frame to obtain a first feature corresponding to a graph node, wherein the first feature is generated by performing feature fusion among modalities on three modal features of text, vision and layout;
abstracting the character information to obtain an initial graph, wherein the initial graph is described by graph nodes, edges among the nodes and an adjacent matrix of the graph;
clustering the graph nodes in the initial graph to divide the initial graph, and performing multiple iterative updates on an allocation matrix for division in the dividing process;
acquiring cluster representation and distribution matrixes during each iterative update in the multiple iterative update process;
updating the first characteristic by utilizing cluster representation and distribution matrix during each iteration updating to obtain a second characteristic;
and carrying out node classification and link prediction based on the second characteristics to obtain the target information.
On the basis of character recognition, the method further extracts key information in the financial asset image data as the target information by combining a multi-mode information extraction technology so as to assist in the follow-up examination of the financial assets of the supply chain.
S103, carrying out validity check on the financial asset image data by using the target information.
In this embodiment, the validity check includes, but is not limited to: the format of the financial asset image data is checked, the financial asset image data of a specified type (such as invoice type data) is checked, and specified information is checked.
Specifically, the performing validity check on the financial asset image data by using the target information includes:
determining whether the financial asset image data meets format requirements according to the target information;
when the financial asset image data does not meet the format requirement, refusing to accept an audit request for the financial asset image data;
and sending prompt information, wherein the prompt information is used for prompting the financial asset image data to have wrong format and prompting to upload the financial asset image data again.
Wherein different types of financial asset image data may correspond to different formatting requirements to unify formatting of various types of documents.
Through format inspection, effective prompts are sent out in time, and quick response can be carried out when the format is wrong, so that the auditing efficiency is improved.
Further, when the financial asset image data satisfies the format requirement, detecting a type of the financial asset image data;
when the financial asset image data is of an invoice type, the verifying the validity of the financial asset image data by using the target information further includes, but is not limited to, one or a combination of multiple verification methods:
(1) And detecting whether the transaction amount of the financial asset image data is a positive number, and prompting that the transaction amount is wrong when the transaction amount is not the positive number.
Meanwhile, when the transaction amount is a positive number, the transaction amount is correct and no prompt is sent.
(2) And acquiring a transaction party from the financial asset image data, performing authenticity verification on the transaction party, and prompting the transaction party that the information is wrong when the transaction party does not pass the authenticity verification.
The transaction parties may include buyers and sellers.
The embodiment may perform the authenticity check on the transaction party by invoking a third party platform (such as an enterprise query platform) or by querying a local record.
(3) And detecting the loan times corresponding to one transaction in the financial asset image data, and prompting that an invoice number exists when the loan times are greater than or equal to one time.
In the embodiment, the loan times corresponding to one transaction are detected, so that the situation that one transaction applies for loans for multiple times can be avoided.
(4) And detecting whether the date format in the financial asset image data is a configuration format, and prompting that the date format is wrong when the date format is not the configuration format.
The configuration format may be a general date format, and the date format may be configured by a user, which is not limited in the present invention.
(5) And acquiring a pre-configured service rule, detecting whether the financial asset image data accords with the service rule, and prompting that the service requirement is not met when the financial asset image data does not accord with the service rule.
The business rules can be configured according to actual business requirement data.
According to the embodiment, the pertinence verification of the financial asset image data of the invoice type can be realized, so that the phenomenon that information errors occur and subsequent asset auditing is influenced is avoided.
Of course, the embodiment may also perform targeted verification on other types of financial asset image data, such as customs declaration, contracts, purchase orders, bill submissions, and the like, which is not described herein again.
And S104, responding to the fact that the financial asset image data passes the validity check, and sending the target information to a configuration platform.
In this embodiment, when the financial asset image data fails to pass the validity check, an error message is sent, and the financial asset image data can be uploaded again after modification.
In this embodiment, before sending the target information to the configuration platform, the method further includes:
acquiring a pre-configured information matching rule;
acquiring configuration information from the target information according to the information matching rule;
detecting whether the configuration information meets the information matching rule or not to obtain a matching result;
and sending the matching result to the configuration platform.
The configuration information may be predefined key information, such as buyer, seller and amount on the invoice and order. Further, according to the information matching rule, the invoice must match with the buyer, seller and amount on the order.
Wherein the configuration platform may include an audit platform of financial asset image data.
In this embodiment, before the target information is sent to the configuration platform, an audit result of the configured key information is sent first, so as to assist in performing faster audit and improve the audit efficiency.
Further, the target information is sent to the configuration platform, so that the configuration platform can check the target information.
And S105, responding to feedback data of the configuration platform aiming at the target information, and inquiring the target opinion from a pre-configured audit opinion set according to the feedback data.
In this embodiment, the feedback data may be keywords uploaded by the loan auditor to query the audit opinions.
In this embodiment, the querying a target opinion from a pre-configured audit opinion set according to the feedback data includes:
determining the feedback data as a keyword;
inquiring in the audit opinion set by using the keywords to obtain the target opinion;
and the audit opinion set is a set obtained by clustering according to historical audit opinions.
For example: the review opinions generated by keyword comparison can be selected by the reviewers, and the reason of the rejected application can be as follows:
1. buyer names do not match and indicate which documents have non-matching key fields;
2. the seller names do not match;
3. the invoice numbers do not match;
4. the invoice dates do not match;
5. the product types do not match;
6. the transaction amounts do not match;
7. other rules formulated by the system do not match.
According to the embodiment, the audit opinions can be automatically matched according to the fed-back keywords by establishing the audit opinion set, so that the loan auditor can give the audit opinions more conveniently and rapidly, and the efficiency of auditing the financial assets of the supply chain is improved.
And S106, sending the target opinion to the configuration platform.
In this embodiment, after the target opinion is sent to the configuration platform, it may be waited for a relevant auditor to select according to an actual requirement, so as to determine whether to use the target opinion as a final audit opinion.
In this embodiment, after sending the target opinion to the configuration platform, the method further includes:
and responding to the received update request of the target opinion, acquiring update data of the target opinion, optimizing the target opinion according to the update data, and updating the optimized target opinion to the review opinion set.
Through the embodiment, the audit opinion set can be updated according to the audit opinion of a loan auditor, so that the opinion in the audit opinion set is more accurate.
And/or receiving the uploaded opinions in response to the received rejection instruction of the target opinions and feeding back the received opinions.
For example: when the character recognition or the information extraction is wrong, the auditor does not approve the audit opinions generated by the system, and the audit opinions of the system can be rejected.
Through the embodiment, the opinion uploaded by the loan auditor can be used as the final audit opinion when the loan auditor refuses the target opinion, and the audit error caused by the fact that the system opinion does not meet the requirement is avoided.
And S107, responding to a selection instruction of the target opinion, and feeding back the target opinion.
In this embodiment, the selection instruction may be triggered by an associated worker, such as a loan auditor.
In this embodiment, the target opinion may be fed back to the person (e.g., loan applicant) who triggered the audit request. For example: the target opinion may be fed back to a terminal device of the loan applicant, such as a mobile phone or a tablet, which triggers the audit request. The whole auditing process can comprise all supply chain finance processes such as payment release, payment and the like, automatically checks whether the files uploaded by the user meet format requirements and provides error reasons, reduces the possibility of file errors uploaded by the user, integrates document image identification and all supply chain finance processes such as asset auditing, asset management, payment release, payment and the like, and can allow an applicant and an auditor to check and search the files uploaded or audited before, so that file management is facilitated, and the auditor can select final auditing opinions from the auditing opinions generated by the system, thereby improving auditing efficiency and customer satisfaction.
In this embodiment, functional modules such as downloading, file searching, loan state searching, sorting, screening, batch exporting and the like can be provided for relevant users, so that persons with relevant rights can conveniently manage files. For example: the loan applicant can see all documents uploaded by the loan applicant, can download the documents uploaded previously, and can search the documents uploaded previously through various elements to play a role in document management. The loan auditor can see all the documents that have been or will be audited by the loan auditor and manage them.
According to the technical scheme, the automatic verification of the supply chain financial assets can be realized by combining character recognition and multi-mode information extraction, the verification efficiency is improved, and meanwhile, the verification suggestion can be generated to assist in verifying the supply chain financial assets and improve the verification efficiency.
The embodiment of the application also provides a supply chain financial asset auditing device, which is used for executing any embodiment of the supply chain financial asset auditing method. Specifically, referring to fig. 3, fig. 3 is a schematic block diagram of a supply chain financial asset auditing apparatus 100 according to an embodiment of the present application.
As shown in fig. 3, the supply chain financial asset auditing apparatus 100 includes an identification unit 101, an extraction unit 102, a verification unit 103, a transmission unit 104, an inquiry unit 105, and a feedback unit 106.
The identification unit 101 is configured to perform image identification on financial asset image data in response to a received audit request for the financial asset image data, so as to obtain position information and character information of each line of text box in the financial asset image data.
In this embodiment, the technical solution may be described with a server as an execution subject. The user end (such as an intelligent terminal like a smart phone or a tablet computer) used by a user can perform data interaction with the server, specifically, the server provides a supply chain financial asset auditing platform, and the user end can log in the supply chain financial asset auditing platform. And a user interaction interface of the supply chain financial asset auditing platform is displayed on a terminal interface of the user side, and at least one picture uploading interface exists in the user interaction interface. When a user selects a certain image as financial asset image data and uploads the image data to the server from the image uploading interface, subsequent supply chain financial asset examination and verification can be carried out in the server.
In this embodiment, the request for approval may be triggered by the loan applicant. Specifically, when a loan applicant uploads the financial asset image data, the request for auditing is determined to be triggered. The financial asset image data may be in a format of jpg, png, pdf, or the like.
In this embodiment, an OCR (Optical Character Recognition) technique may be adopted to perform image Recognition on the financial asset image data.
For example: character recognition can be performed on the financial asset image data by adopting a DBNet model so as to detect text information in the financial asset image data and generate positioning information of the text. Further, single line of text information of the located text is extracted by using a CRNN (Convolutional recurrent neural Network) to obtain position information and character information of each line of text box in the financial asset image data.
And the extraction unit 102 is configured to perform multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text frame to obtain target information.
For example: the SDMGR model can be adopted to read the position information and the character information of the text box to obtain the field of the text box, namely, the text box is regarded as a node, and the label of each node and the relation between two adjacent nodes are obtained through a graph neural network.
Specifically, the extraction unit 102 performs multi-modal information extraction on the financial asset image data according to the position information and the character information of each line of text box to obtain target information, and the method includes:
performing feature extraction on the character information based on the position information of each line of text frame to obtain a first feature corresponding to a graph node, wherein the first feature is generated by performing feature fusion among modalities on three modal features of text, vision and layout;
abstracting the character information to obtain an initial graph, wherein the initial graph is described by graph nodes, edges among the nodes and an adjacent matrix of the graph;
clustering the graph nodes in the initial graph to divide the initial graph, and performing multiple iterative updates on an allocation matrix for division in the dividing process;
acquiring cluster representation and distribution matrixes during each iterative update in the multiple iterative update process;
updating the first characteristic by utilizing cluster representation and distribution matrix during each iteration updating to obtain a second characteristic;
and carrying out node classification and link prediction based on the second characteristics to obtain the target information.
In this embodiment, on the basis of character recognition, a multi-modal information extraction technology is further combined to extract key information in the financial asset image data as the target information, so as to assist in the subsequent auditing of the supply chain financial assets.
The verification unit 103 is configured to perform validity verification on the financial asset image data by using the target information.
In this embodiment, the validity check includes, but is not limited to: the format of the financial asset image data is checked, the financial asset image data of a specified type (such as invoice type data) is checked, and specified information is checked.
Specifically, the verifying unit 103 performs validity verification on the financial asset image data by using the target information, including:
determining whether the financial asset image data meets format requirements according to the target information;
when the financial asset image data does not meet the format requirement, refusing to accept an auditing request for the financial asset image data;
and sending prompt information, wherein the prompt information is used for prompting the financial asset image data to have wrong format and prompting to upload the financial asset image data again.
Wherein different types of financial asset image data may correspond to different formatting requirements to unify formatting of various types of documents.
Through format inspection, effective prompts are sent out in time, and quick response can be carried out when the format is wrong, so that the auditing efficiency is improved.
Further, when the financial asset image data satisfies the format requirement, detecting a type of the financial asset image data;
when the financial asset image data is of an invoice type, the verifying unit 103 performs validity verification on the financial asset image data by using the target information, which further includes, but is not limited to, a combination of one or more of the following verification methods:
(1) And detecting whether the transaction amount of the financial asset image data is a positive number, and prompting that the transaction amount is wrong when the transaction amount is not the positive number.
Meanwhile, when the transaction amount is a positive number, the transaction amount is correct and no prompt is sent.
(2) And acquiring a transaction party from the financial asset image data, performing authenticity verification on the transaction party, and prompting the transaction party that the information is wrong when the transaction party does not pass the authenticity verification.
The transaction parties may include a buyer and a seller.
The embodiment may perform the authenticity check on the transaction party by invoking a third party platform (such as an enterprise query platform) or by querying a local record.
(3) And detecting the loan times corresponding to one transaction in the financial asset image data, and prompting that an invoice number exists when the loan times are greater than or equal to one time.
In the embodiment, the loan times corresponding to one transaction are detected, so that the situation that one transaction applies for loans for multiple times can be avoided.
(4) And detecting whether the date format in the financial asset image data is a configuration format, and prompting that the date format is wrong when the date format is not the configuration format.
The configuration format may be a general date format, and the date format may be configured by a user, which is not limited in the present invention.
(5) And acquiring a pre-configured service rule, detecting whether the financial asset image data accords with the service rule, and prompting that the service requirement is not met when the financial asset image data does not accord with the service rule.
The business rules can be configured according to actual business requirement data.
According to the embodiment, the pertinence verification of the financial asset image data of the invoice type can be realized, so that the phenomenon that information errors occur and subsequent asset audit is influenced is avoided.
Of course, the embodiment may also perform targeted verification on other types of financial asset image data, such as customs declaration, contracts, purchase orders, bill submissions, and the like, which is not described herein again.
The sending unit 104 is configured to send the target information to a configuration platform in response to the financial asset image data passing the validity check.
In this embodiment, when the image data of the financial asset fails to pass the validity check, an error message is sent, and the image data of the financial asset can be uploaded again after modification.
In this embodiment, before the target information is sent to the configuration platform, a pre-configured information matching rule is obtained;
acquiring configuration information from the target information according to the information matching rule;
detecting whether the configuration information meets the information matching rule or not to obtain a matching result;
and sending the matching result to the configuration platform.
The configuration information may be predefined key information, such as buyer, seller and amount on the invoice and order. Further, according to the information matching rule, the invoice must match with the buyer, seller and amount on the order.
Wherein the configuration platform may include an audit platform of financial asset image data.
In this embodiment, before the target information is sent to the configuration platform, an audit result of the configured key information is sent first, so as to assist in performing faster audit and improve the audit efficiency.
Further, the target information is sent to the configuration platform, so that the configuration platform can check the target information.
The query unit 105 is configured to, in response to the feedback data of the configuration platform for the target information, query a target opinion from a pre-configured review opinion set according to the feedback data.
In this embodiment, the feedback data may be keywords uploaded by the loan auditor for inquiring the audit opinions.
In this embodiment, the querying unit 105 queries the target opinion from a pre-configured review opinion set according to the feedback data, including:
determining the feedback data as a keyword;
inquiring in the audit opinion set by using the keywords to obtain the target opinion;
the audit opinion set is a set obtained by clustering according to historical audit opinions.
For example: the review opinions generated by keyword comparison can be selected by the reviewers, and the reason of the rejected application can be as follows:
1. buyer names do not match and indicate in which documents there are key fields that do not match;
2. the seller names do not match;
3. the invoice numbers do not match;
4. the invoice dates do not match;
5. the product types do not match;
6. the transaction amounts do not match;
7. other rules formulated by the system do not match.
According to the embodiment, the audit opinions can be automatically matched according to the fed-back keywords by establishing the audit opinion set, so that the loan auditor can give the audit opinions more conveniently and rapidly, and the efficiency of auditing the financial assets of the supply chain is improved.
The sending unit 104 is further configured to send the target opinion to the configuration platform.
In this embodiment, after the target opinion is sent to the configuration platform, it may be waited for a relevant auditor to select according to an actual requirement, so as to determine whether to use the target opinion as a final audit opinion.
In this embodiment, after the sending unit 104 sends the target opinion to the configuration platform, in response to a received update request for the target opinion, obtain update data for the target opinion, optimize the target opinion according to the update data, and update the optimized target opinion to the review opinion set.
Through the embodiment, the audit opinion set can be updated according to the audit opinion of a loan auditor, so that the opinion in the audit opinion set is more accurate.
And/or receiving the uploaded opinions in response to the received rejection instruction of the target opinions and feeding back the received opinions.
For example: when the character identification or the information extraction is wrong, the auditor does not approve the audit opinions generated by the system, and the audit opinions of the system can be rejected.
Through the embodiment, the opinion uploaded by the loan auditor can be used as the final audit opinion when the loan auditor rejects the target opinion, and the audit error caused by the fact that the system opinion does not meet the requirement can be avoided.
The feedback unit 106 is configured to feed back the target opinion in response to a selection instruction of the target opinion.
In this embodiment, the selection instruction may be triggered by an associated worker, such as a loan auditor.
In this embodiment, the target opinion may be fed back to the person (e.g., loan applicant) who triggered the audit request. For example: the target opinion may be fed back to a terminal device of the loan applicant, such as a mobile phone or a tablet, which triggers the audit request. The whole auditing process can comprise all supply chain finance processes such as payment release, payment and the like, automatically checks whether the files uploaded by the user meet format requirements and provides error reasons, reduces the possibility of file errors uploaded by the user, integrates document image identification and all supply chain finance processes such as asset auditing, asset management, payment release, payment and the like, and can allow an applicant and an auditor to check and search the files uploaded or audited before, so that file management is facilitated, and the auditor can select final auditing opinions from the auditing opinions generated by the system, thereby improving auditing efficiency and customer satisfaction.
In this embodiment, functional modules such as downloading, file searching, loan state searching, sorting, screening, batch exporting and the like can be provided for relevant users, so that persons with relevant rights can conveniently manage files. For example: the loan applicant can see all documents uploaded by the loan applicant, can download the documents uploaded before, and can search the documents uploaded before through various elements to play a role in document management. The loan auditor can see all the documents that have been or will be audited by the loan auditor and manage them.
According to the technical scheme, the automatic checking of the supply chain financial assets can be realized by combining character recognition and multi-mode information extraction, the checking efficiency is improved, and meanwhile, the checking opinions can be generated to assist in checking the supply chain financial assets and improve the checking efficiency.
The supply chain financial asset auditing means described above may be implemented in the form of a computer program which may be run on a computer device as shown in figure 4.
Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server or a server cluster. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
Referring to fig. 4, the computer apparatus 500 includes a processor 502, a memory, which may include a storage medium 503 and an internal memory 504, and a network interface 505 connected by a device bus 501.
The storage medium 503 may store an operating system 5031 and a computer program 5032. The computer programs 5032, when executed, cause the processor 502 to perform a supply chain financial asset auditing method.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 stored on the storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 can be enabled to perform a supply chain financial asset auditing method.
The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration associated with aspects of the present application, and is not intended to limit the computing device 500 to which aspects of the present application may be applied, and that a particular computing device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The processor 502 is configured to run the computer program 5032 stored in the memory to implement the supply chain financial asset auditing method disclosed in the embodiments of the present application.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 4 does not constitute a limitation on the specific construction of the computer device, and that in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 4, and are not described herein again.
It should be understood that, in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field-Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a nonvolatile computer-readable storage medium or a volatile computer-readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the supply chain financial asset auditing method disclosed in embodiments of the present application.
It should be noted that all the data involved in the present application are legally acquired.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only a logical division, and there may be another division in actual implementation, and units having the same function may be grouped into one unit, for example, multiple units or components may be combined or may be integrated into another device, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solutions of the present application may substantially or partially contribute to the prior art, or all or part of the technical solutions may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a background server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A supply chain financial asset auditing method, comprising:
in response to a received auditing request for financial asset image data, performing image recognition on the financial asset image data to obtain position information and character information of each line of text box in the financial asset image data;
performing multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text box to obtain target information;
carrying out validity check on the financial asset image data by using the target information;
sending the target information to a configuration platform in response to the financial asset image data passing the validity check;
responding to feedback data of the configuration platform for the target information, and inquiring a target opinion from a pre-configured audit opinion set according to the feedback data;
sending the target opinion to the configuration platform;
and feeding back the target opinion in response to a selection instruction of the target opinion.
2. The supply chain financial asset auditing method of claim 1, wherein the multi-modal information extraction of the financial asset image data according to position information and character information of each line of text boxes to obtain target information comprises:
performing feature extraction on the character information based on the position information of each line of text frame to obtain a first feature corresponding to a graph node, wherein the first feature is generated by performing feature fusion among modalities on three modal features of text, vision and layout;
abstracting the character information to obtain an initial graph, wherein the initial graph is described by graph nodes, edges among the nodes and an adjacent matrix of the graph;
clustering the graph nodes in the initial graph to divide the initial graph, and performing multiple iterative updates on an allocation matrix for division in the dividing process;
acquiring cluster representation and distribution matrixes during each iterative update in the multiple iterative update process;
updating the first characteristic by utilizing cluster representation and distribution matrix during each iteration updating to obtain a second characteristic;
and carrying out node classification and link prediction based on the second characteristics to obtain the target information.
3. The supply chain financial asset auditing method of claim 1 where said using the target information to validate the financial asset image data comprises:
determining whether the financial asset image data meets format requirements according to the target information;
when the financial asset image data does not meet the format requirement, refusing to accept an auditing request for the financial asset image data;
and sending prompt information, wherein the prompt information is used for prompting the financial asset image data to have wrong format and prompting to upload the financial asset image data again.
4. The supply chain financial asset auditing method according to claim 3, wherein said checking the validity of the financial asset image data using the target information further comprises:
detecting a type of the financial asset image data when the financial asset image data satisfies the format requirement;
when the financial asset image data is of an invoice type, detecting whether the transaction amount of the financial asset image data is a positive number, and when the transaction amount is not the positive number, prompting that the transaction amount is wrong; and/or
Acquiring a trading party from the financial asset image data, performing authenticity verification on the trading party, and prompting the trading party that information is wrong when the trading party does not pass the authenticity verification; and/or
Detecting the loan times corresponding to one transaction in the financial asset image data, and prompting that an invoice number exists when the loan times is more than or equal to one time; and/or
Detecting whether a date format in the financial asset image data is a configuration format, and prompting that the date format is wrong when the date format is not the configuration format; and/or
And acquiring a pre-configured service rule, detecting whether the financial asset image data accords with the service rule, and prompting that the service requirement is not met when the financial asset image data does not accord with the service rule.
5. The supply chain financial asset auditing method according to claim 1 before sending the target information to a configuration platform, the method further comprising:
acquiring a pre-configured information matching rule;
acquiring configuration information from the target information according to the information matching rule;
detecting whether the configuration information meets the information matching rule or not to obtain a matching result;
and sending the matching result to the configuration platform.
6. The supply chain financial asset auditing method according to claim 1 where querying for target opinions from a preconfigured set of audit opinions based on the feedback data comprises:
determining the feedback data as a keyword;
inquiring in the audit opinion set by using the keywords to obtain the target opinion;
and the audit opinion set is a set obtained by clustering according to historical audit opinions.
7. The supply chain financial asset auditing method according to claim 1 where, after sending the target opinion to the configuration platform, the method further comprises:
responding to a received update request for the target opinion, acquiring update data for the target opinion, optimizing the target opinion according to the update data, and updating the optimized target opinion to the review opinion set; and/or
And responding to the received rejection instruction of the target opinion, receiving the uploaded opinion, and feeding back the received opinion.
8. A supply chain financial asset auditing apparatus, comprising:
the identification unit is used for responding to a received auditing request for the financial asset image data, carrying out image identification on the financial asset image data and obtaining position information and character information of each line of text box in the financial asset image data;
the extraction unit is used for performing multi-mode information extraction on the financial asset image data according to the position information and the character information of each line of text frame to obtain target information;
the checking unit is used for carrying out validity checking on the financial asset image data by utilizing the target information;
the sending unit is used for responding to the fact that the financial asset image data passes the validity check and sending the target information to a configuration platform;
the query unit is used for responding to feedback data of the configuration platform aiming at the target information and querying the target opinion from a pre-configured audit opinion set according to the feedback data;
the sending unit is further configured to send the target opinion to the configuration platform;
and the feedback unit is used for responding to a selection instruction of the target opinion and feeding back the target opinion.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements a supply chain financial asset auditing method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the supply chain financial asset auditing method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156964.6A CN115601129A (en) | 2022-09-21 | 2022-09-21 | Supply chain financial asset auditing method, device, equipment and medium |
| PCT/CN2023/103531 WO2024060759A1 (en) | 2022-09-21 | 2023-06-29 | Supply chain financial asset auditing method and apparatus, and device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211156964.6A CN115601129A (en) | 2022-09-21 | 2022-09-21 | Supply chain financial asset auditing method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115601129A true CN115601129A (en) | 2023-01-13 |
Family
ID=84845885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211156964.6A Pending CN115601129A (en) | 2022-09-21 | 2022-09-21 | Supply chain financial asset auditing method, device, equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115601129A (en) |
| WO (1) | WO2024060759A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024060759A1 (en) * | 2022-09-21 | 2024-03-28 | 深圳前海环融联易信息科技服务有限公司 | Supply chain financial asset auditing method and apparatus, and device and medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070136814A1 (en) * | 2005-12-12 | 2007-06-14 | Michael Lee | Critical function monitoring and compliance auditing system |
| CN109472918A (en) * | 2018-10-12 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Invoice validation method, financing checking method, device, equipment and medium |
| CN111159383A (en) * | 2019-12-31 | 2020-05-15 | 重庆百事得大牛机器人有限公司 | Legal opinion book generation system based on target object |
| CN113807955A (en) * | 2021-09-29 | 2021-12-17 | 腾讯科技（深圳）有限公司 | Information auditing method and related equipment |
| CN114202755A (en) * | 2021-12-09 | 2022-03-18 | 兴业银行股份有限公司 | Transaction background authenticity auditing method and system based on OCR (optical character recognition) and NLP (non-line segment) technologies |
| CN115601129A (en) * | 2022-09-21 | 2023-01-13 | 深圳前海环融联易信息科技服务有限公司（Cn） | Supply chain financial asset auditing method, device, equipment and medium |
-
2022
- 2022-09-21 CN CN202211156964.6A patent/CN115601129A/en active Pending
-
2023
- 2023-06-29 WO PCT/CN2023/103531 patent/WO2024060759A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024060759A1 (en) * | 2022-09-21 | 2024-03-28 | 深圳前海环融联易信息科技服务有限公司 | Supply chain financial asset auditing method and apparatus, and device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024060759A1 (en) | 2024-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10546351B2 (en) | System and method for automatic generation of reports based on electronic documents | |
| CN110263024B (en) | Data processing method, terminal device and computer storage medium | |
| US10783116B2 (en) | Systems and methods for managing data | |
| US11062132B2 (en) | System and method for identification of missing data elements in electronic documents | |
| US20160342999A1 (en) | Method, system, and computer program product for linking customer information | |
| US8626617B1 (en) | Method and system for identifying fixed asset transactions from multiple financial transactions | |
| US9020988B2 (en) | Database aggregation of purchase data | |
| CN103782318A (en) | System and methods for producing a credit feedback loop | |
| US20170323006A1 (en) | System and method for providing analytics in real-time based on unstructured electronic documents | |
| US11138372B2 (en) | System and method for reporting based on electronic documents | |
| US20160224674A1 (en) | Dynamic entity rendering framework | |
| US20170169292A1 (en) | System and method for automatically verifying requests based on electronic documents | |
| US20090265279A1 (en) | System and method for managing and distributing hedge fund data | |
| US20240062235A1 (en) | Systems and methods for automated processing and analysis of deduction backup data | |
| CN115601129A (en) | Supply chain financial asset auditing method, device, equipment and medium | |
| CA2623331C (en) | Sales transaction hub | |
| JP4373642B2 (en) | Supplier requirements system, supplier trend display control method, and program | |
| US20160224993A1 (en) | System for determining relationships between entities | |
| US20180357734A1 (en) | Scalable computing systems and methods for intellectual property rights and royalty management | |
| CN115545858A (en) | RPA-based automatic account checking method, device, equipment and storage medium | |
| US20170161315A1 (en) | System and method for maintaining data integrity | |
| US10387561B2 (en) | System and method for obtaining reissues of electronic documents lacking required data | |
| US20170169519A1 (en) | System and method for automatically verifying transactions based on electronic documents | |
| US20170323106A1 (en) | System and method for encrypting data in electronic documents | |
| KR102395415B1 (en) | Service system for management information of general agency |
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 |